Journal articles: 'Minimally-supervised Learning'

1

Althobaiti, Maha, Udo Kruschwitz, and Massimo Poesio. "Combining Minimally-supervised Methods for Arabic Named Entity Recognition." Transactions of the Association for Computational Linguistics 3 (December 2015): 243–55. http://dx.doi.org/10.1162/tacl_a_00136.

Full text

Abstract:

Supervised methods can achieve high performance on NLP tasks, such as Named Entity Recognition (NER), but new annotations are required for every new domain and/or genre change. This has motivated research in minimally supervised methods such as semi-supervised learning and distant learning, but neither technique has yet achieved performance levels comparable to those of supervised methods. Semi-supervised methods tend to have very high precision but comparatively low recall, whereas distant learning tends to achieve higher recall but lower precision. This complementarity suggests that better results may be obtained by combining the two types of minimally supervised methods. In this paper we present a novel approach to Arabic NER using a combination of semi-supervised and distant learning techniques. We trained a semi-supervised NER classifier and another one using distant learning techniques, and then combined them using a variety of classifier combination schemes, including the Bayesian Classifier Combination (BCC) procedure recently proposed for sentiment analysis. According to our results, the BCC model leads to an increase in performance of 8 percentage points over the best base classifiers.

APA, Harvard, Vancouver, ISO, and other styles

2

Ruokolainen, Teemu, Oskar Kohonen, Kairit Sirts, Stig-Arne Grönroos, Mikko Kurimo, and Sami Virpioja. "A Comparative Study of Minimally Supervised Morphological Segmentation." Computational Linguistics 42, no. 1 (March 2016): 91–120. http://dx.doi.org/10.1162/coli_a_00243.

Full text

Abstract:

This article presents a comparative study of a subfield of morphology learning referred to as minimally supervised morphological segmentation. In morphological segmentation, word forms are segmented into morphs, the surface forms of morphemes. In the minimally supervised data-driven learning setting, segmentation models are learned from a small number of manually annotated word forms and a large set of unannotated word forms. In addition to providing a literature survey on published methods, we present an in-depth empirical comparison on three diverse model families, including a detailed error analysis. Based on the literature survey, we conclude that the existing methodology contains substantial work on generative morph lexicon-based approaches and methods based on discriminative boundary detection. As for which approach has been more successful, both the previous work and the empirical evaluation presented here strongly imply that the current state of the art is yielded by the discriminative boundary detection methodology.

APA, Harvard, Vancouver, ISO, and other styles

3

Kiyomaru, Hirokazu, and Sadao Kurohashi. "Minimally-Supervised Joint Learning of Event Volitionality and Subject Animacy Classification." Journal of Natural Language Processing 29, no. 3 (2022): 807–34. http://dx.doi.org/10.5715/jnlp.29.807.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Kiyomaru, Hirokazu, and Sadao Kurohashi. "Minimally-Supervised Joint Learning of Event Volitionality and Subject Animacy Classification." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 10 (June 28, 2022): 10921–29. http://dx.doi.org/10.1609/aaai.v36i10.21339.

Full text

Abstract:

Volitionality and subject animacy are fundamental and closely related properties of an event. Their classification is challenging because it requires contextual text understanding and a huge amount of labeled data. This paper proposes a novel method that jointly learns volitionality and subject animacy at a low cost, heuristically labeling events in a raw corpus. Volitionality labels are assigned using a small lexicon of volitional and non-volitional adverbs such as deliberately and accidentally; subject animacy labels are assigned using a list of animate and inanimate nouns obtained from ontological knowledge. We then consider the problem of learning a classifier from the labeled events so that it can perform well on unlabeled events without the words used for labeling. We view the problem as a bias reduction or unsupervised domain adaptation problem and apply the techniques. We conduct experiments with crowdsourced gold data in Japanese and English and show that our method effectively learns volitionality and subject animacy without manually labeled data.

APA, Harvard, Vancouver, ISO, and other styles

5

Bi, Haixia, Feng Xu, Zhiqiang Wei, Yong Xue, and Zongben Xu. "An Active Deep Learning Approach for Minimally Supervised PolSAR Image Classification." IEEE Transactions on Geoscience and Remote Sensing 57, no. 11 (November 2019): 9378–95. http://dx.doi.org/10.1109/tgrs.2019.2926434.

Full text

APA, Harvard, Vancouver, ISO, and other styles

6

Moioli, Renan C., and Phil Husbands. "Neuronal Assembly Dynamics in Supervised and Unsupervised Learning Scenarios." Neural Computation 25, no. 11 (November 2013): 2934–75. http://dx.doi.org/10.1162/neco_a_00502.

Full text

Abstract:

The dynamic formation of groups of neurons—neuronal assemblies—is believed to mediate cognitive phenomena at many levels, but their detailed operation and mechanisms of interaction are still to be uncovered. One hypothesis suggests that synchronized oscillations underpin their formation and functioning, with a focus on the temporal structure of neuronal signals. In this context, we investigate neuronal assembly dynamics in two complementary scenarios: the first, a supervised spike pattern classification task, in which noisy variations of a collection of spikes have to be correctly labeled; the second, an unsupervised, minimally cognitive evolutionary robotics tasks, in which an evolved agent has to cope with multiple, possibly conflicting, objectives. In both cases, the more traditional dynamical analysis of the system's variables is paired with information-theoretic techniques in order to get a broader picture of the ongoing interactions with and within the network. The neural network model is inspired by the Kuramoto model of coupled phase oscillators and allows one to fine-tune the network synchronization dynamics and assembly configuration. The experiments explore the computational power, redundancy, and generalization capability of neuronal circuits, demonstrating that performance depends nonlinearly on the number of assemblies and neurons in the network and showing that the framework can be exploited to generate minimally cognitive behaviors, with dynamic assembly formation accounting for varying degrees of stimuli modulation of the sensorimotor interactions.

APA, Harvard, Vancouver, ISO, and other styles

7

Ittoo, Ashwin, and Gosse Bouma. "Minimally-supervised learning of domain-specific causal relations using an open-domain corpus as knowledge base." Data & Knowledge Engineering 88 (November 2013): 142–63. http://dx.doi.org/10.1016/j.datak.2013.08.004.

Full text

APA, Harvard, Vancouver, ISO, and other styles

8

Curto, Sergio, Ana Cristina Mendes, and Luisa Coheur. "Question Generation based on Lexico-Syntactic Patterns Learned from the Web." Dialogue & Discourse 3, no. 2 (March 16, 2012): 147–75. http://dx.doi.org/10.5087/dad.2012.207.

Full text

Abstract:

THE MENTOR automatically generates multiple-choice tests from a given text. This tool aims at supporting the dialogue system of the FalaComigo project, as one of FalaComigo's goals is the interaction with tourists through questions/answers and quizzes about their visit. In a minimally supervised learning process and by leveraging the redundancy and linguistic variability of the Web, THE MENTOR learns lexico-syntactic patterns using a set of question/answer seeds. Afterward, these patterns are used to match the sentences from which new questions (and answers) can be generated. Finally, several ï¬lters are applied in order to discard low quality items. In this paper we detail the question generation task as performed by T- Mand evaluate its performance.

APA, Harvard, Vancouver, ISO, and other styles

9

Zhang, Congle, Raphael Hoffmann, and Daniel Weld. "Ontological Smoothing for Relation Extraction with Minimal Supervision." Proceedings of the AAAI Conference on Artificial Intelligence 26, no. 1 (September 20, 2021): 157–63. http://dx.doi.org/10.1609/aaai.v26i1.8102.

Full text

Abstract:

Relation extraction, the process of converting natural language text into structured knowledge, is increasingly important. Most successful techniques use supervised machine learning to generate extractors from sentences that have been manually labeled with the relations' arguments. Unfortunately, these methods require numerous training examples, which are expensive and time-consuming to produce. This paper presents ontological smoothing, a semi-supervisedtechnique that learns extractors for a set of minimally-labeledrelations. Ontological smoothing has three phases. First, itgenerates a mapping between the target relations and a backgroundknowledge-base. Second, it uses distant supervision toheuristically generate new training examples for the targetrelations. Finally, it learns an extractor from a combination of theoriginal and newly-generated examples. Experiments on 65 relationsacross three target domains show that ontological smoothing candramatically improve precision and recall, even rivaling fully supervisedperformance in many cases.

APA, Harvard, Vancouver, ISO, and other styles

10

Farr, Ryan J., Christina L. Rootes, John Stenos, Chwan Hong Foo, Christopher Cowled, and Cameron R. Stewart. "Detection of SARS-CoV-2 infection by microRNA profiling of the upper respiratory tract." PLOS ONE 17, no. 4 (April 5, 2022): e0265670. http://dx.doi.org/10.1371/journal.pone.0265670.

Full text

Abstract:

Host biomarkers are increasingly being considered as tools for improved COVID-19 detection and prognosis. We recently profiled circulating host-encoded microRNA (miRNAs) during SARS-CoV-2 infection, revealing a signature that classified COVID-19 cases with 99.9% accuracy. Here we sought to develop a signature suited for clinical application by analyzing specimens collected using minimally invasive procedures. Eight miRNAs displayed altered expression in anterior nasal tissues from COVID-19 patients, with miR-142-3p, a negative regulator of interleukin-6 (IL-6) production, the most strongly upregulated. Supervised machine learning analysis revealed that a three-miRNA signature (miR-30c-2-3p, miR-628-3p and miR-93-5p) independently classifies COVID-19 cases with 100% accuracy. This study further defines the host miRNA response to SARS-CoV-2 infection and identifies candidate biomarkers for improved COVID-19 detection.

APA, Harvard, Vancouver, ISO, and other styles

11

Kejriwal, Mayank, and Yao Gu. "A Pipeline for Rapid Post-Crisis Twitter Data Acquisition, Filtering and Visualization." Technologies 7, no. 2 (April 2, 2019): 33. http://dx.doi.org/10.3390/technologies7020033.

Full text

Abstract:

Due to instant availability of data on social media platforms like Twitter, and advances in machine learning and data management technology, real-time crisis informatics has emerged as a prolific research area in the last decade. Although several benchmarks are now available, especially on portals like CrisisLex, an important, practical problem that has not been addressed thus far is the rapid acquisition, benchmarking and visual exploration of data from free, publicly available streams like the Twitter API in the immediate aftermath of a crisis. In this paper, we present such a pipeline for facilitating immediate post-crisis data collection, curation and relevance filtering from the Twitter API. The pipeline is minimally supervised, alleviating the need for feature engineering by including a judicious mix of data preprocessing and fast text embeddings, along with an active learning framework. We illustrate the utility of the pipeline by describing a recent case study wherein it was used to collect and analyze millions of tweets in the immediate aftermath of the Las Vegas shootings in 2017.

APA, Harvard, Vancouver, ISO, and other styles

12

Ebadi, Toktam, Ignas Kukenys, Will N. Browne, and Mengjie Zhang. "Human-Interpretable Feature Pattern Classification System Using Learning Classifier Systems." Evolutionary Computation 22, no. 4 (December 2014): 629–50. http://dx.doi.org/10.1162/evco_a_00127.

Full text

Abstract:

Image pattern classification is a challenging task due to the large search space of pixel data. Supervised and subsymbolic approaches have proven accurate in learning a problem’s classes. However, in the complex image recognition domain, there is a need for investigation of learning techniques that allow humans to interpret the learned rules in order to gain an insight about the problem. Learning classifier systems (LCSs) are a machine learning technique that have been minimally explored for image classification. This work has developed the feature pattern classification system (FPCS) framework by adopting Haar-like features from the image recognition domain for feature extraction. The FPCS integrates Haar-like features with XCS, which is an accuracy-based LCS. A major contribution of this work is that the developed framework is capable of producing human-interpretable rules. The FPCS system achieved 91 [Formula: see text] 1% accuracy on the unseen test set of the MNIST dataset. In addition, the FPCS is capable of autonomously adjusting the rotation angle in unaligned images. This rotation adjustment raised the accuracy of FPCS to 95%. Although the performance is competitive with equivalent approaches, this was not as accurate as subsymbolic approaches on this dataset. However, the benefit of the interpretability of rules produced by FPCS enabled us to identify the distribution of the learned angles—a normal distribution around [Formula: see text]—which would have been very difficult in subsymbolic approaches. The analyzable nature of FPCS is anticipated to be beneficial in domains such as speed sign recognition, where underlying reasoning and confidence of recognition needs to be human interpretable.

APA, Harvard, Vancouver, ISO, and other styles

13

Kumar, Vidit, Vikas Tripathi, Bhaskar Pant, Sultan S. Alshamrani, Ankur Dumka, Anita Gehlot, Rajesh Singh, Mamoon Rashid, Abdullah Alshehri, and Ahmed Saeed AlGhamdi. "Hybrid Spatiotemporal Contrastive Representation Learning for Content-Based Surgical Video Retrieval." Electronics 11, no. 9 (April 24, 2022): 1353. http://dx.doi.org/10.3390/electronics11091353.

Full text

Abstract:

In the medical field, due to their economic and clinical benefits, there is a growing interest in minimally invasive surgeries and microscopic surgeries. These types of surgeries are often recorded during operations, and these recordings have become a key resource for education, patient disease analysis, surgical error analysis, and surgical skill assessment. However, manual searching in this collection of long-term surgical videos is an extremely labor-intensive and long-term task, requiring an effective content-based video analysis system. In this regard, previous methods for surgical video retrieval are based on handcrafted features which do not represent the video effectively. On the other hand, deep learning-based solutions were found to be effective in both surgical image and video analysis, where CNN-, LSTM- and CNN-LSTM-based methods were proposed in most surgical video analysis tasks. In this paper, we propose a hybrid spatiotemporal embedding method to enhance spatiotemporal representations using an adaptive fusion layer on top of the LSTM and temporal causal convolutional modules. To learn surgical video representations, we propose exploring the supervised contrastive learning approach to leverage label information in addition to augmented versions. By validating our approach to a video retrieval task on two datasets, Surgical Actions 160 and Cataract-101, we significantly improve on previous results in terms of mean average precision, 30.012 ± 1.778 vs. 22.54 ± 1.557 for Surgical Actions 160 and 81.134 ± 1.28 vs. 33.18 ± 1.311 for Cataract-101. We also validate the proposed method’s suitability for surgical phase recognition task using the benchmark Cholec80 surgical dataset, where our approach outperforms (with 90.2% accuracy) the state of the art.

APA, Harvard, Vancouver, ISO, and other styles

14

Dise, Joseph, Christopher Abraham, Douglas Caruthers, Sasa Mutic, and Clifford Robinson. "RADI-19. EVALUATION OF BRAIN METASTASIS LOCAL CONTROL POST RADIOSURGERY VIA MACHINE LEARNING AND RADIOMICS." Neuro-Oncology Advances 1, Supplement_1 (August 2019): i25. http://dx.doi.org/10.1093/noajnl/vdz014.111.

Full text

Abstract:

Abstract Stereotactic radiosurgery can be used to treat multiple, surgically inaccessible, metastatic brain lesions in a single, minimally invasive outpatient procedure. For brain metastasis, stereotactic radiosurgery can provide excellent local control depending on the robustness of the treatment plan. Previous studies have been performed correlating key radiation planning factors to higher local control probability such as tumor size and maximum dose. However, a separate non-inferiority study demonstrated that higher prescription isodose lines (in excess of 70% or higher) did not correlate to local failure. The previous works were limited to shallow feature levels regarding only the dicom plan information and lacked a predictive model. In order to address these conflicting conclusions and to support clinical decision making, we propose a radiosurgery informatics pipeline to support testing these hypotheses with observational data. First, a multidisciplinary team generated a mind-map of relevant information to inform database design. Portions of this mind-map were implemented in a relational database system (PorstgreSQL), and populated with information from 1024 patients treated for brain metastasis via stereotactic radiosurgery. Clinical information were derived from curated databases and the array of intervention variables were mined from the DICOM RT plans, structure sets, images and dose via MATLAB scripts. These factors include, but are not limited to, radiation dosimetry, prior whole brain radiation, radiomic imaging features, prior radiosurgery status, and physician determined local control status. From this pipeline, we plan to use a multi-level feature-based supervised machine learning approach that will be created via boosting to predict local control in patients using local failure timing, or lack thereof, provided by physician. To control for local failure observer bias, an unsupervised machine learning model via random trees will be created to predict clusters of patient parameters with similar local control rates.

APA, Harvard, Vancouver, ISO, and other styles

15

Hong, Seok-Jun, Boris C. Bernhardt, Benoit Caldairou, Jeffery A. Hall, Marie C. Guiot, Dewi Schrader, Neda Bernasconi, and Andrea Bernasconi. "Multimodal MRI profiling of focal cortical dysplasia type II." Neurology 88, no. 8 (January 27, 2017): 734–42. http://dx.doi.org/10.1212/wnl.0000000000003632.

Full text

Abstract:

Objective:To characterize in vivo MRI signatures of focal cortical dysplasia (FCD) type IIA and type IIB through combined analysis of morphology, intensity, microstructure, and function.Methods:We carried out a multimodal 3T MRI profiling of 33 histologically proven FCD type IIA (9) and IIB (24) lesions. A multisurface approach operating on manual consensus labels systematically sampled intracortical and subcortical lesional features. Geodesic distance mapping quantified the same features in the lesion perimeter. Logistic regression assessed the relationship between MRI and histology, while supervised pattern learning was used for individualized subtype prediction.Results:FCD type IIB was characterized by abnormal morphology, intensity, diffusivity, and function across all surfaces, while type IIA lesions presented only with increased fluid-attenuated inversion recovery signal and reduced diffusion anisotropy close to the gray–white matter interface. Similar to lesional patterns, perilesional anomalies were more marked in type IIB extending up to 16 mm. Structural MRI markers correlated with categorical histologic characteristics. A profile-based classifier predicted FCD subtypes with equal sensitivity of 85%, while maintaining a high specificity of 94% against healthy and disease controls.Conclusions:Image processing applied to widely available MRI contrasts has the ability to dissociate FCD subtypes at a mesoscopic level. Integrating in vivo staging of pathologic traits with automated lesion detection is likely to provide an objective definition of lesional boundary and assist emerging approaches, such as minimally invasive thermal ablation, which do not supply tissue specimen.

APA, Harvard, Vancouver, ISO, and other styles

16

Calderón, José Miguel, Julio Álvarez-Pitti, Irene Cuenca, Francisco Ponce, and Pau Redon. "Development of a Minimally Invasive Screening Tool to Identify Obese Pediatric Population at Risk of Obstructive Sleep Apnea/Hypopnea Syndrome." Bioengineering 7, no. 4 (October 19, 2020): 131. http://dx.doi.org/10.3390/bioengineering7040131.

Full text

Abstract:

Obstructive sleep apnea syndrome is a reduction of the airflow during sleep which not only produces a reduction in sleep quality but also has major health consequences. The prevalence in the obese pediatric population can surpass 50%, and polysomnography is the current gold standard method for its diagnosis. Unfortunately, it is expensive, disturbing and time-consuming for experienced professionals. The objective is to develop a patient-friendly screening tool for the obese pediatric population to identify those children at higher risk of suffering from this syndrome. Three supervised learning classifier algorithms (i.e., logistic regression, support vector machine and AdaBoost) common in the field of machine learning were trained and tested on two very different datasets where oxygen saturation raw signal was recorded. The first dataset was the Childhood Adenotonsillectomy Trial (CHAT) consisting of 453 individuals, with ages between 5 and 9 years old and one-third of the patients being obese. Cross-validation was performed on the second dataset from an obesity assessment consult at the Pediatric Department of the Hospital General Universitario of Valencia. A total of 27 patients were recruited between 5 and 17 years old; 42% were girls and 63% were obese. The performance of each algorithm was evaluated based on key performance indicators (e.g., area under the curve, accuracy, recall, specificity and positive predicted value). The logistic regression algorithm outperformed (accuracy = 0.79, specificity = 0.96, area under the curve = 0.9, recall = 0.62 and positive predictive value = 0.94) the support vector machine and the AdaBoost algorithm when trained with the CHAT datasets. Cross-validation tests, using the Hospital General de Valencia (HG) dataset, confirmed the higher performance of the logistic regression algorithm in comparison with the others. In addition, only a minor loss of performance (accuracy = 0.75, specificity = 0.88, area under the curve = 0.85, recall = 0.62 and positive predictive value = 0.83) was observed despite the differences between the datasets. The proposed minimally invasive screening tool has shown promising performance when it comes to identifying children at risk of suffering obstructive sleep apnea syndrome. Moreover, it is ideal to be implemented in an outpatient consult in primary and secondary care.

APA, Harvard, Vancouver, ISO, and other styles

17

Tagore, Shephali, Bernard Chern Su Min, Shen Li Goh, Lay Kok Tan, Kenneth Kwek, and Kok Hian Tan. "Specialist Training in Obstetrics and Gynecology in Singapore: Transition to Structured Residency Program." Journal of Graduate Medical Education 4, no. 2 (June 1, 2012): 272–75. http://dx.doi.org/10.4300/jgme-04-02-34.

Full text

Abstract:

Abstract Background The article describes the experience of planning and implementing the transition of the residency program in obstetrics and gynecology at Singhealth, Singapore, from a model largely based on British training principles to a new model in accordance with the ACGME-International (ACGME-I) standards. Intervention Initial steps in transitioning to the new model entailed (1) identifying faculty with an interest in education to lead the various initiatives and programs and to ensure appropriate educational role models, (2) securing adequate funding, (3) holding focus groups with physicians to identify opportunities for improvement in the new system, and (4) developing a schedule for the phased implementation of key features of the structured system. Results The program started in July 2011, with 14 residents for a 4-year course of training. The curriculum consisted of 5 modules: (1) general obstetrics and gynecology and ambulatory care, (2) maternal fetal medicine, (3) urogynecology and minimally invasive surgery, (4) reproductive medicine, and (5) gynecology oncology. Faculty was assigned responsibility for teaching and assessing the 6 competencies, and appropriate training was provided through specially designed, professional-development programs. Conclusions Challenges in the implementation of the new training program included the need to replace clinical service previously provided by trainees, a lack of fit between the traditional qualifying exam and the new model for training, and the need to adapt teaching strategies to new competencies not explicitly taught in the prior program, particularly practice-based learning and improvement and systems-based practice. The strength of the new obstetrics and gynecology residency lies in having a structured, competency-based, closely supervised approach to training with standardized evaluations, timely feedback, and a committed faculty.

APA, Harvard, Vancouver, ISO, and other styles

18

Clark, Toshimasa, Trevor Cohen, Bryan R. Haugen, Devika Subramanian, Nikita Pozdeyev, Manjiri Dighe, Martin Barrio, and Michael G. Leu. "RF11 | PSAT234 Deep learning analysis of thyroid nodule ultrasound images has high sensitivity and negative predictive value to rule-out thyroid cancer." Journal of the Endocrine Society 6, Supplement_1 (November 1, 2022): A852. http://dx.doi.org/10.1210/jendso/bvac150.1762.

Full text

Abstract:

Abstract Purpose To evaluate deep learning analysis of thyroid nodule ultrasound images as a rule-out test for thyroid malignancy. Methods Supervised deep learning (DL) classifier of thyroid nodules was trained on 32,545 thyroid US images from 621 nodules representing all major benign and malignant types of thyroid lesions and tested on an independent set of 145 nodules collected at a different healthcare system in the United States. The Big Transfer BiT-M ResNet-50×1 convolutional neural net architecture was modified to contain 3, 4, 6 and 3 PreActBottleneck units per block 1 through 4. Weights pretrained on the ImageNet-21k dataset were loaded and weights for blocks 3 and 4 were fine-tuned for the binary classification task of distinguishing benign and malignant thyroid nodules. Results The deep learning thyroid nodule classifier achieved an area under receiver operating characteristic curve (AUROC) of 0.889 on five-fold cross-validation. The AUROC improved when images were scaled by nodule size and six randomly selected cine clip frames were added to the training set per epoch. GradCAM class activation heatmaps revealed that microcalcifications and spongiform appearance were reliably recognized by the classifier as malignant and benign features, respectively. Spongiform nodules were found to be benign even when microcystic spaces constituted less than 50% of nodule volume. To investigate the clinical relevance of the benign vs. malignant classifier, the binary classification threshold for the probability of malignancy generated by model was set at 7% to achieve sensitivity and negative predictive value (NPV) comparable to that of the fine needle aspiration biopsy (FNA). At this threshold, cross-validated deep-learning model achieved a sensitivity of 90%, specificity of 63%, positive predictive value (PPV) of 46% and negative predictive value of 94%. When tested on an independent image set that includes 18 classic papillary thyroid cancers (PTC), 5 follicular variant PTC, 4 medullary thyroid cancers, 3 follicular thyroid cancers (FTC), and 1 Hurthle cell thyroid cancer, the DL classifier achieved AUROC of 0.88, sensitivity of 97%, specificity of 61%, PPV of 40% and NPV of 99%. A single minimally-invasive FTC that had no suspicious features on thyroid ultrasound was incorrectly classified as benign. Conclusions This study demonstrates that the ultrasound-based deep-learning classifier of thyroid nodules achieves sensitivity and negative predictive value comparable to that of thyroid fine needle aspiration (FNA). Clinicians may use this tool to augment clinical judgment when determining whether to perform FNA procedures. Presentation: Saturday, June 11, 2022 1:00 p.m. - 3:00 p.m., Saturday, June 11, 2022 1:06 p.m. - 1:11 p.m.

APA, Harvard, Vancouver, ISO, and other styles

19

Mesin, Luca, Paola Porcu, Debora Russu, Gabriele Farina, Luigi Borzì, Wei Zhang, Yuzhu Guo, and Gabriella Olmo. "A Multi-Modal Analysis of the Freezing of Gait Phenomenon in Parkinson’s Disease." Sensors 22, no. 7 (March 29, 2022): 2613. http://dx.doi.org/10.3390/s22072613.

Full text

Abstract:

Background: Freezing of Gait (FOG) is one of the most disabling motor complications of Parkinson’s disease, and consists of an episodic inability to move forward, despite the intention to walk. FOG increases the risk of falls and reduces the quality of life of patients and their caregivers. The phenomenon is difficult to appreciate during outpatients visits; hence, its automatic recognition is of great clinical importance. Many types of sensors and different locations on the body have been proposed. However, the advantages of a multi-sensor configuration with respect to a single-sensor one are not clear, whereas this latter would be advisable for use in a non-supervised environment. Methods: In this study, we used a multi-modal dataset and machine learning algorithms to perform different classifications between FOG and non-FOG periods. Moreover, we explored the relevance of features in the time and frequency domains extracted from inertial sensors, electroencephalogram and skin conductance. We developed both a subject-independent and a subject-dependent algorithm, considering different sensor subsets. Results: The subject-independent and subject-dependent algorithms yielded accuracies of 85% and 88% in the leave-one-subject-out and leave-one-task-out test, respectively. Results suggest that the inertial sensors positioned on the lower limb are generally the most significant in recognizing FOG. Moreover, the performance impairment experienced when using a single tibial accelerometer instead of the optimal multi-modal configuration is limited to 2–3%. Conclusions: The achieved results disclose the possibility of getting a good FOG recognition using a minimally invasive set-up made of a single inertial sensor. This is very significant in the perspective of implementing a long-term monitoring of patients in their homes, during activities of daily living.

APA, Harvard, Vancouver, ISO, and other styles

20

Paidi, Santosh K., Joel R. Troncoso, Narasimhan Rajaram, and Ishan Barman. "Abstract 1943: Elucidating early tumor microenvironmental changes due to immunotherapy with label-free Raman spectroscopy and machine learning." Cancer Research 82, no. 12_Supplement (June 15, 2022): 1943. http://dx.doi.org/10.1158/1538-7445.am2022-1943.

Full text

Abstract:

Abstract Clinical benefit is observed in only a limited fraction of patients that undergo immunotherapy for a variety of cancer types. Therefore, the determination of robust biomarkers for accurate prediction of response to immunotherapeutic agents remains one of the grand challenges of 21st century. Our primary goal was to investigate if phenotypic differences due to treatment with ICI can be recognized with minimally perturbative molecular tools and guide personalization of immunotherapy. In this work, we provide first-in-class evidence that Raman spectroscopy (an optical method) and machine learning allows sensitive detection of early changes in biomolecular composition of tumors in response to immunotherapy with immune checkpoint inhibitors (ICI). By studying the widely investigated CT26 murine model of colorectal cancer treated with anti-CTLA-4 (n = 8) and anti-PD-L1 (n = 7) ICIs and controls (n = 10), we revealed new biological insights into the nature and degree of microenvironmental modifications induced by exposure to clinically relevant doses of ICI. Multivariate curve resolution-alternating least squares (MCR-ALS) decomposition of Raman spectral datasets revealed early changes in lipid, nucleic acid, and collagen content of the tumors following therapy. We trained supervised classification models - support vector machines and random forests on the spectral datasets and showed that the models provided excellent prediction accuracies for response to both ICIs and delineated spectral markers specific to each therapy, consistent with their differential mechanisms of action. On the basis of these findings, we sought to determine if the tumor microenvironment changes delineated by Raman spectroscopy correspond to proteomic alterations via quantitative mass spectrometry. Of the more than 6600 proteins identified, about 136 proteins were found to be significantly different in treated tumors relative to controls (p < 0.05 and log2 fold change of > 2). A subset of these differentially expressed proteins is known to regulate lipid metabolism and extracellular matrix composition, while others are known to control transcriptome dynamics or are associated with response to ICI therapy, thereby corroborating our Raman spectroscopic measurements. Our observation of biomolecular changes in the TME should catalyze detailed investigations for translating such markers and label-free Raman spectroscopy for clinical monitoring of immunotherapy response in cancer patients. Citation Format: Santosh K. Paidi, Joel R. Troncoso, Narasimhan Rajaram, Ishan Barman. Elucidating early tumor microenvironmental changes due to immunotherapy with label-free Raman spectroscopy and machine learning [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1943.

APA, Harvard, Vancouver, ISO, and other styles

21

Zeng, Shan, Mark Vaughan, Zhaoyan Liu, Charles Trepte, Jayanta Kar, Ali Omar, David Winker, et al. "Application of high-dimensional fuzzy <i>k</i>-means cluster analysis to CALIOP/CALIPSO version 4.1 cloud–aerosol discrimination." Atmospheric Measurement Techniques 12, no. 4 (April 12, 2019): 2261–85. http://dx.doi.org/10.5194/amt-12-2261-2019.

Full text

Abstract:

Abstract. This study applies fuzzy k-means (FKM) cluster analyses to a subset of the parameters reported in the CALIPSO lidar level 2 data products in order to classify the layers detected as either clouds or aerosols. The results obtained are used to assess the reliability of the cloud–aerosol discrimination (CAD) scores reported in the version 4.1 release of the CALIPSO data products. FKM is an unsupervised learning algorithm, whereas the CALIPSO operational CAD algorithm (COCA) takes a highly supervised approach. Despite these substantial computational and architectural differences, our statistical analyses show that the FKM classifications agree with the COCA classifications for more than 94 % of the cases in the troposphere. This high degree of similarity is achieved because the lidar-measured signatures of the majority of the clouds and the aerosols are naturally distinct, and hence objective methods can independently and effectively separate the two classes in most cases. Classification differences most often occur in complex scenes (e.g., evaporating water cloud filaments embedded in dense aerosol) or when observing diffuse features that occur only intermittently (e.g., volcanic ash in the tropical tropopause layer). The two methods examined in this study establish overall classification correctness boundaries due to their differing algorithm uncertainties. In addition to comparing the outputs from the two algorithms, analysis of sampling, data training, performance measurements, fuzzy linear discriminants, defuzzification, error propagation, and key parameters in feature type discrimination with the FKM method are further discussed in order to better understand the utility and limits of the application of clustering algorithms to space lidar measurements. In general, we find that both FKM and COCA classification uncertainties are only minimally affected by noise in the CALIPSO measurements, though both algorithms can be challenged by especially complex scenes containing mixtures of discrete layer types. Our analysis results show that attenuated backscatter and color ratio are the driving factors that separate water clouds from aerosols; backscatter intensity, depolarization, and mid-layer altitude are most useful in discriminating between aerosols and ice clouds; and the joint distribution of backscatter intensity and depolarization ratio is critically important for distinguishing ice clouds from water clouds.

APA, Harvard, Vancouver, ISO, and other styles

22

Healy, NA, KH Chang, JB Conneely, C. Malone, and MJ Kerin. "Impact of SupervIsed TraInIng on the AcquIsItIon of SImulated LaparoscopIc SkIlls." Bulletin of the Royal College of Surgeons of England 95, no. 6 (June 1, 2013): 1–6. http://dx.doi.org/10.1308/003588413x13643054410340.

Full text

Abstract:

Laparoscopy or minimally invasive surgery requires surgeons to attain proficiency in skills that are fundamentally different to those required for open surgery. As a result, it both challenges junior trainees and surgeons who are experienced in open surgery. Not surprisingly, the initial learning phase of laparoscopy has been associated with an increased incidence of serious complications. Owing to time constraints and the ethical and safety considerations of allowing novices to perform laparoscopic surgery on patients, alternative methods have been sought to train junior surgeons on the basics of laparoscopic surgery.

APA, Harvard, Vancouver, ISO, and other styles

23

Bolen, Mel C., and Patricia C. Martin. "Undergraduate Research Abroad: Challenges and Rewards." Frontiers: The Interdisciplinary Journal of Study Abroad 12, no. 1 (November 15, 2005): xi—xvi. http://dx.doi.org/10.36366/frontiers.v12i1.165.

Full text

Abstract:

Why should international educators encourage research abroad? The work of the students represented in this Special Volume of Frontiers exemplifies the best of undergraduate research abroad. Their research shows an achievement of one, or all, of the goals international educators typically set for learning abroad: linguistic competence, cross-cultural skills, cultural competence, and disciplinary learning. Research abroad often holds strong incentives for successful student learning. Students choose their own research topics, providing intrinsic motivation to move beyond superficial explorations of their topic. Fulfilling faculty expectations for student learning, whether in the form of a paper, thesis, data collection or ethnographic study provides extrinsic motivation. The value of disciplinary learning abroad, especially in course-based programs, disputed on home campuses. Undergraduate research abroad can demonstrate that the cultural context of learning enhances the disciplinary knowledge gained. Disciplinary learning in another cultural context can correct culturally-ingrained research biases. Students gain knowledge difficult to capture without the cultural exposure provided by the experience abroad, which informs their work with nuances of first-hand research, moving it beyond the intellectual. Home-campus faculty may be less skeptical of the merits of sending students abroad for disciplinary learning if that experience results in an increase in knowledge or a demonstration of the application of previously gained disciplinary knowledge in a new context. Developing research skills in an international context means that students must learn how to navigate in another culture. Students must interact with people who are not their peers and who are outside a traditional classroom setting. By approaching organizations and individuals that inform their research, students learn much about the workings of the culture. And success in one attempt to navigate a host-culture can lead to success in further attempts. For the student-researcher, persistence is necessary because their research goal depends on successfully gaining access to the information they require. Cross-cultural skills are the tools that enable student-researchers to accomplish their goals and finish their projects. In order to achieve this in non-English language locations, students must develop a certain level of linguistic competence or, if using an interpreter, basic forms of communication in the host language. They must develop these competencies not only in everyday topics, but also in their fields of research. How will they ask about their topic if they do not learn some of the vocabulary? How will they obtain the help or information they need if they cannot ask people for it in appropriate forms? Since a research project typically requires a number of weeks to complete, student-researchers are likely to use these linguistic skills on an on-going basis. As a result, the linguistic competency gained is reinforced, and becomes more permanent. This cultural and linguistic learning can lead students to develop generalized cross-cultural skills with the assistance of international educators. We can provide valuable help to students doing research by asking them questions that will encourage them to realize that these skills transfer into other cultural situations. Often it requires simple queries: “What did you do to get this information? Did you have someone specific in the culture that gave you good advice? How did you find this person? What steps did you take when you succeeded in doing a piece of your research? When you did not succeed how did you figure out what went wrong? What did you do to try again? Beyond these basic questions, there are larger ones that can spur on student learning: “What did you learn from doing this project that would allow you to do another one in a completely different culture? How did you make sure your project was culturally appropriate? Did you think about making your project useful for local people? How would you share these results in the most effective way?” In posing these questions, we encourage students to examine the specific context of their research, and also to consider a meta-level analysis that places their research in a broader context. The hope is that students will see these skills in the wider global context, and that future cultural learning will be analyzed in a similar manner and transferred into other cross-cultural situations. If we achieve this, then we have certainly met the highest goals of encouraging students to learn to transcend cultural differences in constructive ways and to adapt to differing cultural modes as appropriate. Student research abroad can be a powerful way to accomplish all types of cultural learning. Supporting Undergraduate Research Abroad Even with these benefits, not many undergraduate students undertake research opportunities abroad. Faculty may advise students that research in their chosen discipline is better done at home, given the resources of the home campus. Students may be told that their language skills are not strong enough or that they are simply not mature enough as scholars in their disciplines to conduct relevant research. Students may be encouraged to conduct research or participate in directed study, but not to do field work or participate in experiential learning. A student may be able to receive credit for an internship that requires a substantial paper, but not for an ethnographic study. Moreover, the very idea of conducting research may be daunting to some students. Efforts should be made to advertise existing research opportunities abroad and to encourage new ideas for conducting research. If undergraduate research is endorsed by the highest academic officers of our institutions, our Presidents, Provosts and Academic Deans, faculty are more likely to provide encouragement and support, and then students will be more likely to pursue these options. International educators can assist these efforts by creating programs that offer research options, advertising such programs, and, most importantly, finding funding sources for such efforts. In order for students to take advantage of possible opportunities, it may be necessary to find ways to register students who might otherwise travel abroad independently (and thereby not be registered at their home institutions) in credit-bearing programs that would make them eligible for funding. The National Security Education Program David L. Boren Undergraduate Scholarships provides a model that allows advanced undergraduates with strong language skills to apply for funding for individually-arranged, supervised independent study. International educators may also help by designing processes on the home campus that support student research abroad. Research can take many forms, from the use of original documents and artifacts in libraries, archives, and museums, to service-learning, conducting field work, joining a research group, conducting interviews, doing a creative project, or interning or volunteering for an organization. On-campus administrative processes should make clear to students what types of projects are eligible to receive credit. If a student expects to receive credit at their home institution, they need to be able to review easily the criteria for determining whether credit will be granted with the appropriate on-campus authority (e.g. academic dean, department head, or registrar). Receiving credit helps to motivate the student and to validate the undertaking; making the credit-granting process clear can make a big difference to students exploring these options. It also assures that there will be faculty input, if not throughout the project, at least in the determination of granting credit on the home campus. In designing programs abroad with research components, faculty involvement is essential. Indeed, faculty supervision and support can make or break such projects for students. Faculty supervisors on the home campus or abroad will be more likely to agree to support a student researcher if they feel that this is a recognized part of their teaching. The supervision of an independent study can be time-consuming. Do departments consider this supervision when assigning workloads? Is extra compensation provided? Should these financial concerns be addressed in the budgets of the abroad programs? Can students continue follow-up work with faculty after they return home? Faculty supervision of student research abroad may follow various models. In some cases, research is an integral part of a study abroad program. Arrangements may be made to train the student on-site, perhaps as part of a course. The student conducts the research on-site, under the supervision of a resident director, or an on-site faculty member, and the course ultimately becomes a part of the student’s academic record, along with all other courses taken abroad. Another model has a faculty member at the student’s home institution supervising the student, along with some support given by a local faculty member. This model requires effective communication between the student and the faculty member on the home campus. In both cases clear goals need to be established about the nature of the project, research methods, and the final product. Fortunately, many of these formats can follow timelines and processes already developed on the home campus. However, once in the host country, parameters may change. Students may discover new opportunities, or their original ideas and plans may not be feasible. The logistics of conducting research in an international setting may make it impossible to keep to the original goals. In addition to guiding research and assessing the final product, faculty can serve in other important roles. They may introduce students to opportunities to submit their work for publication, present it at professional conferences, or compete for academic awards. Undergraduate research funding from the home institution might require a student to present their findings. Some institutions organize annual opportunities for students to give oral presentations or poster sessions during research fairs or conferences on campus. Others have a journal of student research. Resources and opportunities that are provided to students who conduct research on campus should also be extended to those whose work is done overseas. In many cases students may use the research conducted abroad as the foundation for a senior thesis. Students may choose to conduct independent research abroad. If students do research and are not enrolled in a program (e.g., during the summer) and have been encouraged to do so by their institution, have received funds from their institution, and will perhaps receive credit, their home institution should prepare them for the experience. Faculty and administrators should conduct seminars, orientation programs, and research methodology sessions to prepare students. Institutions should consider offering benefits to individual students that they would normally offer to students going abroad on registered study abroad programs (i.e., access to emergency services). By regularizing these aspects of going abroad, even to conduct independent research, institutions will be better able to track students who are conducting research abroad. At the minimum, students going abroad independently should be directed to information sources on health, safety, and security preparations when traveling to the host country. Additionally, students should be made aware of any legal issues related to doing research, and have their proposals vetted through the usual campus channels such as institutional review boards. Outcomes of Student Research Little data exists on how many students conduct research abroad, or on how this experience affects their academic work when they return to campus as well as their career decisions after graduation. Currently the national data on study abroad from the Institute of International Education’s annual Open Doors report documents only participation in credit-bearing programs. No statistics are kept on the numbers of students conducting research abroad who will not receive credit for their research. Among the questions this lack of data raises are: Are these students more likely to attend graduate school in their major discipline and to look for opportunities to conduct research abroad? Are they more likely to pursue independent research in sites that are less common as study abroad destinations? If they conducted research in a foreign language, are they more likely to study this language at an advanced level? The Lincoln Commission articulates the need for more in-depth international educational experiences, of which research can play an important part: An understanding of the diverse cultures of the world, especially those of developing countries, should be an essential component of the 21st-century education of our nation’s students. Direct exposure to foreign languages and other aspects of these cultures can best be achieved through a meaningful study abroad experience. Broader global awareness among America’s future leaders will, in turn, lead to more effective U.S. foreign policy, greater security from terrorism and economic resilience in the increasingly competitive world of trade. The research benefits discussed above mesh well with the current national interests that call for broader global awareness, and international educators should seriously consider designing and supporting research opportunities as one of their efforts to increase such competencies. Conducting research abroad can be one of the most personally satisfying parts of a student’s undergraduate academic career. These undertakings can also be frustrating and fraught with difficulties unless there is good planning and communication with a students’ academic advisors. International educators can assist in making these opportunities as effective, safe, and rewarding as possible. Faculty and administrators should look for ways to help students overcome the potential barriers to a successful experience, including the credit-approval process, organizing faculty supervision, and accessing information about opportunities, as well as funding. Since undergraduate student research abroad can lead to improved linguistic competence, cross-cultural skills, cultural competence, and disciplinary knowledge, we should do everything we can to develop and promote it. Mell C. Bolen~ Brown University Pat Martin~ University of Pennsylvania About the IFSA Foundation: The IFSA Foundation was founded to assist the continuing advancement of international education through direct and indirect support of study abroad by undergraduate students from U.S. colleges and universities. This is the first foundation whose mission focuses exclusively on the advancement of study abroad as a major component of higher education in the United States The Directors of the Foundation believe that effective study abroad for U.S. students involves minimally a semester length experience and, wherever possible, close academic integration with recognized universities abroad and, in all cases, the provision by the program sponsors of comprehensive student services to maximize the academic and cultural benefit of the experience and provide for the welfare and security of students. The IFSA Foundation intends to concentrate on projects that will provide muchneeded strength to undergraduate study abroad in the United States: scholarships to extend opportunities (particularly among underrepresented groups); start-up funding for underdeveloped areas of semester and full year study abroad programs; and support for the development of innovative projects designed to broaden the scope of the undergraduate study abroad experience. The IFSA Foundation grants are given only to institutions; scholarship grants are not tied to participation of students on any particular program. For more information: http://www.theifsafoundation.org

APA, Harvard, Vancouver, ISO, and other styles

24

Fayez, R., A. AlMuntashery, G. Bodie, A. Almamar, R. S. Gill, I. Raîche, C. L. Mueller, et al. "Canadian Surgery Forum1 Is laparoscopic sleeve gastrectomy a reasonable stand-alone procedure for super morbidly obese patients?2 Postoperative monitoring requirements of patients with obstructive sleep apnea undergoing bariatric surgery3 Role of relaparoscopy in the diagnosis and treatment of bariatric complications in the early postoperative period4 Changes of active and total ghrelin, GLP-1 and PYY following restrictive bariatric surgery and their impact on satiety: comparison of sleeve gastrectomy and adjustable gastric banding5 Prioritization and willingness to pay for bariatric surgery: the patient perspective6 Ventral hernia at the time of laparoscopic gastric bypass surgery: Should it be repaired?7 Linear stapled gastrojejunostomy with transverse handsewn enterotomy closure significantly reduces strictures for laparoscopic Roux-en-Y bypass8 Laparoscopic biliopancreatic diversion with duodenal switch as second stage for super super morbidly obese patients. Do all patients benefit?9 Sleeve gastrectomy in the super super morbidly obese (BMI > 60 kg/m²): a Canadian experience10 Laparoscopic gastric bypass for the treatment of refractory idiopathic gastroparesis: a report of 2 cases11 Duodeno-ileal switch as a primary bariatric and metabolic surgical option for the severely obese patient with comorbidities: review of a single-institution case series of duodeno-ileal intestinal bypass12 Management of large paraesophageal hernias in morbidly obese patients with laparoscopic sleeve gastrectomy: a case series13 Early results of the Ontario bariatric surgical program: using the bariatric registry14 Improving access to bariatric surgical care: Is universal health care the answer?15 Early and liberal postoperative exploration can reduce morbidity and mortality in patients undergoing bariatric surgery16 Withdrawn17 Identification and assessment of technical errors in laparoscopic Roux-en-Y gastric bypass18 A valid and reliable tool for assessment of surgical skill in laparoscopic Roux-en-Y gastric bypass19 Psychiatric predictors of presurgery drop-out following suitability assessment for bariatric surgery20 Predictors of outcomes following Roux-en-Y gastric bypass surgery at The Ottawa Hospital21 Prophylactic management of cholelithiasis in bariatric patients: Is routine cholecystectomy warranted?22 Early outcomes of Roux-en-Y gastric bypass in a publicly funded obesity program23 Similar incidence of gastrojejunal anastomotic stricture formation with hand-sewn and 21 mm circular stapler techniques during Roux-en-Y gastric bypass24 (CAGS Basic Science Award) Exogenous glucagon-like peptide-1 improves clinical, morphological and histological outcomes of intestinal adaptation in a distal-intestinal resection piglet model of short bowel syndrome25 (CAGS Clinical Research Award) Development and validation of a comprehensive curriculum to teach an advanced minimally invasive procedure: a randomized controlled trial26 Negative-pressure wound therapy (iVAC) on closed, high-risk incisions following abdominal wall reconstruction27 The impact of seed granting on research in the University of British Columbia Department of Surgery28 Quality of surgical care is inadequate for elderly patients29 Recurrence of inguinal hernia in general and hernia specialty hospitals in Ontario, Canada30 Oncostatin M receptor deficiency results in increased mortality in an intestinal ischemia reperfusion model in mice31 Laparoscopic repair of large paraesophageal hernias with anterior gastropexy: a multicentre trial32 Response to preoperative medical therapy predicts success of laparoscopic splenectomy for immune thrombocytopenic purpura33 Perioperative sepsis, but not hemorrhagic shock, promotes the development of cancer metastases in a murine model34 Measuring the impact of implementing an acute care surgery service on the management of acute biliary disease35 Patient flow and efficiency in an acute care surgery service36 The relationship between treatment factors and postoperative complications after radical surgery for rectal cancer37 Risk of ventral hernia after laparoscopic colon surgery38 Urinary metabolomics as a tool for early detection of Barrett’s and esophageal cancer39 Construct validity of individual and summary performance metrics associated with a computer-based laparo-scopic simulator40 Impact of a city-wide health system reorganization on emergency department visits in hospitals in surrounding communities41 Transcatheter aortic valve implantation for the nonoperative management of aortic stenosis: a cost-effectiveness analysis42 Breast cancer: racial differences in age of onset. A potential confounder in Canadian screening recommendations43 Risk taking in surgery: in and out of the comfort zone44 A tumour board in the office: Track those cancer patients!45 Increased patient BMI is not associated with advanced colon cancer stage or grade on presentation: a retrospective chart review46 Consensus statements regarding the multidisciplinary care of limb amputation patients in disasters or humanitarian emergencies. Report of the 2011 Humanitarian Action Summit Surgical Working Group on amputations following disasters or conflict47 Learning the CanMEDS role of professional: a pilot project of supervised discussion groups addressing the hidden curriculum48 Assessing the changing scope of training in Canadian general surgery programs: expected versus actual experience49 Predicting need for surgical management for massive gastrointestinal hemorrhage50 International health care experience: using CanMEDS to evaluate learning outcomes following a surgical mission in Mampong, Ghana51 The open abdomen: risk factors for mortality and rates of closure52 How surgeons think: an exploration of mental practice in surgical preparation53 The surgery wiki: a novel method for delivery of under-graduate surgical education54 Understanding surgical residents’ postoperative practices before implementing an enhanced recovery after surgery (ERAS) guideline at the University of Toronto55 From laparoscopic transabdominal to posterior retroperitoneal adrenalectomy: a paradigm shift in operative approach56 A retrospective audit of outcomes in patients over the age of 80 undergoing acute care abdominal surgery57 Canadian general surgery residents’ perspectives on work-hour regulations58 Timing of surgical intervention and its outcomes in acute appendicitis59 Preparing surgical trainees to deal with adverse events. An outline of learning issues60 Acute care surgical service: surgeon agreement at the time of handover61 Predicting discharge of elderly patients to prehospitalization residence following emergency general surgery62 Morbidity and mortality after emergency abdominal surgery in octo- and nonagenarians63 The impact of acute abdominal illness and urgent admission to hospital on the living situation of elderly patients64 A comparison of laparoscopic versus open subtotal gastrectomy for antral gastric adenocarcinoma: a North American perspective65 Minimally invasive excision of ectopic mediastinal parathyroid adenomas66 Perioperative outcomes of laparoscopic hernia repair in a tertiary care centre: a single institution’s experience67 Evaluation of a student-run, practical and didactic curriculum for preclerkship medical students68 Joseph Lister: Father of Modern Surgery69 Comparisons of melanoma sentinel lymph node biopsy prediction nomograms in a cohort of Canadian patients70 Local experience with myocutaneous flaps after extensive pelvic surgery71 The treatment of noncirrhotic splanchnic vein thrombosis: Is anticoagulation enough?72 Implementation of an acute care surgery service does not affect wait-times for elective cancer surgeries: an institutional experience73 Use of human collagen mesh for closure of a large abdominal wall defect, after colon cancer surgery, a case report74 The role of miR-200b in pulmonary hypoplasia associated with congenital diaphragmatic hernia75 Systematic review and meta-analysis of electrocautery versus scalpel for incising epidermis and dermis76 Accuracy of sentinel lymph node biopsy for early breast cancer in the community setting in St. John’s, New-foundland: results of a retrospective review77 Acute surgical outcomes in the 80 plus population78 The liberal use of platelets transfusions in the acute phase of trauma resuscitation: a systematic review79 Implementation of an acute care surgical on call program in a Canadian community hospital80 Short-term outcomes following paraesophageal hernia repair in the elderly patient81 First experience with single incision surgery: feasibility in the pediatric population and cost evaluation82 The impact of the establishment of an acute care surgery unit on the outcomes of appendectomies and cholecystectomies83 Description and preliminary evaluation of a low-cost simulator for training and evaluation of flexible endoscopic skills84 Tumour lysis syndrome in metastatic colon cancer: a case report85 Acute care surgery service model implementation study at a single institution86 Colonic disasters approached by emergent subtotal and total colectomy: lessons learned from 120 consecutive cases87 Acellular collagen matrix stent to protect bowel anastomoses88 Lessons we learned from preoperative MRI-guided wire localization of breast lesions: the University Health Network (UHN) experience89 Interim cost comparison for the use of platinum micro-coils in the operative localization of small peripheral lung nodules90 Routine barium esophagram has minimal impact on the postoperative management of patients undergoing esophagectomy for esophageal cancer91 Iron deficiency anemia is a common presenting issue with giant paraesophageal hernia and resolves following repair92 A randomized comparison of different ventilation strategies during thoracotomy and lung resection93 The Canadian Lung Volume Reduction Surgery study: an 8-year follow-up94 A comparison of minimally invasive versus open Ivor-Lewis esophagectomy95 A new paradigm in the follow-up after curative resection for lung cancer: minimal-dose CT scan allows for early detection of asymptomatic cancer activity96 Predictors of lymph node metastasis in early esophageal adenocarcinoma: Is endoscopic resection worth the risk?97 How well can thoracic surgery residents operate? Comparing resident and program director opinions98 The impact of extremes of age on short- and long-term outcomes following surgical resection of esophageal malignancy99 Epidermal growth factor receptor targeted gold nanoparticles for the enhanced radiation treatment of non–small cell lung cancer100 Laparoscopic Heller myotomy results in excellent outcomes in all subtypes of achalasia as defined by the Chicago classification101 Neoadjuvant chemoradiation versus surgery in managing esophageal cancer102 Quality of life postesophagectomy for cancer!103 The implementation, evolution and translocation of standardized clinical pathways can improve perioperative outcomes following surgical treatment of esophageal cancer104 A tissue-mimicking phantom for applications in thoracic surgical simulation105 Sublobar resection compared with lobectomy for early stage non–small cell lung cancer: a single institution study106 Not all reviews are equal: the quality of systematic reviews and meta-analyses in thoracic surgery107 Do postoperative complications affect health-related quality of life after video-assisted thoracoscopic lobectomy for patients with lung cancer? A cohort study108 Thoracoscopic plication for palliation of dyspnea secondary to unilateral diaphragmatic paralysis: A worthwhile venture?109 Thoracic surgery experience in Canadian general surgery residency programs110 Perioperative morbidity and pathologic response rates following neoadjuvant chemotherapy and chemoradiation for locally advanced esophageal carcinoma111 An enhanced recovery pathway reduces length of stay after esophagectomy112 Predictors of dysplastic and neoplastic progression of Barrett’s esophagus113 Recurrent esophageal cancer complicated by tracheoesophageal fistula: management by means of palliative airway stenting114 Pancreaticopleural fistula-induced empyema thoracis: principles and results of surgical management115 Prognostic factors of early postoperative mortality following right extended hepatectomy116 Optimizing steatotic livers for transplantation using a cell-penetrating peptide CPP-fused heme oxygenase117 Video outlining the technical steps for a robot-assisted laparoscopic pancreaticoduodenectomy118 Establishment of a collaborative group to conduct innovative clinical trials in Canada119 Hepatic resection for metastatic malignant melanoma: a systematic review and meta-analysis120 Acellular normothermic ex vivo liver perfusion for donor liver preservation121 Pancreatic cancer and predictors of survival: comparing the CA 19–9/bilirubin ratio with the McGill Brisbane Scoring System122 Staged liver resections for bilobar hepatic colorectal metastases: a single centre experience123 Economic model of observation versus immediate resection of hepatic adenomas124 Resection of colorectal liver metastasis in the elderly125 Acceptable long-term survival in patients undergoing liver resection for metastases from noncolorectal, non-neuroendocrine, nonsarcoma malignancies126 Patient and clinicopathological features and prognosis of CK19+ hepatocellular carcinomas: a case–control study127 The management of blunt hepatic trauma in the age of angioembolization: a single centre experience128 Liver resections for noncolorectal and non-neuroendocrine metastases: an evaluation of oncologic outcomes129 Developing an evidence-based clinical pathway for patients undergoing pancreaticoduodenectomy130 Hepatitis C infection and hepatocellular carcinoma in liver transplant: a 20 year experience131 The effect of medication on the risk of post-ERCP pancreatitis132 Temporal trends in the use of diagnostic imaging for patients with hepato-pancreato-biliary (HPB) conditions: How much ionizing radiation are we really using?196 A phase II study of aggressive metastasectomy for intra-and extrahepatic metastases from colorectal cancer133 Why do women choose mastectomy for breast cancer treatment? A conceptual framework for understanding surgical decision-making in early-stage breast cancer134 Synoptic operative reporting: documentation of quality of care data for rectal cancer surgery135 Learning curve analysis for cytoreductive surgery: a useful application of the cumulative sum (CUSUM) method136 Pancreatic cancer is strongly associated with a unique urinary metabolomic signature137 Concurrent neoadjuvant chemo/radiation in locally advanced breast cancer138 Impact of positron emission tomography on clinical staging of newly diagnosed rectal cancer: a specialized single centre retrospective study139 An evaluation of intraoperative Faxitron microradiography versus conventional specimen radiography for the excision of nonpalpable breast lesions140 Comparison of breast cancer treatment wait-times in the Southern Interior of British Columbia in 2006 and 2010141 Factors affecting lymph nodes harvest in colorectal carcinoma142 Laparoscopic adrenalectomy for metastases143 You have a message! Social networking as a motivator for fundamentals of laparoscopic surgery (FLS) training144 The evaluation and validation of a rapid diagnostic and support clinic for women assessment for breast cancer145 Oncoplastic breast surgery: oncologic benefits and limitations146 A qualitative study on rectal cancer patients’ preferences for location of surgical care147 The effect of surgery on local recurrence in young women with breast cancer148 Elevated IL-6 and IL-8 levels in tumour microenvironment is not associated with increased serum levels in humans with Pseudomyxoma peritonei and peritoneal mesothelioma149 Conversion from laparoscopic to open approach during gastrectomy: a population-based analysis150 A scoping review of surgical process improvement tools (SPITs) in cancer surgery151 Splenectomy during gastric cancer surgery: a population-based study152 Defining the polo-like kinase 4 (Plk4) interactome in cancer cell protrusions153 Neoadjuvant imatinib mesylate for locally advanced gastrointestinal stromal tumours154 Implementing results from ACOSOG Z0011: Practice-changing or practice-affirming?155 Should lymph node retrieval be a surgical quality indicator in colon cancer?156 Long-term outcomes following resection of retroperitoneal recurrence of colorectal cancer157 Clinical research in surgical oncology: an analysis of clinicaltrials.gov158 Radiation therapy after breast conserving surgery: When are we missing the mark?159 The accuracy of endorectal ultrasound in staging rectal lesions in patients undergoing transanal endoscopic microsurgery160 Quality improvement in gastrointestinal cancer surgery: expert panel recommendations for priority research areas161 Factors influencing the quality of local management of ductal carcinoma in situ: a cohort study162 Papillary thyroid microcarcinoma: Does size matter?163 Hyperthermic isolated limb perfusion for extremity soft tissue sarcomas: systematic review of clinical efficacy and quality assessment of reported trials164 Adherence to antiestrogen therapy in seniors with breast cancer: How well are we doing?165 Parathyroid carcinoma: Challenging the surgical dogma?166 A qualitative assessment of the journey to delayed breast reconstruction195 The role of yoga therapy in breast cancer patients167 Outcomes reported in comparative studies of surgical interventions168 Enhanced recovery pathways decrease length of stay following colorectal surgery, but how quickly do patients actually recover?169 The impact of complications on bed utilization after elective colorectal resection170 Impact of trimodal prehabilitation program on functional recovery after colorectal cancer surgery: a pilot study171 Complex fistula-in-ano: Should the plug be abandoned in favour of the LIFT or BioLIFT?172 Prognostic utility of cyclooxygenase-2 expression by colon and rectal cancer173 Laparoscopic right hemicolectomy with complete mesocolic excision provides acceptable perioperative outcomes but is complex and time-consuming: analysis of learning curves for a novice minimally invasive surgeon174 Intraoperative quality assessment following double stapled circular colorectal anastomosis175 Improving patient outcomes through quality assessment of rectal cancer care176 Are physicians willing to accept a decrease in treatment effectiveness for improved functional outcomes for low rectal cancer?177 Turnbull-Cutait delayed coloanal anastomosis for the treatment of distal rectal cancer: a prospective cohort study178 Preoperative high-dose rate brachytherapy in preparation for sphincter preservation surgery for patients with advanced cancer of the lower rectum179 Impact of an enhanced recovery program on short-term outcomes after scheduled laparoscopic colon resection180 The clinical results of the Turnbull-Cutait delayed coloanal anastomosis: a systematic review181 Is a vertical rectus abdominus flap (VRAM) necessary? An analysis of perineal wound complications182 Fistula plug versus endorectal anal advancement flap for the treatment of high transsphincteric cryptoglandular anal fistulas: a systematic review and meta-analysis183 Maternal and neonatal outcomes following colorectal cancer surgery184 Transanal drainage to treat anastomotic leaks after low anterior resection for rectal cancer: a valuable option185 Trends in colon cancer in Ontario: 2002–2009186 Validation of electronically derived short-term outcomes in colorectal surgery187 A population-based assessment of transanal and endoscopic resection for adenocarcinoma of the rectum188 Laparoscopic colorectal surgery in the emergency setting: trends in the province of Ontario from 2002 to 2009189 Prevention of perineal hernia after laparoscopic and robotic abdominoperineal resection: review with case series of internal hernia through pelvic mesh which was placed in attempt to prevent perineal hernia190 Effect of rectal cancer treatments on quality of life191 The use of antibacterial sutures as an adjunctive preventative strategy for surgical site infection in Canada: an economic analysis192 Impact of socioeconomic status on colorectal cancer screening and stage at presentation: preliminary results of a population-based study from an urban Canadian centre193 Initial perioperative results of the first transanal endoscopic microsurgery (TEM) program in the province of Quebec194 Use of negative pressure wound therapy decreases perineal wound infections following abdominal perineal resection." Canadian Journal of Surgery 55, no. 4 Suppl 1 (August 2012): S63—S135. http://dx.doi.org/10.1503/cjs.016712.

Full text

APA, Harvard, Vancouver, ISO, and other styles

25

Birnie, Claire, and Tariq Alkhalifah. "Transfer learning for self-supervised, blind-spot seismic denoising." Frontiers in Earth Science 10 (December 12, 2022). http://dx.doi.org/10.3389/feart.2022.1053279.

Full text

Abstract:

Noise is ever present in seismic data and arises from numerous sources and is continually evolving, both spatially and temporally. The use of supervised deep learning procedures for denoising of seismic datasets often results in poor performance: this is due to the lack of noise-free field data to act as training targets and the large difference in characteristics between synthetic and field datasets. Self-supervised, blind-spot networks typically overcome these limitation by training directly on the raw, noisy data. However, such networks often rely on a random noise assumption, and their denoising capabilities quickly decrease in the presence of even minimally-correlated noise. Extending from blind-spots to blind-masks has been shown to efficiently suppress coherent noise along a specific direction, but it cannot adapt to the ever-changing properties of noise. To preempt the network’s ability to predict the signal and reduce its opportunity to learn the noise properties, we propose an initial, supervised training of the network on a frugally-generated synthetic dataset prior to fine-tuning in a self-supervised manner on the field dataset of interest. Considering the change in peak signal-to-noise ratio, as well as the volume of noise reduced and signal leakage observed, using a semi-synthetic example we illustrate the clear benefit in initialising the self-supervised network with the weights from a supervised base-training. This is further supported by a test on a field dataset where the fine-tuned network strikes the best balance between signal preservation and noise reduction. Finally, the use of the unrealistic, frugally-generated synthetic dataset for the supervised base-training includes a number of benefits: minimal prior geological knowledge is required, substantially reduced computational cost for the dataset generation, and a reduced requirement of re-training the network should recording conditions change, to name a few. Such benefits result in a robust denoising procedure suited for long term, passive seismic monitoring.

APA, Harvard, Vancouver, ISO, and other styles

26

Reichert, Johannes C., Georgi I. Wassilew, Eberhard von Rottkay, and Ulrich Noeth. "Compared learning curves of the direct anterior and anterolateral approach for minimally invasive hip replacement." Orthopedic Reviews 14, no. 3 (August 25, 2022). http://dx.doi.org/10.52965/001c.37500.

Full text

Abstract:

Minimally invasive hip arthroplasty becomes increasingly popular. It is technically challenging and the approaches used are associated with a considerable learning curve. This nurtures concerns regarding patient safety, surgical training, and cost effectiveness. Consequently, we initiated a study comparing the learning curves of a supervised trainee surgeon utilizing both the anterolateral and direct anterior approach (DAA) when introduced to minimally invasive hip replacement surgery. Outcome measurements included the Harris hip score (HHS), cup inclination and anteversion, offset and leg length, stem placement, surgical time and complications. Time from incision to suture decreased significantly over time but did not differ between both groups. The functional outcomes (HHS) after six weeks and three months were comparable (p=0.069 and 0.557) and within the expected range equalling 90.3 (anterior) and 89.2 (anterolateral) points. With both approaches safe component placement was readily achieved. Both offset and leg length, however, were reconstructed more reliably with the DAA (p=0.02 and 0.001). A higher rate of dislocations was seen with the anterior, more perioperative infections with the anterolateral approach. We suggest that supervision by an experienced surgeon favourably influences the learning curves for both the minimally invasive DAA and anterolateral approach and conclude that the greatest improvement is seen within the first 60 cases.

APA, Harvard, Vancouver, ISO, and other styles

27

Abdelhameed, Ahmed, and Magdy Bayoumi. "A Deep Learning Approach for Automatic Seizure Detection in Children With Epilepsy." Frontiers in Computational Neuroscience 15 (April 8, 2021). http://dx.doi.org/10.3389/fncom.2021.650050.

Full text

Abstract:

Over the last few decades, electroencephalogram (EEG) has become one of the most vital tools used by physicians to diagnose several neurological disorders of the human brain and, in particular, to detect seizures. Because of its peculiar nature, the consequent impact of epileptic seizures on the quality of life of patients made the precise diagnosis of epilepsy extremely essential. Therefore, this article proposes a novel deep-learning approach for detecting seizures in pediatric patients based on the classification of raw multichannel EEG signal recordings that are minimally pre-processed. The new approach takes advantage of the automatic feature learning capabilities of a two-dimensional deep convolution autoencoder (2D-DCAE) linked to a neural network-based classifier to form a unified system that is trained in a supervised way to achieve the best classification accuracy between the ictal and interictal brain state signals. For testing and evaluating our approach, two models were designed and assessed using three different EEG data segment lengths and a 10-fold cross-validation scheme. Based on five evaluation metrics, the best performing model was a supervised deep convolutional autoencoder (SDCAE) model that uses a bidirectional long short-term memory (Bi-LSTM) – based classifier, and EEG segment length of 4 s. Using the public dataset collected from the Children’s Hospital Boston (CHB) and the Massachusetts Institute of Technology (MIT), this model has obtained 98.79 ± 0.53% accuracy, 98.72 ± 0.77% sensitivity, 98.86 ± 0.53% specificity, 98.86 ± 0.53% precision, and an F1-score of 98.79 ± 0.53%, respectively. Based on these results, our new approach was able to present one of the most effective seizure detection methods compared to other existing state-of-the-art methods applied to the same dataset.

APA, Harvard, Vancouver, ISO, and other styles

28

de’Angelis, Nicola, Francesco Marchegiani, Carlo Alberto Schena, Jim Khan, Vanni Agnoletti, Luca Ansaloni, Ana Gabriela Barría Rodríguez, et al. "Training curriculum in minimally invasive emergency digestive surgery: 2022 WSES position paper." World Journal of Emergency Surgery 18, no. 1 (January 27, 2023). http://dx.doi.org/10.1186/s13017-023-00476-w.

Full text

Abstract:

Abstract Background Minimally invasive surgery (MIS), including laparoscopic and robotic approaches, is widely adopted in elective digestive surgery, but selectively used for surgical emergencies. The present position paper summarizes the available evidence concerning the learning curve to achieve proficiency in emergency MIS and provides five expert opinion statements, which may form the basis for developing standardized curricula and training programs in emergency MIS. Methods This position paper was conducted according to the World Society of Emergency Surgery methodology. A steering committee and an international expert panel were involved in the critical appraisal of the literature and the development of the consensus statements. Results Thirteen studies regarding the learning curve in emergency MIS were selected. All but one study considered laparoscopic appendectomy. Only one study reported on emergency robotic surgery. In most of the studies, proficiency was achieved after an average of 30 procedures (range: 20–107) depending on the initial surgeon’s experience. High heterogeneity was noted in the way the learning curve was assessed. The experts claim that further studies investigating learning curve processes in emergency MIS are needed. The emergency surgeon curriculum should include a progressive and adequate training based on simulation, supervised clinical practice (proctoring), and surgical fellowships. The results should be evaluated by adopting a credentialing system to ensure quality standards. Surgical proficiency should be maintained with a minimum caseload and constantly evaluated. Moreover, the training process should involve the entire surgical team to facilitate the surgeon’s proficiency. Conclusions Limited evidence exists concerning the learning process in laparoscopic and robotic emergency surgery. The proposed statements should be seen as a preliminary guide for the surgical community while stressing the need for further research.

APA, Harvard, Vancouver, ISO, and other styles

29

Dong, Sheng-tao, Jieyang Zhu, Hua Yang, Guangyi Huang, Chenning Zhao, and Bo Yuan. "Development and Internal Validation of Supervised Machine Learning Algorithm for Predicting the Risk of Recollapse Following Minimally Invasive Kyphoplasty in Osteoporotic Vertebral Compression Fractures." Frontiers in Public Health 10 (May 2, 2022). http://dx.doi.org/10.3389/fpubh.2022.874672.

Full text

Abstract:

BackgroundThe published literatures indicate that patients with osteoporotic vertebral compression fractures (OVCFs) benefit significantly from percutaneous kyphoplasty (PKP), but this surgical technique is associated with frequent postoperative recollapse, a complication that severely limits long-term postoperative functional recovery.MethodsThis study retrospectively analyzed single-segment OVCF patients who underwent bilateral PKP at our academic center from January 1, 2017 to September 30, 2019. Comparing the plain films of patients within 3 days after surgery and at the final follow-up, we classified patients with more than 10% loss of sagittal anterior height as the recollapse group. Univariate and multivariate logistic regression analyses were performed to determine the risk factors affecting recollapse after PKP. Based on the logistic regression results, we constructed one support vector machine (SVM) classifier to predict recollapse using machine learning (ML) algorithm. The predictive performance of this prediction model was validated by the receiver operating characteristic (ROC) curve, 10-fold cross validation, and confusion matrix.ResultsAmong the 346 consecutive patients (346 vertebral bodies in total), postoperative recollapse was observed in 40 patients (11.56%). The results of the multivariate logistical regression analysis showed that high body mass index (BMI) (Odds ratio [OR]: 2.08, 95% confidence interval [CI]: 1.58–2.72, p < 0.001), low bone mineral density (BMD) T-scores (OR: 4.27, 95% CI: 1.55–11.75, p = 0.005), presence of intravertebral vacuum cleft (IVC) (OR: 3.10, 95% CI: 1.21–7.99, p = 0.019), separated cement masses (OR: 3.10, 95% CI: 1.21–7.99, p = 0.019), cranial endplate or anterior cortical wall violation (OR: 0.17, 95% CI: 0.04–0.79, p = 0.024), cement-contacted upper endplate alone (OR: 4.39, 95% CI: 1.20–16.08, p = 0.025), and thoracolumbar fracture (OR: 6.17, 95% CI: 1.04–36.71, p = 0.045) were identified as independent risk factors for recollapse after a kyphoplasty surgery. Furthermore, the evaluation indices demonstrated a superior predictive performance of the constructed SVM model, including mean area under receiver operating characteristic curve (AUC) of 0.81, maximum AUC of 0.85, accuracy of 0.81, precision of 0.89, and sensitivity of 0.98.ConclusionsFor patients with OVCFs, the risk factors leading to postoperative recollapse were multidimensional. The predictive model we constructed provided insights into treatment strategies targeting secondary recollapse prevention.

APA, Harvard, Vancouver, ISO, and other styles

30

Wang, Haosheng, Tingting Fan, Bo Yang, Qiang Lin, Wenle Li, and Mingyu Yang. "Development and Internal Validation of Supervised Machine Learning Algorithms for Predicting the Risk of Surgical Site Infection Following Minimally Invasive Transforaminal Lumbar Interbody Fusion." Frontiers in Medicine 8 (December 20, 2021). http://dx.doi.org/10.3389/fmed.2021.771608.

Full text

Abstract:

Purpose: Machine Learning (ML) is rapidly growing in capability and is increasingly applied to model outcomes and complications in medicine. Surgical site infections (SSI) are a common post-operative complication in spinal surgery. This study aimed to develop and validate supervised ML algorithms for predicting the risk of SSI following minimally invasive transforaminal lumbar interbody fusion (MIS-TLIF).Methods: This single-central retrospective study included a total of 705 cases between May 2012 and October 2019. Data of patients who underwent MIS-TLIF was extracted by the electronic medical record system. The patient's clinical characteristics, surgery-related parameters, and routine laboratory tests were collected. Stepwise logistic regression analyses were used to screen and identify potential predictors for SSI. Then, these factors were imported into six ML algorithms, including k-Nearest Neighbor (KNN), Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), Multi-Layer Perceptron (MLP), and Naïve Bayes (NB), to develop a prediction model for predicting the risk of SSI following MIS-TLIF under Quadrant channel. During the training process, 10-fold cross-validation was used for validation. Indices like the area under the receiver operating characteristic (AUC), sensitivity, specificity, and accuracy (ACC) were reported to test the performance of ML models.Results: Among the 705 patients, SSI occurred in 33 patients (4.68%). The stepwise logistic regression analyses showed that pre-operative glycated hemoglobin A1c (HbA1c), estimated blood loss (EBL), pre-operative albumin, body mass index (BMI), and age were potential predictors of SSI. In predicting SSI, six ML models posted an average AUC of 0.60–0.80 and an ACC of 0.80–0.95, with the NB model standing out, registering an average AUC and an ACC of 0.78 and 0.90. Then, the feature importance of the NB model was reported.Conclusions: ML algorithms are impressive tools in clinical decision-making, which can achieve satisfactory prediction of SSI with the NB model performing the best. The NB model may help access the risk of SSI following MIS-TLIF and facilitate clinical decision-making. However, future external validation is needed.

APA, Harvard, Vancouver, ISO, and other styles

31

Werner, Charlotte, Josef G. Schönhammer, Marianne K. Steitz, Olivier Lambercy, Andreas R. Luft, László Demkó, and Chris Awai Easthope. "Using Wearable Inertial Sensors to Estimate Clinical Scores of Upper Limb Movement Quality in Stroke." Frontiers in Physiology 13 (May 3, 2022). http://dx.doi.org/10.3389/fphys.2022.877563.

Full text

Abstract:

Neurorehabilitation is progressively shifting from purely in-clinic treatment to therapy that is provided in both clinical and home-based settings. This transition generates a pressing need for assessments that can be performed across the entire continuum of care, a need that might be accommodated by application of wearable sensors. A first step toward ubiquitous assessments is to augment validated and well-understood standard clinical tests. This route has been pursued for the assessment of motor functioning, which in clinical research and practice is observation-based and requires specially trained personnel. In our study, 21 patients performed movement tasks of the Action Research Arm Test (ARAT), one of the most widely used clinical tests of upper limb motor functioning, while trained evaluators scored each task on pre-defined criteria. We collected data with just two wrist-worn inertial sensors to guarantee applicability across the continuum of care and used machine learning algorithms to estimate the ARAT task scores from sensor-derived features. Tasks scores were classified with approximately 80% accuracy. Linear regression between summed clinical task scores (across all tasks per patient) and estimates of sum task scores yielded a good fit (R2 = 0.93; range reported in previous studies: 0.61–0.97). Estimates of the sum scores showed a mean absolute error of 2.9 points, 5.1% of the total score, which is smaller than the minimally detectable change and minimally clinically important difference of the ARAT when rated by a trained evaluator. We conclude that it is feasible to obtain accurate estimates of ARAT scores with just two wrist worn sensors. The approach enables administration of the ARAT in an objective, minimally supervised or remote fashion and provides the basis for a widespread use of wearable sensors in neurorehabilitation.

APA, Harvard, Vancouver, ISO, and other styles

32

Jacobsen, Christian, and Karthik Duraisamy. "Disentangling Generative Factors of Physical Fields Using Variational Autoencoders." Frontiers in Physics 10 (June 30, 2022). http://dx.doi.org/10.3389/fphy.2022.890910.

Full text

Abstract:

The ability to extract generative parameters from high-dimensional fields of data in an unsupervised manner is a highly desirable yet unrealized goal in computational physics. This work explores the use of variational autoencoders for non-linear dimension reduction with the specific aim of disentangling the low-dimensional latent variables to identify independent physical parameters that generated the data. A disentangled decomposition is interpretable, and can be transferred to a variety of tasks including generative modeling, design optimization, and probabilistic reduced order modelling. A major emphasis of this work is to characterize disentanglement using VAEs while minimally modifying the classic VAE loss function (i.e., the Evidence Lower Bound) to maintain high reconstruction accuracy. The loss landscape is characterized by over-regularized local minima which surround desirable solutions. We illustrate comparisons between disentangled and entangled representations by juxtaposing learned latent distributions and the true generative factors in a model porous flow problem. Hierarchical priors are shown to facilitate the learning of disentangled representations. The regularization loss is unaffected by latent rotation when training with rotationally-invariant priors, and thus learning non-rotationally-invariant priors aids in capturing the properties of generative factors, improving disentanglement. Finally, it is shown that semi-supervised learning - accomplished by labeling a small number of samples (O (1%))–results in accurate disentangled latent representations that can be consistently learned.

APA, Harvard, Vancouver, ISO, and other styles

33

Sankhala, Devangsingh, Abha Umesh Sardesai, Madhavi Pali, Kai-Chun Lin, Badrinath Jagannath, Sriram Muthukumar, and Shalini Prasad. "A machine learning-based on-demand sweat glucose reporting platform." Scientific Reports 12, no. 1 (February 14, 2022). http://dx.doi.org/10.1038/s41598-022-06434-x.

Full text

Abstract:

AbstractDiabetes is a chronic endocrine disease that occurs due to an imbalance in glucose levels and altering carbohydrate metabolism. It is a leading cause of morbidity, resulting in a reduced quality of life even in developed societies, primarily affected by a sedentary lifestyle and often leading to mortality. Keeping track of blood glucose levels noninvasively has been made possible due to diverse breakthroughs in wearable sensor technology coupled with holistic digital healthcare. Efficient glucose management has been revolutionized by the development of continuous glucose monitoring sensors and wearable, non/minimally invasive devices that measure glucose concentration by exploiting different physical principles, e.g., glucose oxidase, fluorescence, or skin dielectric properties, and provide real-time measurements every 1–5 min. This paper presents a highly novel and completely non-invasive sweat sensor platform technology that can measure and report glucose concentrations from passively expressed human eccrine sweat using electrochemical impedance spectroscopy and affinity capture probe functionalized sensor surfaces. The sensor samples 1–5 µL of sweat from the wearer every 1–5 min and reports sweat glucose from a machine learning algorithm that samples the analytical reference values from the electrochemical sweat sensor. These values are then converted to continuous time-varying signals using the interpolation methodology. Supervised machine learning, the decision tree regression algorithm, shows the goodness of fit R2 of 0.94 was achieved with an RMSE value of 0.1 mg/dL. The output of the model was tested on three human subject datasets. The results were able to capture the glucose progression trend correctly. Sweet sensor platform technology demonstrates a dynamic response over the physiological sweat glucose range of 1–4 mg/dL measured from 3 human subjects. The technology described in the manuscript shows promise for real-time biomarkers such as glucose reporting from passively expressed human eccrine sweat.

APA, Harvard, Vancouver, ISO, and other styles

34

Tavolara, Thomas E., M. Khalid Khan Niazi, Vidya Arole, Wei Chen, Wendy Frankel, and Metin N. Gurcan. "A modular cGAN classification framework: Application to colorectal tumor detection." Scientific Reports 9, no. 1 (December 2019). http://dx.doi.org/10.1038/s41598-019-55257-w.

Full text

Abstract:

AbstractAutomatic identification of tissue structures in the analysis of digital tissue biopsies remains an ongoing problem in digital pathology. Common barriers include lack of reliable ground truth due to inter- and intra- reader variability, class imbalances, and inflexibility of discriminative models. To overcome these barriers, we are developing a framework that benefits from a reliable immunohistochemistry ground truth during labeling, overcomes class imbalances through single task learning, and accommodates any number of classes through a minimally supervised, modular model-per-class paradigm. This study explores an initial application of this framework, based on conditional generative adversarial networks, to automatically identify tumor from non-tumor regions in colorectal H&E slides. The average precision, sensitivity, and F1 score during validation was 95.13 ± 4.44%, 93.05 ± 3.46%, and 94.02 ± 3.23% and for an external test dataset was 98.75 ± 2.43%, 88.53 ± 5.39%, and 93.31 ± 3.07%, respectively. With accurate identification of tumor regions, we plan to further develop our framework to establish a tumor front, from which tumor buds can be detected in a restricted region. This model will be integrated into a larger system which will quantitatively determine the prognostic significance of tumor budding.

APA, Harvard, Vancouver, ISO, and other styles

35

Uemura, K., T. Nishikawa, T. Kawada, and M. Sugimachi. "A minimally-occlusive cuff method utilizing ultrasound vascular imaging for stress-free blood pressure measurement." European Heart Journal 41, Supplement_2 (November 1, 2020). http://dx.doi.org/10.1093/ehjci/ehaa946.2753.

Full text

Abstract:

Abstract Objective Occlusive cuff inflation in ambulatory blood pressure (BP) monitoring disturbs the daily life of the user, and affects efficacy of monitoring. To overcome this limitation, we have developed a novel minimally-occlusive cuff method for stress-free measurement of BP. This study aimed to experimentally evaluate the reliability of this method, and improve the precision of this method by implementing a machine learning algorithm. Methods In this method, a thin-plate-type ultrasound probe (Size: 5.6mm-thickness × 28mm × 26mm; weight: 10g) is placed between the cuff and the skin, and used to measure the ultrasonic dimension of the artery (Figure 1). The cuff pressure (Pc), arterial dimension at systole (Ds) and diastole (Dd), systolic BP (SBP) and diastolic BP (DBP) during cuff inflation are theoretically related by the following equations, SBP-Pc = P0·Exp[α·Ds] DBP-Pc = P0·Exp[α·Dd] Where P0 and α are constants, and α indicates arterial stiffness. Since multiple sets of the two equations can be defined over multiple cardiac beats while measuring Pc, Ds and Dd during mild cuff inflation (Pc is controlled less than 50 mmHg, Figure 1), it is possible to estimate SBP (SBPe) and DBP (DBPe) as solutions of the equations. In 6 anesthetized dogs, we attached the cuff and the probe to the right thigh to get SBPe and DBPe, which were one-time calibrated in each animal against reference SBP and DBP measured by using an intra-arterial catheter. We also determined the pulse arrival time (PAT), which is a commonly employed parameter in cuff-less BP monitoring. In all the dogs, BP was changed extensively by infusing noradrenaline or sodium nitroprusside. Results DBPe correlated tightly with DBP with a coefficient of determination (R2) of 0.85±0.08, and predicted DBP with error of 3.9±7.9 mmHg after one-time calibration (Figure 2). PAT correlated poorly with DBP (R2=0.49±0.17), and predicted DBP less accurately than this method. SBPe correlated well with SBP (R2=0.78±0.08) (Figure 3). However, even after one-time calibration, difference between SBPe and SBP was 2.6±18.9 mmHg, which was not acceptable. To improve the precision in SBP prediction, we used supervised machine learning approach with use of a support vector algorithm (Python, Scikit-learn), which regressed feature variables (SBPe, DBPe, Ds, Dd heart rate, and PAT) against teacher signal (reference SBP). The support vector algorithm, once trained, predicted SBP with acceptable accuracy with error of 0.7±6.9 mmHg (Figure 3). Conclusions This method reliably tracks BP changes without occlusive cuff inflation. Once calibrated, this method measures DBP accurately. With the aid of machine learning, precision in SBP prediction was greatly improved to an acceptable level. This method with machine learning approach has potential for stress-free BP measurement in ambulatory BP monitoring. Funding Acknowledgement Type of funding source: Public grant(s) – National budget only. Main funding source(s): Japan Society for the Promotion of Science

APA, Harvard, Vancouver, ISO, and other styles

36

Ulicna, Kristina, Giulia Vallardi, Guillaume Charras, and Alan R. Lowe. "Automated Deep Lineage Tree Analysis Using a Bayesian Single Cell Tracking Approach." Frontiers in Computer Science 3 (October 20, 2021). http://dx.doi.org/10.3389/fcomp.2021.734559.

Full text

Abstract:

Single-cell methods are beginning to reveal the intrinsic heterogeneity in cell populations, arising from the interplay of deterministic and stochastic processes. However, it remains challenging to quantify single-cell behaviour from time-lapse microscopy data, owing to the difficulty of extracting reliable cell trajectories and lineage information over long time-scales and across several generations. Therefore, we developed a hybrid deep learning and Bayesian cell tracking approach to reconstruct lineage trees from live-cell microscopy data. We implemented a residual U-Net model coupled with a classification CNN to allow accurate instance segmentation of the cell nuclei. To track the cells over time and through cell divisions, we developed a Bayesian cell tracking methodology that uses input features from the images to enable the retrieval of multi-generational lineage information from a corpus of thousands of hours of live-cell imaging data. Using our approach, we extracted 20,000 + fully annotated single-cell trajectories from over 3,500 h of video footage, organised into multi-generational lineage trees spanning up to eight generations and fourth cousin distances. Benchmarking tests, including lineage tree reconstruction assessments, demonstrate that our approach yields high-fidelity results with our data, with minimal requirement for manual curation. To demonstrate the robustness of our minimally supervised cell tracking methodology, we retrieve cell cycle durations and their extended inter- and intra-generational family relationships in 5,000 + fully annotated cell lineages. We observe vanishing cycle duration correlations across ancestral relatives, yet reveal correlated cyclings between cells sharing the same generation in extended lineages. These findings expand the depth and breadth of investigated cell lineage relationships in approximately two orders of magnitude more data than in previous studies of cell cycle heritability, which were reliant on semi-manual lineage data analysis.

APA, Harvard, Vancouver, ISO, and other styles

37

Zhang, Yipeng, Zahra M. Aghajan, Matias Ison, Qiujing Lu, Hanlin Tang, Guldamla Kalender, Tonmoy Monsoor, et al. "Decoding of human identity by computer vision and neuronal vision." Scientific Reports 13, no. 1 (January 12, 2023). http://dx.doi.org/10.1038/s41598-022-26946-w.

Full text

Abstract:

AbstractExtracting meaning from a dynamic and variable flow of incoming information is a major goal of both natural and artificial intelligence. Computer vision (CV) guided by deep learning (DL) has made significant strides in recognizing a specific identity despite highly variable attributes. This is the same challenge faced by the nervous system and partially addressed by the concept cells—neurons exhibiting selective firing in response to specific persons/places, described in the human medial temporal lobe (MTL) ⁠. Yet, access to neurons representing a particular concept is limited due to these neurons’ sparse coding. It is conceivable, however, that the information required for such decoding is present in relatively small neuronal populations. To evaluate how well neuronal populations encode identity information in natural settings, we recorded neuronal activity from multiple brain regions of nine neurosurgical epilepsy patients implanted with depth electrodes, while the subjects watched an episode of the TV series “24”. First, we devised a minimally supervised CV algorithm (with comparable performance against manually-labeled data) to detect the most prevalent characters (above 1% overall appearance) in each frame. Next, we implemented DL models that used the time-varying population neural data as inputs and decoded the visual presence of the four main characters throughout the episode. This methodology allowed us to compare “computer vision” with “neuronal vision”—footprints associated with each character present in the activity of a subset of neurons—and identify the brain regions that contributed to this decoding process. We then tested the DL models during a recognition memory task following movie viewing where subjects were asked to recognize clip segments from the presented episode. DL model activations were not only modulated by the presence of the corresponding characters but also by participants’ subjective memory of whether they had seen the clip segment, and by the associative strengths of the characters in the narrative plot. The described approach can offer novel ways to probe the representation of concepts in time-evolving dynamic behavioral tasks. Further, the results suggest that the information required to robustly decode concepts is present in the population activity of only tens of neurons even in brain regions beyond MTL.

APA, Harvard, Vancouver, ISO, and other styles

38

Dort, Katharina, Johannes Bilk, Stepahnie Käs, Jens Sören Lange, Marvin Peter, Timo Schellhaas, Benjamin Schwenker, and Björn Spruck. "Comparison of supervised and unsupervised anomaly detection in Belle II pixel detector data." European Physical Journal C 82, no. 7 (July 2022). http://dx.doi.org/10.1140/epjc/s10052-022-10548-x.

Full text

Abstract:

AbstractMachine learning has become a popular instrument for the search of undiscovered particles and mechanisms at particle collider experiments. It enables the investigation of large datasets and is therefore suitable to operate directly on minimally-processed data coming from the detector instead of reconstructed objects. Here, we study patterns of raw pixel hits recorded by the Belle II pixel detector, that is operational since 2019 and presently features 4 M pixels and trigger rates up to 5 kHz. In particular, we focus on unsupervised techniques that operate without the need for a theoretical model. These model-agnostic approaches allow for an unbiased exploration of data while filtering out anomalous detector signatures that could hint at new physics scenarios. We present the identification of hypothetical magnetic monopoles against Belle II beam background using self-organizing kohonen maps and autoencoders. These two unsupervised algorithms are compared to a Multilayer Perceptron and a superior signal efficiency of the Autoencoder is found at high background-rejection levels. Our results strengthen the case for using unsupervised machine learning techniques to complement traditional search strategies at particle colliders and pave the way to potential online applications of the algorithms in the near future.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Minimally-supervised Learning'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles