Siga este enlace para ver otros tipos de publicaciones sobre el tema: ML diagnostic model.
Artículos de revistas sobre el tema "ML diagnostic model"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 50 mejores artículos de revistas para su investigación sobre el tema "ML diagnostic model".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore artículos de revistas sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
1
Liu, Xinran, James Anstey, Ron Li, Chethan Sarabu, Reiri Sono y Atul J. Butte. "Rethinking PICO in the Machine Learning Era: ML-PICO". Applied Clinical Informatics 12, n.º 02 (marzo de 2021): 407–16. http://dx.doi.org/10.1055/s-0041-1729752.
Texto completoResumen
Abstract Background Machine learning (ML) has captured the attention of many clinicians who may not have formal training in this area but are otherwise increasingly exposed to ML literature that may be relevant to their clinical specialties. ML papers that follow an outcomes-based research format can be assessed using clinical research appraisal frameworks such as PICO (Population, Intervention, Comparison, Outcome). However, the PICO frameworks strain when applied to ML papers that create new ML models, which are akin to diagnostic tests. There is a need for a new framework to help assess such papers. Objective We propose a new framework to help clinicians systematically read and evaluate medical ML papers whose aim is to create a new ML model: ML-PICO (Machine Learning, Population, Identification, Crosscheck, Outcomes). We describe how the ML-PICO framework can be applied toward appraising literature describing ML models for health care. Conclusion The relevance of ML to practitioners of clinical medicine is steadily increasing with a growing body of literature. Therefore, it is increasingly important for clinicians to be familiar with how to assess and best utilize these tools. In this paper we have described a practical framework on how to read ML papers that create a new ML model (or diagnostic test): ML-PICO. We hope that this can be used by clinicians to better evaluate the quality and utility of ML papers.
2
Wang, Dong, Jian Liu, Lijun Deng y Honglin Wang. "Intelligent diagnosis of resistance variant multiple fault locations of mine ventilation system based on ML-KNN". PLOS ONE 17, n.º 9 (30 de septiembre de 2022): e0275437. http://dx.doi.org/10.1371/journal.pone.0275437.
Texto completoResumen
The resistance variant faults (RVFs) observed in the mine ventilation system can utterly restrict mine safety production. Herein, a machine learning model, which is based on multi-label k-nearest neighbor (ML-KNN), is proposed to solve the problem of the rapid and accurate diagnosis of the RVFs that occur at multiple locations within the mine ventilation system. The air volume that passes through all the branches of the ventilation network, including the residual branches, was used as the diagnostic model input after the occurrence of multiple faults, whereas the label vector of the fault locations was used as the model’s output. In total, seven evaluation indicators and 1800 groups of randomly simulated faults at the typical locations in a production mine with 153 nodes and 223 branches were considered to evaluate the feasibility of the proposed model to solve for multiple fault locations diagnostic and verify the model’s generalization ability. After ten-fold cross-validation of the training sets containing 1600 groups of fault instances, the diagnostic accuracy of the model tested with the air volume of all 223 branches and the 71 residual branches’ air volume as input was 73.6% and 72.3%, respectively. On the other hand, To further evaluate the diagnostic performance of the model, 200 groups of the multiple fault instances that were not included in the training were tested. The accuracy of the fault location diagnosis was 76.5% and 73.5%, and the diagnostic time was 9.9s and 12.16s for the multiple faults instances with all 223 branches’ air volume and the 71 residual branches’ air volume as observation characteristics, respectively. The data show that the machine learning model based on ML-KNN shows good performance in the problem of resistance variant multiple fault locations diagnoses of the mine ventilation system, the multiple fault locations diagnoses can be carried out with all the branches’ air volume or the residual branches’ air volume as the input of the model, the diagnostic average accuracy is higher than 70%, and the average diagnosis time is less than one minute. Hence, the proposed model’s diagnostic accuracy and speed can meet the engineering requirements for the diagnosis of multiple fault locations for a real ventilation system in the field, and this model can effectively replace personnel to discover ventilation system failures, and also lays a good foundation for the construction of intelligent ventilation systems.
3
Babar, Zaheer, Twan van Laarhoven y Elena Marchiori. "Encoder-decoder models for chest X-ray report generation perform no better than unconditioned baselines". PLOS ONE 16, n.º 11 (29 de noviembre de 2021): e0259639. http://dx.doi.org/10.1371/journal.pone.0259639.
Texto completoResumen
High quality radiology reporting of chest X-ray images is of core importance for high-quality patient diagnosis and care. Automatically generated reports can assist radiologists by reducing their workload and even may prevent errors. Machine Learning (ML) models for this task take an X-ray image as input and output a sequence of words. In this work, we show that ML models for this task based on the popular encoder-decoder approach, like ‘Show, Attend and Tell’ (SA&T) have similar or worse performance than models that do not use the input image, called unconditioned baseline. An unconditioned model achieved diagnostic accuracy of 0.91 on the IU chest X-ray dataset, and significantly outperformed SA&T (0.877) and other popular ML models (p-value < 0.001). This unconditioned model also outperformed SA&T and similar ML methods on the BLEU-4 and METEOR metrics. Also, an unconditioned version of SA&T obtained by permuting the reports generated from images of the test set, achieved diagnostic accuracy of 0.862, comparable to that of SA&T (p-value ≥ 0.05).
4
Venkatesh, Veeramuthu, M. M. Anishin Raj, K. Mohamed Sajith, R. Anushiadevi y T. Suriya Praba. "A precision-based diagnostic model ADOBE-accurate detection of breast cancer using logistic regression approach". Journal of Intelligent & Fuzzy Systems 39, n.º 6 (4 de diciembre de 2020): 8419–26. http://dx.doi.org/10.3233/jifs-189160.
Texto completoResumen
Cancer is a prevalent disease which comes in several forms. The need of the hour in cancer research is to be able to diagnose cancer in its early stages. The furthermost common forms of cancer among women us breast cancer. In recent times, there has been a drastic increase in the number of breast cancer cases among women. As a wide range of medical data is available in electronic form and with easy access to Machine Learning(ML) techniques disease progression risk evaluation has been made easier. These ML tools can aid in giving us complex insights from the massive amounts of available data. Some of the techniques used for developing predictive models for perfect decision making in cancer research are Artificial Neural Networks (ANNs), Bayesian Networks (BNs), Support Vector Machines (SVMs), and Decision Trees (DTs). Although it is acceptable that ML is used to predict cancer progression, we need some level of validation. In this paper, we have come up with a review of several ML methods in modelling cancer progression. We discuss several predictive models based on supervised ML techniques and the inputs given by users, along with the data available. The results that were obtained from Logistic Regression show us that this method gave a significantly higher accuracy than most other classifiers. The best accuracy is 98.2%, however, the best precision and recall is 100 and 98.60% correspondingly.
5
Carreiro Pinasco, Gustavo, Eduardo Moreno Júdice de Mattos Farina, Fabiano Novaes Barcellos Filho, Willer França Fiorotti, Matheus Coradini Mariano Ferreira, Sheila Cristina de Souza Cruz, Andre Louzada Colodette et al. "An interpretable machine learning model for covid-19 screening". Journal of Human Growth and Development 32, n.º 2 (23 de junio de 2022): 268–74. http://dx.doi.org/10.36311/jhgd.v32.13324.
Texto completoResumen
Introduction: the Coronavirus Disease 2019 (COVID-19) is a viral disease which has been declared a pandemic by the WHO. Diagnostic tests are expensive and are not always available. Researches using machine learning (ML) approach for diagnosing SARS-CoV-2 infection have been proposed in the literature to reduce cost and allow better control of the pandemic. Objective: we aim to develop a machine learning model to predict if a patient has COVID-19 with epidemiological data and clinical features. Methods: we used six ML algorithms for COVID-19 screening through diagnostic prediction and did an interpretative analysis using SHAP models and feature importances. Results: our best model was XGBoost (XGB) which obtained an area under the ROC curve of 0.752, a sensitivity of 90%, a specificity of 40%, a positive predictive value (PPV) of 42.16%, and a negative predictive value (NPV) of 91.0%. The best predictors were fever, cough, history of international travel less than 14 days ago, male gender, and nasal congestion, respectively. Conclusion: We conclude that ML is an important tool for screening with high sensitivity, compared to rapid tests, and can be used to empower clinical precision in COVID-19, a disease in which symptoms are very unspecific.
6
Smirnova, Darya Ilyinichna, Anastasiya Vyacheslavovna Gracheva, Elena Aleksandrovna Volynskaya, Vitaliy Vasilievich Zverev y Evgeniy Bakhtiyorovich Faizuloev. "Diagnostic value of the LAMP method with real-time fluo-rescence detection on a model of herpesvirus infection". Sanitarnyj vrač (Sanitary Doctor), n.º 1 (1 de enero de 2021): 52–61. http://dx.doi.org/10.33920/med-08-2101-06.
Texto completoResumen
Due to the high prevalence and clinical significance of herpesvirus diseases, improvement of methods of their diagnostic remains relevant.The aim of the work: improvement of the methodological approaches to the rapid differential diagnosis of herpesvirus infections based on the LAMP method with real-time fluorescence detection (LAMPRT). 201 urogenital swabs were examined using RT-PCR and LAMP-RT, 27of which contained DNAof Epstein-Barr virus (EBV), 34 — Cytomegalovirus (CMV), 14 — Herpes simplex virus type 1 (HSV-1), 36 — Herpes simplex virus type 2 (HSV-2). For LAMP-RT reaction we used Bst 2.0 WarmStart DNA polymerase (BioLabs, Great Britain), SYTO-82 dye (Invitrogen, USA), and sets of primers for herpesvirus DNA detection by LAMP. High efficiency of using the SYTO-82 dye for the detection of herpesvirus DNA in the LAMP-RT reactionwas shown. Under the optimal conditions, the LAMP-RT allows to reduce the reaction time to 25 minutes, that 3 times less then real-time PCR. The diagnostic sensitivity of the LAMP-RT reaction for HSV-1 was 100 %, HSV-2 — 94.50 %, EBV — 89 %, CMV — 94 %. The diagnostic specificity for all studied viruses was 100 %. The analytical sensitivity of EBV detection was 104 DNA copies/ ml, for HSV types 1 and 2 and CMV — 103 DNA copies/ml. Thus, the LAMP-RT reaction with SYTO-82 dye makes it possible to detect the DNA of various herpesviruses in clinical specimens with high sensitivity and specificity and can be considered as a promising method for point-of-care diagnostics. For the widespread implementation of the method into the practice of laboratory diagnostics, it is necessary to solve the problem of creating an internal positive control of the reaction and the development of portable specialized analyzers.
7
Baker, Mohammed Rashad, D. Lakshmi Padmaja, R. Puviarasi, Suman Mann, Jeidy Panduro-Ramirez, Mohit Tiwari y Issah Abubakari Samori. "Implementing Critical Machine Learning (ML) Approaches for Generating Robust Discriminative Neuroimaging Representations Using Structural Equation Model (SEM)". Computational and Mathematical Methods in Medicine 2022 (14 de abril de 2022): 1–12. http://dx.doi.org/10.1155/2022/6501975.
Texto completoResumen
Critical ML or CML is a critical approach development of the standard ML (SML) procedure. Conventional ML (ML) is being used in radiology departments where complex neuroimages are discriminated using ML technology. Radiologists and researchers found that sole decision by the ML algorithms is not accurate enough to implement the treatment procedure. Thus, an intelligent decision is required further by the radiologists after evaluating the ML outcomes. The current research is based on the critical ML, where radiologists’ critical thinking ability, IQ (intelligence quotient), and experience in radiology have been examined to understand how these factors affect the accuracy of neuroimaging discrimination. A primary quantitative survey has been carried out, and the data were analysed in IBM SPSS. The results showed that experience in works has a positive impact on neuroimaging discrimination accuracy. IQ and trained ML are also responsible for improving the accuracy as well. Thus, radiologists with more experience in that field are able to improve the discriminative and diagnostic capability of CML.
8
Chatterjee, S., R. Alkhaldi, P. Yaadav, D. Bethineedi, A. Shreya y N. Bankole. "P.115 Diagnostic performance of machine learning based MR algorithm vs conventional MR images for predicting the likelihood of brain tumors". Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques 49, s1 (junio de 2022): S38. http://dx.doi.org/10.1017/cjn.2022.207.
Texto completoResumen
Background: MRI forms an imperative part of the diagnostic and treatment protocol for primary brain tumors and metastasis. Though conventional T1W MRI forms the basis for diagnosis at present, it faces several limitations. Machine learning (ML) algorithms require less expertise and provide better diagnostic accuracy. Methods: A systematic review of PubMed, Google Scholar, and Cochrane databases along with registries through 1980-2021 was done. Original articles in English evaluating Conventional MRI or ML algorithms. Data was extracted by 2 reviewers and meta-analysis was performed using bivariate regression model. Results: The study protocol was registered under PROSPERO. Twelve studies with 1247 participants were included for systematic analysis and three studies for meta-analysis. ML algorithms had better aggregate sensitivity and specificity (80%, 83.14%) than Conventional MRI (81.84%, 74.78%).The pooled sensitivity, specificity, DOR for the studies were 0.926 (95% CI, 0.840-0.926), 0.991 (95% CI, 0.955-0.998) and 1446.946 (312.634-6692.646) with AUC=0.904 under HSROC. On subgroup analysis, MRS and Random Forest Model had highest sensitivity and specificity (100%,100%;100%,100%), DSC MRI and Deep Neural Network had highest AUC (0.98,0.986). Conclusions: ML algorithm has superior diagnostic performance and faster diagnostic capability once trained than conventional imaging for brain tumors. It has immense potential to be the standard of care in the future.
9
Kahlen, Jannis N., Michael Andres y Albert Moser. "Improving Machine-Learning Diagnostics with Model-Based Data Augmentation Showcased for a Transformer Fault". Energies 14, n.º 20 (18 de octubre de 2021): 6816. http://dx.doi.org/10.3390/en14206816.
Texto completoResumen
Machine-learning diagnostic systems are widely used to detect abnormal conditions in electrical equipment. Training robust and accurate diagnostic systems is challenging because only small databases of abnormal-condition data are available. However, the performance of the diagnostic systems depends on the quantity and quality of the data. The training database can be augmented utilizing data augmentation techniques that generate synthetic data to improve diagnostic performance. However, existing data augmentation techniques are generic methods that do not include additional information in the synthetic data. In this paper, we develop a model-based data augmentation technique integrating computer-implementable electromechanical models. Synthetic normal- and abnormal-condition data are generated with an electromechanical model and a stochastic parameter value sampling method. The model-based data augmentation is showcased to detect an abnormal condition of a distribution transformer. First, the synthetic data are compared with the measurements to verify the synthetic data. Then, ML-based diagnostic systems are created using model-based data augmentation and are compared with state-of-the-art diagnostic systems. It is shown that using the model-based data augmentation results in an improved accuracy compared to state-of-the-art diagnostic systems. This holds especially true when only a small abnormal-condition database is available.
10
Gui, Chloe y Victoria Chan. "Machine learning in medicine". University of Western Ontario Medical Journal 86, n.º 2 (3 de diciembre de 2017): 76–78. http://dx.doi.org/10.5206/uwomj.v86i2.2060.
Texto completoResumen
Machine learning (ML) is a powerful and flexible tool that can be used to analyze and predict outcomes from biological and clinical data. ML models have the potential to improve healthcare efficiency in a number of ways. Algorithms that predict prognosis empower healthcare officials to allocate resources optimally and physicians to select better treatment options for patients. Diagnostic models can be used in screening, in risk stratification, and to recommend appropriate testing and treatment. This would decrease the burden on physicians, increase and expedite patient access to care, save resources, and reduce costs. However, despite the research advances of ML in medicine, its role in the clinic is currently limited. Model building and validation may require large amounts of high-quality data that can be difficult and expensive to obtain, and diagnostic models must be individually built for each disease, a lengthy process. The psychological aspect of trusting black box algorithms may also be challenging to accept. Continued ML research, however, may enable the use of smaller datasets and the development of more transparent models. Careful trials in the clinic will need to be conducted before the more impactful uses of ML, such as diagnosis, can be implemented.
11
Djulbegovic, Benjamin, Jennifer Berano Teh, Lennie Wong, Iztok Hozo y Saro H. Armenian. "Diagnostic Predictive Model for Diagnosis of Heart Failure after Hematopoietic Cell Transplantation (HCT): Comparison of Traditional Statistical with Machine Learning Modeling". Blood 134, Supplement_1 (13 de noviembre de 2019): 5799. http://dx.doi.org/10.1182/blood-2019-130764.
Texto completoResumen
Background: Therapy-related heart failure (HF) is a leading cause of morbidity and mortality in patients who undergo successful HCT for hematological malignancies. To eventually help improve management of HF, timely and accurate diagnosis of HF is crucial. Currently, no established method for diagnosis of HF exist. One approach to help improve diagnosis and management of HF is to use predictive modeling to assess the likelihood of HF, using key predictors known to be associated with HF. Such models can, in turn, be used for bedside management, including implementation of early screening approaches. That said, many techniques for predictive modeling exist. Currently, it is not known if Artificial Intelligence machine learning (ML) approaches are superior to standard statistical techniques for the development of predictive models for clinical practice. Here we present a comparative analysis of traditional multivariable models with ML learning predictive modeling in an attempt to identify the best predictive model for diagnosis of HF after HCT. Methods: At City of Hope, we have established a large prospective cohort (>12,000 patients) of HCT survivors (HCT survivorship registry). This registry is dynamic, and interfaces with other registries and databases (e.g., electronically indexed inpatient and outpatient medical records, national death index [NDI]). We utilized natural language processing (NLP) to extract 13 key demographics and clinical data that are known to be associated with HF. For the purposes of this project, we extracted data from 1,834 patients (~15% sample) who underwent HCT between 1994 to 2004 to allow adequate follow-up for the development of HF. We fit and compared 6 models [standard logistic regression (glm), FFT (fast-and-frugal tree) decision model and four ML models: CART (classification and regression trees), SVM (support vector machine), NN (neural network) and RF (random forest)]. Data were randomly split (50:50) into training and validation samples; the ultimate assessment of the best algorithm was based on its performance (in terms of calibration and discrimination) in the validation sample. DeLong test was used to test for statistical differences in discrimination [i.e. area under the curve (AUC)] among the models. Results: The accuracy of NLP was consistently >95%. Only the standard logistic regression model LR (glm) resulted in a well-calibrated model (Hosmer-Lemeshow goodness of fitness test: p=0.104); all other models were miscalibrated. The standard glm model also had best discrimination properties (AUC=0.704 in training and 0.619 in validation set). CART performed the worst (AUC=0.5). Other ML models (RF, NN, and SVM) also showed modest discriminatory characteristics (AUCs of 0.547, 0.573, and 0.619, respectively). DeLong test indicated that all models outperformed CART model (at nominal p<0.05 ), but were statistically indistinguishable among each other (see Figure). Power of analysis was borderline sufficient for the glm model and very limited for ML models. Conclusions: None of tested models showed optimal performance characteristics for their use in clinical practice. ML models performed even worse than standard logistic models; given increasing use of ML models in medicine, we caution against the use of these models without adequate comparative testing. Figure Disclosures No relevant conflicts of interest to declare.
12
Khan, Yusera Farooq, Baijnath Kaushik, Chiranji Lal Chowdhary y Gautam Srivastava. "Ensemble Model for Diagnostic Classification of Alzheimer’s Disease Based on Brain Anatomical Magnetic Resonance Imaging". Diagnostics 12, n.º 12 (16 de diciembre de 2022): 3193. http://dx.doi.org/10.3390/diagnostics12123193.
Texto completoResumen
Alzheimer’s is one of the fast-growing diseases among people worldwide leading to brain atrophy. Neuroimaging reveals extensive information about the brain’s anatomy and enables the identification of diagnostic features. Artificial intelligence (AI) in neuroimaging has the potential to significantly enhance the treatment process for Alzheimer’s disease (AD). The objective of this study is two-fold: (1) to compare existing Machine Learning (ML) algorithms for the classification of AD. (2) To propose an effective ensemble-based model for the same and to perform its comparative analysis. In this study, data from the Alzheimer’s Diseases Neuroimaging Initiative (ADNI), an online repository, is utilized for experimentation consisting of 2125 neuroimages of Alzheimer’s disease (n = 975), mild cognitive impairment (n = 538) and cognitive normal (n = 612). For classification, the framework incorporates a Decision Tree (DT), Random Forest (RF), Naïve Bayes (NB), and K-Nearest Neighbor (K-NN) followed by some variations of Support Vector Machine (SVM), such as SVM (RBF kernel), SVM (Polynomial Kernel), and SVM (Sigmoid kernel), as well as Gradient Boost (GB), Extreme Gradient Boosting (XGB) and Multi-layer Perceptron Neural Network (MLP-NN). Afterwards, an Ensemble Based Generic Kernel is presented where Master-Slave architecture is combined to attain better performance. The proposed model is an ensemble of Extreme Gradient Boosting, Decision Tree and SVM_Polynomial kernel (XGB + DT + SVM). At last, the proposed method is evaluated using cross-validation using statistical techniques along with other ML models. The presented ensemble model (XGB + DT + SVM) outperformed existing state-of-the-art algorithms with an accuracy of 89.77%. The efficiency of all the models was optimized using Grid-based tuning, and the results obtained after such process showed significant improvement. XGB + DT + SVM with optimized parameters outperformed all other models with an efficiency of 95.75%. The implication of the proposed ensemble-based learning approach clearly shows the best results compared to other ML models. This experimental comparative analysis improved understanding of the above-defined methods and enhanced their scope and significance in the early detection of Alzheimer’s disease.
13
Daimiel Naranjo, Isaac, Peter Gibbs, Jeffrey S. Reiner, Roberto Lo Gullo, Caleb Sooknanan, Sunitha B. Thakur, Maxine S. Jochelson et al. "Radiomics and Machine Learning with Multiparametric Breast MRI for Improved Diagnostic Accuracy in Breast Cancer Diagnosis". Diagnostics 11, n.º 6 (21 de mayo de 2021): 919. http://dx.doi.org/10.3390/diagnostics11060919.
Texto completoResumen
The purpose of this multicenter retrospective study was to evaluate radiomics analysis coupled with machine learning (ML) of dynamic contrast-enhanced (DCE) and diffusion-weighted imaging (DWI) radiomics models separately and combined as multiparametric MRI for improved breast cancer detection. Consecutive patients (Memorial Sloan Kettering Cancer Center, January 2018–March 2020; Medical University Vienna, from January 2011–August 2014) with a suspicious enhancing breast tumor on breast MRI categorized as BI-RADS 4 and who subsequently underwent image-guided biopsy were included. In 93 patients (mean age: 49 years ± 12 years; 100% women), there were 104 lesions (mean size: 22.8 mm; range: 7–99 mm), 46 malignant and 58 benign. Radiomics features were calculated. Subsequently, the five most significant features were fitted into multivariable modeling to produce a robust ML model for discriminating between benign and malignant lesions. A medium Gaussian support vector machine (SVM) model with five-fold cross validation was developed for each modality. A model based on DWI-extracted features achieved an AUC of 0.79 (95% CI: 0.70–0.88), whereas a model based on DCE-extracted features yielded an AUC of 0.83 (95% CI: 0.75–0.91). A multiparametric radiomics model combining DCE- and DWI-extracted features showed the best AUC (0.85; 95% CI: 0.77–0.92) and diagnostic accuracy (81.7%; 95% CI: 73.0–88.6). In conclusion, radiomics analysis coupled with ML of multiparametric MRI allows an improved evaluation of suspicious enhancing breast tumors recommended for biopsy on clinical breast MRI, facilitating accurate breast cancer diagnosis while reducing unnecessary benign breast biopsies.
14
Barayan, Mohammed A., Arwa A. Qawas, Asma S. Alghamdi, Turki S. Alkhallagi, Raghad A. Al-Dabbagh, Ghadah A. Aldabbagh y Amal I. Linjawi. "Effectiveness of Machine Learning in Assessing the Diagnostic Quality of Bitewing Radiographs". Applied Sciences 12, n.º 19 (24 de septiembre de 2022): 9588. http://dx.doi.org/10.3390/app12199588.
Texto completoResumen
Background: Identifying the diagnostic value of bitewing radiographs (BW) is highly dependent on the operator’s knowledge and experience. The aim of this study is to assess the effectiveness of machine learning (ML) to classify the BW according to their diagnostic quality. Methods: 864 BW radiographs from records of 100 patients presented at King Abdulaziz University Dental Hospital, Jeddah, Saudi Arabia were assessed. The radiographic errors in representing proximal contact areas (n = 1951) were categorized into diagnostic and non-diagnostic. Labeling and training of the BW were done using Roboflow. Data were divided into validation, training, and testing sets to train the pre-trained model Efficientdet-d0 using TensorFlow. The model’s performance was assessed by calculating recall, precision, F1 score, and log loss value. Results: The model excelled at detecting “overlap within enamel” and “overlap within restoration (clear margins) with F1 score of 0.89 and 0.76, respectively. The overall system errors made by the built model showed a log loss value of 0.15 indicating high accuracy of the model. Conclusions: The model is a “proof of concept” for the effectiveness of ML in diagnosing the quality of the BW radiographs based on the contact areas. More dataset specification and optimization are needed to overcome the class imbalance.
15
Al-Hasani, Maryam, Laith R. Sultan, Hersh Sagreiya, Theodore W. Cary, Mrigendra B. Karmacharya y Chandra M. Sehgal. "Ultrasound Radiomics for the Detection of Early-Stage Liver Fibrosis". Diagnostics 12, n.º 11 (9 de noviembre de 2022): 2737. http://dx.doi.org/10.3390/diagnostics12112737.
Texto completoResumen
Objective: The study evaluates quantitative ultrasound (QUS) texture features with machine learning (ML) to enhance the sensitivity of B-mode ultrasound (US) for the detection of fibrosis at an early stage and distinguish it from advanced fibrosis. Different ML methods were evaluated to determine the best diagnostic model. Methods: 233 B-mode images of liver lobes with early and advanced-stage fibrosis induced in a rat model were analyzed. Sixteen features describing liver texture were measured from regions of interest (ROIs) drawn on B-mode images. The texture features included a first-order statistics run length (RL) and gray-level co-occurrence matrix (GLCM). The features discriminating between early and advanced fibrosis were used to build diagnostic models with logistic regression (LR), naïve Bayes (nB), and multi-class perceptron (MLP). The diagnostic performances of the models were compared by ROC analysis using different train-test sampling approaches, including leave-one-out, 10-fold cross-validation, and varying percentage splits. METAVIR scoring was used for histological fibrosis staging of the liver. Results: 15 features showed a significant difference between the advanced and early liver fibrosis groups, p < 0.05. Among the individual features, first-order statics features led to the best classification with a sensitivity of 82.1–90.5% and a specificity of 87.1–89.8%. For the features combined, the diagnostic performances of nB and MLP were high, with the area under the ROC curve (AUC) approaching 0.95–0.96. LR also yielded high diagnostic performance (AUC = 0.91–0.92) but was lower than nB and MLP. The diagnostic variability between test-train trials, measured by the coefficient-of-variation (CV), was higher for LR (3–5%) than nB and MLP (1–2%). Conclusion: Quantitative ultrasound with machine learning differentiated early and advanced fibrosis. Ultrasound B-mode images contain a high level of information to enable accurate diagnosis with relatively straightforward machine learning methods like naïve Bayes and logistic regression. Implementing simple ML approaches with QUS features in clinical settings could reduce the user-dependent limitation of ultrasound in detecting early-stage liver fibrosis.
16
Aksoy, Özgür, Başak Kurt, Celal Şahin Ermutlu, Kürşat Çeçen, Sadık Yayla, Metin Ekinci, İsa Özaydin y Süleyman Erdinç Ünlüer. "Fluorescein as a diagnostic marker of bladder ruptures: an experimental study on rabbit model". Journal of Veterinary Research 60, n.º 2 (1 de junio de 2016): 213–17. http://dx.doi.org/10.1515/jvetres-2016-0031.
Texto completoResumen
Abstract Introduction: The aim of this study was to investigate fluorescein use in the diagnosis of bladder ruptures in rabbits as an experimental model. Material and Methods: The study was conducted on male New Zealand rabbits divided into a retrograde fluorescein group (n = 8) and an intravenous (IV) fluorescein group (n = 8). Following general anaesthesia, 10 mL of 10% fluorescein dye (sodium fluoresceine powder) was administered via ureterorenoscope to the bladder of the first group, and 0.5 mL of 10% fluorescein was administered intravenously to the second group. Then, the bladder was viewed through the cystoscope by urethral aspect. After experimental bladder perforation, groups were comparatively evaluated by paracentesis and laparotomy. Results: Following IV injection of fluorescein dye, the bladder veins were stained green within 10 s and then fluorescein mixed with urine flowed into bladder lumen. The green fluid flow was observed in the abdominal cavity after the perforation of the bladder in both groups. Conclusion: Fluorescein can be used as a marker in diagnosis of bladder ruptures. If there is no bleeding or intestinal content in the abdominal cavity, although a smoky yellow-green image is observed, bladder rupture can be suspected.
17
Koo, Hyun Jung, Joon-Won Kang, Soo-Jin Kang, Jihoon Kweon, June-Goo Lee, Jung-Min Ahn, Duk-Woo Park et al. "Impact of coronary calcium score and lesion characteristics on the diagnostic performance of machine-learning-based computed tomography-derived fractional flow reserve". European Heart Journal - Cardiovascular Imaging 22, n.º 9 (11 de abril de 2021): 998–1006. http://dx.doi.org/10.1093/ehjci/jeab062.
Texto completoResumen
Abstract Aims To evaluate the impact of coronary artery calcium (CAC) score, minimal lumen area (MLA), and length of coronary artery stenosis on the diagnostic performance of the machine-learning-based computed tomography-derived fractional flow reserve (ML-FFR). Methods and results In 471 patients with coronary artery disease, computed tomography angiography (CTA) and invasive coronary angiography were performed with fractional flow reserve (FFR) in 557 lesions at a single centre. Diagnostic performances of ML-FFR, computational fluid dynamics-based CT-FFR (CFD-FFR), MLA, quantitative coronary angiography (QCA), and visual stenosis grading were evaluated using invasive FFR as a reference standard. Diagnostic performances were analysed according to lesion characteristics including the MLA, length of stenosis, CAC score, and stenosis degree. ML-FFR was obtained by automated feature selection and model building from quantitative CTA. A total of 272 lesions showed significant ischaemia, defined by invasive FFR ≤0.80. There was a significant correlation between CFD-FFR and ML-FFR (r = 0.99, P < 0.001). ML-FFR showed moderate sensitivity and specificity in the per-patient analysis. Diagnostic performances of CFD-FFR and ML-FFR did not decline in patients with high CAC scores (CAC > 400). Sensitivities of CFD-FFR and ML-FFR showed a downward trend along with the increase in lesion length and decrease in MLA. The area under the curve (AUC) of ML-FFR (0.73) was higher than those of QCA and visual grading (AUC = 0.65 for both, P < 0.001) and comparable to those of MLA (AUC = 0.71, P = 0.21) and CFD-FFR (AUC = 0.73, P = 0.86). Conclusion ML-FFR showed comparable results to MLA and CFD-FFR for the prediction of lesion-specific ischaemia. Specificities and accuracies of CFD-FFR and ML-FFR decreased with smaller MLA and long lesion length.
18
Berlet, Maximilian, Jonas Fuchtmann, Lukas Bernhard, Alissa Jell, Marie-Christin Weber, Philipp Alexander Neumann, Helmut Friess, Michael Kranzfelder, Hubertus Feussner y Dirk Wilhelm. "Laparoscopic Cholecystectomy – A Proper Model Surgery for AI based Prediction of Adverse Events?" Current Directions in Biomedical Engineering 8, n.º 1 (1 de julio de 2022): 5–8. http://dx.doi.org/10.1515/cdbme-2022-0002.
Texto completoResumen
Abstract Laparoscopic cholecystectomy (LCHE) is a widely employed model for surgical instrument and phase recognition in the field of machine learning (ML), with the latter being assigned to identify critical events and to avoid complications. Although ML algorithms have been proven to be effective for this instance and in selected patients, it is questionable whether patients receiving LCHE in daily clinical routine would actually benefit from adverse event prediction by ML applications. We believe, that the statistical problem of low prevalence (PREV) of potential adverse events in an unselected population and consequential low diagnostic yield was not considered adequately in recent research. Therefore, we performed a query to the G-DRG (German Diagnosis Related Groups) database of the German Federal Statistical Office with the aim to calculate prevalence of surgical and postoperative adverse events coming along with LCHE. The results enable an estimation of positive (PPV) and negative (NPV) predictive values hypothetically achievable by ML applications aiming to predict an adverse surgical course.
19
Jian, Anne, Kevin Jang, Maurizio Manuguerra, Sidong Liu, John Magnussen y Antonio Di Ieva. "Machine Learning for the Prediction of Molecular Markers in Glioma on Magnetic Resonance Imaging: A Systematic Review and Meta-Analysis". Neurosurgery 89, n.º 1 (7 de abril de 2021): 31–44. http://dx.doi.org/10.1093/neuros/nyab103.
Texto completoResumen
Abstract BACKGROUND Molecular characterization of glioma has implications for prognosis, treatment planning, and prediction of treatment response. Current histopathology is limited by intratumoral heterogeneity and variability in detection methods. Advances in computational techniques have led to interest in mining quantitative imaging features to noninvasively detect genetic mutations. OBJECTIVE To evaluate the diagnostic accuracy of machine learning (ML) models in molecular subtyping gliomas on preoperative magnetic resonance imaging (MRI). METHODS A systematic search was performed following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) guidelines to identify studies up to April 1, 2020. Methodological quality of studies was assessed using the Quality Assessment for Diagnostic Accuracy Studies (QUADAS)-2. Diagnostic performance estimates were obtained using a bivariate model and heterogeneity was explored using metaregression. RESULTS Forty-four original articles were included. The pooled sensitivity and specificity for predicting isocitrate dehydrogenase (IDH) mutation in training datasets were 0.88 (95% CI 0.83-0.91) and 0.86 (95% CI 0.79-0.91), respectively, and 0.83 to 0.85 in validation sets. Use of data augmentation and MRI sequence type were weakly associated with heterogeneity. Both O6-methylguanine-DNA methyltransferase (MGMT) gene promoter methylation and 1p/19q codeletion could be predicted with a pooled sensitivity and specificity between 0.76 and 0.83 in training datasets. CONCLUSION ML application to preoperative MRI demonstrated promising results for predicting IDH mutation, MGMT methylation, and 1p/19q codeletion in glioma. Optimized ML models could lead to a noninvasive, objective tool that captures molecular information important for clinical decision making. Future studies should use multicenter data, external validation and investigate clinical feasibility of ML models.
20
Chen, Fangyue, Piyawat Kantagowit, Tanawin Nopsopon, Arisa Chuklin y Krit Pongpirul. "Prediction and diagnosis of chronic kidney disease development and progression using machine-learning: Protocol for a systematic review and meta-analysis of reporting standards and model performance". PLOS ONE 18, n.º 2 (23 de febrero de 2023): e0278729. http://dx.doi.org/10.1371/journal.pone.0278729.
Texto completoResumen
Chronic Kidney disease (CKD) is an important yet under-recognized contributor to morbidity and mortality globally. Machine-learning (ML) based decision support tools have been developed across many aspects of CKD care. Notably, algorithms developed in the prediction and diagnosis of CKD development and progression may help to facilitate early disease prevention, assist with early planning of renal replacement therapy, and offer potential clinical and economic benefits to patients and health systems. Clinical implementation can be affected by the uncertainty surrounding the methodological rigor and performance of ML-based models. This systematic review aims to evaluate the application of prognostic and diagnostic ML tools in CKD development and progression. The protocol has been prepared using the Preferred Items for Systematic Review and Meta-analysis Protocols (PRISMA-P) guidelines. The systematic review protocol for CKD prediction and diagnosis have been registered with the International Prospective Register of Systematic Reviews (PROSPERO) (CRD42022356704, CRD42022372378). A systematic search will be undertaken of PubMed, Embase, the Cochrane Central Register of Controlled Trials (CENTRAL), the Web of Science, and the IEEE Xplore digital library. Studies in which ML has been applied to predict and diagnose CKD development and progression will be included. The primary outcome will be the comparison of the performance of ML-based models with non-ML-based models. Secondary analysis will consist of model use cases, model construct, and model reporting quality. This systematic review will offer valuable insight into the performance and reporting quality of ML-based models in CKD diagnosis and prediction. This will inform clinicians and technical specialists of the current development of ML in CKD care, as well as direct future model development and standardization.
21
Akella, Aravind y Sudheer Akella. "Machine learning algorithms for predicting coronary artery disease: efforts toward an open source solution". Future Science OA 7, n.º 6 (julio de 2021): FSO698. http://dx.doi.org/10.2144/fsoa-2020-0206.
Texto completoResumen
Aim: The development of coronary artery disease (CAD), a highly prevalent disease worldwide, is influenced by several modifiable risk factors. Predictive models built using machine learning (ML) algorithms may assist clinicians in timely detection of CAD and may improve outcomes. Materials & methods: In this study, we applied six different ML algorithms to predict the presence of CAD amongst patients listed in ‘the Cleveland dataset.’ The generated computer code is provided as a working open source solution with the ultimate goal to achieve a viable clinical tool for CAD detection. Results: All six ML algorithms achieved accuracies greater than 80%, with the ‘neural network’ algorithm achieving accuracy greater than 93%. The recall achieved with the ‘neural network’ model is also the highest of the six models (0.93), indicating that predictive ML models may provide diagnostic value in CAD.
22
Xia, Shujie, Jia Zhang, Guodong Du, Shaozi Li, Chi Teng Vong, Zhaoyang Yang, Jiliang Xin, Long Zhu, Bizhen Gao y Candong Li. "A Microcosmic Syndrome Differentiation Model for Metabolic Syndrome with Multilabel Learning". Evidence-Based Complementary and Alternative Medicine 2020 (26 de noviembre de 2020): 1–10. http://dx.doi.org/10.1155/2020/9081641.
Texto completoResumen
Background. Metabolic syndrome (MS) is a complex multisystem disease. Traditional Chinese medicine (TCM) is effective in preventing and treating MS. Syndrome differentiation is the basis of TCM treatment, which is composed of location and/or nature syndrome elements. At present, there are still some problems for objective and comprehensive syndrome differentiation in MS. This study mainly proposes a solution to two problems. Firstly, TCM syndromes are concurrent, that is, multiple TCM syndromes may develop in the same patient. Secondly, there is a lack of holistic exploration of the relationship between microscopic indexes, and TCM syndromes. In regard to these two problems, multilabel learning (MLL) method in machine learning can be used to solve them, and a microcosmic syndrome differentiation model can also be built innovatively, which can provide a foundation for the establishment of the next model of multidimensional syndrome differentiation in MS. Methods. The standardization scale of TCM four diagnostic information for MS was designed, which was used to obtain the results of TCM diagnosis. The model of microcosmic syndrome differentiation was constructed based on 39 physicochemical indexes by MLL techniques, called ML-kNN. Firstly, the multilabel learning method was compared with three commonly used single learning algorithms. Then, the results from ML-kNN were compared between physicochemical indexes and TCM information. Finally, the influence of the parameter k on the diagnostic model was investigated and the best k value was chosen for TCM diagnosis. Results. A total of 698 cases were collected for the modeling of the microcosmic diagnosis of MS. The comprehensive performance of the ML-kNN model worked obviously better than the others, where the average precision of diagnosis was 71.4%. The results from ML-kNN based on physicochemical indexes were similar to the results based on TCM information. On the other hand, the k value had less influence on the prediction results from ML-kNN. Conclusions. In the present study, the microcosmic syndrome differentiation model of MS with MLL techniques was good at predicting syndrome elements and could be used to solve the diagnosis problems of multiple labels. Besides, it was suggested that there was a complex correlation between TCM syndrome elements and physicochemical indexes, which worth future investigation to promote the development of objective differentiation of MS.
23
Busko, Ekaterina, Anastasiya Goncharova, Nadezhda Rozhkova, Vladislav Semiglazov, Alena Shishova, Elena Zhiltsova, Grigory Zinovev, Kseniya Beloborodova y Petr Krivorotko. "Model for making diagnostic decisions in multiparametric ultrasound of breast lesions". Problems in oncology 66, n.º 6 (30 de diciembre de 2020): 653–58. http://dx.doi.org/10.37469/0507-3758-2020-66-6-653-658.
Texto completoResumen
In order to standardize the description of the breast imaging, the BI-RADS (Breast Imaging Reporting And Data System) imaging system developed by the American College of Radiologists ACR is widely used in world practice. At the same time, numerous visual characteristics of breast lesions with different diagnostic methods complicate the adoption of diagnostic decisions while using the BI-RADS system. The greatest difficulties arise when assessing a variety of multiparametric ultrasound signs of diseases. In this regard, in order to increase the efficiency of these technologies and make fast diagnostic decisions, it becomes relevant to develop a system model based on algorithms using the BI-RADS lexicon.
Materials and methods: from 2017 to 2019 on the basis of the Research Oncology Center named after N.N. Petrov 277 women with various complaints of breast disease were examined using multiparametric ultrasound with elastography and contrast enhancement (2.5 ml Sonovue) on a Hitachi Hi Vision Ascendus ultrasound scanner. The software implementation of the diagnostic decision-making model was carried out using the C # programming language using the Microsoft Visual integrated development environment.
Results: The effectiveness of the developed diagnostic model using the optimal algorithm for the use of various ultrasound technologies in determining the malignancy of the formation showed Sensitivity (Se) = 90.8%, Specificity (Sp) = 95.5%, Positive Predictive Value (PPV) = 88.5%, Negative Predictive Value (NPV) = 96.4%, Accuracy (Ac) = 94.2%. The effectiveness of the developed model in grouping diseases showed Se = 84.2%, Sp = 81.1%, PPV = 62.7%, NPV = 93.1%, Ac = 81.9%.
Conclusions: The proposed system model of the optimal algorithm for making a diagnostic decision based on statistically significant multiparametric ultrasound signs increases the diagnostic efficiency.
24
Agibetov, Asan, Benjamin Seirer, Theresa-Marie Dachs, Matthias Koschutnik, Daniel Dalos, René Rettl, Franz Duca et al. "Machine Learning Enables Prediction of Cardiac Amyloidosis by Routine Laboratory Parameters: A Proof-of-Concept Study". Journal of Clinical Medicine 9, n.º 5 (3 de mayo de 2020): 1334. http://dx.doi.org/10.3390/jcm9051334.
Texto completoResumen
(1) Background: Cardiac amyloidosis (CA) is a rare and complex condition with poor prognosis. While novel therapies improve outcomes, many affected individuals remain undiagnosed due to a lack of awareness among clinicians. This study was undertaken to develop an expert-independent machine learning (ML) prediction model for CA relying on routinely determined laboratory parameters. (2) Methods: In a first step, we developed baseline linear models based on logistic regression. In a second step, we used an ML algorithm based on gradient tree boosting to improve our linear prediction model, and to perform non-linear prediction. Then, we compared the performance of all diagnostic algorithms. All prediction models were developed on a training cohort, consisting of patients with proven CA (positive cases, n = 121) and amyloidosis-unrelated heart failure (HF) patients (negative cases, n = 415). Performances of all prediction models were evaluated on a separate prognostic validation cohort with 37 CA-positive and 124 CA-negative patients. (3) Results: Our best model, based on gradient-boosted ensembles of decision trees, achieved an area under the receiver operating characteristic curve (ROC AUC) score of 0.86, with sensitivity and specificity of 89.2% and 78.2%, respectively. The best linear model had an ROC AUC score of 0.75, with sensitivity and specificity of 84.6 and 71.7, respectively. (4) Conclusions: Our work demonstrates that ML makes it possible to utilize basic laboratory parameters to generate a distinct CA-related HF profile compared with CA-unrelated HF patients. This proof-of-concept study opens a potential new avenue in the diagnostic workup of CA and may assist physicians in clinical reasoning.
25
Friera, Alfonsa, Pilar Artieda, Paloma Caballero, Pilar Moliní, Marta Morales, Carmen Suárez y Nuria Ruiz-Giménez. "Rapid D-dimer test combined a clinical model for deep vein thrombosis". Thrombosis and Haemostasis 91, n.º 06 (2004): 1237–46. http://dx.doi.org/10.1160/th03-02-0080.
Texto completoResumen
SummaryAn optimal approach to the diagnosis of deep vein thrombosis (DVT) in lower limbs in the emergency department is still unknown. In this prospective cohort study, we aimed to evaluate the accuracy of the widely available plasma D-dimer test (VIDAS) and establish the usefulness of combining D-dimer testing with a clinical model to reduce the need for serial ultrasonographies and improve the diagnostic strategy of DVT. We performed a cohort study in 383 consecutive outpatients referred to the emergency department of Hospital La Princesa, with clinical suspicion of DVT. The patients were stratified into three pre-test probability categories using an explicit clinical model (Wells score), and underwent a quantitative automated ELISA D-dimer assay (VIDAS D-Dimer® bioMérieux). Patients were managed according to the diagnostic strategy based on clinical probability and compression ultrasonography (CU). Patients for whom DVT was considered a high pre-test probability with negative ultrasonographic findings in the initial CU, returned the following week for repeat ultrasonography. All patients with DVT excluded did not receive anticoagulant therapy, and were followed up for three months to monitor the development of venous thromboembolic complications. DVT was confirmed in 102 patients (26.6%): 95 in the initial test, four in the second test, and three who developed venous thromboembolic complications in the three-month follow-up period. The calculated D-dimer cut-off level was 1 µg/ml. One hundred patients (98%) with DVT had positive D-dimer. D-dimer had a sensitivity of 98% and a negative predictive value of 98.6%. Among the high-probability patients with positive D-dimer tests and initial negative CU, 9.75% had DVT on repeat CU at one week. The study results suggest that the addition of VIDAS D-dimer to this diagnostic algorithm could improve the management of patients with suspected DVT in daily practice. A diagnostic approach of DVT based on D-dimer (cut-off ≥1 μg/ml) as the first diagnostic tool for the exclusion of DVT, and the clinical probability model as the tool that identifies those patients requiring a second ultrasonography is useful and suitable for daily medical practice.
26
Bäuerlein, Carina A., Simone S. Riedel, Brede Christian, Ana-Laura Jordán Garrote, Agnes Birner, Carolin Kiesel, Miriam Ritz et al. "Definition of a Diagnostic Window Prior to the Onset of Clinically Apparent Acute Graft-Versus-Host Disease." Blood 116, n.º 21 (19 de noviembre de 2010): 3746. http://dx.doi.org/10.1182/blood.v116.21.3746.3746.
Texto completoResumen
Abstract Abstract 3746 Acute graft-versus-host disease (aGvHD) is an immune syndrome after allogeneic hematopoietic cell transplantation (allo-HCT) caused by alloreactive donor T cells that attack the gastrointestinal tract, liver and skin. Thus, early T cell migration patterns to these organs could provide first cues for the onset of aGvHD. Hence, a unique surface marker profile of donor T cells at early time points after allo-HCT may be an indicator for patients at risk of aGVHD. Therefore, we analyzed the course of donor T cell activation, proliferation and homing in a clinical relevant murine MHC minor mismatch (miHAg) allo-HCT model to define critical time points and marker profiles for the detection of alloreactive T cells. Luciferase-labeled C57Bl/6 (H-2b) T cells plus bone marrow cells were transplanted into conditioned (8 Gy) MHC major mismatched Balb/c (H-2d) or miHAg Balb/b (H-2b) recipients. Donor T cell migration was visualized by in vivo bioluminescence imaging (BLI) and cells were characterized by multiparameter flow cytometry for 30 consecutive days after allo-HCT. GVHD scoring was performed by histopathology. Donor T cells proliferated exclusively in secondary lymphoid organs until day+3 (initiation phase) before migrating via the peripheral blood into target organs (effector phase). This occured in both models, MHC major mismatch and miHAg allo-HCT, which resulted in hyper-acute (starting at day+6) or acute GVHD (starting at day+21), respectively. In the hyper-acute scenario one wave of T cell migration starting at day+4 sufficed to cause lethal aGVHD. We detected a 4000-fold increase in CD4 and a 1500-fold increase in CD8 donor T cell numbers in the peripheral blood between day+3 and day+6 in this model. In contrast, in the more clinical relevant miHAg allo-HCT model we found 3 waves of T cell migration with peaks at days +6, +11 and +15 after allo-HCT. In the peripheral blood CD4 T cells increased 20-fold, CD8 T cells 50-fold between day+3 and day+6, but more than 40-fold (CD4) and 400-fold (CD8) between day+3 and day+11. After the third peak on day+15 a period followed when we could only detect very few migrating donor T cells in the peripheral blood before aGvHD became clinically apparent on day+21. Next, we asked whether we could identify alloreactive T cells by testing a large panel of surface markers at the defined migration peaks. Indeed, allogeneic T cells upregulated certain homing receptors at these peaks (e.g. at day+11: α4β7 integrin: 27% of CD4 T cells, 3.4×104/ml, 60% of CD8 T cells, 1.6×105/ml; P-selectin ligand: 28% of CD4 T cells, 3.5×104/ml, 35% of CD8 T cells, 9.1×104/ml). In contrast, syngeneic transplanted mice only showed a constant low expression level of those receptors (e.g. at day+11: α4β7 integrin: 20% of CD4 T cells, 9.6×103/ml, 5% of CD8 T cells, 3.1×103/ml; P-selectin ligand: 17% of CD4 T cells, 8.5×103/ml, 10% of CD8 T cells, 6.6×103/ml). However, other markers such as CD44 could be found on more than 80% of all donor T cells in allogeneic or syngeneic recipients. Our results in this clinical relevant mouse model show accelerating waves of T cell migration consistent with an enhancing feedback loop model of aGvHD pathogenesis. The homing receptor expression profile of donor T cells correlated with critical migration waves and clearly differed between mice with or without aGvHD. The assessment of critical time points frame a diagnostic window for a potential predictive test based on the dynamic change of the T cell homing receptor profile after allo-HCT. This preclinical study now awaits to be evaluated in patients undergoing allo-HCT. Disclosures: No relevant conflicts of interest to declare.
27
Yusuf, Mohamed, Ignacio Atal, Jacques Li, Philip Smith, Philippe Ravaud, Martin Fergie, Michael Callaghan y James Selfe. "Reporting quality of studies using machine learning models for medical diagnosis: a systematic review". BMJ Open 10, n.º 3 (marzo de 2020): e034568. http://dx.doi.org/10.1136/bmjopen-2019-034568.
Texto completoResumen
AimsWe conducted a systematic review assessing the reporting quality of studies validating models based on machine learning (ML) for clinical diagnosis, with a specific focus on the reporting of information concerning the participants on which the diagnostic task was evaluated on.MethodMedline Core Clinical Journals were searched for studies published between July 2015 and July 2018. Two reviewers independently screened the retrieved articles, a third reviewer resolved any discrepancies. An extraction list was developed from the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis guideline. Two reviewers independently extracted the data from the eligible articles. Third and fourth reviewers checked, verified the extracted data as well as resolved any discrepancies between the reviewers.ResultsThe search results yielded 161 papers, of which 28 conformed to the eligibility criteria. Detail of data source was reported in 24 of the 28 papers. For all of the papers, the set of patients on which the ML-based diagnostic system was evaluated was partitioned from a larger dataset, and the method for deriving such set was always reported. Information on the diagnostic/non-diagnostic classification was reported well (23/28). The least reported items were the use of reporting guideline (0/28), distribution of disease severity (8/28 patient flow diagram (10/28) and distribution of alternative diagnosis (10/28). A large proportion of studies (23/28) had a delay between the conduct of the reference standard and ML tests, while one study did not and four studies were unclear. For 15 studies, it was unclear whether the evaluation group corresponded to the setting in which the ML test will be applied to.ConclusionAll studies in this review failed to use reporting guidelines, and a large proportion of them lacked adequate detail on participants, making it difficult to replicate, assess and interpret study findings.PROSPERO registration numberCRD42018099167.
28
Andaur Navarro, Constanza L., Johanna A. A. G. Damen, Toshihiko Takada, Steven W. J. Nijman, Paula Dhiman, Jie Ma, Gary S. Collins et al. "Protocol for a systematic review on the methodological and reporting quality of prediction model studies using machine learning techniques". BMJ Open 10, n.º 11 (noviembre de 2020): e038832. http://dx.doi.org/10.1136/bmjopen-2020-038832.
Texto completoResumen
IntroductionStudies addressing the development and/or validation of diagnostic and prognostic prediction models are abundant in most clinical domains. Systematic reviews have shown that the methodological and reporting quality of prediction model studies is suboptimal. Due to the increasing availability of larger, routinely collected and complex medical data, and the rising application of Artificial Intelligence (AI) or machine learning (ML) techniques, the number of prediction model studies is expected to increase even further. Prediction models developed using AI or ML techniques are often labelled as a ‘black box’ and little is known about their methodological and reporting quality. Therefore, this comprehensive systematic review aims to evaluate the reporting quality, the methodological conduct, and the risk of bias of prediction model studies that applied ML techniques for model development and/or validation.Methods and analysisA search will be performed in PubMed to identify studies developing and/or validating prediction models using any ML methodology and across all medical fields. Studies will be included if they were published between January 2018 and December 2019, predict patient-related outcomes, use any study design or data source, and available in English. Screening of search results and data extraction from included articles will be performed by two independent reviewers. The primary outcomes of this systematic review are: (1) the adherence of ML-based prediction model studies to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD), and (2) the risk of bias in such studies as assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). A narrative synthesis will be conducted for all included studies. Findings will be stratified by study type, medical field and prevalent ML methods, and will inform necessary extensions or updates of TRIPOD and PROBAST to better address prediction model studies that used AI or ML techniques.Ethics and disseminationEthical approval is not required for this study because only available published data will be analysed. Findings will be disseminated through peer-reviewed publications and scientific conferences.Systematic review registrationPROSPERO, CRD42019161764.
29
Ji, Jin, Xi Chen, Yalong Xu, Zhi Cao, Huan Xu, Chen kong, Fubo Wang y Yinghao Sun. "Prostate Cancer Diagnosis Using Urine Sediment Analysis-Based α-Methylacyl-CoA Racemase Score: A Single-Center Experience". Cancer Control 26, n.º 1 (1 de enero de 2019): 107327481988769. http://dx.doi.org/10.1177/1073274819887697.
Texto completoResumen
To evaluate the diagnostic value of α-methylacyl-CoA racemase (AMACR) score in Han Chinese patients with prostate cancer (PCa) through urine sediment analysis. We collected 292 urine sediment samples after digital rectal examination. Levels of AMACR and prostate-specific antigen (PSA) messenger RNA (mRNAs) were evaluated by quantitative real time-polymerase chain reaction. The diagnostic value of AMACR score was assessed by receiver-operating characteristic analysis (ROC), Mann-Whitney test, logistic regression analysis and decision curve analysis. In all patients (n = 292), the area under the curve (AUC) for serum PSA, AMACR score, and a combinative model of these 2 parameters were 0.745 (95% confidence interval [CI]: 0.691-0.794), 0.753 (95% CI: 0.700-0.802), and 0.784 (95% CI: 0.732-0.830). No statistical difference was found between AMACR score and serum PSA ( P = .826), while the combinative model was better than AMACR score (Z = 5.222, P < .001). Among patients with serum PSA level of 4 to 10 ng/mL (n = 121), the AMACR score was significantly higher in patients with PCa ( P = 0.0002), while serum PSA showed no difference ( P = 0.3023). Alpha-methylacyl-CoA racemase score (AUC = 0.712, 95% CI: 0.623-0.790) and a combinative model (AUC = 0.714, 95% CI: 0.626-0.793) showed a better diagnostic value than serum PSA (AUC = 0.559, 95% CI: 0.466-0.649), ( P = .048, P = .042). Decision curve analysis showed a biopsy prediction model including AMACR score have a better net benefit when the threshold probability greater than 20%. The diagnostic model combing serum PSA and AMACR score has a better diagnostic value in patients with abnormal PSA level (including PSA level ranging from 4-10 ng/mL), and could reduce unnecessary prostate biopsy in clinical use.
30
Alfian, Ganjar, Muhammad Syafrudin, Imam Fahrurrozi, Norma Latif Fitriyani, Fransiskus Tatas Dwi Atmaji, Tri Widodo, Nurul Bahiyah, Filip Benes y Jongtae Rhee. "Predicting Breast Cancer from Risk Factors Using SVM and Extra-Trees-Based Feature Selection Method". Computers 11, n.º 9 (12 de septiembre de 2022): 136. http://dx.doi.org/10.3390/computers11090136.
Texto completoResumen
Developing a prediction model from risk factors can provide an efficient method to recognize breast cancer. Machine learning (ML) algorithms have been applied to increase the efficiency of diagnosis at the early stage. This paper studies a support vector machine (SVM) combined with an extremely randomized trees classifier (extra-trees) to provide a diagnosis of breast cancer at the early stage based on risk factors. The extra-trees classifier was used to remove irrelevant features, while SVM was utilized to diagnose the breast cancer status. A breast cancer dataset consisting of 116 subjects was utilized by machine learning models to predict breast cancer, while the stratified 10-fold cross-validation was employed for the model evaluation. Our proposed combined SVM and extra-trees model reached the highest accuracy up to 80.23%, which was significantly better than the other ML model. The experimental results demonstrated that by applying extra-trees-based feature selection, the average ML prediction accuracy was improved by up to 7.29% as contrasted to ML without the feature selection method. Our proposed model is expected to increase the efficiency of breast cancer diagnosis based on risk factors. In addition, we presented the proposed prediction model that could be employed for web-based breast cancer prediction. The proposed model is expected to improve diagnostic decision-support systems by predicting breast cancer disease accurately.
31
Varley-Campbell, Jo, Rubén Mújica-Mota, Helen Coelho, Neel Ocean, Max Barnish, David Packman, Sophie Dodman et al. "Three biomarker tests to help diagnose preterm labour: a systematic review and economic evaluation". Health Technology Assessment 23, n.º 13 (marzo de 2019): 1–226. http://dx.doi.org/10.3310/hta23130.
Texto completoResumen
Background Preterm birth may result in short- and long-term health problems for the child. Accurate diagnoses of preterm births could prevent unnecessary (or ensure appropriate) admissions into hospitals or transfers to specialist units. Objectives The purpose of this report is to assess the test accuracy, clinical effectiveness and cost-effectiveness of the diagnostic tests PartoSure™ (Parsagen Diagnostics Inc., Boston, MA, USA), Actim® Partus (Medix Biochemica, Espoo, Finland) and the Rapid Fetal Fibronectin (fFN)® 10Q Cassette Kit (Hologic, Inc., Marlborough, MA, USA) at thresholds ≠50 ng/ml [quantitative fFN (qfFN)] for women presenting with signs and symptoms of preterm labour relative to fFN at 50 ng/ml. Methods Systematic reviews of the published literature were conducted for diagnostic test accuracy (DTA) studies of PartoSure, Actim Partus and qfFN for predicting preterm birth, the clinical effectiveness following treatment decisions informed by test results and economic evaluations of the tests. A model-based economic evaluation was also conducted to extrapolate long-term outcomes from the results of the diagnostic tests. The model followed the structure of the model that informed the 2015 National Institute for Health and Care Excellence guidelines on preterm labour diagnosis and treatment, but with antenatal steroids use, as opposed to tocolysis, driving health outcomes. Results Twenty studies were identified evaluating DTA against the reference standard of delivery within 7 days and seven studies were identified evaluating DTA against the reference standard of delivery within 48 hours. Two studies assessed two of the index tests within the same population. One study demonstrated that depending on the threshold used, qfFN was more or less accurate than Actim Partus, whereas the other indicated little difference between PartoSure and Actim Partus. No study assessing qfFN and PartoSure in the same population was identified. The test accuracy results from the other included studies revealed a high level of uncertainty, primarily attributable to substantial methodological, clinical and statistical heterogeneity between studies. No study compared all three tests simultaneously. No clinical effectiveness studies evaluating any of the three biomarker tests were identified. One partial economic evaluation was identified for predicting preterm birth. It assessed the number needed to treat to prevent a respiratory distress syndrome case with a ‘treat-all’ strategy, relative to testing with qualitative fFN. Because of the lack of data, our de novo model involved the assumption that management of pregnant women fully adhered to the results of the tests. In the base-case analysis for a woman at 30 weeks’ gestation, Actim Partus had lower health-care costs and fewer quality-adjusted life-years (QALYs) than qfFN at 50 ng/ml, reducing costs at a rate of £56,030 per QALY lost compared with qfFN at 50 ng/ml. PartoSure is less costly than Actim Partus while being equally effective, but this is based on diagnostic accuracy data from a small study. Treatment with qfFN at 200 ng/ml and 500 ng/ml resulted in lower cost savings per QALY lost relative to fFN at 50 ng/ml than treatment with Actim Partus. In contrast, qfFN at 10 ng/ml increased QALYs, by 0.002, and had a cost per QALY gained of £140,267 relative to fFN at 50 ng/ml. Similar qualitative results were obtained for women presenting at different gestational ages. Conclusion There is a high degree of uncertainty surrounding the test accuracy and cost-effectiveness results. We are aware of four ongoing UK trials, two of which plan to enrol > 1000 participants. The results of these trials may significantly alter the findings presented here. Study registration The study is registered as PROSPERO CRD42017072696. Funding The National Institute for Health Research Health Technology Assessment programme.
32
Eckardt, Jan-Niklas, Martin Bornhäuser, Karsten Wendt y Jan Moritz Middeke. "Application of machine learning in the management of acute myeloid leukemia: current practice and future prospects". Blood Advances 4, n.º 23 (8 de diciembre de 2020): 6077–85. http://dx.doi.org/10.1182/bloodadvances.2020002997.
Texto completoResumen
Abstract Machine learning (ML) is rapidly emerging in several fields of cancer research. ML algorithms can deal with vast amounts of medical data and provide a better understanding of malignant disease. Its ability to process information from different diagnostic modalities and functions to predict prognosis and suggest therapeutic strategies indicates that ML is a promising tool for the future management of hematologic malignancies; acute myeloid leukemia (AML) is a model disease of various recent studies. An integration of these ML techniques into various applications in AML management can assure fast and accurate diagnosis as well as precise risk stratification and optimal therapy. Nevertheless, these techniques come with various pitfalls and need a strict regulatory framework to ensure safe use of ML. This comprehensive review highlights and discusses recent advances in ML techniques in the management of AML as a model disease of hematologic neoplasms, enabling researchers and clinicians alike to critically evaluate this upcoming, potentially practice-changing technology.
33
Hsieh, Hsien-Yi, Jingyu Ning, Yi-Ru Chen, Hsun-Chung Wu, Hua Li Chen, Chien-Ming Wu y Ray-Kuang Lee. "Direct Parameter Estimations from Machine Learning-Enhanced Quantum State Tomography". Symmetry 14, n.º 5 (25 de abril de 2022): 874. http://dx.doi.org/10.3390/sym14050874.
Texto completoResumen
With the power to find the best fit to arbitrarily complicated symmetry, machine-learning (ML)-enhanced quantum state tomography (QST) has demonstrated its advantages in extracting complete information about the quantum states. Instead of using the reconstruction model in training a truncated density matrix, we develop a high-performance, lightweight, and easy-to-install supervised characteristic model by generating the target parameters directly. Such a characteristic model-based ML-QST can avoid the problem of dealing with a large Hilbert space, but cab keep feature extractions with high precision, capturing the underlying symmetry in data. With the experimentally measured data generated from the balanced homodyne detectors, we compare the degradation information about quantum noise squeezed states predicted by the reconstruction and characteristic models; both are in agreement with the empirically fitting curves obtained from the covariance method. Such a ML-QST with direct parameter estimations illustrates a crucial diagnostic toolbox for applications with squeezed states, from quantum information process, quantum metrology, advanced gravitational wave detectors, to macroscopic quantum state generation.
34
Hsieh, Hsien-Yi, Jingyu Ning, Yi-Ru Chen, Hsun-Chung Wu, Hua Li Chen, Chien-Ming Wu y Ray-Kuang Lee. "Direct Parameter Estimations from Machine Learning-Enhanced Quantum State Tomography". Symmetry 14, n.º 5 (25 de abril de 2022): 874. http://dx.doi.org/10.3390/sym14050874.
Texto completoResumen
With the power to find the best fit to arbitrarily complicated symmetry, machine-learning (ML)-enhanced quantum state tomography (QST) has demonstrated its advantages in extracting complete information about the quantum states. Instead of using the reconstruction model in training a truncated density matrix, we develop a high-performance, lightweight, and easy-to-install supervised characteristic model by generating the target parameters directly. Such a characteristic model-based ML-QST can avoid the problem of dealing with a large Hilbert space, but cab keep feature extractions with high precision, capturing the underlying symmetry in data. With the experimentally measured data generated from the balanced homodyne detectors, we compare the degradation information about quantum noise squeezed states predicted by the reconstruction and characteristic models; both are in agreement with the empirically fitting curves obtained from the covariance method. Such a ML-QST with direct parameter estimations illustrates a crucial diagnostic toolbox for applications with squeezed states, from quantum information process, quantum metrology, advanced gravitational wave detectors, to macroscopic quantum state generation.
35
Druzhilov, M. A., T. Yu Kuznetsova, D. V. Gavrilov y A. V. Gusev. "Verification of subclinical carotid atherosclerosis as part of risk stratification in overweight and obesity: the role of machine learning in the development of a diagnostic algorithm". Cardiovascular Therapy and Prevention 21, n.º 7 (6 de julio de 2022): 3222. http://dx.doi.org/10.15829/1728-8800-2022-3222.
Texto completoResumen
Aim. Comparative analysis of mathematical models obtained using multivariate logistic regression (MLR) with stepwise inclusion of predictors and machine learning (ML) for assessing the probability of subclinical carotid atherosclerosis in normotensive overweight and obese patients without cardiovascular diseases and/or diabetes.Material and methods. We received data on patients from the Webiomed platform database. The inclusion criteria were age ≥18 years, body mass index ≥25 kg/m2, extracranial artery ultrasound results, while the exclusion criteria included diabetes and/or cardiovascular disease. MLR analysis was carried out with stepwise inclusion of predictors. ML algorithms were used to create an alternative model.Results. The overall percentage of true results for MLR model was 73,2%, while the proportion of true negative and positive predictions was 80,1% and 63,4%, respectively. Mathematical models created using ML methods are characterized by a predictive value from 75 to 97% with a sensitivity of 77 to 92% and a specificity of 80 to 98%.Conclusion. A significant superiority of ML models was revealed in the study of available clinical and paraclinical parameters. Integration of ML mathematical models into a diagnostic algorithm for making a decision to refer a low-risk patient for extracranial artery ultrasound will significantly improve its accuracy and cost efficiency.
36
Takkar, Sakshi, Aman Singh y Babita Pandey. "Application of Machine Learning Algorithms to a Well Defined Clinical Problem: Liver Disease". International Journal of E-Health and Medical Communications 8, n.º 4 (octubre de 2017): 38–60. http://dx.doi.org/10.4018/ijehmc.2017100103.
Texto completoResumen
Liver diseases represent a major health burden worldwide. Machine learning (ML) algorithms have been extensively used to diagnose liver disease. This study accordingly aims to employ various individual and integrated ML algorithms on distinct liver disease datasets for evaluating the diagnostic performances, to integrate dimensionality reduction method with the ML algorithms for analyzing variation in results, to find the best classification model and to analyze the merits and demerits of these algorithms. KNN and PCA-KNN emerged to be the top individual and integrated models. The study also concluded that one specific algorithm can't show best results for all types of datasets and integrated models not always perform better than the individuals. It is observed that no algorithm is perfect and performance of an algorithm totally depends on the dataset type and structure, its number of observations, its dimensions and the decision boundary.
37
Colakoglu, Bulent, Deniz Alis y Mert Yergin. "Diagnostic Value of Machine Learning-Based Quantitative Texture Analysis in Differentiating Benign and Malignant Thyroid Nodules". Journal of Oncology 2019 (31 de octubre de 2019): 1–7. http://dx.doi.org/10.1155/2019/6328329.
Texto completoResumen
Aim. The aim of this study is to evaluate the diagnostic value of machine learning- (ML-) based quantitative texture analysis in the differentiation of benign and malignant thyroid nodules. Materials and methods. A sum of 306 quantitative textural features of 235 thyroid nodules (102 malignant, 43.4%; 133 benign, 56.4%) of a total of 198 patients were investigated using the random forest ML classifier. Feature selection and dimension reduction were conducted using reproducibility testing and a wrapper method. The diagnostic accuracy, sensitivity, specificity, and area under curve (AUC) of the proposed method were compared with the histopathological or cytopathological findings as reference methods. Results. Of the 306 initial texture features, 284 (92.2%) showed good reproducibility (intraclass correlation ≥0.80). The random forest classifier accurately identified 87 out of 102 malignant thyroid nodules and 117 out of 133 benign thyroid nodules, which is a diagnostic sensitivity of 85.2%, specificity of 87.9%, and accuracy of 86.8%. The AUC of the model was 0.92. Conclusions. Quantitative textural analysis of thyroid nodules using ML classification can accurately discriminate benign and malignant thyroid nodules. Our findings should be validated by multicenter prospective studies using completely independent external data.
38
Chen, Wei-Hsin, Yuan-Hong Jiang y Hann-Chorng Kuo. "Urinary Oxidative Stress Biomarkers in the Diagnosis of Detrusor Overactivity in Female Patients with Stress Urinary Incontinence". Biomedicines 11, n.º 2 (26 de enero de 2023): 357. http://dx.doi.org/10.3390/biomedicines11020357.
Texto completoResumen
Ninety-three women with urodynamic stress incontinence (USI) and a mean age of 60.8 ± 10.7 (36–83) years were retrospectively enrolled. According to their VUDS, 31 (33%) were grouped into USI and detrusor overactivity (DO), 28 (30.1%) were grouped into USI and hypersensitive bladder (HSB), and 34 (36.6%) were controls (USI and stable bladder). The USI and DO group had significantly increased 8-isoprostane (mean, 33.3 vs. 10.8 pg/mL) and 8-hydroxy-2-deoxyguanosine (8-OHdG; mean, 28.9 vs. 17.4 ng/mL) and decreased interleukin (IL)-2 (mean, 0.433 vs. 0.638 pg/mL), vascular endothelial growth factor (mean, 5.51 vs. 8.99 pg/mL), and nerve growth factor (mean, 0.175 vs. 0.235 pg/mL) levels compared to controls. Oxidative stress biomarkers were moderately diagnostic of DO from controls, especially 8-isoprostane (area under the curve (AUC) > 0.7). Voided volume was highly diagnostic of DO from either controls or non-DO patients (AUC 0.750 and 0.915, respectively). The proposed prediction model with voided volume, 8-OHdG, and 8-isoprostane (cutoff values 384 mL, 35 ng/mL, and 37 pg/mL, respectively) had an accuracy of 81.7% (sensitivity, 67.7%; specificity, 88.7%; positive predictive value, 75.0%; negative predictive value, 84.6%). Combined with voided volume, urinary oxidative stress biomarkers have the potential to be used to identify urodynamic DO in patients with USI.
39
Mehra, Saanvi, Binoy Shah, Ankur Sethi, Ratna Puri y Somashekhar Nimbalkar. "Down Syndrome Detection Through Graphical Analysis of Facial Dysmorphic Features in Newborn Children With Ethnicity/Racial Slicing: An AI/ML-Based Approach". Journal of Neonatology 36, n.º 3 (septiembre de 2022): 199–205. http://dx.doi.org/10.1177/09732179221113677.
Texto completoResumen
Background Down syndrome (DS) is associated with high mortality in India, due to nondiagnosis/late-diagnosis caused by unavailability of qualified doctors and/or lack of access to expensive medical/diagnostic facilities, especially in rural India. Using artificial intelligence/machine learning graphical pattern recognition tools, relevant facial points can be extracted from children’s photographs, facial anomalies can be identified, and probability of DS affliction can be predicted. Methods: Trained Google’s Cloud Vision AutoML Image Classification model was employed with ~2,000 photographs of DS positive children and ~3,000 photographs of DS negative children. A subset of 300 images, 100 each of Asian, Caucasian, and Other-Race children, was used to train and test 3 race-specific models. These results were compared against a unified model trained and tested with same 300 images. Results: The CloudML model trained with ~5,000 images initially achieved: Sensitivity—94.6%, specificity—96.9%, and accuracy—96.0%. Upon optimizing confidence threshold to 0.1, model maximized sensitivity at 99.6%, specificity dropped to 93.8%, and accuracy maintained at 96.0%. Each of the race-specific models trained with 100 images each, after optimization, yielded perfect scores on sensitivity, specificity, and accuracy of 100% each. Against this, the unified model with 300 images yielded overall accuracy of 98% (100% sensitivity, 83% specificity for Caucasian children, and 100% sensitivity, 100% specificity for Asian/Other children). Conclusions: Post optimization, this model can be used as an effective postnatal screening tool for DS detection. Preliminary results indicate that race-specific models can achieve even higher accuracy, sensitivity, and specificity.
40
Radzi, Siti Fairuz Mat, Muhammad Khalis Abdul Karim, M. Iqbal Saripan, Mohd Amiruddin Abd Rahman, Iza Nurzawani Che Isa y Mohammad Johari Ibahim. "Hyperparameter Tuning and Pipeline Optimization via Grid Search Method and Tree-Based AutoML in Breast Cancer Prediction". Journal of Personalized Medicine 11, n.º 10 (29 de septiembre de 2021): 978. http://dx.doi.org/10.3390/jpm11100978.
Texto completoResumen
Automated machine learning (AutoML) has been recognized as a powerful tool to build a system that automates the design and optimizes the model selection machine learning (ML) pipelines. In this study, we present a tree-based pipeline optimization tool (TPOT) as a method for determining ML models with significant performance and less complex breast cancer diagnostic pipelines. Some features of pre-processors and ML models are defined as expression trees and optimal gene programming (GP) pipelines, a stochastic search system. Features of radiomics have been presented as a guide for the ML pipeline selection from the breast cancer data set based on TPOT. Breast cancer data were used in a comparative analysis of the TPOT-generated ML pipelines with the selected ML classifiers, optimized by a grid search approach. The principal component analysis (PCA) random forest (RF) classification was proven to be the most reliable pipeline with the lowest complexity. The TPOT model selection technique exceeded the performance of grid search (GS) optimization. The RF classifier showed an outstanding outcome amongst the models in combination with only two pre-processors, with a precision of 0.83. The grid search optimized for support vector machine (SVM) classifiers generated a difference of 12% in comparison, while the other two classifiers, naïve Bayes (NB) and artificial neural network—multilayer perceptron (ANN-MLP), generated a difference of almost 39%. The method’s performance was based on sensitivity, specificity, accuracy, precision, and receiver operating curve (ROC) analysis.
41
Skielka, Udo Tersiano, Jacyra Soares y Amauri Pereira de Oliveira. "Study of the equatorial Atlantic Ocean mixing layer using a one-dimensional turbulence model". Brazilian Journal of Oceanography 58, spe3 (junio de 2010): 57–69. http://dx.doi.org/10.1590/s1679-87592010000700008.
Texto completoResumen
The General Ocean Turbulence Model (GOTM) is applied to the diagnostic turbulence field of the mixing layer (ML) over the equatorial region of the Atlantic Ocean. Two situations were investigated: rainy and dry seasons, defined, respectively, by the presence of the intertropical convergence zone and by its northward displacement. Simulations were carried out using data from a PIRATA buoy located on the equator at 23º W to compute surface turbulent fluxes and from the NASA/GEWEX Surface Radiation Budget Project to close the surface radiation balance. A data assimilation scheme was used as a surrogate for the physical effects not present in the one-dimensional model. In the rainy season, results show that the ML is shallower due to the weaker surface stress and stronger stable stratification; the maximum ML depth reached during this season is around 15 m, with an averaged diurnal variation of 7 m depth. In the dry season, the stronger surface stress and the enhanced surface heat balance components enable higher mechanical production of turbulent kinetic energy and, at night, the buoyancy acts also enhancing turbulence in the first meters of depth, characterizing a deeper ML, reaching around 60 m and presenting an average diurnal variation of 30 m.
42
Savalia, Meshwa Rameshbhai y Jaiprakash Vinodkumar Verma. "Classifying Malignant and Benign Tumors of Breast Cancer". International Journal of Reliable and Quality E-Healthcare 12, n.º 1 (24 de febrero de 2023): 1–19. http://dx.doi.org/10.4018/ijrqeh.318483.
Texto completoResumen
Breast cancer is the second major cause of cancer deaths in women. Machine learning classification techniques can be used to increase the precision of diagnosis and bring it closer to 100%, thus saving the lives of many people. This paper proposed four different models, built using different combinations of selected features and applying five ML classification techniques to all the models to identify the best model with the highest accuracy. It analyzes five machine learning techniques, namely logistic regression (LR), support vector machines (SVM), naive bayes (NB), decision trees (DT), and k-nearest neighbor (KNN), for prediction of breast cancer using the Wisconsin Diagnostic Breast Cancer Dataset on these four models. The objective of the paper is to find the best ML algorithm that can most accurately predict breast cancer for a particular model. The outcome of this paper helps the doctors to improvise the diagnosis by knowing the effect of combinations of symptoms with the growth of breast cancer.
43
Jeon, Min Ji, Hojoon Choi, Eun Sang Yu, Ka-Won Kang, Byung-Hyun Lee, Dae Sik Kim, Yong Park et al. "Immature Platelet Fraction Based Diagnostic Predictive Model for Immune Thrombocytopenic Purpura". Blood 132, Supplement 1 (29 de noviembre de 2018): 1149. http://dx.doi.org/10.1182/blood-2018-99-117754.
Texto completoResumen
Abstract Introduction Immune thrombocytopenic purpura (ITP) is known as an acquired, immune-mediated disease characterized by isolated thrombocytopenia. Many studies have asserted that a diagnosis of ITP does not require a routine bone marrow examination. However, bone marrow examination is necessary in many cases because the diagnosis of ITP requires exclusion of other diseases including bone marrow disease. As both physicians and patients are reluctant to perform an invasive bone marrow examination, other parameters, including the immature platelet fraction (IPF, %), have been incorporated into the differential diagnosis of thrombocytopenia. In this study, we assessed its usefulness of IPF as a diagnostic marker and developed a diagnostic predictive model for ITP. Methods We retrospectively analyzed 330 patients with thrombocytopenia (platelet count < 100 x 109/L) who presented to Korea University Guro hospital between April 2013 and December 2017. We classified patients into 2 groups: those diagnosed with ITP (ITP group) and those without ITP (non-ITP group). ITP was diagnosed on the basis of clinical manifestations and laboratory results according to International Working Group diagnostic criteria. Non-ITP group included thrombocytopenia due to bone marrow disease, infection, drug, liver disease, etc. We used an automated hematologic analyzer (Sysmex XE-2100) to quantify the IPF and estimated other laboratory variables, including hemoglobin, platelet, white blood cell counts, reticulocytes, protein, albumin, bilirubin, pro-thrombin, activated partial thromboplastin time, ferritin, lactate dehydrogenase, blood urea nitrogen, creatinine, and C-reactive protein. All data were statistically analyzed using SPSS version 20. Logistic regression analysis was performed with the laboratory variables to access their diagnostic contribution. We used receiver-operating characteristic (ROC) and the point with the highest sum of sensitivity and specificity on the ROC curve was determined as the cut-off value of each variables. P-values < 0.05 were considered statistically significant. Results A total of 103 and 227 patients were diagnosed as ITP and non-ITP. The median IPF is significantly higher in ITP group, with a value of 10.5% (1.3-48%) vs. 5.9% (0.7-31.5%) in the non-ITP group, and cut-off value for differentiation of ITP was 7.0% with a sensitivity of 64.8% and a specificity of 65.2%. Since ITP remains a diagnosis of exclusion, some patients who did not undergo a bone marrow examination might have been misclassified into the ITP group. To exclude the possibility of misclassification, we conducted a subgroup analysis of only patients who had undergone a bone marrow examination (BM group). A total of 162 patients performed bone marrow examination, 47 and 115 were classified into the ITP and non-ITP group. The median IPF was significantly higher in ITP group, with a value of 13.6% (4.3-38.5%) vs. 4.7% (0.7-31.5%) for the non-ITP group. The cut-off value was 9.25%, with a sensitivity of 78.7% and a specificity of 78.3%. The median IPF was higher in this subgroup and the sensitivity and specificity of the cut-off value were also higher than the former group. (Figure 1) We confirmed that IPF could be a useful parameter for diagnosing ITP, but since IPF alone could not diagnose ITP, we also evaluated other laboratory variables by the logistic regression analysis. Hemoglobin, ferritin showed statistical significance, and the optimal cut-off value was 12 g/dl and 175 mg/ml. To adequately reflect sensitivity and specificity, we divided patients into 3 groups according to IPF; IPF<5, ≥5 and <10, ≥10. We developed simple diagnostic predictive model with these variables. Our model gave point to each of variables; 1 to high hemoglobin level (>12g/dl), low ferritin level (<175ng/ml) and IPF ≥5 and <10, 2 to IPF ≥10. The final score was obtained by summing the points. We demonstrated that ITP could be highly predicted in patients with score 3-4 (80% in all patients group, 89% in BM group) and could be excluded in patients with score 0-1 (95% in all patients group, 97% in BM group). (Table 1) Conclusions The results showed that IPF could be a good diagnostic marker for ITP. We suggested the diagnostic predictive model for ITP using IPF, hemoglobin and ferritin. This model could diagnose ITP with high probability and avoid a bone marrow examination. Further studies would be needed to refine and validate this predictive model. Disclosures No relevant conflicts of interest to declare.
44
Kim, Harin, Sung Woo Joo, Yeon Ho Joo y Jungsun Lee. "S152. DIAGNOSTIC CLASSIFICATION OF SCHIZOPHRENIA USING 3D CONVOLUTIONAL NEURAL NETWORK WITH RESTING-STATE FUNCTIONAL MRI". Schizophrenia Bulletin 46, Supplement_1 (abril de 2020): S94. http://dx.doi.org/10.1093/schbul/sbaa031.218.
Texto completoResumen
Abstract Background Several machine-learning (ML) algorithms have been deployed in the diagnostic classification of schizophrenia. Compared to other ML methods, the 3D convolutional neural network (CNN) has an advantage of learning complex and subtle patterns in data and preserving spatial information, which is a more suitable tool for brain imaging data. Although resting-state functional MRI (rsfMRI) data has been used in previous ML studies relating to the diagnostic classification of schizophrenia, a limited number of studies have been conducted using resting-state functional connectivity resulted from group independent component analysis (ICA) and dual regression. The objective of this study was to investigate whether a successful diagnostic classification of schizophrenia vs. healthy controls could be achieved by the 3D CNN using resting-state networks in which areas with a significant group difference in activity existed. Methods T1 and rsfMRI data were collected in 46 patients with recent-onset schizophrenia and 22 healthy controls. In the pre-processing steps of rsfMRI, the ICA-based automatic removal of motion artifacts was applied to subject-level ICA results and the resulting rsfMRI data were temporally concatenated for group ICA and dual regression. The executive control and auditory networks had areas with significantly higher activity in the control group compared with the patient group. The independent components (ICs) respective to the executive control and auditory networks were used as input for the 3D CNN model which was developed to discriminate the schizophrenia patients from the healthy controls. Results The 3D CNN model using the executive control and auditory networks as inputs showed classification accuracies of 65~70%, and error rates of 30~35% approximately. Discussion Our findings suggest that the 3D CNN model using rsfMRI data can be useful for learning patterns implicated in schizophrenia and identifying discriminative patterns of schizophrenia in brain imaging data.
45
Gallardo, Diego I., Marcelo Bourguignon, Yolanda M. Gómez, Christian Caamaño-Carrillo y Osvaldo Venegas. "Parametric Quantile Regression Models for Fitting Double Bounded Response with Application to COVID-19 Mortality Rate Data". Mathematics 10, n.º 13 (27 de junio de 2022): 2249. http://dx.doi.org/10.3390/math10132249.
Texto completoResumen
In this paper, we develop two fully parametric quantile regression models, based on the power Johnson SB distribution for modeling unit interval response in different quantiles. In particular, the conditional distribution is modeled by the power Johnson SB distribution. The maximum likelihood (ML) estimation method is employed to estimate the model parameters. Simulation studies are conducted to evaluate the performance of the ML estimators in finite samples. Furthermore, we discuss influence diagnostic tools and residuals. The effectiveness of our proposals is illustrated with a data set of the mortality rate of COVID-19 in different countries. The results of our models with this data set show the potential of using the new methodology. Thus, we conclude that the results are favorable to the use of proposed quantile regression models for fitting double bounded data.
46
Pane, Katia, Mario Zanfardino, Anna Maria Grimaldi, Gustavo Baldassarre, Marco Salvatore, Mariarosaria Incoronato y Monica Franzese. "Discovering Common miRNA Signatures Underlying Female-Specific Cancers via a Machine Learning Approach Driven by the Cancer Hallmark ERBB". Biomedicines 10, n.º 6 (2 de junio de 2022): 1306. http://dx.doi.org/10.3390/biomedicines10061306.
Texto completoResumen
Big data processing, using omics data integration and machine learning (ML) methods, drive efforts to discover diagnostic and prognostic biomarkers for clinical decision making. Previously, we used the TCGA database for gene expression profiling of breast, ovary, and endometrial cancers, and identified a top-scoring network centered on the ERBB2 gene, which plays a crucial role in carcinogenesis in the three estrogen-dependent tumors. Here, we focused on microRNA expression signature similarity, asking whether they could target the ERBB family. We applied an ML approach on integrated TCGA miRNA profiling of breast, endometrium, and ovarian cancer to identify common miRNA signatures differentiating tumor and normal conditions. Using the ML-based algorithm and the miRTarBase database, we found 205 features and 158 miRNAs targeting ERBB isoforms, respectively. By merging the results of both databases and ranking each feature according to the weighted Support Vector Machine model, we prioritized 42 features, with accuracy (0.98), AUC (0.93–95% CI 0.917–0.94), sensitivity (0.85), and specificity (0.99), indicating their diagnostic capability to discriminate between the two conditions. In vitro validations by qRT-PCR experiments, using model and parental cell lines for each tumor type showed that five miRNAs (hsa-mir-323a-3p, hsa-mir-323b-3p, hsa-mir-331-3p, hsa-mir-381-3p, and hsa-mir-1301-3p) had expressed trend concordance between breast, ovarian, and endometrium cancer cell lines compared with normal lines, confirming our in silico predictions. This shows that an integrated computational approach combined with biological knowledge, could identify expression signatures as potential diagnostic biomarkers common to multiple tumors.
47
Bustamante-Arias, Andres, Abbas Cheddad, Julio Cesar Jimenez-Perez y Alejandro Rodriguez-Garcia. "Digital Image Processing and Development of Machine Learning Models for the Discrimination of Corneal Pathology: An Experimental Model". Photonics 8, n.º 4 (10 de abril de 2021): 118. http://dx.doi.org/10.3390/photonics8040118.
Texto completoResumen
Machine learning (ML) has an impressive capacity to learn and analyze a large volume of data. This study aimed to train different algorithms to discriminate between healthy and pathologic corneal images by evaluating digitally processed spectral-domain optical coherence tomography (SD-OCT) corneal images. A set of 22 SD-OCT images belonging to a random set of corneal pathologies was compared to 71 healthy corneas (control group). A binary classification method was applied where three approaches of ML were explored. Once all images were analyzed, representative areas from every digital image were also extracted, processed and analyzed for a statistical feature comparison between healthy and pathologic corneas. The best performance was obtained from transfer learning—support vector machine (TL-SVM) (AUC = 0.94, SPE 88%, SEN 100%) and transfer learning—random forest (TL- RF) method (AUC = 0.92, SPE 84%, SEN 100%), followed by convolutional neural network (CNN) (AUC = 0.84, SPE 77%, SEN 91%) and random forest (AUC = 0.77, SPE 60%, SEN 95%). The highest diagnostic accuracy in classifying corneal images was achieved with the TL-SVM and the TL-RF models. In image classification, CNN was a strong predictor. This pilot experimental study developed a systematic mechanized system to discern pathologic from healthy corneas using a small sample.
48
Hassan, Ch Anwar ul, Jawaid Iqbal, Rizwana Irfan, Saddam Hussain, Abeer D. Algarni, Syed Sabir Hussain Bukhari, Nazik Alturki y Syed Sajid Ullah. "Effectively Predicting the Presence of Coronary Heart Disease Using Machine Learning Classifiers". Sensors 22, n.º 19 (23 de septiembre de 2022): 7227. http://dx.doi.org/10.3390/s22197227.
Texto completoResumen
Coronary heart disease is one of the major causes of deaths around the globe. Predicating a heart disease is one of the most challenging tasks in the field of clinical data analysis. Machine learning (ML) is useful in diagnostic assistance in terms of decision making and prediction on the basis of the data produced by healthcare sector globally. We have also perceived ML techniques employed in the medical field of disease prediction. In this regard, numerous research studies have been shown on heart disease prediction using an ML classifier. In this paper, we used eleven ML classifiers to identify key features, which improved the predictability of heart disease. To introduce the prediction model, various feature combinations and well-known classification algorithms were used. We achieved 95% accuracy with gradient boosted trees and multilayer perceptron in the heart disease prediction model. The Random Forest gives a better performance level in heart disease prediction, with an accuracy level of 96%.
49
Diprose, William K., Nicholas Buist, Ning Hua, Quentin Thurier, George Shand y Reece Robinson. "Physician understanding, explainability, and trust in a hypothetical machine learning risk calculator". Journal of the American Medical Informatics Association 27, n.º 4 (27 de febrero de 2020): 592–600. http://dx.doi.org/10.1093/jamia/ocz229.
Texto completoResumen
Abstract Objective Implementation of machine learning (ML) may be limited by patients’ right to “meaningful information about the logic involved” when ML influences healthcare decisions. Given the complexity of healthcare decisions, it is likely that ML outputs will need to be understood and trusted by physicians, and then explained to patients. We therefore investigated the association between physician understanding of ML outputs, their ability to explain these to patients, and their willingness to trust the ML outputs, using various ML explainability methods. Materials and Methods We designed a survey for physicians with a diagnostic dilemma that could be resolved by an ML risk calculator. Physicians were asked to rate their understanding, explainability, and trust in response to 3 different ML outputs. One ML output had no explanation of its logic (the control) and 2 ML outputs used different model-agnostic explainability methods. The relationships among understanding, explainability, and trust were assessed using Cochran-Mantel-Haenszel tests of association. Results The survey was sent to 1315 physicians, and 170 (13%) provided completed surveys. There were significant associations between physician understanding and explainability (P < .001), between physician understanding and trust (P < .001), and between explainability and trust (P < .001). ML outputs that used model-agnostic explainability methods were preferred by 88% of physicians when compared with the control condition; however, no particular ML explainability method had a greater influence on intended physician behavior. Conclusions Physician understanding, explainability, and trust in ML risk calculators are related. Physicians preferred ML outputs accompanied by model-agnostic explanations but the explainability method did not alter intended physician behavior.
50
Arokiaraj, Mark Christopher. "Angioplasty with Stenting in Acute Coronary Syndromes with Very Low Contrast Volume Using 6F Diagnostic Catheters and Bench Testing of Catheters". Open Access Macedonian Journal of Medical Sciences 7, n.º 6 (29 de marzo de 2019): 1004–12. http://dx.doi.org/10.3889/oamjms.2019.238.
Texto completoResumen
AIM: To safely perform angioplasties in acute coronary syndromes with low contrast volume using Cordis 6F diagnostic catheters and to perform mechanical bench tests on the diagnostic and guide catheters in a radial path model.
METHODS: In 191 patients (242 lesions/268 stents) with acute coronary syndromes angioplasty were performed with cordis 6F diagnostic catheters.
RESULTS: The lesions were present at left anterior descending (121), Left main (5), left circumflex (51), ramus (5) and right coronary artery (60). In 72% of cases, Iodixanol was used. All contrast injections were given by hand. Regular follow-up of the patients was performed at 30 days. The procedures were performed in the femoral route only. Pre-dilatation was performed in 43 cases. Successful revascularization of the target lesion was achieved in all cases. The mean contrast volume used per patient was 28 ml (± 8 ml). Mild reversible contrast-induced nephropathy (CIN) was observed in two patients. Cardiogenic shock was seen in 7 cases, and one death was observed. Pushability and trackability tests showed good force transmission and hysteresis in diagnostic catheters compared to guide catheters.
CONCLUSIONS: Angioplasty with stenting could be performed safely in patients using cordis 6F diagnostic catheters using a low volume of contrast in acute coronary syndromes. Low contrast volume usage would result in a lower incidence of contrast-induced nephropathy and cardiac failures.