Articles de revues : « Predictive HCI models »

1

Paton, Chris, Andre W. Kushniruk, Elizabeth M. Borycki, Mike English et Jim Warren. « Improving the Usability and Safety of Digital Health Systems : The Role of Predictive Human-Computer Interaction Modeling ». Journal of Medical Internet Research 23, n^o 5 (27 mai 2021) : e25281. http://dx.doi.org/10.2196/25281.

Texte intégral

Résumé :

In this paper, we describe techniques for predictive modeling of human-computer interaction (HCI) and discuss how they could be used in the development and evaluation of user interfaces for digital health systems such as electronic health record systems. Predictive HCI modeling has the potential to improve the generalizability of usability evaluations of digital health interventions beyond specific contexts, especially when integrated with models of distributed cognition and higher-level sociotechnical frameworks. Evidence generated from building and testing HCI models of the user interface (UI) components for different types of digital health interventions could be valuable for informing evidence-based UI design guidelines to support the development of safer and more effective UIs for digital health interventions.

Styles APA, Harvard, Vancouver, ISO, etc.

2

Segkouli, Sofia, Ioannis Paliokas, Dimitrios Tzovaras, Thanos Tsakiris, Magda Tsolaki et Charalampos Karagiannidis. « Novel Virtual User Models of Mild Cognitive Impairment for Simulating Dementia ». Computational and Mathematical Methods in Medicine 2015 (2015) : 1–15. http://dx.doi.org/10.1155/2015/358638.

Texte intégral

Résumé :

Virtual user modeling research has attempted to address critical issues of human-computer interaction (HCI) such as usability and utility through a large number of analytic, usability-oriented approaches as cognitive models in order to provide users with experiences fitting to their specific needs. However, there is demand for more specific modules embodied in cognitive architecture that will detect abnormal cognitive decline across new synthetic task environments. Also, accessibility evaluation of graphical user interfaces (GUIs) requires considerable effort for enhancing ICT products accessibility for older adults. The main aim of this study is to develop and test virtual user models (VUM) simulating mild cognitive impairment (MCI) through novel specific modules, embodied at cognitive models and defined by estimations of cognitive parameters. Well-established MCI detection tests assessed users’ cognition, elaborated their ability to perform multitasks, and monitored the performance of infotainment related tasks to provide more accurate simulation results on existing conceptual frameworks and enhanced predictive validity in interfaces’ design supported by increased tasks’ complexity to capture a more detailed profile of users’ capabilities and limitations. The final outcome is a more robust cognitive prediction model, accurately fitted to human data to be used for more reliable interfaces’ evaluation through simulation on the basis of virtual models of MCI users.

Styles APA, Harvard, Vancouver, ISO, etc.

3

Isiaka, Fatima, Kassim S. Mwitondi et Adamu M. Ibrahim. « Detection of natural structures and classification of HCI-HPR data using robust forward search algorithm ». International Journal of Intelligent Computing and Cybernetics 9, n^o 1 (14 mars 2016) : 23–41. http://dx.doi.org/10.1108/ijicc-08-2015-0029.

Texte intégral

Résumé :

Purpose – The purpose of this paper is to proposes a forward search algorithm for detecting and identifying natural structures arising in human-computer interaction (HCI) and human physiological response (HPR) data. Design/methodology/approach – The paper portrays aspects that are essential to modelling and precision in detection. The methods involves developed algorithm for detecting outliers in data to recognise natural patterns in incessant data such as HCI-HPR data. The detected categorical data are simultaneously labelled based on the data reliance on parametric rules to predictive models used in classification algorithms. Data were also simulated based on multivariate normal distribution method and used to compare and validate the original data. Findings – Results shows that the forward search method provides robust features that are capable of repelling over-fitting in physiological and eye movement data. Research limitations/implications – One of the limitations of the robust forward search algorithm is that when the number of digits for residuals value is more than the expected size for stack flow, it normally yields an error caution; to counter this, the data sets are normally standardized by taking the logarithmic function of the model before running the algorithm. Practical implications – The authors conducted some of the experiments at individual residence which may affect environmental constraints. Originality/value – The novel approach to this method is the detection of outliers for data sets based on the Mahalanobis distances on HCI and HPR. And can also involve a large size of data with p possible parameters. The improvement made to the algorithm is application of more graphical display and rendering of the residual plot.

Styles APA, Harvard, Vancouver, ISO, etc.

4

Krabbe, Laura-Maria, Aditya Bagrodia, Ahmed Q. Haddad, Payal Kapur, Dina Khalil, Linda S. Hynan, Christopher G. Wood et al. « Multi-institutional validation of the predictive value of Ki-67 in patients with high-grade urothelial carcinoma of the upper urinary tract. » Journal of Clinical Oncology 33, n^o 7_suppl (1 mars 2015) : 371. http://dx.doi.org/10.1200/jco.2015.33.7_suppl.371.

Texte intégral

Résumé :

371 Background: To validate the independent predictive value of Ki-67 in patients with high-grade upper tract urothelial carcinoma (UTUC). Methods: 475 patients from the international UTUC collaboration who underwent extirpative surgery for high-grade UTUC were included in this study. Immunohistochemical staining for Ki-67 was performed on tissue microarray (TMA) formed from this patient cohort. Ki-67 expression was assessed in a semi-quantitative fashion and considered overexpressed at a cut-off of 20%. Multivariate analyses (MVA) were performed to assess independent predictors of oncological outcomes and Harrell’s C indices (HCI) were calculated for predictive models. Results: Median age of the cohort was 69.7 years and 55.2% of patients were male. Ki-67 was overexpressed in 25.9% of patients. Ki-67 overexpression was significantly associated with ureteral tumor location, higher pT-stage, lymphovascular invasion, sessile tumor architecture, tumor necrosis, concomitant carcinoma in situ (CIS), and regional lymph node metastases. In Kaplan-Meier analyses, overexpressed Ki-67 was associated with worse recurrence-free (RFS) (HR 12.6, p<0.001) and cancer-specific survival (CSS) (HR 15.8, p<0.001). In MVA, Ki-67 was an independent predictor of RFS (HR 1.6, 95% CI 1.07-2.30, p=0.021) and CSS (HR 1.9, 95% CI 1.29-2.90, p=0.001). Ki-67 improved HCI from 0.66 to 0.70 (p<0.0001) for both RFS and CSS in our preoperative model, and from 0.81 to 0.82 (p=0.0018) for RFS and 0.81 to 0.83 (p=0.005) for CSS in our post-operative model. Conclusions: Ki-67 was validated as an independent prognostic predictor of RFS and CSS in patients treated with extirpative surgery for high-grade UTUC in a large, multi-institutional cohort.

Styles APA, Harvard, Vancouver, ISO, etc.

5

Bakaev, Maxim, Sebastian Heil et Martin Gaedke. « Reasonable Effectiveness of Features in Modeling Visual Perception of User Interfaces ». Big Data and Cognitive Computing 7, n^o 1 (8 février 2023) : 30. http://dx.doi.org/10.3390/bdcc7010030.

Texte intégral

Résumé :

Training data for user behavior models that predict subjective dimensions of visual perception are often too scarce for deep learning methods to be applicable. With the typical datasets in HCI limited to thousands or even hundreds of records, feature-based approaches are still widely used in visual analysis of graphical user interfaces (UIs). In our paper, we benchmarked the predictive accuracy of the two types of neural network (NN) models, and explored the effects of the number of features, and the dataset volume. To this end, we used two datasets that comprised over 4000 webpage screenshots, assessed by 233 subjects per the subjective dimensions of Complexity, Aesthetics and Orderliness. With the experimental data, we constructed and trained 1908 models. The feature-based NNs demonstrated 16.2%-better mean squared error (MSE) than the convolutional NNs (a modified GoogLeNet architecture); however, the CNNs’ accuracy improved with the larger dataset volume, whereas the ANNs’ did not: therefore, provided that the effect of more data on the models’ error improvement is linear, the CNNs should become superior at dataset sizes over 3000 UIs. Unexpectedly, adding more features to the NN models caused the MSE to somehow increase by 1.23%: although the difference was not significant, this confirmed the importance of careful feature engineering.

Styles APA, Harvard, Vancouver, ISO, etc.

6

Lee, Jae Seung, Tae Seop Lim, Hye Won Lee, Seung Up Kim, Jun Yong Park, Do Young Kim, Sang Hoon Ahn et al. « Suboptimal Performance of Hepatocellular Carcinoma Prediction Models in Patients with Hepatitis B Virus-Related Cirrhosis ». Diagnostics 13, n^o 1 (20 décembre 2022) : 3. http://dx.doi.org/10.3390/diagnostics13010003.

Texte intégral

Résumé :

This study aimed to evaluate the predictive performance of pre-existing well-validated hepatocellular carcinoma (HCC) prediction models, established in patients with HBV-related cirrhosis who started potent antiviral therapy (AVT). We retrospectively reviewed the cases of 1339 treatment-naïve patients with HBV-related cirrhosis who started AVT (median period, 56.8 months). The scores of the pre-existing HCC risk prediction models were calculated at the time of AVT initiation. HCC developed in 211 patients (15.1%), and the cumulative probability of HCC development at 5 years was 14.6%. Multivariate Cox regression analysis revealed that older age (adjusted hazard ratio [aHR], 1.023), lower platelet count (aHR, 0.997), lower serum albumin level (aHR, 0.578), and greater LS value (aHR, 1.012) were associated with HCC development. Harrell’s c-indices of the PAGE-B, modified PAGE-B, modified REACH-B, CAMD, aMAP, HCC-RESCUE, AASL-HCC, Toronto HCC Risk Index, PLAN-B, APA-B, CAGE-B, and SAGE-B models were suboptimal in patients with HBV-related cirrhosis, ranging from 0.565 to 0.667. Nevertheless, almost all patients were well stratified into low-, intermediate-, or high-risk groups according to each model (all log-rank p < 0.05), except for HCC-RESCUE (p = 0.080). Since all low-risk patients had cirrhosis at baseline, they had unneglectable cumulative incidence of HCC development (5-year incidence, 4.9–7.5%). Pre-existing risk prediction models for patients with chronic hepatitis B showed suboptimal predictive performances for the assessment of HCC development in patients with HBV-related cirrhosis.

Styles APA, Harvard, Vancouver, ISO, etc.

7

Nishida, Nao, Jun Ohashi, Goki Suda, Takehiro Chiyoda, Nobuharu Tamaki, Takahiro Tomiyama, Sachiko Ogasawara et al. « Prediction Model with HLA-A*33:03 Reveals Number of Days to Develop Liver Cancer from Blood Test ». International Journal of Molecular Sciences 24, n^o 5 (1 mars 2023) : 4761. http://dx.doi.org/10.3390/ijms24054761.

Texte intégral

Résumé :

The development of liver cancer in patients with hepatitis B is a major problem, and several models have been reported to predict the development of liver cancer. However, no predictive model involving human genetic factors has been reported to date. For the items incorporated in the prediction model reported so far, we selected items that were significant in predicting liver carcinogenesis in Japanese patients with hepatitis B and constructed a prediction model of liver carcinogenesis by the Cox proportional hazard model with the addition of Human Leukocyte Antigen (HLA) genotypes. The model, which included four items—sex, age at the time of examination, alpha-fetoprotein level (log10AFP) and presence or absence of HLA-A*33:03—revealed an area under the receiver operating characteristic curve (AUROC) of 0.862 for HCC prediction within 1 year and an AUROC of 0.863 within 3 years. A 1000 repeated validation test resulted in a C-index of 0.75 or higher, or sensitivity of 0.70 or higher, indicating that this predictive model can distinguish those at high risk of developing liver cancer within a few years with high accuracy. The prediction model constructed in this study, which can distinguish between chronic hepatitis B patients who develop hepatocellular carcinoma (HCC) early and those who develop HCC late or not, is clinically meaningful.

Styles APA, Harvard, Vancouver, ISO, etc.

8

Lim, Jihye, Young Eun Chon, Mi Na Kim, Joo Ho Lee, Seong Gyu Hwang, Han Chu Lee et Yeonjung Ha. « Cirrhosis, Age, and Liver Stiffness-Based Models Predict Hepatocellular Carcinoma in Asian Patients with Chronic Hepatitis B ». Cancers 13, n^o 22 (9 novembre 2021) : 5609. http://dx.doi.org/10.3390/cancers13225609.

Texte intégral

Résumé :

Objectives: Predicting hepatocellular carcinoma (HCC) in patients with chronic hepatitis B who received long-term therapy with potent nucleos(t)ide analogs is of utmost importance to refine the strategy for HCC surveillance. Methods: We conducted a multicenter retrospective cohort study to validate the CAGE-B and SAGE-B scores, HCC prediction models developed for Caucasian patients receiving entecavir (ETV) or tenofovir (TFV) for >5 years. Consecutive patients who started ETV or TFV at two hospitals in Korea from January 2009 to December 2015 were identified. The prediction scores were calculated, and model performance was assessed using receiver operating characteristics (ROC) curves. Results: Among 1557 patients included, 57 (3.7%) patients had HCC during a median follow-up of 93 (95% confidence interval, 73–119) months. In the entire cohort, CAGE-B predicted HCC with an area under the ROC curve of 0.78 (95% CI, 0.72–0.84). Models that have “liver cirrhosis” in the calculation, such as AASL (0.79 (0.72–0.85)), CU-HCC (0.77 (0.72–0.82)), and GAG-HCC (0.79 (0.74–0.85)), showed accuracy similar to that of CAGE-B (p > 0.05); however, models without “liver cirrhosis”, including SAGE-B (0.71 (0.65–0.78)), showed a lower predictive ability than CAGE-B. CAGE-B performed well in subgroups of patients treated without treatment modification (0.81 (0.73–0.88)) and of male sex (0.79 (0.71–0.86)). Conclusions: This study validated the clinical usefulness of the CAGE-B score in a large number of Asian patients treated with long-term ETV or TFV. The results could provide the basis for the reappraisal of HCC surveillance strategies and encourage future prospective validation studies with liver stiffness measurements.

Styles APA, Harvard, Vancouver, ISO, etc.

9

Li, Huikai, Han Mu, Yajie Xiao, Zhikun Zhao, Xiaoli Cui et Dongfang Wu. « Comprehensive Analysis of Histone Modifications in Hepatocellular Carcinoma Reveals Different Subtypes and Key Prognostic Models ». Journal of Oncology 2022 (1 août 2022) : 1–20. http://dx.doi.org/10.1155/2022/5961603.

Texte intégral

Résumé :

Histone modification, an important epigenetic mechanism, is related to the carcinogenesis of hepatocellular carcinoma (HCC). In three datasets, we screened 88 epigenetic-dysregulated PCGs (epi-PCGs) , which were significantly associated with HCC survival and could cluster HCC into three molecular subtypes. These subtypes were associated with prognosis, immunomodulatory alterations, and response to different treatment strategies. Based on 88 epi-PCGs in the TCGA training set, a risk prediction model composed of 4 epi-PCGs was established. The model was closely related to the clinicopathological features and showed a strong predictive ability in different clinical subgroups. In addition, the risk prediction model was an independent prognostic factor for patients with HCC. The significance of epi-PCGs in HCC is revealed by our data analysis.

Styles APA, Harvard, Vancouver, ISO, etc.

10

Li, Yao, Wei Wang, Weisheng Zeng, Jianjun Wang et Jinghui Meng. « Development of Crown Ratio and Height to Crown Base Models for Masson Pine in Southern China ». Forests 11, n^o 11 (19 novembre 2020) : 1216. http://dx.doi.org/10.3390/f11111216.

Texte intégral

Résumé :

Crown ratio (CR) and height to crown base (HCB) are important crown characteristics influencing the behavior of forest canopy fires. However, the labor-intensive and costly measurement of CR and HCB have hindered their wide application to forest fire management. Here, we use 301 sample trees collected in 11 provinces in China to produce predictive models of CR and HCB for Masson pine forests (Pinus massoniana Lamb.), which are vulnerable to forest canopy fires. We first identified the best basic model that used only diameter at breast height (DBH) and height (H) as independent variables to predict CR and HCB, respectively, from 11 of the most used potential candidate models. Second, we introduced other covariates into the best basic model of CR and HCB and developed the final CR and HCB predictive models after evaluating the model performance of different combinations of covariates. The results showed that the Richards form of the candidate models performed best in predicting CR and HCB. The final CR model included DBH, H, DBH0.5 and height-to-diameter ratio (HDR), while the final HCB model was the best basic model (i.e., it did not contain any other covariates). We hope that our CR and HCB predictive models contribute to the forest crown fire management of Masson pine forests.

Styles APA, Harvard, Vancouver, ISO, etc.

11

Hui, Yongfeng, Junzhi Leng, Dong Jin, Di Liu, Genwang Wang, Qi Wang et Yanyang Wang. « A Cell Cycle Progression-Derived Gene Signature to Predict Prognosis and Therapeutic Response in Hepatocellular Carcinoma ». Disease Markers 2021 (21 octobre 2021) : 1–36. http://dx.doi.org/10.1155/2021/1986159.

Texte intégral

Résumé :

Objective. Dysregulation of cell cycle progression (CCP) is one of the hallmarks of cancer. Here, our study is aimed at developing a CCP-derived gene signature for predicting high-risk population of hepatocellular carcinoma (HCC). Methods. Our study retrospectively analyzed the transcriptome profiling and clinical information of HCC patients from The Cancer Genome Atlas (TCGA) and International Cancer Genome Consortium (ICGC) projects. Uni- and multivariate cox regression models were conducted for identifying which hallmarks of cancer were risk factors of HCC. CCP-derived gene signature was developed with LASSO method. The predictive efficacy was verified by ROC curves and subgroup analyses. A nomogram was then generated and validated by ROC, calibration, and decisive curves. Immune cell infiltration was estimated with ssGSEA method. Potential small molecular compounds were predicted via CTRP and CMap analyses. The response to chemotherapeutic agents was evaluated based on the GDSC project. Results. Among hallmarks of cancer, CCP was identified as a dominant risk factor for HCC prognosis. CCP-derived gene signature displayed the favorable predictive efficacy in HCC prognosis independent of other clinicopathological parameters. A nomogram was generated for optimizing risk stratification and quantifying risk evaluation. CCP-derived signature was in relation to immune cell infiltration, HLA, and immune checkpoint expression. Combining CTRP and CMap analyses, fluvastatin was identified as a promising therapeutic agent against HCC. Furthermore, CCP-derived signature might be applied for predicting the response to doxorubicin and gemcitabine. Conclusion. Collectively, CCP-derived gene signature was a promising marker in prediction of survival outcomes and therapeutic responses for HCC patients.

Styles APA, Harvard, Vancouver, ISO, etc.

12

Lin, Tao, Tian-Tian Xie, Yi Mou et Ning-Jiu Tang. « Markov Chain Models for Menu Item Prediction ». International Journal of Technology and Human Interaction 9, n^o 4 (octobre 2013) : 75–94. http://dx.doi.org/10.4018/ijthi.2013100105.

Texte intégral

Résumé :

With the increase in the number of menu items and the menu structure complexity, users have to spend more time in locating menu items when using menu-based interfaces, which tends to result in the decrease of task performance and the increase of mental load. How to reduce the navigation time has been a great challenge in the HCI (human-computer interaction) field. Recently, adaptive menu techniques have been explored in response to the challenge, and menu item prediction plays a crucial role in the techniques. Unfortunately, there still lacks effective prediction models for menu items. This paper explores the potential of three prediction models (i.e., Absolute Distribution Markov Chain, Probability Summation Markov Chain and Weighted Markov Chain based on Genetic Algorithm) in predicting the most possible N (Top-N) menu items based on the users’ historical menu item clicks. And the results show that Weighted Markov Chain based on Genetic Algorithm can obtain the highest prediction accuracy and significantly decrease navigation time by 22.6% when N equals 4 as compared to the static counterpart.

Styles APA, Harvard, Vancouver, ISO, etc.

13

Wang, W. C. « Personalized Prediction Model for Hepatocellular Carcinoma With a Bayesian Clinical Reasoning Approach ». Journal of Global Oncology 4, Supplement 2 (1 octobre 2018) : 210s. http://dx.doi.org/10.1200/jgo.18.84600.

Texte intégral

Résumé :

Background: Predictive models for the risk of hepatocellular carcinoma (HCC) are often appropriate for average-risk population but not tailored for a personalized prediction model for individual risk of hepatocellular carcinoma (HCC), namely personalized prediction model. Aim: The objective of this study is to build up an individually tailored predictive model for HCC by using a Bayesian clinical reasoning algorithm to stratify risk groups of the underlying population. Methods: Data were derived from a community-based screening cohort consisting of 98,552 subjects between 1999 and 2007. Information on HBV and HCV infection status, liver function test, AFT, family history of liver cancer, demographic characteristics, lifestyle variables and relevant biomarkers were collected. The occurrence of HCC was ascertained by the linkage of the nationwide cancer registry till the end of 2007. Bayesian clinical reasoning model was adopted by constructing the basic model taken as the prior model for average-risk subject. We then updated the basic model by sequentially incorporating other risk factors for HCC encrypted in the likelihood ratio to form posterior probability that was used for predicting individual risk of HCC. Results: By dint of Bayesian clinical reasoning model with a step-by-step update of the risk of HCC for the sequentially obtained information, a 57-year-old man was predicted to yield 0.69% of HCC risk with the prior model. After history-taking of having hepatitis B carrier (likelihood ratio [LR]: 3.65), family history (LR: 1.43), and no alcohol drinking (LR: 0.89), the posterior risk for HCC was enhanced up to 3.13%. After further biochemical examination, the updated risk of HCC for a man [the following biomarkers [ALT = 30 IU/L (LR: 0.78), AST = 56 IU/L (LR: 8.99), platelets = (203 × /μL) (unit cube of ten) (LR: 0.55)] was increase to 11.07%. Conclusion: We proposed a individually tailored prediction model for HCC by incorporating routine information with a sequential Bayesian clinical reasoning approach.

Styles APA, Harvard, Vancouver, ISO, etc.

14

Ma, Jun, Zhiyuan Bo, Zhengxiao Zhao, Jinhuan Yang, Yan Yang, Haoqi Li, Yi Yang et al. « Machine Learning to Predict the Response to Lenvatinib Combined with Transarterial Chemoembolization for Unresectable Hepatocellular Carcinoma ». Cancers 15, n^o 3 (19 janvier 2023) : 625. http://dx.doi.org/10.3390/cancers15030625.

Texte intégral

Résumé :

Background: Lenvatinib and transarterial chemoembolization (TACE) are first-line treatments for unresectable hepatocellular carcinoma (HCC), but the objective response rate (ORR) is not satisfactory. We aimed to predict the response to lenvatinib combined with TACE before treatment for unresectable HCC using machine learning (ML) algorithms based on clinical data. Methods: Patients with unresectable HCC receiving the combination therapy of lenvatinib combined with TACE from two medical centers were retrospectively collected from January 2020 to December 2021. The response to the combination therapy was evaluated over the following 4–12 weeks. Five types of ML algorithms were applied to develop the predictive models, including classification and regression tree (CART), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM). The performance of the models was assessed by the receiver operating characteristic (ROC) curve and area under the receiver operating characteristic curve (AUC). The Shapley Additive exPlanation (SHAP) method was applied to explain the model. Results: A total of 125 unresectable HCC patients were included in the analysis after the inclusion and exclusion criteria, among which 42 (33.6%) patients showed progression disease (PD), 49 (39.2%) showed stable disease (SD), and 34 (27.2%) achieved partial response (PR). The nonresponse group (PD + SD) included 91 patients, while the response group (PR) included 34 patients. The top 40 most important features from all 64 clinical features were selected using the recursive feature elimination (RFE) algorithm to develop the predictive models. The predictive power was satisfactory, with AUCs of 0.74 to 0.91. The SVM model and RF model showed the highest accuracy (86.5%), and the RF model showed the largest AUC (0.91, 95% confidence interval (CI): 0.61–0.95). The SHAP summary plot and decision plot illustrated the impact of the top 40 features on the efficacy of the combination therapy, and the SHAP force plot successfully predicted the efficacy at the individualized level. Conclusions: A new predictive model based on clinical data was developed using ML algorithms, which showed favorable performance in predicting the response to lenvatinib combined with TACE for unresectable HCC. Combining ML with SHAP could provide an explicit explanation of the efficacy prediction.

Styles APA, Harvard, Vancouver, ISO, etc.

15

Hu, Xiaojun, Changfeng Li, Qiang Wang, Xueyun Wu, Zhiyu Chen, Feng Xia, Ping Cai, Leida Zhang, Yingfang Fan et Kuansheng Ma. « Development and External Validation of a Radiomics Model Derived from Preoperative Gadoxetic Acid-Enhanced MRI for Predicting Histopathologic Grade of Hepatocellular Carcinoma ». Diagnostics 13, n^o 3 (23 janvier 2023) : 413. http://dx.doi.org/10.3390/diagnostics13030413.

Texte intégral

Résumé :

Histopathologic grade of hepatocellular carcinoma (HCC) is an important predictor of early recurrence and poor prognosis after curative treatments. This study aims to develop a radiomics model based on preoperative gadoxetic acid-enhanced MRI for predicting HCC histopathologic grade and to validate its predictive performance in an independent external cohort. Clinical and imaging data of 403 consecutive HCC patients were retrospectively collected from two hospitals (265 and 138, respectively). Patients were categorized into poorly differentiated HCC and non-poorly differentiated HCC groups. A total of 851 radiomics features were extracted from the segmented tumor at the hepatobiliary phase images. Three classifiers, logistic regression (LR), support vector machine, and Adaboost were adopted for modeling. The areas under the curve of the three models were 0.70, 0.67, and 0.61, respectively, in the external test cohort. Alpha-fetoprotein (AFP) was the only significant clinicopathological variable associated with HCC grading (odds ratio: 2.75). When combining AFP, the LR+AFP model showed the best performance, with an AUC of 0.71 (95%CI: 0.59–0.82) in the external test cohort. A radiomics model based on gadoxetic acid-enhanced MRI was constructed in this study to discriminate HCC with different histopathologic grades. Its good performance indicates a promise in the preoperative prediction of HCC differentiation levels.

Styles APA, Harvard, Vancouver, ISO, etc.

16

Cao, Linping, Qing Wang, Jiawei Hong, Yuzhe Han, Weichen Zhang, Xun Zhong, Yongqian Che et al. « MVI-TR : A Transformer-Based Deep Learning Model with Contrast-Enhanced CT for Preoperative Prediction of Microvascular Invasion in Hepatocellular Carcinoma ». Cancers 15, n^o 5 (28 février 2023) : 1538. http://dx.doi.org/10.3390/cancers15051538.

Texte intégral

Résumé :

In this study, we considered preoperative prediction of microvascular invasion (MVI) status with deep learning (DL) models for patients with early-stage hepatocellular carcinoma (HCC) (tumor size ≤ 5 cm). Two types of DL models based only on venous phase (VP) of contrast-enhanced computed tomography (CECT) were constructed and validated. From our hospital (First Affiliated Hospital of Zhejiang University, Zhejiang, P.R. China), 559 patients, who had histopathological confirmed MVI status, participated in this study. All preoperative CECT were collected, and the patients were randomly divided into training and validation cohorts at a ratio of 4:1. We proposed a novel transformer-based end-to-end DL model, named MVI-TR, which is a supervised learning method. MVI-TR can capture features automatically from radiomics and perform MVI preoperative assessments. In addition, a popular self-supervised learning method, the contrastive learning model, and the widely used residual networks (ResNets family) were constructed for fair comparisons. With an accuracy of 99.1%, a precision of 99.3%, an area under the curve (AUC) of 0.98, a recalling rate of 98.8%, and an F1-score of 99.1% in the training cohort, MVI-TR achieved superior outcomes. Additionally, the validation cohort’s MVI status prediction had the best accuracy (97.2%), precision (97.3%), AUC (0.935), recalling rate (93.1%), and F1-score (95.2%). MVI-TR outperformed other models for predicting MVI status, and showed great preoperative predictive value for early-stage HCC patients.

Styles APA, Harvard, Vancouver, ISO, etc.

17

Demuyser, Thomas, Lucie Seyler, Rhea Buttiens, Oriane Soetens, Els Van Nedervelde, Ben Caljon, Jessy Praet et al. « Healthcare-Associated COVID-19 across Five Pandemic Waves : Prediction Models and Genomic Analyses ». Viruses 14, n^o 10 (18 octobre 2022) : 2292. http://dx.doi.org/10.3390/v14102292.

Texte intégral

Résumé :

Background: Healthcare-associated SARS-CoV-2 infections need to be explored further. Our study is an analysis of hospital-acquired infections (HAIs) and ambulatory healthcare workers (aHCWs) with SARS-CoV-2 across the pandemic in a Belgian university hospital. Methods: We compared HAIs with community-associated infections (CAIs) to identify the factors associated with having an HAI. We then performed a genomic cluster analysis of HAIs and aHCWs. We used this alongside the European Centre for Disease Control (ECDC) case source classifications of an HAI. Results: Between March 2020 and March 2022, 269 patients had an HAI. A lower BMI, a worse frailty index, lower C-reactive protein (CRP), and a higher thrombocyte count as well as death and length of stay were significantly associated with having an HAI. Using those variables to predict HAIs versus CAIs, we obtained a positive predictive value (PPV) of 83.6% and a negative predictive value (NPV) of 82.2%; the area under the ROC was 0.89. Genomic cluster analyses and representations on epicurves and minimal spanning trees delivered further insights into HAI dynamics across different pandemic waves. The genomic data were also compared with the clinical ECDC definitions for HAIs; we found that 90.0% of the ‘definite’, 87.8% of the ‘probable’, and 70.3% of the ‘indeterminate’ HAIs belonged to one of the twenty-two COVID-19 genomic clusters we identified. Conclusions: We propose a novel prediction model for HAIs. In addition, we show that the management of nosocomial outbreaks will benefit from genome sequencing analyses.

Styles APA, Harvard, Vancouver, ISO, etc.

18

Niu, Xiang-Ke, et Xiao-Feng He. « A Nomogram Based on Preoperative Lipiodol Deposition after Sequential Retreatment with Transarterial Chemoembolization to Predict Prognoses for Intermediate-Stage Hepatocellular Carcinoma ». Journal of Personalized Medicine 12, n^o 9 (25 août 2022) : 1375. http://dx.doi.org/10.3390/jpm12091375.

Texte intégral

Résumé :

(1) Background: Conventional transarterial chemoembolization (cTACE) is the mainstay treatment for patients with Barcelona Clinic Liver Cancer (BCLC) B-stage hepatocellular carcinoma (HCC). However, BCLC B-stage patients treated with cTACE represent a prognostically heterogeneous population. We aim to develop and validate a lipiodol-deposition-based nomogram for predicting the long-term survival of BCLC B-stage HCC patients after sequential cTACE. (2) Methods: In this retrospective study, 229 intermediate-stage HCC patients from two hospitals were separately allocated to a training cohort (n = 142) and a validation cohort (n = 87); these patients underwent repeated TACE (≥4 TACE sessions) between May 2010 and May 2017. Lipiodol deposition was assessed by semiautomatic volumetric measurement with multidetector computed tomography (MDCT) before cTACE and was characterized by two ordinal levels: ≤50% (low) and >50% (high). A clinical lipiodol deposition nomogram was constructed based on independent risk factors identified by univariate and multivariate Cox regression analyses, and the optimal cutoff points were obtained. Prediction models were assessed by time-dependent receiver-operating characteristic curves, calibration curves, and decision curve analysis. (3) Results: The median number of TACE sessions was five (range, 4–7) in both cohorts. Before the TACE-3 sessions, the newly constructed nomogram based on lipiodol deposition achieved desirable diagnostic performance in the training and validation cohorts with AUCs of 0.72 (95% CI, 0.69–0.74) and 0.71 (95% CI, 0.68–0.73), respectively, and demonstrated higher predictive ability compared with previously published prognostic models (all p<0.05). The prognostic nomogram obtained good clinical usefulness in predicting the patient outcomes after TACE. (4) Conclusions: Based on each pre-TACE lipiodol deposition, two sessions are recommended before abandoning cTACE or combining treatment for patients with intermediate-stage HCC. Furthermore, the nomogram based on pre-TACE-3 lipiodol deposition can be used to predict the prognoses of patients with BCLC B-stage HCC.

Styles APA, Harvard, Vancouver, ISO, etc.

19

Yang, Haoyu, Roshan Tourani, Ying Zhu, Vipin Kumar, Genevieve B. Melton, Michael Steinbach et Gyorgy Simon. « Strategies for building robust prediction models using data unavailable at prediction time ». Journal of the American Medical Informatics Association 29, n^o 1 (19 novembre 2021) : 72–79. http://dx.doi.org/10.1093/jamia/ocab229.

Texte intégral

Résumé :

Abstract Objective Hospital-acquired infections (HAIs) are associated with significant morbidity, mortality, and prolonged hospital length of stay. Risk prediction models based on pre- and intraoperative data have been proposed to assess the risk of HAIs at the end of the surgery, but the performance of these models lag behind HAI detection models based on postoperative data. Postoperative data are more predictive than pre- or interoperative data since it is closer to the outcomes in time, but it is unavailable when the risk models are applied (end of surgery). The objective is to study whether such data, which is temporally unavailable at prediction time (TUP) (and thus cannot directly enter the model), can be used to improve the performance of the risk model. Materials and Methods An extensive array of 12 methods based on logistic/linear regression and deep learning were used to incorporate the TUP data using a variety of intermediate representations of the data. Due to the hierarchical structure of different HAI outcomes, a comparison of single and multi-task learning frameworks is also presented. Results and Discussion The use of TUP data was always advantageous as baseline methods, which cannot utilize TUP data, never achieved the top performance. The relative performances of the different models vary across the different outcomes. Regarding the intermediate representation, we found that its complexity was key and that incorporating label information was helpful. Conclusions Using TUP data significantly helped predictive performance irrespective of the model complexity.

Styles APA, Harvard, Vancouver, ISO, etc.

20

Dieste-Pérez, Peña, Ricardo Savirón-Cornudella, Mauricio Tajada-Duaso, Faustino R. Pérez-López, Sergio Castán-Mateo, Gerardo Sanz et Luis Mariano Esteban. « Personalized Model to Predict Small for Gestational Age at Delivery Using Fetal Biometrics, Maternal Characteristics, and Pregnancy Biomarkers : A Retrospective Cohort Study of Births Assisted at a Spanish Hospital ». Journal of Personalized Medicine 12, n^o 5 (8 mai 2022) : 762. http://dx.doi.org/10.3390/jpm12050762.

Texte intégral

Résumé :

Small for gestational age (SGA) is defined as a newborn with a birth weight for gestational age < 10th percentile. Routine third-trimester ultrasound screening for fetal growth assessment has detection rates (DR) from 50 to 80%. For this reason, the addition of other markers is being studied, such as maternal characteristics, biochemical values, and biophysical models, in order to create personalized combinations that can increase the predictive capacity of the ultrasound. With this purpose, this retrospective cohort study of 12,912 cases aims to compare the potential value of third-trimester screening, based on estimated weight percentile (EPW), by universal ultrasound at 35–37 weeks of gestation, with a combined model integrating maternal characteristics and biochemical markers (PAPP-A and β-HCG) for the prediction of SGA newborns. We observed that DR improved from 58.9% with the EW alone to 63.5% with the predictive model. Moreover, the AUC for the multivariate model was 0.882 (0.873–0.891 95% C.I.), showing a statistically significant difference with EPW alone (AUC 0.864 (95% C.I.: 0.854–0.873)). Although the improvements were modest, contingent detection models appear to be more sensitive than third-trimester ultrasound alone at predicting SGA at delivery.

Styles APA, Harvard, Vancouver, ISO, etc.

21

Chen, Yiming, Bin Wu, Yijie Chen, Wenwen Ning et Huimin Zhang. « A Risk Model for Predicting Fetuses with Trisomy 21 Using Alpha-Fetoprotein Variants L2 Combined with Maternal Serum Biomarkers in Early Pregnancy ». Reproductive Sciences 29, n^o 4 (8 novembre 2021) : 1287–95. http://dx.doi.org/10.1007/s43032-021-00762-5.

Texte intégral

Résumé :

AbstractTo establish a risk prediction model and the clinical value of trisomy 21 using alpha-fetoprotein variants L2 (AFP-L2) combined with maternal serum biomarkers and nuchal translucency (NT) thickness in early pregnancy. A retrospective case–control study was conducted. The subjects were divided into the case group (n = 40) or the control group (n = 40). An enzyme-linked immunosorbent assay was used to measure the maternal serum AFP-L2 level in both groups. The AFP-L2 single-index or multi-index combined risk model was used to predict the efficiency of trisomy 21. The best cut-off value and area under the curve (AUC) were determined to evaluate the predictive efficacy of different risk models constructed by AFP-L2. The maternal serum AFP-L2 level in the case group was 1.59 (0.61–3.61) Multiple of medium (MoM), which was higher than 1.00 (0.39–2.12) MoM in the control group (P < 0.001). The free beta-human chorionic gonadotropin (free β-hCG) level and NT in the case group were significantly higher than those in the control group (P < 0.001). The pregnancy-associated plasma protein A (PAPP-A) level in the case group was lower than that in the control group (P < 0.001). The AUC of AFP-L2 in predicting trisomy 21 was 0.797. After considering the maternal serum AFP-L2 level, the AUC, detection rate (DR), positive predictive value (PPV), negative predictive value (NPV), falsepositive rate (FPR), false negative rate (FNR), positive likelihood ratio (+LR), and negative likelihood ratio (-LR) were significantly improved. In this study, PAPP-A + free β-hCG + NT + AFP-L2 and PAPP-A + free β-hCG + AFP-L2 increased the integrated discrimination improvement (IDI) and net classification improvement (NRI) of predicting fetuses with trisomy 21 (1.10% and 5.27%; 11.07% and 2.78%) (1.10% and 5.27%; 11.07% and 2.78%), respectively, after considering the maternal serum AFP-L2 level. The maternal serum AFP-L2 level in early pregnancy had high sensitivity and specificity, and it was a good biomarker to predict fetuses with trisomy 21.

Styles APA, Harvard, Vancouver, ISO, etc.

22

Chu, Hee Ho, Jin Hyoung Kim, Ju Hyun Shim, Dong Il Gwon, Heung-Kyu Ko, Ji Hoon Shin, Gi-Young Ko, Hyun-Ki Yoon et Nayoung Kim. « Neutrophil-to-Lymphocyte Ratio as a Biomarker Predicting Overall Survival after Chemoembolization for Intermediate-Stage Hepatocellular Carcinoma ». Cancers 13, n^o 11 (6 juin 2021) : 2830. http://dx.doi.org/10.3390/cancers13112830.

Texte intégral

Résumé :

The clinical impact of neutrophil-to-lymphocyte ratio (NLR) in predicting outcomes in hepatocellular carcinoma (HCC) patients treated with transarterial chemoembolization (TACE) remain unclear, and additional large-scale studies are required. This retrospective study evaluated outcomes in treatment-naïve patients who received TACE as first-line treatment for intermediate-stage HCC between 2008 and 2017. Patients who underwent TACE before and after 2013 were assigned to the development (n = 495) and validation (n = 436) cohorts, respectively. Multivariable Cox analysis identified six factors predictive of outcome, including NLR, which were used to create models predictive of overall survival (OS) in the development cohort. Risk scores of 0–3, 4–7, and 8–12 were defined as low, intermediate, and high risk, respectively. Median OS times in the low-, medium-, and high-risk groups in the validation cohort were 48.1, 24.3, and 9.7 months, respectively (p < 0.001). Application to the validation cohort of time-dependent ROC curves for models predictive of OS showed AUC values of 0.72 and 0.70 at 3 and 5 years, respectively. Multivariable logistic regression analysis found that NLR ≥ 3 was a significant predictor (odds ratio, 3.4; p < 0.001) of disease progression 6 months after TACE. Higher baseline NLR was predictive of poor prognosis in patients who underwent TACE for intermediate-stage HCC.

Styles APA, Harvard, Vancouver, ISO, etc.

23

Shen, Po-Chien, Wen-Yen Huang, Yang-Hong Dai, Cheng-Hsiang Lo, Jen-Fu Yang, Yu-Fu Su, Ying-Fu Wang, Chia-Feng Lu et Chun-Shu Lin. « Radiomics-Based Predictive Model of Radiation-Induced Liver Disease in Hepatocellular Carcinoma Patients Receiving Stereo-Tactic Body Radiotherapy ». Biomedicines 10, n^o 3 (3 mars 2022) : 597. http://dx.doi.org/10.3390/biomedicines10030597.

Texte intégral

Résumé :

(1) Background: The application of stereotactic body radiation therapy (SBRT) in hepatocellular carcinoma (HCC) limited the risk of the radiation-induced liver disease (RILD) and we aimed to predict the occurrence of RILD more accurately. (2) Methods: 86 HCC patients were enrolled. We identified key predictive factors from clinical, radiomic, and dose-volumetric parameters using a multivariate analysis, sequential forward selection (SFS), and a K-nearest neighbor (KNN) algorithm. We developed a predictive model for RILD based on these factors, using the random forest or logistic regression algorithms. (3) Results: Five key predictive factors in the training set were identified, including the albumin–bilirubin grade, difference average, strength, V5, and V30. After model training, the F1 score, sensitivity, specificity, and accuracy of the final random forest model were 0.857, 100, 93.3, and 94.4% in the test set, respectively. Meanwhile, the logistic regression model yielded an F1 score, sensitivity, specificity, and accuracy of 0.8, 66.7, 100, and 94.4% in the test set, respectively. (4) Conclusions: Based on clinical, radiomic, and dose-volumetric factors, our models achieved satisfactory performance on the prediction of the occurrence of SBRT-related RILD in HCC patients. Before undergoing SBRT, the proposed models may detect patients at high risk of RILD, allowing to assist in treatment strategies accordingly.

Styles APA, Harvard, Vancouver, ISO, etc.

24

He, Cheng, Jing Yang, Zheng Jin, Ying Zhu, Wei Hu, Lingfeng Zeng et Xiaocheng Li. « An ALBI- and Ascites-Based Model to Predict Survival for BCLC Stage B Hepatocellular Carcinoma ». Evidence-Based Complementary and Alternative Medicine 2022 (7 juillet 2022) : 1–12. http://dx.doi.org/10.1155/2022/1801230.

Texte intégral

Résumé :

Background. We aimed to develop a predictive model constituted with the ALBI grade, the ascites, and tumor burden related parameters in patients with BCLC stage B HCC. Methods. Patients diagnosed as the BCLC stage B HCC were collected from a retrospective database. Construction and validation of the predictive model were performed based on multivariate Cox regression analysis. Predictive accuracy, discrimination (c-index), and fitness performance (calibration curve) of the model were compared with the other eight models. The decision curve analysis (DCA) was used to evaluate the clinical utility. Results. A total of 1773 patients diagnosed as BCLC stage B HCC between 2007 and 2016 were included in the present study. The ALBI-AS grade, the AFP level, and the 8-and-14 grade were used for the development of a prognostic prediction model after multivariate analysis. The area under the receiver operator characteristic curve (AUROC) for overall survival at 1, 2, and 3 years predicted by the present model were 0.73, 0.69, and 0.67 in the training cohort. The concordance index (c-index) and the Aiken information criterion (AIC) were 0.68 and 6216.3, respectively. In the internal and external validation cohorts, the present model still revealed excellent predictive accuracy, discrimination, and fitness performance. Then the ALBI-AS based model was evaluated to be superior to other prognostic models with the highest AUROC, c-index, and lowest AIC values. Moreover, DCA also demonstrated that the present model was clinically beneficial. Conclusion. The ALBI-AS grade is a novel predictor of survival for patients with BCLC stage B HCC.

Styles APA, Harvard, Vancouver, ISO, etc.

25

Argirion, Ilona, Jalen Brown, Sarah Jackson, Ruth M. Pfeiffer, Tram Kim Lam, Thomas R. O’Brien, Kelly J. Yu et al. « Association between Immunologic Markers and Cirrhosis in Individuals from a Prospective Chronic Hepatitis C Cohort ». Cancers 14, n^o 21 (27 octobre 2022) : 5280. http://dx.doi.org/10.3390/cancers14215280.

Texte intégral

Résumé :

Background: Chronic hepatitis C virus (HCV) infection can affect immune response and inflammatory pathways, leading to severe liver diseases such as cirrhosis and hepatocellular carcinoma (HCC). Methods: In a prospective cohort of chronically HCV-infected individuals, we sampled 68 individuals who developed cirrhosis, 91 controls who did not develop cirrhosis, and 94 individuals who developed HCC. Unconditional odds ratios (ORs) from polytomous logistic regression models and canonical discriminant analyses (CDAs) were used to compare categorical (C) baseline plasma levels for 102 markers in individuals who developed cirrhosis vs. controls and those who developed HCC vs. cirrhosis. Leave-one-out cross validation was used to produce receiver operating characteristic curves to assess predictive ability of markers. Lastly, biological pathways were assessed in association with cirrhotic development compared to controls. Results: After multivariable adjustment, DEFA-1 (OR: C2v.C1 = 7.73; p < 0.0001), ITGAM (OR: C2v.C1 = 4.03; p = 0.0002), SCF (OR: C4v.C1 = 0.19; p-trend = 0.0001), and CCL11 (OR: C4v.C1 = 0.31; p-trend= 0.002) were all associated with development of cirrhosis compared to controls; these markers, together with clinical/demographics variables, improved prediction of cirrhosis from 55.7% (in clinical/demographic-only model) to 74.9% accuracy. A twelve-marker model based on CDA results further increased prediction of cirrhosis to 88.0%. While six biological pathways were found to be associated with cirrhosis, cell adhesion was the only pathway associated with cirrhosis after Bonferroni correction. In contrast to cirrhosis, DEFA-1 and ITGAM levels were inversely associated with HCC risk. Conclusions: Pending validation, these findings highlight the important role of immunological markers in predicting HCV-related cirrhosis even 11 years post-enrollment.

Styles APA, Harvard, Vancouver, ISO, etc.

26

Zheng, Xiaomin, Feng Cao, Liting Qian et Jiangning Dong. « Body Composition Changes in Hepatocellular Carcinoma : Prediction of Survival to Transcatheter Arterial Chemoembolization in Combination With Clinical Prognostic Factors ». Cancer Control 28 (janvier 2021) : 107327482110384. http://dx.doi.org/10.1177/10732748211038445.

Texte intégral

Résumé :

Treatment-related toxicities and decreased levels of patient performance during cancer therapy might contribute to body composition changes (BCC) and thereby impact outcomes. This study investigated the association between BCC during transcatheter arterial chemoembolization (TACE) and outcome in patients with hepatocellular carcinoma (HCC), and developed a nomogram for predicting survival in combination with clinical prognostic factors (CPF). Pretreatment and posttreatment computed tomography (CT) images of 75 patients with HCC who were treated between 2015 and 2018 were analyzed. The bone mineral density (BMD), cross-sectional area of paraspinal muscles (CSAmuscle), subcutaneous fat area (SFA), and visceral fat area (VFA) were measured from two sets of CT images. Count the changes in body composition during treatment and sort out the CPF of patients. Using cox regression models, CSAmuscle change, SFA change, VFA change, child-push class, and portal vein thrombosis were independent prognostic factors for overall survival (OS) (HR=5.932, 2.384, 3.140, 1.744, 1.794, respectively. P < 0.05). Receiver operating characteristic curves (ROCs) showed the prediction model combination of BCC and CPF exhibited the highest predictive performance (AUC=0.937). Independent prognostic factors were all contained into the prognostic nomogram, the concordance index (C-index) of prognostic nomogram was 0.787 (95% CI, 0.675−0.887). Decision curve analysis (DCA) demonstrated that the prognostic nomogram was clinically useful. Nomogram-based risk classification systems were also constructed to facilitate risk stratification in HCC for optimization of clinical management. In conclusion, we identified CSAmuscle change, SFA change, VFA change, Child-Pugh class, and portal vein thrombosis were independent prognostic factors for HCC. The prognostic nomogram with a combination of BCC and CPF that can be applied in the individualized prediction of survival in patients with HCC after TACE.

Styles APA, Harvard, Vancouver, ISO, etc.

27

Zheng, Jinghui, Youming Tang, Encun Hou, Guangde Bai, Zuping Lian, Peisheng Xie et Weizhi Tang. « Identification of Susceptibility Genes in Hepatic Cancer Using Whole Exome Sequencing and Risk Prediction Model Construction ». Revista Romana de Medicina de Laborator 28, n^o 1 (1 janvier 2020) : 67–74. http://dx.doi.org/10.2478/rrlm-2020-0008.

Texte intégral

Résumé :

AbstractObjective: To identify the susceptible single nucleotide polymorphisms (SNPs) loci in HCC patients in Guangxi Region, screen biomarkers from differential SNPs loci by using predictors, and establish risk prediction models for HCC, to provide a basis of screening high-risk individuals of HCC.Methods: Blood sample and clinical data of 50 normal participants and 50 hepatic cancer (HCC) patients in Rui Kang Hospital affiliated to Guangxi University of Traditional Chinese Medicine were collected. Normal participants and HCC patients were assigned to training set and testing set, respectively. Whole Exome Sequencing (WES) technique was employed to compare the exon sequence of the normal participants and HCC patients. Five predictors were used to screen the biomarkers and construct HCC prediction models. The prediction models were validated with both training and testing set.Results: Two-hundred seventy SNPs were identified to be significantly different from HCC, among which 100 SNPs were selected as biomarkers for prediction models. Five prediction models constructed with the 100 SNPs showed good sensitivity and specificity for HCC prediction among the training set and testing set.Conclusion: A series of SNPs were identified as susceptible genes for HCC. Some of these SNPs including CNN2, CD177, KMT2C, and HLADQB1 were consistent with the previously identified polymorphisms by targeted genes examination. The prediction models constructed with part of those SNPs could accurately predict HCC development.

Styles APA, Harvard, Vancouver, ISO, etc.

28

Wei, Yi, Meiyi Yang, Lifeng Xu, Minghui Liu, Feng Zhang, Tianshu Xie, Xuan Cheng et al. « Novel Computed-Tomography-Based Transformer Models for the Noninvasive Prediction of PD-1 in Pre-Operative Settings ». Cancers 15, n^o 3 (20 janvier 2023) : 658. http://dx.doi.org/10.3390/cancers15030658.

Texte intégral

Résumé :

The expression status of programmed cell death protein 1 (PD-1) in patients with hepatocellular carcinoma (HCC) is associated with the checkpoint blockade treatment responses of PD-1/PD-L1. Thus, accurately and preoperatively identifying the status of PD-1 has great clinical implications for constructing personalized treatment strategies. To investigate the preoperative predictive value of the transformer-based model for identifying the status of PD-1 expression, 93 HCC patients with 75 training cohorts (2859 images) and 18 testing cohorts (670 images) were included. We propose a transformer-based network architecture, ResTransNet, that efficiently employs convolutional neural networks (CNNs) and self-attention mechanisms to automatically acquire a persuasive feature to obtain a prediction score using a nonlinear classifier. The area under the curve, receiver operating characteristic curve, and decision curves were applied to evaluate the prediction model’s performance. Then, Kaplan–Meier survival analyses were applied to evaluate the overall survival (OS) and recurrence-free survival (RFS) in PD-1-positive and PD-1-negative patients. The proposed transformer-based model obtained an accuracy of 88.2% with a sensitivity of 88.5%, a specificity of 88.9%, and an area under the curve of 91.1% in the testing cohort.

Styles APA, Harvard, Vancouver, ISO, etc.

29

Fistouris, Johan, Christina Bergh et Annika Strandell. « Pregnancy of unknown location : external validation of the hCG-based M6NP and M4 prediction models in an emergency gynaecology unit ». BMJ Open 12, n^o 11 (novembre 2022) : e058454. http://dx.doi.org/10.1136/bmjopen-2021-058454.

Texte intégral

Résumé :

ObjectiveTo investigate if M6NP predicting ectopic pregnancy (EP) among women with pregnancy of unknown location (PUL) is valid in an emergency gynaecology setting and comparing it with its predecessor M4.DesignRetrospective cohort study.SettingUniversity Hospital.ParticipantsWomen with PUL.MethodsAll consecutive women with a PUL during a study period of 3 years were screened for inclusion. Risk prediction of an EP was based on two serum human chorionic gonadotropin (hCG) levels taken at least 24 hours and no longer than 72 hours apart.Main outcome measuresThe area under the ROC curve (AUC) expressed the ability of a model to distinguish an EP from a non-EP (discrimination). Calibration assessed the agreement between the predicted risk of an EP and the true risk (proportion) of EP. The proportion of EPs and non-EPs classified as high risk assessed the model’s sensitivity and false positive rate (FPR). The proportion of non-EPs among women classified as low risk was the model’s negative predictive value (NPV). The clinical utility of a model was evaluated with decision curve analysis.Results1061 women were included in the study, of which 238 (22%) had a final diagnosis of EP. The AUC for EP was 0.85 for M6NP and 0.81 for M4. M6NP made accurate risk predictions of EP up to predictions of 20% but thereafter risks were underestimated. M4 was poorly calibrated up to risk predictions of 40%. With a 5% threshold for high risk classification the sensitivity for EP was 95% for M6NP, the FPR 50% and NPV 97%. M6NP had higher sensitivity and NPV than M4 but also a higher FPR. M6NP had utility at all thresholds as opposed to M4 that had no utility at thresholds≤5%.ConclusionsM6NP had better predictive performance than M4 and is valid in women with PUL attending an emergency gynaecology unit. Our results can encourage implementation of M6NP in related yet untested clinical settings to effectively support clinical decision-making.

Styles APA, Harvard, Vancouver, ISO, etc.

30

Lee, Ji Hun, Seung Kak Shin, Seong Hee Kang, Tae Hyung Kim, Hyung Joon Yim, Sun Young Yim, Young-Sun Lee et al. « Long-Term Prediction Model for Hepatocellular Carcinoma in Patients with Chronic Hepatitis B Receiving Antiviral Therapy : Based on Data from Korean Patients ». Journal of Clinical Medicine 11, n^o 22 (8 novembre 2022) : 6613. http://dx.doi.org/10.3390/jcm11226613.

Texte intégral

Résumé :

Predicting the development of hepatocellular carcinoma (HCC) is a key clinical issue in patients with chronic hepatitis B (CHB). The aim of this study was to develop a precise and simple HCC risk score for up to 10 years. A total of 1895 CHB patients treated with entecavir or tenofovir disoproxil fumarate were retrospectively recruited and randomized into derivation (n = 1239) and validation cohorts (n = 656). Variables proven to be independent risk factors for HCC in the derivation cohort were used to develop the prediction model. The ACCESS-HCC model included five variables (age, cirrhosis, consumption of ethanol, liver stiffness, and serum alanine aminotransferase). Areas under curves were 0.798, 0.762, and 0.883 for HCC risk at 3, 5, and 10 years, respectively, which were higher than those of other prediction models. The scores were categorized according to significantly different HCC incidences: 0–4, low; 5–8, intermediate; and 9–14, high-risk. The annual incidence rates were 0.5%, 3.2%, and 11.3%, respectively. The performance of this model was validated in an independent cohort. The ACCESS-HCC model shows improved long-term prediction and provides three distinct risk categories for HCC in CHB patients receiving antiviral therapy. Further research is needed for external validation using larger cohorts.

Styles APA, Harvard, Vancouver, ISO, etc.

31

Brancato, Valentina, Nunzia Garbino, Marco Salvatore et Carlo Cavaliere. « MRI-Based Radiomic Features Help Identify Lesions and Predict Histopathological Grade of Hepatocellular Carcinoma ». Diagnostics 12, n^o 5 (26 avril 2022) : 1085. http://dx.doi.org/10.3390/diagnostics12051085.

Texte intégral

Résumé :

Hepatocellular carcinoma (HCC) is the most common form of liver cancer. Radiomics is a promising tool that may increase the value of magnetic resonance imaging (MRI) in the management of HCC. The purpose of our study is to develop an MRI-based radiomics approach to preoperatively detect HCC and predict its histological grade. Thirty-eight HCC patients at staging who underwent axial T2-weighted and dynamic contrast-enhanced MRI (DCE-MRI) were considered. Three-dimensional volumes of interest (VOIs) were manually placed on HCC lesions and normal hepatic tissue (HT) on arterial phase post-contrast images. Radiomic features from T2 images and arterial, portal and tardive post-contrast images from DCE-MRI were extracted by using Pyradiomics. Feature selection was performed using correlation filter, Wilcoxon-rank sum test and mutual information. Predictive models were constructed for HCC differentiation with respect to HT and HCC histopathologic grading used at each step an imbalance-adjusted bootstrap resampling (IABR) on 1000 samples. Promising results were obtained from radiomic prediction models, with best AUCs ranging from 71% to 96%. Radiomics MRI based on T2 and DCE-MRI revealed promising results concerning both HCC detection and grading. It may be a suitable tool for personalized treatment of HCC patients and could also be used to develop new prognostic biomarkers useful for HCC assessment without the need for invasive procedures.

Styles APA, Harvard, Vancouver, ISO, etc.

32

Brancato, Valentina, Nunzia Garbino, Marco Salvatore et Carlo Cavaliere. « MRI-Based Radiomic Features Help Identify Lesions and Predict Histopathological Grade of Hepatocellular Carcinoma ». Diagnostics 12, n^o 5 (26 avril 2022) : 1085. http://dx.doi.org/10.3390/diagnostics12051085.

Texte intégral

Résumé :

Hepatocellular carcinoma (HCC) is the most common form of liver cancer. Radiomics is a promising tool that may increase the value of magnetic resonance imaging (MRI) in the management of HCC. The purpose of our study is to develop an MRI-based radiomics approach to preoperatively detect HCC and predict its histological grade. Thirty-eight HCC patients at staging who underwent axial T2-weighted and dynamic contrast-enhanced MRI (DCE-MRI) were considered. Three-dimensional volumes of interest (VOIs) were manually placed on HCC lesions and normal hepatic tissue (HT) on arterial phase post-contrast images. Radiomic features from T2 images and arterial, portal and tardive post-contrast images from DCE-MRI were extracted by using Pyradiomics. Feature selection was performed using correlation filter, Wilcoxon-rank sum test and mutual information. Predictive models were constructed for HCC differentiation with respect to HT and HCC histopathologic grading used at each step an imbalance-adjusted bootstrap resampling (IABR) on 1000 samples. Promising results were obtained from radiomic prediction models, with best AUCs ranging from 71% to 96%. Radiomics MRI based on T2 and DCE-MRI revealed promising results concerning both HCC detection and grading. It may be a suitable tool for personalized treatment of HCC patients and could also be used to develop new prognostic biomarkers useful for HCC assessment without the need for invasive procedures.

Styles APA, Harvard, Vancouver, ISO, etc.

33

Lee, Jae Seung, Hyun Woong Lee, Tae Seop Lim, In Kyung Min, Hye Won Lee, Seung Up Kim, Jun Yong Park, Do Young Kim, Sang Hoon Ahn et Beom Kyung Kim. « External Validation of the FSAC Model Using On-Therapy Changes in Noninvasive Fibrosis Markers in Patients with Chronic Hepatitis B : A Multicenter Study ». Cancers 14, n^o 3 (29 janvier 2022) : 711. http://dx.doi.org/10.3390/cancers14030711.

Texte intégral

Résumé :

Antiviral therapy (AVT) induces the regression of non-invasive fibrosis markers (NFMs) and reduces hepatocellular carcinoma (HCC) risk among chronic hepatitis B (CHB) patients. We externally validated the predictive performance of the FSAC prediction model for HCC using on-therapy NFM responses. Our multicenter study consecutively recruited treatment-naïve CHB patients (n = 3026; median age, 50.0 years; male predominant (61.3%); cirrhosis in 1391 (46.0%) patients) receiving potent AVTs for >18 months between 2007 and 2018. During follow-up (median 64.0 months), HCC developed in 303 (10.0%) patients. Patients with low FIB-4 or APRI levels at 12 months showed significantly lower HCC risk than those with high NFM levels at 12 months (all p < 0.05). Cumulative 3-, 5-, and 8-year HCC probabilities were 0.0%, 0.3% and 1.2% in the low-risk group (FSAC ≤ 2); 2.1%, 5.2%, and 11.1% in the intermediate-risk group (FSAC 3−8); and 5.2%, 15.5%, and 29.8% in the high-risk group (FSAC ≥ 9) (both p < 0.001 between each adjacent pair). Harrell’s c-index value for FSAC score (0.770) was higher than those for PAGE-B (0.725), modified PAGE-B (0.738), modified REACH-B (0.737), LSM-HCC (0.734), and CAMD (0.742). Our study showed that the FSAC model, which incorporates on-therapy changes in NFMs, had better predictive performance than other models using only baseline parameters.

Styles APA, Harvard, Vancouver, ISO, etc.

34

Teixeira, Cláudia, Eduardo Tejera, Helena Martins, António Tomé Pereira, Altamiro Costa-Pereira et Irene Rebelo. « First Trimester Aneuploidy Screening Program for Preeclampsia Prediction in a Portuguese Obstetric Population ». Obstetrics and Gynecology International 2014 (2014) : 1–7. http://dx.doi.org/10.1155/2014/435037.

Texte intégral

Résumé :

Objective. To evaluate the performance of a first trimester aneuploidy screening program for preeclampsia (PE) prediction in a Portuguese obstetric population, when performed under routine clinical conditions.Materials and Methods. Retrospective cohort study of 5672 pregnant women who underwent routine first trimester aneuploidy screening in a Portuguese university hospital from January 2009 to June 2013. Logistic regression-based predictive models were developed for prediction of PE based on maternal characteristics, crown-rump length (CRL), nuchal translucency thickness (NT), and maternal serum levels of pregnancy-associated plasma protein-A (PAPP-A) and free beta-subunit of human chorionic gonadotropin (freeβ-hCG).Results. At a false-positive rate of 5/10%, the detection rate for early-onset (EO-PE) and late-onset (LO-PE) PE was 31.4/45.7% and 29.5/35.2%, respectively. Although both forms of PE were associated with decreased PAPP-A, logistic regression analysis revealed significant contributions from maternal factors, freeβ-hCG, CRL, and NT, but not PAPP-A, for prediction of PE.Conclusion. Our findings support that both clinical forms of EO-PE and LO-PE can be predicted using a combination of maternal history and biomarkers assessed at first trimester aneuploidy screening. However, detection rates were modest, suggesting that models need to be improved with additional markers not included in the current aneuploidy screening programs.

Styles APA, Harvard, Vancouver, ISO, etc.

35

Tao, Yun-Yun, Yue Shi, Xue-Qin Gong, Li Li, Zu-Mao Li, Lin Yang et Xiao-Ming Zhang. « Radiomic Analysis Based on Magnetic Resonance Imaging for Predicting PD-L2 Expression in Hepatocellular Carcinoma ». Cancers 15, n^o 2 (5 janvier 2023) : 365. http://dx.doi.org/10.3390/cancers15020365.

Texte intégral

Résumé :

Hepatocellular carcinoma (HCC) is the sixth most common malignant tumour and the third leading cause of cancer death in the world. The emerging field of radiomics involves extracting many clinical image features that cannot be recognized by the human eye to provide information for precise treatment decision making. Radiomics has shown its importance in HCC identification, histological grading, microvascular invasion (MVI) status, treatment response, and prognosis, but there is no report on the preoperative prediction of programmed death ligand-2 (PD-L2) expression in HCC. The purpose of this study was to investigate the value of MRI radiomic features for the non-invasive prediction of immunotherapy target PD-L2 expression in hepatocellular carcinoma (HCC). A total of 108 patients with HCC confirmed by pathology were retrospectively analysed. Immunohistochemical analysis was used to evaluate the expression level of PD-L2. 3D-Slicer software was used to manually delineate volumes of interest (VOIs) and extract radiomic features on preoperative T2-weighted, arterial-phase, and portal venous-phase MR images. Least absolute shrinkage and selection operator (LASSO) was performed to find the best radiomic features. Multivariable logistic regression models were constructed and validated using fivefold cross-validation. The area under the receiver characteristic curve (AUC) was used to evaluate the predictive performance of each model. The results show that among the 108 cases of HCC, 50 cases had high PD-L2 expression, and 58 cases had low PD-L2 expression. Radiomic features correlated with PD-L2 expression. The T2-weighted, arterial-phase, and portal venous-phase and combined MRI radiomics models showed AUCs of 0.789 (95% CI: 0.702–0.875), 0.727 (95% CI: 0.632–0.823), 0.770 (95% CI: 0.682–0.875), and 0.871 (95% CI: 0.803–0.939), respectively. The combined model showed the best performance. The results of this study suggest that prediction based on the radiomic characteristics of MRI could noninvasively predict the expression of PD-L2 in HCC before surgery and provide a reference for the selection of immune checkpoint blockade therapy.

Styles APA, Harvard, Vancouver, ISO, etc.

36

Wang, Yikai, Le Ma, Pengjun Xue, Bianni Qin, Ting Wang, Bo Li, Lina Wu, Liyan Zhao et Xiongtao Liu. « Construction and Analysis of Hepatocellular Carcinoma Prognostic Model Based on Random Forest ». Canadian Journal of Gastroenterology and Hepatology 2023 (12 janvier 2023) : 1–20. http://dx.doi.org/10.1155/2023/6707698.

Texte intégral

Résumé :

Introduction and Aims. Hepatocellular carcinoma (HCC) is one of the most lethal tumors of the digestive system, but its mechanisms remain unclear. The purpose of this study was to study HCC-related genes, build a survival prognosis prediction model, and provide references for treatment and mechanism research. Methods. Transcriptome data and clinical data of HCC were downloaded from the TCGA database. Screen important genes based on the random forest method, combined with differential expression genes (DEGs) to screen out important DEGs. The Kaplan‒Meier curve was used to evaluate its prognostic significance. Cox regression analysis was used to construct a survival prognosis prediction model, and the ROC curve was used to verify it. Finally, the mechanism of action was explored through GO and KEGG pathway enrichment and GeneMANIA coexpression analyses. Results. Seven important DEGs were identified, three were highly expressed and four were lowly expressed. Among them, GPRIN1, MYBL2, and GSTM5 were closely related to prognosis ( P < 0.05 ). After the survival prognosis prediction model was established, the survival analysis showed that the survival time of the high-risk group was significantly shortened ( P < 0.001 ), but the ROC analysis indicated that the model was not superior to staging. Twenty coexpressed genes were screened, and enrichment analysis indicated that glutathione metabolism was an important mechanism for these genes to regulate HCC progression. Conclusion. This study revealed the important DEGs affecting HCC progression and provided references for clinical assessment of patient prognosis and exploration of HCC progression mechanisms through the construction of predictive models and gene enrichment analysis.

Styles APA, Harvard, Vancouver, ISO, etc.

37

Lee, Jae Seung, Hyun Woong Lee, Tae Seop Lim, Hye Jung Shin, Hye Won Lee, Seung Up Kim, Jun Yong Park, Do Young Kim, Sang Hoon Ahn et Beom Kyung Kim. « Novel Liver Stiffness-Based Nomogram for Predicting Hepatocellular Carcinoma Risk in Patients with Chronic Hepatitis B Virus Infection Initiating Antiviral Therapy ». Cancers 13, n^o 23 (23 novembre 2021) : 5892. http://dx.doi.org/10.3390/cancers13235892.

Texte intégral

Résumé :

Hepatocellular carcinoma (HCC) risk prediction is important to developing individualized surveillance approaches. We designed a novel HCC prediction model using liver stiffness on transient elastography for patients receiving antiviral therapy against hepatitis B virus (HBV) infection. We recruited 2037 patients receiving entecavir or tenofovir as first-line antivirals and used the Cox regression analysis to determine key variables for model construction. Within 58.1 months (median), HCC developed in 182 (8.9%) patients. Patients with HCC showed a higher prevalence of cirrhosis (90.7% vs. 45.9%) and higher liver stiffness values (median 13.9 vs. 7.2 kPa) than those without. A novel nomogram (score 0–304) was established using age, platelet count, cirrhosis development, and liver stiffness values, which were independently associated with increased HCC risk, along with hepatitis B e antigen positivity and serum albumin and total bilirubin levels. Cumulative HCC probabilities were 0.7%, 5.0%, and 22.7% in the low- (score ≤87), intermediate- (88–222), and high-risk (≥223) groups, respectively. The c-index value was 0.799 (internal validity: 0.805), higher than that of the PAGE-B (0.726), modified PAGE-B (0.756), and modified REACH-B (0.761) models (all p < 0.05). Our nomogram showed acceptable performance in predicting HCC in Asian HBV-infected patients receiving potent antiviral therapy.

Styles APA, Harvard, Vancouver, ISO, etc.

38

Chiu, Herng-Chia, Te-Wei Ho, King-Teh Lee, Hong-Yaw Chen et Wen-Hsien Ho. « Mortality Predicted Accuracy for Hepatocellular Carcinoma Patients with Hepatic Resection Using Artificial Neural Network ». Scientific World Journal 2013 (2013) : 1–10. http://dx.doi.org/10.1155/2013/201976.

Texte intégral

Résumé :

The aim of this present study is firstly to compare significant predictors of mortality for hepatocellular carcinoma (HCC) patients undergoing resection between artificial neural network (ANN) and logistic regression (LR) models and secondly to evaluate the predictive accuracy of ANN and LR in different survival year estimation models. We constructed a prognostic model for 434 patients with 21 potential input variables by Cox regression model. Model performance was measured by numbers of significant predictors and predictive accuracy. The results indicated that ANN had double to triple numbers of significant predictors at 1-, 3-, and 5-year survival models as compared with LR models. Scores of accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) of 1-, 3-, and 5-year survival estimation models using ANN were superior to those of LR in all the training sets and most of the validation sets. The study demonstrated that ANN not only had a great number of predictors of mortality variables but also provided accurate prediction, as compared with conventional methods. It is suggested that physicians consider using data mining methods as supplemental tools for clinical decision-making and prognostic evaluation.

Styles APA, Harvard, Vancouver, ISO, etc.

39

Rosen, M. A., A. Ruutiainen, E. Siegelman, L. Jones, W. Sun, R. Reddy, A. Shaked, K. Olthoff et M. Soulen. « Response assessment of HCC undergoing chemoembolization by necrosis-adjusted models ». Journal of Clinical Oncology 27, n^o 15_suppl (20 mai 2009) : e15528-e15528. http://dx.doi.org/10.1200/jco.2009.27.15_suppl.e15528.

Texte intégral

Résumé :

e15528 Background: Chemoembolization (CE) is an accepted therapy for unresectable HCC. As treated tumors may not shrink in size, response assessment via measurement of the enhancing tumor (EASL) has been proposed as an alternate to whole tumor (RECIST) measures. However, the reliability of this model has not been tested in clinical practice. Methods: We identified 29 HCC patients treated with CE with known overall survival (OS) in whom MRI before and after initial CE therapy was available for review. Three radiologists evaluated the imaging, measuring the largest liver lesion in three dimensions and the largest enhancing region in two dimensions. Readers also assessed percent tumor necrosis and overall tumor response qualitatively. Response models in 1-, 2-, or 3- dimensions, with or without necrosis adjustment, were created to assign patients to CR/PR/SD/PD classes, based on majority classification. Predictive value for OS was assessed for PD vs. other, and for PR/CR vs. SD/PD by the Students’ t-test. Inter-reader concordance was assessed by the Fleiss κ statistic. Results: For non-necrosis adjusted models, OS for progressors vs. non-progressors was statistically significant (p values: 0.0002–0.04), but could not identify early responders. Necrosis adjusted models failed to identify early progressors, but identified responders with improved OS (p values: 0.02–0.12). Inter-reader concordance was higher for necrosis adjusted models (κ range: 0.36–0.52) than for non-necrosis adjusted models (0.16–0.23). Viable tumor response by a two-dimensional product was superior to a one-dimensional diameter for predicting OS (p=0.04 vs. 0.74), and demonstrated higher inter-reader concordance (κ=0.46 vs. 0.30). Qualitative assessment of hepatic tumor could predict differences in OS for both PD vs. others (p=0.0001) and responders vs. non-responders (p=0.04), with acceptable inter-reader concordance (κ=0.34). Conclusions: Two- dimensional, but not one-dimensional, viable tumor measurement can identify response of HCC to chemoembolization and predict OS. Models which incorporate qualitative reader assessment of tumor necrosis may be more flexible than direct measures of viable tumor, and should be considered as alternatives for tumor assessment in chemoembolization. No significant financial relationships to disclose.

Styles APA, Harvard, Vancouver, ISO, etc.

40

Guan, Shenheng, Michael F. Moran et Bin Ma. « Prediction of LC-MS/MS Properties of Peptides from Sequence by Deep Learning ». Molecular & ; Cellular Proteomics 18, n^o 10 (27 juin 2019) : 2099–107. http://dx.doi.org/10.1074/mcp.tir119.001412.

Texte intégral

Résumé :

Deep learning models for prediction of three key LC-MS/MS properties from peptide sequences were developed. The LC-MS/MS properties or behaviors are indexed retention times (iRT), MS1 or survey scan charge state distributions, and sequence ion intensities of HCD spectra. A common core deep supervised learning architecture, bidirectional long-short term memory (LSTM) recurrent neural networks was used to construct the three prediction models. Two featurization schemes were proposed and demonstrated to allow for efficient encoding of modifications. The iRT and charge state distribution models were trained with on order of 105 data points each. An HCD sequence ion prediction model was trained with 2 × 106 experimental spectra. The iRT prediction model and HCD sequence ion prediction model provide improved accuracies over the start-of-the-art models available in literature. The MS1 charge state distribution prediction model offers excellent performance. The prediction models can be used to enhance peptide identification and quantification in data-dependent acquisition and data-independent acquisition (DIA) experiments as well as to assist MRM (multiple reaction monitoring) and PRM (parallel reaction monitoring) experiment design.

Styles APA, Harvard, Vancouver, ISO, etc.

41

Lai, Yung-Chi, Kuo-Chen Wu, Chao-Jen Chang, Yi-Jin Chen, Kuan-Pin Wang, Long-Bin Jeng et Chia-Hung Kao. « Predicting Overall Survival with Deep Learning from 18F-FDG PET-CT Images in Patients with Hepatocellular Carcinoma before Liver Transplantation ». Diagnostics 13, n^o 5 (4 mars 2023) : 981. http://dx.doi.org/10.3390/diagnostics13050981.

Texte intégral

Résumé :

Positron emission tomography and computed tomography with 18F-fluorodeoxyglucose (18F-FDG PET-CT) were used to predict outcomes after liver transplantation in patients with hepatocellular carcinoma (HCC). However, few approaches for prediction based on 18F-FDG PET-CT images that leverage automatic liver segmentation and deep learning were proposed. This study evaluated the performance of deep learning from 18F-FDG PET-CT images to predict overall survival in HCC patients before liver transplantation (LT). We retrospectively included 304 patients with HCC who underwent 18F-FDG PET/CT before LT between January 2010 and December 2016. The hepatic areas of 273 of the patients were segmented by software, while the other 31 were delineated manually. We analyzed the predictive value of the deep learning model from both FDG PET/CT images and CT images alone. The results of the developed prognostic model were obtained by combining FDG PET-CT images and combining FDG CT images (0.807 AUC vs. 0.743 AUC). The model based on FDG PET-CT images achieved somewhat better sensitivity than the model based on CT images alone (0.571 SEN vs. 0.432 SEN). Automatic liver segmentation from 18F-FDG PET-CT images is feasible and can be utilized to train deep-learning models. The proposed predictive tool can effectively determine prognosis (i.e., overall survival) and, thereby, select an optimal candidate of LT for patients with HCC.

Styles APA, Harvard, Vancouver, ISO, etc.

42

Naucler, Pontus, Suzanne D. van der Werff, John Valik, Logan Ward, Anders Ternhag, Hideyuki Tanushi, Aikaterini Mougkou et al. « HAI-Proactive : Development of an Automated Surveillance System for Healthcare-Associated Infections in Sweden ». Infection Control & ; Hospital Epidemiology 41, S1 (octobre 2020) : s39. http://dx.doi.org/10.1017/ice.2020.519.

Texte intégral

Résumé :

Background: Healthcare-associated infection (HAI) surveillance is essential for most infection prevention programs and continuous epidemiological data can be used to inform healthcare personal, allocate resources, and evaluate interventions to prevent HAIs. Many HAI surveillance systems today are based on time-consuming and resource-intensive manual reviews of patient records. The objective of HAI-proactive, a Swedish triple-helix innovation project, is to develop and implement a fully automated HAI surveillance system based on electronic health record data. Furthermore, the project aims to develop machine-learning–based screening algorithms for early prediction of HAI at the individual patient level. Methods: The project is performed with support from Sweden’s Innovation Agency in collaboration among academic, health, and industry partners. Development of rule-based and machine-learning algorithms is performed within a research database, which consists of all electronic health record data from patients admitted to the Karolinska University Hospital. Natural language processing is used for processing free-text medical notes. To validate algorithm performance, manual annotation was performed based on international HAI definitions from the European Center for Disease Prevention and Control, Centers for Disease Control and Prevention, and Sepsis-3 criteria. Currently, the project is building a platform for real-time data access to implement the algorithms within Region Stockholm. Results: The project has developed a rule-based surveillance algorithm for sepsis that continuously monitors patients admitted to the hospital, with a sensitivity of 0.89 (95% CI, 0.85–0.93), a specificity of 0.99 (0.98–0.99), a positive predictive value of 0.88 (0.83–0.93), and a negative predictive value of 0.99 (0.98–0.99). The healthcare-associated urinary tract infection surveillance algorithm, which is based on free-text analysis and negations to define symptoms, had a sensitivity of 0.73 (0.66–0.80) and a positive predictive value of 0.68 (0.61–0.75). The sensitivity and positive predictive value of an algorithm based on significant bacterial growth in urine culture only was 0.99 (0.97–1.00) and 0.39 (0.34–0.44), respectively. The surveillance system detected differences in incidences between hospital wards and over time. Development of surveillance algorithms for pneumonia, catheter-related infections and Clostridioides difficile infections, as well as machine-learning–based models for early prediction, is ongoing. We intend to present results from all algorithms. Conclusions: With access to electronic health record data, we have shown that it is feasible to develop a fully automated HAI surveillance system based on algorithms using both structured data and free text for the main healthcare-associated infections.Funding: Sweden’s Innovation Agency and Stockholm County CouncilDisclosures: None

Styles APA, Harvard, Vancouver, ISO, etc.

43

Castaldo, Anna, Davide Raffaele De Lucia, Giuseppe Pontillo, Marco Gatti, Sirio Cocozza, Lorenzo Ugga et Renato Cuocolo. « State of the Art in Artificial Intelligence and Radiomics in Hepatocellular Carcinoma ». Diagnostics 11, n^o 7 (30 juin 2021) : 1194. http://dx.doi.org/10.3390/diagnostics11071194.

Texte intégral

Résumé :

The most common liver malignancy is hepatocellular carcinoma (HCC), which is also associated with high mortality. Often HCC develops in a chronic liver disease setting, and early diagnosis as well as accurate screening of high-risk patients is crucial for appropriate and effective management of these patients. While imaging characteristics of HCC are well-defined in the diagnostic phase, challenging cases still occur, and current prognostic and predictive models are limited in their accuracy. Radiomics and machine learning (ML) offer new tools to address these issues and may lead to scientific breakthroughs with the potential to impact clinical practice and improve patient outcomes. In this review, we will present an overview of these technologies in the setting of HCC imaging across different modalities and a range of applications. These include lesion segmentation, diagnosis, prognostic modeling and prediction of treatment response. Finally, limitations preventing clinical application of radiomics and ML at the present time are discussed, together with necessary future developments to bring the field forward and outside of a purely academic endeavor.

Styles APA, Harvard, Vancouver, ISO, etc.

44

Lok, James, et Kosh Agarwal. « Screening for Hepatocellular Carcinoma in Chronic Hepatitis B : An Update ». Viruses 13, n^o 7 (10 juillet 2021) : 1333. http://dx.doi.org/10.3390/v13071333.

Texte intégral

Résumé :

(1) Background: Hepatocellular carcinoma (HCC) is an important cause of mortality in individuals with chronic hepatitis B infection, with screening of high-risk groups recommended in all major international guidelines. Our understanding of the risk factors involved has improved over time, encouraging researchers to develop models that predict future risk of HCC development. (2) Methods: A literature search of the PubMed database was carried out to identify studies that derive or validate models predicting HCC development in patients with chronic hepatitis B. Subsequently, a second literature search was carried out to explore the potential role of novel viral biomarkers in this field. (3) Results: To date, a total of 23 models have been developed predicting future HCC risk, of which 12 have been derived from cohorts of treatment-naïve individuals. Most models have been developed in Asian populations (n = 20), with a smaller number in Caucasian cohorts (n = 3). All of the models demonstrate satisfactory performance in their original derivation cohorts, but many lack external validation. In recent studies, novel viral biomarkers have demonstrated utility in predicting HCC risk in patients with chronic hepatitis B, amongst both treated and treatment-naïve patients. (4) Conclusion: Several models have been developed to predict the risk of HCC development in individuals with chronic hepatitis B infection, but many have not been externally validated outside of the Asian population. Further research is needed to refine these models and facilitate a more tailored HCC surveillance programme in the future.

Styles APA, Harvard, Vancouver, ISO, etc.

45

Mirza-Aghazadeh-Attari, Mohammad, Bharath Ambale Venkatesh, Mounes Aliyari Ghasabeh, Alireza Mohseni, Seyedeh Panid Madani, Ali Borhani, Haneyeh Shahbazian, Golnoosh Ansari et Ihab R. Kamel. « The Additive Value of Radiomics Features Extracted from Baseline MR Images to the Barcelona Clinic Liver Cancer (BCLC) Staging System in Predicting Transplant-Free Survival in Patients with Hepatocellular Carcinoma : A Single-Center Retrospective Analysis ». Diagnostics 13, n^o 3 (2 février 2023) : 552. http://dx.doi.org/10.3390/diagnostics13030552.

Texte intégral

Résumé :

Background: To study the additive value of radiomics features to the BCLC staging system in clustering HCC patients. Methods: A total of 266 patients with HCC were included in this retrospective study. All patients had undergone baseline MR imaging, and 95 radiomics features were extracted from 3D segmentations representative of lesions on the venous phase and apparent diffusion coefficient maps. A random forest algorithm was utilized to extract the most relevant features to transplant-free survival. The selected features were used alongside BCLC staging to construct Kaplan–Meier curves. Results: Out of 95 extracted features, the three most relevant features were incorporated into random forest classifiers. The Integrated Brier score of the prediction error curve was 0.135, 0.072, and 0.048 for the BCLC, radiomics, and combined models, respectively. The mean area under the receiver operating curve (ROC curve) over time for the three models was 81.1%, 77.3%, and 56.2% for the combined radiomics and BCLC models, respectively. Conclusions: Radiomics features outperformed the BCLC staging system in determining prognosis in HCC patients. The addition of a radiomics classifier increased the classification capability of the BCLC model. Texture analysis features could be considered as possible biomarkers in predicting transplant-free survival in HCC patients.

Styles APA, Harvard, Vancouver, ISO, etc.

46

Morsica, Giulia, Laura Galli, Emanuela Messina, Alessandro Cibarelli, Sabrina Bagaglio, Andrea Poli, Martina Ranzenigo, Antonella Castagna, Hamid Hasson et Caterina Uberti-Foppa. « Levels of Alpha-Fetoprotein and Association with Mortality in Hepatocellular Carcinoma of HIV-1-Infected Patients ». Journal of Oncology 2022 (10 février 2022) : 1–10. http://dx.doi.org/10.1155/2022/3586064.

Texte intégral

Résumé :

Background and Aim. The clinical course of hepatocellular carcinoma (HCC) is determined by cancer-related and nonrelated factors. We evaluated the effect of a cancer-related factor, alpha-fetoprotein (AFP) levels, on mortality in HIV-1-infected patients with HCC. Methods. This is a retrospective cohort study on patients living with HIV-1 infection (PLWH) followed at the Division of Infectious Diseases of the San Raffaele Hospital, with cirrhosis and HCC diagnosed between 1999 and 2018 and with an available AFP value at HCC diagnosis. The area under the receiver operating characteristic curve (AUC) was used to estimate the accuracy of baseline AFP in predicting death. Factors associated with the risk of death were identified using multivariable Cox proportional-hazards regression models. Results. Overall, 53 PLWH were evaluated: 18 patients received a curative treatment (9 liver transplantation, 5 liver resections and 4 radiofrequency ablation) and 35 a noncurative treatment (17 chemo or radio embolization, 10 sorafenib and 8 best supportive care). Baseline AFP was predictive of death [AUC 0.71, 95% confidence interval (CI) 0.54–0.83], and the optimal cut-off was 28.8 ng/mL. At multivariable analysis, BL AFP ≥28.8 ng/mL was associated with death [adjusted hazard ratio (aHR) 7.05, 95% CI 1.94–25.71 P = 0.003]. Other factors were HBV infection (aHR 8.57, 95% CI 1.47–50.08, P = 0.017) and treatment allocation (curative vs. noncurative, aHR 0.08, 95% CI 0.02–0.40, P = 0.0004). Conclusions. Our findings suggest that in PLWH AFP serum levels ≥28.8 ng/mL, HBV coinfection and treatment allocation represent predictive markers for death at the time of HCC diagnosis.

Styles APA, Harvard, Vancouver, ISO, etc.

47

Klar, Markus, Florian Fischer, Arthur Fleig, Miroslav Bachinski et Jörg Müller. « Simulating Interaction Movements via Model Predictive Control ». ACM Transactions on Computer-Human Interaction, 20 décembre 2022. http://dx.doi.org/10.1145/3577016.

Texte intégral

Résumé :

We present a Model Predictive Control (MPC) framework to simulate movement in interaction with computers, focusing on mid-air pointing as an example. Starting from understanding interaction from an Optimal Feedback Control (OFC) perspective, we assume that users aim to minimize an internalized cost function, subject to the constraints imposed by the human body and the interactive system. Unlike previous approaches used in HCI, MPC can compute optimal controls for nonlinear systems. This allows to use state-of-the-art biomechanical models and handle nonlinearities that occur in almost any interactive system. Instead of torque actuation, our model employs second-order muscles acting directly at the joints. We compare three different cost functions and evaluate the simulation against user movements in a pointing study. Our results show that the combination of distance, control, and joint acceleration cost matches individual users’ movements best, and predicts movements with an accuracy that is within the between-user variance. To aid HCI researchers and designers applying our approach for different users, interaction techniques, or tasks, we make our SimMPC framework, including CFAT, a tool to identify maximum voluntary torques in joint-actuated models, publicly available, and give step-by-step instructions.

Styles APA, Harvard, Vancouver, ISO, etc.

48

Palano, Giorgia, Ariana Foinquinos et Erik Müllers. « In vitro Assays and Imaging Methods for Drug Discovery for Cardiac Fibrosis ». Frontiers in Physiology 12 (8 juillet 2021). http://dx.doi.org/10.3389/fphys.2021.697270.

Texte intégral

Résumé :

As a result of stress, injury, or aging, cardiac fibrosis is characterized by excessive deposition of extracellular matrix (ECM) components resulting in pathological remodeling, tissue stiffening, ventricular dilatation, and cardiac dysfunction that contribute to heart failure (HF) and eventually death. Currently, there are no effective therapies specifically targeting cardiac fibrosis, partially due to limited understanding of the pathological mechanisms and the lack of predictive in vitro models for high-throughput screening of antifibrotic compounds. The use of more relevant cell models, three-dimensional (3D) models, and coculture systems, together with high-content imaging (HCI) and machine learning (ML)-based image analysis, is expected to improve predictivity and throughput of in vitro models for cardiac fibrosis. In this review, we present an overview of available in vitro assays for cardiac fibrosis. We highlight the potential of more physiological 3D cardiac organoids and coculture systems and discuss HCI and automated artificial intelligence (AI)-based image analysis as key methods able to capture the complexity of cardiac fibrosis in vitro. As 3D and coculture models will soon be sufficiently mature for application in large-scale preclinical drug discovery, we expect the combination of more relevant models and high-content analysis to greatly increase translation from in vitro to in vivo models and facilitate the discovery of novel targets and drugs against cardiac fibrosis.

Styles APA, Harvard, Vancouver, ISO, etc.

49

Finka, Lauren R., Lucia Ripari, Lindsey Quinlan, Camilla Haywood, Jo Puzzo, Amelia Jordan, Jaclyn Tsui, Rachel Foreman-Worsley, Laura Dixon et Marnie L. Brennan. « Investigation of humans individual differences as predictors of their animal interaction styles, focused on the domestic cat ». Scientific Reports 12, n^o 1 (15 juillet 2022). http://dx.doi.org/10.1038/s41598-022-15194-7.

Texte intégral

Résumé :

AbstractHumans’ individual differences including their demographics, personality, attitudes and experiences are often associated with important outcomes for the animals they interact with. This is pertinent to companion animals such as cats and dogs, given their social and emotional importance to humans and degree of integration into human society. However, the mechanistic underpinnings and causal relationships that characterise links between human individual differences and companion animal behaviour and wellbeing are not well understood. In this exploratory investigation, we firstly quantified the underlying structure of, and variation in, human’s styles of behaviour during typical human-cat interactions (HCI), focusing on aspects of handling and interaction known to be preferred by cats (i.e. ‘best practice’), and their variation. We then explored the potential significance of various human individual differences as predictors of these HCI styles. Seven separate HCI styles were identified via Principal Component Analysis (PCA) from averaged observations for 119 participants, interacting with sociable domestic cats within a rehoming context. Using General Linear Models (GLMs) and an Information Theoretic (IT) approach, we found these HCI PC components were weakly to strongly predicted by factors including cat-ownership history, participant personality (measured via the Big Five Inventory, or BFI), age, work experience with animals and participants’ subjective ratings of their cat behaviour knowledge. Paradoxically, greater cat ownership experiences and self-assessed cat knowledge were not positively associated with ‘best practice’ styles of HCI, but were instead generally predictive of HCI styles known to be less preferred by cats, as was greater participant age and Neuroticism. These findings have important implications regarding the quality of human-companion animal relationships and dyadic compatibility, in addition to the role of educational interventions and their targeting for optimal efficacy. In the context of animal adoption, these results strengthen the (limited) evidence base for decision making associated with cat-adopter screening and matching. In particular, our results suggest that greater cat ownership experiences and self-reports of cat knowledge might not necessarily convey advantages for cats in the context of HCI.

Styles APA, Harvard, Vancouver, ISO, etc.

50

Gao, Shan, Elena Albu, Ben van Calster, Laure Wynants, Krizia Tuand, Veerle Cossey et Frank Rademakers. « A systematic review of risk prediction models for central line-associated bloodstream infection (CLA-BSI) in hospitalized patients (MEDLINE) ». searchRxiv 2023 (6 janvier 2023). http://dx.doi.org/10.1079/searchrxiv.2023.00113.

Texte intégral

Résumé :

Abstract Objectives: To systematically review the risk of bias and applicability of published prediction models for risk of central line-associated bloodstream infection (CLA-BSI) in hospitalized patients. Introduction: CLA-BSIs are the most common source of hospital-acquired infections (HAIs), and are always associated with higher morbidity, longer length of stay and increased financial burdens. As a priority target for prevention, tools that were developed to predict the risk of CLA-BSI for individuals may help improve the infection control in hospitals. In this systematic review, we evaluated the current risk prediction models for CLA-BSI and discussed the practical problems for implementing the models. Inclusion criteria: All inpatients (no age limit) with at least a central line in place during their hospitalization anytime. Methods: Four key databases including PubMed (MEDLINE), Embase (Embase.com), Web of Science Core Collection (SCI-EXPANDED, SSCI, A&HCI, CPCI-S, CPCI-SSH, BKCI-S, BKCI-SSH, ESCI, CCR-EXPANDED, IC) and Scopus were used to conduct the search. The search was conducted on the 10th of June 2022. We included studies that describe the development or validation of a prediction model for CLABSI and have at least two predictor variables to build multivariable predictive models. Articles that do not report original research (i.e. reviews), or that are not full papers (i.e. letters, notes, and conference abstracts), or qualitative studies were excluded. References were imported and deduplicated using EndNote (Clarivate Analytics) and Rayyan (Qatar Computing Research Institute). Titles and abstracts were initially screened for exclusion by at least two authors. As interreviewer agreement was considered reliable, the remaining title-abstract screening was done by one author and irrelevant articles were excluded. Then, full text of the potentially relevant articles were screened independently by two authors. Discrepancies were resolved through discussion with a third author. We also used forward and backward snowballing from the final articles that will be included within this review.

Styles APA, Harvard, Vancouver, ISO, etc.

Articles de revues sur le sujet « Predictive HCI models »

Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres