首页|Hunan University of Chinese Medicine Reports Findings in Non-Alcoholic Fatty Liv er Disease (Advancing non-alcoholic fatty liver disease prediction: a comprehens ive machine learning approach integrating SHAP interpretability and multi-cohort ...)
Hunan University of Chinese Medicine Reports Findings in Non-Alcoholic Fatty Liv er Disease (Advancing non-alcoholic fatty liver disease prediction: a comprehens ive machine learning approach integrating SHAP interpretability and multi-cohort ...)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News-New research on Liver Diseases and Con ditions - Non-Alcoholic Fatty Liver Diseaseis the subject of a report. Accordin g to news reporting from Changsha, People's Republic of China, byNewsRx journal ists, research stated, "Non-alcoholic fatty liver disease (NAFLD) represents a m ajor globalhealth challenge, often undiagnosed because of suboptimal screening tools. Advances in machine learning(ML) offer potential improvements in predict ive diagnostics, leveraging complex clinical datasets."The news correspondents obtained a quote from the research from the Hunan Univer sity of ChineseMedicine, "We utilized a comprehensive dataset from the Dryad da tabase for model development andtraining and performed external validation usin g data from the National Health and Nutrition ExaminationSurvey (NHANES) 2017-2 020 cycles. Seven distinct ML models were developed and rigorouslyevaluated. Ad ditionally, we employed the SHapley Additive exPlanations (SHAP) method to enhan cethe interpretability of the models, allowing for a detailed understanding of how each variable contributesto predictive outcomes. A total of 14,913 particip ants were eligible for this study. Among the sevenconstructed models, the light gradient boosting machine achieved the highest performance, with an areaunder the receiver operating characteristic curve of 0.90 in the internal validation s et and 0.81 in theexternal NHANES validation cohort. In detailed performance me trics, it maintained an accuracy of 87%,a sensitivity of 92.9% , and an F1 score of 0.92. Key predictive variables identified included alanine aminotransferase,gammaglutamyl transpeptidase, triglyceride glucose-waist circu mference, metabolic score forinsulin resistance, and HbA1c, which are strongly associated with metabolic dysfunctions integral to NAFLDprogression. The integr ation of ML with SHAP interpretability provides a robust predictive tool for NAFLD, enhancing the early identification and potential management of the disease."
ChangshaPeople's Republic of ChinaAs iaAlcohol-InducedDiseases and ConditionsAlcoholic Fatty LiverAlcoholismCyborgsDigestive System Diseases and ConditionsEmerging TechnologiesFatty LiverFatty Liver DiseaseHealth and MedicineLiver Diseases and ConditionsMachine LearningNon-Alcoholic Fatty Liver Disease
NETL
NSTL
