首页|Beijing University of Chinese Medicine Reports Findings in Machine Learning (Dev elopment of an interpretable machine learning model associated with genetic indi cators to identify Yin-deficiency constitution)
Beijing University of Chinese Medicine Reports Findings in Machine Learning (Dev elopment of an interpretable machine learning model associated with genetic indi cators to identify Yin-deficiency constitution)
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 Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting out of Beijing, People's Repu blic of China, by NewsRx editors, research stated, "Traditional Chinese Medicine (TCM) defines constitutions which are relevant to corresponding diseases among people. As one of the common constitutions, Yin-deficiency constitution influenc es a number of Chinese population in the disease onset." Funders for this research include Technology Project of Beijing University of Ch inese Medicine, Fundamental Research Funds for the Central Universities, Nationa l Administration of Traditional Chinese Medicine. Our news journalists obtained a quote from the research from the Beijing Univers ity of Chinese Medicine, "Therefore, accurate Yin-deficiency constitution identi fication is significant for disease prevention and treatment. In this study, we collected participants with Yin-deficiency constitution and balanced constitutio n, separately. The least absolute shrinkage and selection operator (LASSO) and l ogistic regression were used to analyze genetic predictors. Four machine learnin g models for Yin-deficiency constitution classification with multiple combined g enetic indicators were integrated to analyze and identify the optimal model and features. The Shapley Additive exPlanations (SHAP) interpretation was developed for model explanation. The results showed that, NF-kBIA, BCL2A1 and CCL4 were th e most associated genetic indicators with Yin-deficiency constitution. Random fo rest with three genetic predictors including NF-kBIA, BCL2A1 and CCL4 was the op timal model, area under curve (AUC): 0.937 (95% CI 0.844- 1.000), s ensitivity: 0.870, specificity: 0.900. The SHAP method provided an intuitive exp lanation of risk leading to individual predictions."
BeijingPeople's Republic of ChinaAsi aCyborgsEmerging TechnologiesGeneticsMachine Learning
NETL
NSTL
