Prediction of Cold and Heat Patterns Using Anthropometric Measures Based on Machine Learning

• 来源期刊: 中国结合医学杂志（英文版）
• 年，卷（期）: 2018,（1）
• 页码范围: 16-23
• 页数: 8页
• 语种: 英文
• DOI: 10.1007/s11655-016-2641-8

摘要

Objective:To examine the association of body shape with cold and heat patterns,to determine which anthropometric measure is the best indicator for discriminating between the two patterns,and to investigate whether using a combination of measures can improve the predictive power to diagnose these pattems.Methods:Based on a total of 4,859 subjects (3,000 women and 1,859 men),statistical analyses using binary logistic regression were performed to assess the significance of the difference and the predictive power of each anthropometdc measure,and binary logistic regression and Naive Bayes with the variable selection technique were used to assess the improvement in the predictive power of the pattems using the combined measures.Results:In women,the strongest indicators for determining the cold and heat patterns among anthropometdc measures were body mass index (BMI) and rib circumference;in men,the best indicator was BMI.In experiments using a combination of measures,the values of the area under the receiver operating characteristic curve in women were 0.776 by Naive Bayes and 0.772 by logistic regression,and the values in men were 0.788 by Naive Bayes and 0.779 by logistic regression.Conclusions:Individuals with a higher BMI have a tendency toward a heat pattem in both women and men.The use of a combination of anthropometric measures can slightly improve the diagnostic accuracy.Our findings can provide fundamental information for the diagnosis of cold and heat pattems based on body shape for personalized medicine.