Prediction of Body Constitutions through Life-Style for Health Guidance

The body constitutions (BCs) of traditional Chinese medical theory are predicted through machine learning algorithms in this work. On the basis of the original questionnaire including 258 life-style features, the least absolute shrinkage and selection operator (LASSO) algorithm is employed for predicting the BCs over the population of 851 persons. Moreover, the principle features (PFs) of life-style are identified to recover the biased BCs into the gentle constitutions as the health guidance. Compared to the state-of-art works, the prediction accuracy is improved by 29% and the amount of identified PFs is reduced to 66.7%.

Automated summary

In this study, machine learning algorithms are used to predict the body constitutions (BCs) of traditional Chinese medical theory. By identifying the principle features (PFs) of life-style, biased BCs are transformed into gentle constitutions to provide health guidance. The prediction accuracy is improved by 29% and the amount of identified PFs is reduced to 66.7% compared to previous works.