Machine Learning Applications for the Development of a Questionnaire to Identify Sasang Constitution Typology

Abstract

Sasang constitutional medicine emphasizes personalized disease prevention and treatment and has been used in various fields. Nevertheless, more efforts are required to improve the validity and reliability of the Sasang analysis tools. Hence, this study aimed to (1) identify key constructs and measurement items of the Sasang constitution questionnaire that characterize different Sasang constitutions and (2) investigate the similarities and differences in pathophysiological and personality traits between Sasang constitutions. The results of the Sasang constitution questionnaire were analyzed using multiple machine learning-based approaches, including feature selection, hierarchical clustering analysis, and multiple correspondence analysis. The selected 47 key measurement items were clustered into six groups based on the similarity measures. The findings of this study are expected to be beneficial for future research on the development of more robust and reliable Sasang conservation questionnaires, allowing Sasang constitutional medicine to be more widely implemented in various sectors.