Development of an explicit and implicit knowledge identification tool for the analysis of the decision-making process of traditional Asian medicine doctors

Abstract

AbstractBackground and objectivesWhile pattern identification (PI) is an essential process for diagnosis and treatment in traditional Asian medicine (TAM), it is difficult to objectify since it relies heavily on implicit knowledge. Here, we propose a machine learning-based analysis tool to objectify and evaluate the clinical decision-making process of PI in terms of explicit and implicit knowledge.MethodsClinical data for the development of the analysis tool were collected using a questionnaire administered to allergic rhinitis (AR) patients and the diagnosis and prescription results of TAM doctors based on the completed AR questionnaires. Explicit knowledge and implicit knowledge were defined based on the explicit and implicit importance scores of the AR questionnaire, which were obtained through doctors’ explicit scoring and feature evaluations of machine learning models, respectively. The analysis tool consists of eight evaluation indicators used to compare, analyze and visualize the explicit and implicit knowledge of TAM doctors.ResultsThe analysis results for 8 doctors showed that our tool could successfully identify explicit and implicit knowledge in the PI process. We also conducted a postquestionnaire study with the doctors who participated to evaluate the applicability of our tool.ConclusionsThis study proposed a tool to evaluate and compare decision-making processes of TAM doctors in terms of their explicit and implicit knowledge. We identified the differences between doctors’ own explicit and implicit knowledge and the differences among TAM doctors. The proposed tool would be helpful for the clinical standardization of TAM, doctors’ own clinical practice, and intern/resident training.