Decision of Acupoints in Acupuncture and Moxibustion Treatment by Artificial Intelligence

Acupoints prescription is the basis of acupuncture and moxibustion treatment. The combination of different acupoints is used to treat corresponding diseases. Different diseases are manifested through the combination of various symptoms. Acupuncturists judge the health status of patients according to the combination of symptoms, and decide the acupoints prescription according to the theory of traditional Chinese medicine and many years of clinical experience. Artificial intelligence technology represented by machine learning is expected to provide a more objective and accurate acupuncture and moxibustion treatment prescription. In this paper, we propose a method to determine the acupoints of acupuncture and moxibustion treatment according to the patient's symptoms by using machine learning. Specifically, in this paper we build a database of symptoms and acupuncture and moxibustion treatment prescriptions, and perform learning by machine learning using several models. Furthermore, we evaluate the models using the test data and discuss the evaluation criteria.

I. Introduction

In recent years, the Artificial Intelligence (AI for short here-after) industry has developed vigorously. As the core branch of AI, machine learning has penetrated into all walks of life, and has also set off a wave in the medical field [1]. The main method of machine learning is to recognize the input data sets through the computer, encode them into the computer model or algorithm, and test and verify them on the new data. The ability to collect and analyze large datasets related to medical treatments and outcomes promises to transform medicine into a data-driven, outcomes-oriented discipline with profound implications for disease detection, diagnosis, and treatment [2].