Method and Model for Analyzing the Rationality of Medical Visits Based on Automatic Machine Learning

With the continuous deepening of medical supervision, traditional analysis of the rationality of medical visits mainly relies on experienced experts, which suffers from issues such as low efficiency, significant influence from subjective factors, and limited coverage, making it difficult to comprehensively supervise medical visits. Therefore, this paper addresses these issues by constructing an analysis method and model for the rationality of medical visits based on automatic machine learning. This method collects data such as visit information, settlement information, and expense details from medical records. Through preprocessing and feature extraction, an analysis model is constructed using an automatic machine learning system, enabling automated analysis of the rationality of medical visits and identification of irregularities. This system has good generalization ability and robustness, solving the problems of existing technology focusing on a single scene, small coverage range, and inability to identify specific violations.