DIAGNOSIS AND TREATMENT SYSTEM BASED ON ARTIFICIAL INTELLIGENCE AND DEEP LEARNING

This paper designs an assisted diagnosis and treatment system based on deep learning algorithms and medical knowledge to solve the problem of poor use efficiency of massive electronic medical information. First, the disease data in the medical database is segmented to get the reverse order search table. Secondly, the similarity between the obtained clinical manifestation data and the corresponding diseases is analyzed and classified to obtain the clinical diagnosis. Then, the feedback-query method is used to analyze the weighted ratio of the original and feedback data, and the optimal fault diagnosis is carried out. The method of implicit semantic modeling is used to give the diagnosis scheme of the disease. The search method based on inference rules is introduced to realize personalized diagnosis and treatment resource recommendations to users. In this way, the specific attributes of medical resources based on individual information are effectively combined. Experiments show that the initial diagnosis recognition rate of the proposed method is 95%, the correct rate is 85%, and the recognition rate is 95% after optimization.