Abstract The innovation of the digital medical field, derived from the algorithms of the intelligent era, is bound to have ethical and risky problems while greatly improving diagnosis and treatment efficiency. The purpose of this paper is to outline the overall function of the intelligent diagnosis and treatment system and propose a standardized governance route to address doctor-patient conflicts and ethical risks that arise from it in the medical industry. This involves establishing a diagnosis and treatment decision-making system that targets common and multiple diseases, both in urban and rural areas. Incorporating CBR technology and improving the KNN method, the improved nearest neighbor method for spatial fuzzy number calculation is formed, together with the fuzzy hybrid case retrieval algorithm (FHRA-M) based on the characteristics of hospital diagnosis and treatment decision-making cases, to jointly innovate the case-based hospital diagnosis and treatment intelligent decision-support system. We look at how well the FHRA-M model retrieves information based on hospital diagnosis and treatment decision-making case features. The intelligent diagnosis and treatment system is utilized to assist medical students in learning clinical skills and doctors in determining what is wrong with patients. The self-assessment results of the trainees’ clinical skills showed that the study group had a higher completion rate of clinical skills, and the self-assessment results of first-aid skills, clinical thinking in emergency medicine, and proactive provision of first-aid services for chest pain patients were significantly better than those of the control group. Intelligent assisted diagnostic film reading has better diagnostic consistency than the conventional film reading method, and the average diagnostic time is 0.81±0.55min, which is significantly lower than the conventional film reading diagnostic time and obviously reduces the workload of diagnostic imaging physicians. The intelligent diagnosis and treatment system, as part of the standardized governance of medical regulations, must continue to enhance its diagnostic and treatment decision-making capabilities and establish algorithmic governance trust in the field of intelligent diagnosis and treatment.
Read full abstract