Bayesian Matrix Completion for Planning Diabetes Treatment Based on Urban Cases

For patients in the early stages of diabetes, it is crucial for patients and doctors to make treatment decisions to prevent the condition from getting worse and developing complications such as diabetic eyes and feet. Both undertreatment and overtreatment can do harm to the patient. In this paper, the probability of taking each treatment option for different symptoms is complemented by a database of existing successful cases of diabetic treatment options to recommend an appropriate treatment for patients with specific symptoms. The matrix completion process adopts the assumption of high rank and completes the matrix based on the unique properties of Bayesian matrices. The results demonstrate the practicality and effectiveness of this algorithm.