Objective:To explore the effect of precision nutrition therapy on the dietary pattern and appetite of patients with type 2 diabetes mellitus (T2DM) .Methods:From September 2018 to September 2019, convenience sampling method was used to select 155 patients with T2DM discharged from the Endocrinology Department of the First Affiliated Hospital of Xinjiang Medical University. All patients were randomly divided into control group (73 cases) and experimental group (82 cases) . Control group received routine nutritional intervention. Based on routine follow-up intervention, experimental group established a patient's personalized data model according to the medical artificial intelligence system for precise nutritional treatment, including the establishment of diabetes diet management prescriptions and intelligent diet intervention. The Dietary Pattern Questionnaire and the Simplified Nutritional Appetite Questionnaire (SNAQ) were used to compare the changes in dietary patterns and appetite before and after intervention between two groups.Results:After three months of intervention, the proportion of patients with reasonable protein, fat, and carbohydrate intake in two groups was higher than that before intervention, and that of experimental group was higher than that of control group, and the difference was statistically significant ( P<0.05) . After three months of intervention, the score of SNAQ of experimental group and control group was (13.20±1.54) and (10.32±1.25) respectively, and the difference was statistically significant ( t=-12.838, P<0.05) . Conclusions:The establishment of a big data model based on a medical artificial intelligence system for precise nutritional therapy can regulate the dietary behavior of patients with T2DM and increase their appetite.