Diabetes diet scheme adaptive generation system based on deep learning

Abstract

The invention discloses a deep learning-based diabetic diet scheme self-adaptive generation system, which comprises a collection and storage module, which is configured to collect and make data of total calorie dynamic change of a patient, and according to basic metabolism, occupational consumption, exercise consumption, diet supplement and a difference value between a waist-hip ratio and a fasting blood-glucose mean value, the data of the total calorie dynamic change of the patient is calculated; constructing a personalized data set for generating a heat supplement plan; the calculation module is used for importing the personalized data set into an improved linear regression model and carrying out data training to obtain an optimal weight corresponding to each piece of data in the data set; and the evaluation and feedback module is used for automatically calculating a diet calorie supplement value by setting a double-gradient target according to the optimal weight and the deviation value of the calculation module, generating a personalized diet scheme and timely feeding back and optimizing the diet scheme. According to the method, the personalized data set of the total calorie change of the patient is constructed, and the deep learning method is introduced into the formulation of the diet scheme of the patient, so that more accurate and scientific diet guidance is provided for the diabetic patient.

Description

technical field [0001] The embodiment of the present invention relates to the field of medical and health technologies, and in particular to a deep learning-based self-adaptive generation system for diabetes diet plan. Background technique [0002] Diabetes is a chronic metabolic disease with a relatively high incidence. The quality of intervention on the patient's lifestyle (diet, exercise, etc.) directly affects the development of the disease and the effect of rehabilitation. expression. At present, the dietary management of diabetic patients is mainly based on daily calorie consumption. Specifically, it simply estimates the calorie consumption based on the comparison of the patient's body weight with the standard body weight, physical activity and other indicators, and proposes a fuzzy and uniform diet plan. In fact, this management method appears to be very extensive, not only lacks precise dietary guidance for patients' individualized condition changes, but also lacks ...

AI Technical Summary

Problems solved by technology

[0019] However, there are obvious defects in such a diet plan formulation method: first, the degree of individualization is low, the calorie consumption is estimated according to the general type of physical activity and body weight, and the average calorie requirement of the population is used to increase or decrease supplements, only considering the daily life of the patient. Physical activity, without considering the patient's additional physical exercise, blood sugar fluctuations, etc., it is difficult to comprehensively evaluate calorie consumption and it is difficult to accurately supplement calories according to the actual needs of individuals to alleviate the disease; second, the efficiency is not high, and each physician or nutritionist is served The number of patients is limited, and it is difficult to dynamically evaluate individual calorie consumption, so it is impossible to provide precise dietary guidance to most patients; third, the effect is poor, and most of the current diet plans are based on controlling calorie intake For the purpose, the improvement of the patient's own physiological characteristics (such as visceral fat content, muscle content, etc.) and the control target of blood sugar level are ignored, so that the effect of dietary rehabilitation is generally poor; (exercise, diet, etc.) changes cannot be linked in time, and it is difficult to accurately implement dynamic assessment and diet adjustments based on fluctuations in daily calorie consumption of patients

Images