Understanding Type 2 Diabetes Mellitus Risk Parameters through Intermittent Fasting: A Machine Learning Approach

Area of Science:

• Metabolic disorders
• Endocrinology
• Personalized medicine

Background:

• Type 2 diabetes mellitus (T2DM) is a chronic metabolic disorder with significant mortality despite existing treatments.
• Lifestyle interventions, including intermittent fasting (IF), are gaining attention for T2DM management.
• There is a need for personalized strategies to optimize IF's effectiveness in improving T2DM risk parameters.

Purpose of the Study:

• To identify patterns and principles for improving T2DM risk parameters using intermittent fasting (IF).
• To develop a personalized recommendation system for IF interventions based on individual characteristics.
• To enhance the understanding of IF's impact on metabolic health in pre-diabetic and diabetic individuals.

Main Methods:

• Analysis of data from multiple randomized clinical trials on IF interventions in humans.
• Application of a machine learning algorithm to identify key features influencing T2DM risk parameters.
• Development of a personalized recommendation system for IF tailored to individual needs.

Main Results:

• A machine learning-based recommendation system achieved a 95% success rate in providing individualized IF advice.
• Identified that body weight is a critical factor for females, while age is a determining factor for males in reducing blood glucose levels.
• Demonstrated the system's ability to optimize IF benefits for diverse population subgroups.

Conclusions:

• Weight and age are crucial demographic features influencing blood glucose reduction through IF in females and males, respectively.
• Personalized IF recommendations can significantly improve T2DM risk parameters.
• This study provides practical guidance and insights into the mechanisms underlying T2DM management through lifestyle interventions.