Artificial Intelligence-Driven Personalized Eating Time Intervention: Precise Practice in the Year of Weight Management
In recent years, using artificial intelligence to recommend individualized eating time has become an emerging direction in weight management. This paper systematically reviews four technical pathways in this field: blood glucose prediction based on continuous glucose monitoring, eating window optimization based on chronotype, metabolic peak prediction based on cortisol load, and dynamic adjustment through multimodal fusion and reinforcement learning. The existing evidence shows a clear gradient. Blood glucose prediction and chronotype-based optimization have accumulated a certain amount of research, but the former is mostly single-modality retrospective analysis and the latter is dominated by cross-sectional studies; cortisol assessment and multimodal fusion are still at an early exploratory stage. At present no study has integrated the above factors into a unified model, and long-term clinical verification is also lacking. This means that "AI-personalized eating time" still has a long way to go from technical feasibility to clinical implementation.
Authors
- Chang Zou
Institutions
- Southern Medical University (CN)
Publication Details
- Journal
- Theoretical and Natural Science
- Published
- 2026-11-17
- DOI
- https://doi.org/10.54254/2753-8818/2026.es39041
- Primary Topic
- Dietary Effects on Health
- Type
- article
- Field-Weighted Citation Impact
- 0.00