AIM: An Advanced Hybrid Inference Model Combining Clinical Rules and Lifelog-Based Learning for Health Risk...

Background: Early identification of metabolic health risk is important for preventive intervention, but routine laboratory testing is not always available in everyday health-management environments. Artificial intelligence models can estimate risk from accessible variables, but purely data-driven models may provide limited clinical interpretability. Objective: This study presents the Advanced Hybrid Inference Model (AIM), a clinically interpretable screening support framework that combines biomarker estimation, Random Forest-based risk prediction, and rule-based clinical interpretation. Methods: AIM was intentionally implemented as a three-stage, Random Forest-centered pipeline: (1) Selected anthropometric and demographic variables were used to estimate clinically relevant metabolic biomarkers when direct measurements were unavailable. (2) A Random Forest model generated metabolic risk estimates from measured or estimated biomarkers and clinical variables. (3) Rule-based interpretation mapped the model outputs and biomarker thresholds to clinically meaningful risk-support messages. Results: Experimental validation was conducted using clinically collected datasets under class-imbalanced conditions. The results indicate that the proposed framework showed exploratory potential for identifying high-risk patterns. These findings suggest that the AIM framework may be useful as a screening-oriented approach. Conclusions: AIM should be interpreted as an exploratory clinical screening support framework that prioritizes interpretability, structured rule-based reasoning, and risk prioritization rather than a diagnostic classifier or universally superior prediction model.