SUN-845 - Phase Angle-Driven Predictive Health Index Identifies Earlyendocrine-Metabolic Dysregulation

Background:
Early endocrine and metabolic dysregulation frequently precedes the clinical onset of chronic non-communicable diseases, remaining undetected by conventional diagnostic frameworks. Phase Angle (PhA), derived from bioimpedance analysis, is a well-established, clinically interpretable marker of cellular integrity, inflammation, and metabolic status. We aimed to develop and validate a Phase Angle–driven Predictive Health Index (PHI) integrating autonomic nervous system regulation and body composition metrics to identify early endocrine–metabolic dysfunction and predict disease risk.

Methods:
Data from 35,405 clinically characterized adults (18–90 years) followed over 5 years were retrospectively analyzed. Non-invasive assessments included bioimpedance- derived Phase Angle and body composition parameters (fat mass, intramuscular adipose tissue, extracellular matrix, hydration compartments) and photoplethysmography-derived heart rate variability (HRV) indices reflecting autonomic regulation (RMSSD, SDNN, LF/VLF ratio, total power). Five independent random forest models were trained to discriminate healthy controls from individuals with cardiovascular, metabolic, psychological, neoplastic, and chronic inflammatory conditions. Model performance was evaluated using ROC-AUC analysis, probability calibration, and variable importance ranking.

Results:
The Phase Angle–centered PHI demonstrated significant discriminative ability across all disease categories (all p < 0.001), with AUC values ranging from 0.78 to 0.87. Phase Angle consistently emerged as one of the most influential predictors across models, together with age and HRV-derived autonomic indices. Lower Phase Angle values were associated with reduced autonomic variability and adverse body composition profiles, reflecting a progressive loss of systemic endocrine–metabolic resilience. Predicted PHI scores showed a monotonic relation to estimated disease probability, supporting clinical interpretability.

Conclusion:
A Phase Angle–driven Predictive Health Index integrating autonomic regulation and body composition provides a non-invasive and physiologically grounded approach to detect early endocrine–metabolic dysregulation prior to overt disease. This framework shifts risk assessment toward resilience evaluation, aligning with emerging preventive and precision endocrinology paradigms.

*Unless otherwise noted, all abstracts presented at ENDO must not be released to the press or the public until the date and time of presentation. For oral presentations, the abstracts are embargoed until the session begins. The Endocrine Society reserves the right to lift the embargo on specific abstracts that are selected for promotion prior to or during ENDO.*