Daily Core Body Temperature Oscillation (ΔT) as an Ecological Marker of Autonomic Coherence: Identification of Energy Resistance (eR) Phenotypes in a 15-Day Observational Cohort of 16 Adults

BackgroundArtificial intelligence applications for preventive stress monitoring remain limited by dependence on expensive continuous biosensors. We developed and validated an AI-based framework for automated phenotyping of stress-energy responses from accessible smartphone-based circadian temperature monitoring and cognitive-autonomic assessments, enabling scalable population health monitoring without wearable devices. MethodsThis 15-day prospective observational study collected 239 daily observations from 16 adults (age 58.35{+/-}7.8 years; 100% adherence). Daily axillary temperature oscillation ({Delta}T = night-minus-morning), a 6-item cognitive-autonomic index (MiSBIE Brief-6), morning light exposure, and screen time were analyzed using unsupervised K-means clustering. A Composite Stress Load (CSL) index integrating subjective stress (40%), thermal variance (30%), and pain (30%) was computed. Cluster validation employed silhouette analysis, Gap statistics, and Hopkins test. ResultsUnsupervised machine learning identified three distinct stress-energy phenotypes (k=3; silhouette=0.75; Gap p<0.001): Cluster 1 (Low {Delta}T/High Recovery; n=87; {Delta}T=-0.19{+/-}0.09{degrees}C; MiSBIE-delta=+1.84{+/-}0.62), Cluster 2 (Neutral/Intermediate; n=98; {Delta}T=+0.00{+/-}0.07{degrees}C; MiSBIE-delta=+1.12{+/-}0.51), and Cluster 3 (High {Delta}T/Minimal Recovery; n=54; {Delta}T=+0.21{+/-}0.10{degrees}C; MiSBIE-delta=+0.41{+/-}0.68). Elevated {Delta}T strongly correlated with CSL (r=0.52; p<0.001). AI-derived phenotypes predicted 78% of thermal stability variance (R2=0.78; p<0.001). Morning light >15 minutes reduced {Delta}T ({beta}=-0.24{degrees}C; p=0.002). ConclusionsThis validated AI framework achieves automated stress phenotyping at <$5 per participant versus $200-500 for wearables, supporting early identification of elevated allostatic load aligned with the Energy Resistance Principle. Longitudinal phenotype tracking enables predictive early warning and individualized exercise optimization in real-world settings, advancing health equity in preventive monitoring for resource-limited contexts. Integration into public health systems serving millions (e.g., Brazils SUS) could enable anticipatory care delivery, improving quality of life through early intervention before clinical deterioration HighlightsO_LIK-means clustering identified 3 autonomic phenotypes (silhouette=0.75) C_LIO_LI{Delta}T>0{degrees}C predicts stress load elevation (r=0.52, p<0.001) C_LIO_LIMiSBIE-6 explains 78% of thermal variance (R2=0.78, p<0.001) C_LIO_LIMorning light reduces {Delta}T by 0.24{degrees}C; screens increase it 0.19{degrees}C/hour C_LIO_LISmartphone-based framework enables scalable stress phenotyping[AA1] C_LI