Age-Normalized HRV Features for Non-Invasive Glucose Prediction: A Pilot Sleep-Aware Machine Learning Study

TL;DR

This study introduces an age-normalization technique for HRV features during sleep, significantly improving the accuracy of non-invasive glucose prediction using machine learning, with promising results for diabetes management.

Contribution

The paper presents a novel age-normalization method for HRV features that enhances glucose prediction accuracy in a sleep-aware setting, addressing age-related confounding.

Findings

Age-normalized HRV features improved R2 by 25.6% over non-normalized features.

Top predictive features include age-normalized HRV metrics and diastolic blood pressure.

Systematic ablation confirmed age-normalization as critical for prediction performance.

Abstract

Non-invasive glucose monitoring remains a critical challenge in the management of diabetes. HRV during sleep shows promise for glucose prediction however, age-related autonomic changes significantly confound traditional HRV analyses. We analyzed 43 subjects with multi-modal data including sleep-stage specific ECG, HRV features, and clinical measurements. A novel age-normalization technique was applied to the HRV features by, dividing the raw values by age-scaled factors. BayesianRidge regression with 5-fold cross-validation was employed for log-glucose prediction. Age-normalized HRV features achieved R2 = 0.161 (MAE = 0.182) for log-glucose prediction, representing a 25.6% improvement over non-normalized features (R2 = 0.132). The top predictive features were hrv rem mean rr age normalized (r = 0.443, p = 0.004), hrv ds mean rr age normalized (r = 0.438, p = 0.005), and diastolic blood pressure (r = 0.437, p = 0.005). Systematic ablation studies confirmed age-normalization as the critical component, with sleep-stage specific features providing additional predictive value. Age-normalized HRV features significantly enhance glucose prediction accuracy compared with traditional approaches. This sleep-aware methodology addresses fundamental limitations in autonomic function assessment and suggests a preliminary feasibility for non-invasive glucose monitoring applications. However, these results require validation in larger cohorts before clinical consideration.