AI Insight
Researchers developed machine learning models using data from continuous glucose monitors (CGM) and smartwatches to detect insulin resistance in free-living conditions, without blood tests or clinical procedures. The best-performing model, trained on 97 participants and validated on an independent cohort of 61 participants, achieved an AU-ROC of 0.873, outperforming a baseline model relying solely on anthropometric measurements. This represents the first demonstration that wearable sensor data collected during daily life can reliably identify insulin resistance in adults with normoglycemia or prediabetes.
Why it matters
Insulin resistance affects one in four adults and often goes undetected for years before a diabetes diagnosis, so a non-invasive, continuous screening method could enable earlier identification of at-risk individuals and prompt timely clinical follow-up. If validated at scale, this approach could shift insulin resistance screening from infrequent clinical visits to passive, population-level monitoring.
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
One in four adults has insulin resistance (IR), a modifiable driver of type-2 diabetes that can precede diagnosis by a decade. However, IR assessment remains clinic- and laboratory-based, limiting repeated population screening. We tested whether free-living wearable data can detect IR in adults with normoglycemia or prediabetes. Machine-learning models using continuous glucose monitor (CGM)-based glucose dynamics and smartwatch-based heart rate/heart rate variability were developed in Study 1 (N = 97) and externally validated without retraining in Study 2 (N = 61, 31% IR prevalence). The best-performing CGM-based model achieved AU-ROC = 0.873 [0.756-0.967] and AU-PRC = 0.816 [0.640-0.934], outperforming an anthropometrics-only baseline (AU-ROC = 0.749, AU-PRC = 0.593). Findings are the first to detect IR from wearables without blood tests or structured glucose challenges, with state-of-the-art comparable performance. By enabling continuous at-home screening, this approach can identify undetected at-risk individuals and trigger confirmatory blood tests to close detection gaps.
Source: Digital biomarkers for insulin resistance screening in daily life