Identification of Activity, Insulin, and Dietary Thresholds Associated With Exercise‐Related Hypoglycaemia and Hyperglycaemia in Children With Type 1 Diabetes: A Free‐Living Study Using Explainable Machine Learning
Diabetes, Obesity and Metabolism · 2026
DOI: 10.1111/dom.71165 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diabetes, Obesity and Metabolism, 2026. Verfasst von Asif Iqbal und 8 weiteren Autor:innen. Beteiligte Einrichtung: ULR 7369 - URePSSS - Unité de Recherche Pluridisciplinaire Sport Santé Société, Univ. Lille, Univ. Artois, Univ. Littoral Côte d'Opale, Lille, France. Hauptthemen laut MEDLINE: Diabetes Mellitus, Type 1, Hypoglycemia, Exercise, Hyperglycemia. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Santélys Association (Lille), Université de Lille.
Themen: Künstliche Intelligenz in der Pflege, Diabetes mellitus, Kinderkrankenpflege
Abstract (Originalsprache)
Aims
Some studies have explored associations between physical activity (PA) and hypoglycaemia in real‐life in type 1 diabetes (T1D) but without fully accounting for two major confounders, diet and insulin. We aimed to identify thresholds of PA characteristics, insulin, and carbohydrates associated with dysglycaemia across the exercise‐recovery cycle in children with T1D. Materials and Methods Continuous glucose monitoring and accelerometry data, self‐reported PA sessions (timing, duration and perceived intensity), diet (timing, type and quantity; optional photographs) and insulin data (doses and timing; corrective/meal boluses and basal insulin) were collected in 36 children with T1D (11.9 ± 3.3 years, injections or open‐loop pumps) over seven free‐living days. Accelerometer data were analysed for periods corresponding to self‐reported PA sessions. Ensemble machine‐learning models classified hypoglycaemia (< 70 mg/dL) and hyperglycaemia (> 180 mg/dL) during three phases: PA, 2‐h post‐exercise (early recovery), overnight. Shapley analysis identified risk and protection thresholds of features with high importance.
Results
Models achieved moderate to strong performance (AUC: 0.65–0.99; F1‐score: 0.62–0.95) across outcomes and phases. Insulin boluses > 11% of total daily dose within 4‐h pre‐exercise and > 17% during early recovery were associated with hypoglycaemia risk during PA and early recovery respectively. Carbohydrate intake showed collinearity with insulin, resulting in complex associations with glycaemia. Self‐reported PA > 80 min was associated with hypoglycaemia risk during PA, while accumulating > 15 min of accelerometer‐derived vigorous PA was actually protective against early recovery hypoglycaemia. Multiple daily sessions were associated with nocturnal hyperglycaemia protection.
Conclusions
Phase‐specific thresholds across exercise and insulin domains associated with exercise‐related dysglycaemia were identified.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- ULR 7369 - URePSSS - Unité de Recherche Pluridisciplinaire Sport Santé Société, Univ. Lille, Univ. Artois, Univ. Littoral Côte d'Opale, Lille, France.
- CNRS, Inria, Centrale Lille, UMR 9189 - CRIStAL, Université de Lille, Lille, France.
- ULR 7369 - URePSSS - Unité de Recherche Pluridisciplinaire Sport Santé Société, Univ. Littoral Côte d'Opale, Univ. Artois, Univ. Lille, Dunkerque, France.
- CNRS, UMR 6118, Transferts d'eau et de Matière dans les Milieux Hétérogènes Complexes - Géosciences, Université Rennes, Rennes, France.
- Institut de Recherches Cliniques de Montréal (IRCM), Montréal, Québec, Canada.
- Endocrinology Division, Centre Hospitaller de l'Université de Montréal (CHUM), Montréal, Québec, Canada.
ORCID-Profile: Rémi Rabasa-Lhoret, Elsa Heyman
Förderung
- Santélys Association (Lille)
- Université de Lille
Zitieren
APA
Iqbal, A., Dahimi, H., Preux, P., Lespagnol, E., Melin, A., Morel, P., Heyman, J., Rabasa-Lhoret, R., & Heyman, E. (2026). Identification of Activity, Insulin, and Dietary Thresholds Associated With Exercise‐Related Hypoglycaemia and Hyperglycaemia in Children With Type 1 Diabetes: A Free‐Living Study Using Explainable Machine Learning. Diabetes, Obesity and Metabolism. https://doi.org/10.1111/dom.71165
Vancouver
Iqbal A, Dahimi H, Preux P, Lespagnol E, Melin A, Morel P, et al. Identification of Activity, Insulin, and Dietary Thresholds Associated With Exercise‐Related Hypoglycaemia and Hyperglycaemia in Children With Type 1 Diabetes: A Free‐Living Study Using Explainable Machine Learning. Diabetes, Obesity and Metabolism. 2026. doi:10.1111/dom.71165
BibTeX
@article{Iqbal2026,
author = {Iqbal, Asif and Dahimi, Haithem and Preux, Philippe and Lespagnol, Elodie and Melin, Angéline and Morel, Pierre and Heyman, Joris and Rabasa-Lhoret, Rémi and Heyman, Elsa},
title = {Identification of Activity, Insulin, and Dietary Thresholds Associated With Exercise‐Related Hypoglycaemia and Hyperglycaemia in Children With Type 1 Diabetes: A Free‐Living Study Using Explainable Machine Learning},
journal = {Diabetes, Obesity and Metabolism},
year = {2026},
doi = {10.1111/dom.71165}
}
EUVIMED