Multi-Modal Wearable and Biological Data Integration Reveals Physiological Signatures of Weight Variation in Overweight and Obese Adults: An AI4Food Machine Learning Study
- 1Computational Biology Group. IMDEA Nutrition Institute, Madrid, Spain
Abstract
This study is part of the AI4Food project, which aims to identify the physiological and behavioral factors influencing weight variation in overweight and obese individuals through integrative analysis of multi-source data. A 30-day crossover intervention was conducted on 93 participants at IMDEA Nutrition Institute, combining a traditional phase (questionnaires, food diaries) and a digital phase (Fitbit Sense Smartwatch, FreeStyle Libre 2 glucose sensor). The collected data encompassed sleep, glucose, skin temperature, nutrition, and gut microbiome information. After rigorous preprocessing and alignment by intervention days, unsupervised clustering, association analysis, and machine learning models were applied to uncover physiological patterns linked to weight dynamics. Results showed greater weight reduction during the digital phase in Group 2, while between-group differences were not significant. Significant associations were observed between nocturnal respiratory rate, skin temperature, and weight variation. Under participant-level five-fold cross-validation, Random Forest models achieved mean accuracies of 64.3% for thermoregulation and 61.7% for glucose phenotype prediction, with RMSSD, restlessness, and nocturnal respiratory rate among the most influential predictors. In contrast, microbiome composition remained almost stable over the short intervention period. These findings support the potential of AI-driven integration of wearable and nutritional data to stratify metabolic phenotypes and advance personalized nutrition strategies in obesity management.
Related
- Early mobilization in neurocritical care as a threshold-regulated intervention: a narrative review of mechanistic integration and implications for neurological recovery and physiological stability
- Germline structural variation involving gynecologic and breast cancers reveals polygenic signatures of tumor mutational load
- Artificial Intelligence, Multi-Omics, and Multimodal Integration in Precision Radiotherapy for Head and Neck Cancer: From Biological Insights to Treatment Decisions
- Exploratory Integration of Metabolomics and Machine Learning Identifies Candidate Signatures of Spontaneous Preterm Birth
- Pathways linking to behavioural and biological risk factors on diabetes and overweight/obese among adults in urban slums from Western India: a structural equation modelling analysis
BibTeX
@misc{attioui2026multimodal,
title = {{Multi-Modal Wearable and Biological Data Integration Reveals Physiological Signatures of Weight Variation in Overweight and Obese Adults: An AI4Food Machine Learning Study}},
author = {H. Attioui and B. Lacruz-Pleguezuelos and E. Carrillo de Santa Pau},
howpublished = {medRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.03.26367178},
url = {https://www.medrxiv.org/content/10.64898/2026.11.03.26367178v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Multi-Modal Wearable and Biological Data Integration Reveals Physiological Signatures of Weight Variation in Overweight and Obese Adults: An AI4Food Machine Learning Study
AU - H. Attioui
AU - B. Lacruz-Pleguezuelos
AU - E. Carrillo de Santa Pau
PY - 2026
DA - 2026/11/03
PB - medRxiv
DO - 10.64898/2026.11.03.26367178
UR - https://www.medrxiv.org/content/10.64898/2026.11.03.26367178v1
AB - This study is part of the AI4Food project, which aims to identify the physiological and behavioral factors influencing weight variation in overweight and obese individuals through integrative analysis of multi-source data. A 30-day crossover intervention was conducted on 93 participants at IMDEA Nutrition Institute, combining a traditional phase (questionnaires, food diaries) and a digital phase (Fitbit Sense Smartwatch, FreeStyle Libre 2 glucose sensor). The collected data encompassed sleep, glucose, skin temperature, nutrition, and gut microbiome information. After rigorous preprocessing and alignment by intervention days, unsupervised clustering, association analysis, and machine learning models were applied to uncover physiological patterns linked to weight dynamics. Results showed greater weight reduction during the digital phase in Group 2, while between-group differences were not significant. Significant associations were observed between nocturnal respiratory rate, skin temperature, and weight variation. Under participant-level five-fold cross-validation, Random Forest models achieved mean accuracies of 64.3% for thermoregulation and 61.7% for glucose phenotype prediction, with RMSSD, restlessness, and nocturnal respiratory rate among the most influential predictors. In contrast, microbiome composition remained almost stable over the short intervention period. These findings support the potential of AI-driven integration of wearable and nutritional data to stratify metabolic phenotypes and advance personalized nutrition strategies in obesity management.
ER -