Potential predictors of type-2 diabetes risk: machine learning, synthetic data and wearable health devices

• Published in: BMC bioinformatics Vol. 21; no. S17; pp. 508 - 19
• Main Authors: Stolfi, Paola, Valentini, Ilaria, Palumbo, Maria Concetta, Tieri, Paolo, Grignolio, Andrea, Castiglione, Filippo
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 14.12.2020; BioMed Central; BMC
• Subjects: Adult; Aged; Approximation; Computational modeling; Computer applications; Computer simulation; Computer-generated environments; COVID-19; Cytokines; Datasets; Diabetes; Diabetes mellitus (non-insulin dependent); Diabetes Mellitus, Type 2 - metabolism; Diabetes Mellitus, Type 2 - pathology; Electronic devices; Emulator; Epidemics; Exercise intensity; Familiarity; Female; Health risks; Homeostasis; Humans; Immunology; Inflammation; Insulin resistance; Learning algorithms; Machine Learning; Male; Mathematical models; Metabolism; Metabolites; Methods; Middle Aged; Models, Theoretical; Ordinary differential equations; Physical fitness; Random forest; Research projects; Risk; Risk factors; Self-assessment; Statistical models; Synthetic data; T2D; Tumor necrosis factor-TNF; Type 2 diabetes; User-Computer Interface; Wearable computers; Wearable Electronic Devices; Web services; Italy; Emulator; Random forest; Computational modeling; Machine learning; T2D; Synthetic data
• ISSN: 1471-2105; 1471-2105
• DOI: 10.1186/s12859-020-03763-4

The aim of a recent research project was the investigation of the mechanisms involved in the onset of type 2 diabetes in the absence of familiarity. This has led to the development of a computational model that recapitulates the aetiology of the disease and simulates the immunological and metabolic alterations linked to type-2 diabetes subjected to clinical, physiological, and behavioural features of prototypical human individuals. We analysed the time course of 46,170 virtual subjects, experiencing different lifestyle conditions. We then set up a statistical model able to recapitulate the simulated outcomes. The resulting machine learning model adequately predicts the synthetic dataset and can, therefore, be used as a computationally-cheaper version of the detailed mathematical model, ready to be implemented on mobile devices to allow self-assessment by informed and aware individuals. The computational model used to generate the dataset of this work is available as a web-service at the following address: http://kraken.iac.rm.cnr.it/T2DM .