@misc{10481/112035,
year = {2025},
month = {12},
url = {https://hdl.handle.net/10481/112035},
abstract = {This work investigates the impact of patients’ heterogeneity, including factors such as gender, age, and clinical conditions, on the performance of machine learning models in predicting blood glucose levels in individuals with Type 1 Diabetes. Using the T1DiabetesGranada dataset, various datasets were generated based on these heterogeneity factors. Three popular prediction models —a Linear model, an LSTM neural network, and a CNN— were applied to both the generated datasets and the complete dataset to measure prediction performance at a 30-minute prediction horizon. The preliminary results suggest that incorporating patient-specific heterogeneity factors generally improves prediction performance, highlighting the existence of bias in standard blood glucose level prediction models. Future research should explore whether these findings hold in other related datasets.},
organization = {MICIU/AEI/10.13039/501100011033 and ERDF EU (PID2023-148188OA-I00)},
publisher = {IEEE},
title = {Exploring the Influence of Patients’ Heterogeneity on Automated Prediction of Blood Glucose Levels in Type 1 Diabetes},
doi = {10.1109/EMBC58623.2025.11253928},
author = {Baños Legrán, Oresti and Avilés-Pérez, María Dolores and Gayaroa, Álvaro and Lopez-Ibarra Lozano, Pablo J. and Muñoz Torres, Manuel Eduardo and Quesada Charneco, Miguel and Rodríguez León, Ciro and Villalonga Palliser, Claudia},
}