A meta-learning approach to personalized blood glucose prediction in type 1 diabetes
| dc.contributor.author | Langarica, Saul | |
| dc.contributor.author | Rodriguez-Fernandez, Maria | |
| dc.contributor.author | Nunez, Felipe | |
| dc.contributor.author | Doyle III, Francis J. | |
| dc.date.accessioned | 2025-01-20T20:15:34Z | |
| dc.date.available | 2025-01-20T20:15:34Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | Accurate blood glucose prediction is a critical element in modern artificial pancreas systems. Recently, many deep learning-based models have been proposed for glucose prediction, showing encouraging results in population modeling. However, due to the large amount of data required for training deep learning -based models, few studies have successfully addressed personalized modeling, which is critical to ensure safe policies in a closed-loop scheme given the high inter-patient variability. To address this concern, we propose a meta-learning-based technique for accurate personalized modeling that requires minimal data volume to personalize from its population version, needs few training iterations, and has a low risk of over-fitting. Results using the UVA/Padova simulator show that the proposed technique generalizes better and outperforms other approaches in standard and task-specific metrics, particularly for longer prediction horizons and higher degrees of distributional shifts. | |
| dc.description.funder | ANID | |
| dc.fuente.origen | WOS | |
| dc.identifier.doi | 10.1016/j.conengprac.2023.105498 | |
| dc.identifier.eissn | 1873-6939 | |
| dc.identifier.issn | 0967-0661 | |
| dc.identifier.uri | https://doi.org/10.1016/j.conengprac.2023.105498 | |
| dc.identifier.uri | https://repositorio.uc.cl/handle/11534/92268 | |
| dc.identifier.wosid | WOS:000965347200001 | |
| dc.language.iso | en | |
| dc.revista | Control engineering practice | |
| dc.rights | acceso restringido | |
| dc.subject | Deep learning | |
| dc.subject | Meta learning | |
| dc.subject | Type 1 diabetes | |
| dc.subject | Artificial pancreas | |
| dc.subject.ods | 03 Good Health and Well-being | |
| dc.subject.odspa | 03 Salud y bienestar | |
| dc.title | A meta-learning approach to personalized blood glucose prediction in type 1 diabetes | |
| dc.type | artículo | |
| dc.volumen | 135 | |
| sipa.index | WOS | |
| sipa.trazabilidad | WOS;2025-01-12 |