A deep attention-based encoder for the prediction of type 2 diabetes longitudinal outcomes from routinely collected health care data
Recent evidence indicates that Type 2 Diabetes Mellitus (T2DM) is a complex and highly heterogeneous disease involving various pathophysiological and genetic pathways, which presents clinicians with challenges in disease management. While deep learning models have made significant progress in helpin...
| Autores: | , , , , , , , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2025 |
| País: | España |
| Institución: | Institut d’Investigació Biomèdica Sant Pau (IIB Sant Pau) |
| Repositorio: | r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pau |
| OAI Identifier: | oai:iibsantpau.fundanetsuite.com:p19389 |
| Acceso en línea: | https://iibsantpau.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=19389 |
| Access Level: | acceso abierto |
| Palabra clave: | Deep learning Transformer Type 2 diabetes Diabetes complications Electronic health records |
| Sumario: | Recent evidence indicates that Type 2 Diabetes Mellitus (T2DM) is a complex and highly heterogeneous disease involving various pathophysiological and genetic pathways, which presents clinicians with challenges in disease management. While deep learning models have made significant progress in helping practitioners manage T2DM treatments, several important limitations persist. In this paper we propose DARE, a model based on the transformer encoder, designed for analyzing longitudinal heterogeneous diabetes data. The model can be easily fine-tuned for various clinical prediction tasks, enabling a computational approach to assist clinicians in the management of the disease. We trained DARE using data from over 200,000 diabetic subjects from the primary healthcare SIDIAP database, which includes diagnosis and drug codes, along with various clinical and analytical measurements. After an unsupervised pre-training phase, we fine-tuned the model for predicting three specific clinical outcomes: i) occurrence of comorbidity, ii) achievement of target glycemic control (defined as glycated hemoglobin <7%) and iii) changes in glucose-lowering treatment. In cross-validation, the embedding vectors generated by DARE outperformed those from baseline models (comorbidities prediction task AUC = 0.88, treatment prediction task AUC = 0.91, HbA1c target prediction task AUC = 0.82). Our findings suggest that attention-based encoders improve results with respect to different deep learning and classical baseline models when used to predict different clinical relevant outcomes from T2DM longitudinal data. |
|---|