Key result
PPG-based multitask learning achieves high accuracy for simultaneous blood pressure and blood glucose monitoring.
Why the study?
Simultaneous monitoring of blood glucose level and blood pressure has rarely been studied directly, and the lack of available datasets with labels for both targets presents an obstacle.
Does multi-dataset transfer multitask learning using PPG features improve the simultaneous prediction accuracy of blood glucose and blood pressure compared to baseline models?
Does multi-dataset transfer multitask learning using PPG features improve the simultaneous prediction accuracy of blood glucose and blood pressure compared to baseline models?
A novel multi-dataset transfer multitask learning approach using PPG signals enables highly accurate, simultaneous non-invasive monitoring of blood glucose and blood pressure.
The simultaneous monitoring of both blood glucose level (BGL) and blood pressure (BP) has rarely been studied directly. The exploitation of physiological interactions between them will advance the learning of either task. However, the lack of available datasets with labels of both targets presents an obstacle. Therefore, in this paper, we propose three methods for multi-dataset (MD) learning. First, we extract PPG features from three datasets: a source dataset comprising diabetes mellitus (DM) and hypertension (HTN) classes labels and two target datasets for each BP and BGL. Subsequently, we select a common merged feature set for all datasets tasks. This study experiments with the three proposed multi-dataset methods: 1) transfer learning (MD-TL) to transfer knowledge from a source task-DM and HTN single-task classifier, to a target task, BGL and BP single-task regression, respectively, 2) multitask learning (MD-MTL) of both targets via a shared two-way TL, and 3) combined TL with MTL (MD-TL-MTL) to transfer knowledge from a source multitasking classifier to the target tasks in the MD-MTL network. The final proposed MD-TL-MTL achieves an MAE±SD of 2.53 ± 3.73 for SBP, 1.47 ± 1.84 for DBP, and MAE of 1.36 for BGL. Clarke error grid analysis shows that 99.86 % of samples fall into zone A. Overall, the MD-TL-MTL improves performance in all tasks compared to baseline models. An interpretability analysis using Shapley Additive Explanations (SHAP) and permutation importance is conducted to facilitate the clinical understanding behind predictions. • Multi-dataset learning enables simultaneous blood glucose and pressure monitoring. • MD-TL-MTL integrates multitask and transfer learning for accurate BGL and BP prediction. • Achieved state-of-the-art BGL (1.36 mg/dL) and BP (2.53 mmHg) accuracy using PPG signals. • SHAP and permutation importance enhance model interpretability for clinical applications
No takes yet. Share an insight, caveat, or question.
Ali et al. (2025) studied Diabetes mellitus and hypertension. Multi-dataset transfer multitask learning (MD-TL-MTL) vs. Baseline models was evaluated on Mean absolute error (MAE) for SBP, DBP, and BGL. Multi-dataset transfer multitask learning using PPG signals achieved high accuracy for simultaneous blood glucose (MAE 1.36 mg/dL) and blood pressure (MAE 2.53 mmHg for SBP) monitoring.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: