Subject-wise model generalization through pooling and patching for regression: Application on non-invasive systolic blood pressure estimation

• Published in: Computers in biology and medicine Vol. 151; no. Pt A; p. 106299
• Main Authors: Mohammed, Hazem, Wang, Kai, Wu, Hao, Wang, Guoxing
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.12.2022; Elsevier Limited
• Subjects: Accuracy; Algorithms; Blood Pressure; Complexity; Datasets; EKG; Electrocardiography; Errors; Generalization; Humans; Internal Medicine; Machine learning; Medical equipment; Medicine; Model testing; Other; Overfitting; Photoplethysmography; Regression; Regression models; Segments; Systolic blood pressure; Training; Systolic blood pressure; Machine learning; Regression; Electrocardiography; Photoplethysmography; Generalization; Overfitting

Subject-wise modeling using machine learning is useful in many applications requiring low error and complexity, such as wearable medical devices. However, regression accuracy depends highly on the data available to train the model and the model’s generalization ability. Adversely, the prediction err...