Multi-Source Causal Invariance for Cuffless Blood Pressure Estimation Based on Photoplethysmography Signal Features
Cuffless continuous blood pressure (BP) monitoring is essential for personal health management. However, its accuracy is challenged by the diversity and heterogeneity of physiological data sources. We propose a multi-source feature selection framework based on Markov blanket theory and the concept o...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/11/3254 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850129780529168384 |
|---|---|
| author | Yiliu Xu Zhaoming He Hao Wang |
| author_facet | Yiliu Xu Zhaoming He Hao Wang |
| author_sort | Yiliu Xu |
| collection | DOAJ |
| description | Cuffless continuous blood pressure (BP) monitoring is essential for personal health management. However, its accuracy is challenged by the diversity and heterogeneity of physiological data sources. We propose a multi-source feature selection framework based on Markov blanket theory and the concept of causal invariance. We extracted 218 BP-related photoplethysmography (PPG) features from three heterogeneous datasets (differing in subject population, acquisition devices, and methods) and constructed a causal feature set using the Multi-Dataset Stable Feature Selection via Ensemble Markov Blanket (MDSFS-EMB) algorithm. BP estimation was then performed using four machine learning models. The MDSFS-EMB algorithm integrated PPFS and HITON-MB, enabling adaptability to different data scales and distribution scenarios. It employed Gaussian Copula Mutual Information, which was robust to outliers and capable of modeling nonlinear relationships. To validate the effectiveness of the selected feature set, we conducted experiments using an independent external validation dataset and explored the impact of data segmentation strategies on model prediction outcomes. The results demonstrated that the MDSFS-EMB algorithm has advantages in feature selection efficiency, prediction accuracy, and generalization capability. This study innovatively explores the causal relationships between PPG features and BP across multiple data sources, providing a clinically applicable approach for cuffless BP estimation. |
| format | Article |
| id | doaj-art-8c24691ba4dd45dfbc1af5ca3608e08b |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-8c24691ba4dd45dfbc1af5ca3608e08b2025-08-20T02:32:52ZengMDPI AGSensors1424-82202025-05-012511325410.3390/s25113254Multi-Source Causal Invariance for Cuffless Blood Pressure Estimation Based on Photoplethysmography Signal FeaturesYiliu Xu0Zhaoming He1Hao Wang2Research Center of Fluid Machinery Engineering & Technology, Jiangsu University, Zhenjiang 212013, ChinaDepartment of Mechanical Engineering, Texas Tech University, Lubbock, TX 79411, USASchool of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, ChinaCuffless continuous blood pressure (BP) monitoring is essential for personal health management. However, its accuracy is challenged by the diversity and heterogeneity of physiological data sources. We propose a multi-source feature selection framework based on Markov blanket theory and the concept of causal invariance. We extracted 218 BP-related photoplethysmography (PPG) features from three heterogeneous datasets (differing in subject population, acquisition devices, and methods) and constructed a causal feature set using the Multi-Dataset Stable Feature Selection via Ensemble Markov Blanket (MDSFS-EMB) algorithm. BP estimation was then performed using four machine learning models. The MDSFS-EMB algorithm integrated PPFS and HITON-MB, enabling adaptability to different data scales and distribution scenarios. It employed Gaussian Copula Mutual Information, which was robust to outliers and capable of modeling nonlinear relationships. To validate the effectiveness of the selected feature set, we conducted experiments using an independent external validation dataset and explored the impact of data segmentation strategies on model prediction outcomes. The results demonstrated that the MDSFS-EMB algorithm has advantages in feature selection efficiency, prediction accuracy, and generalization capability. This study innovatively explores the causal relationships between PPG features and BP across multiple data sources, providing a clinically applicable approach for cuffless BP estimation.https://www.mdpi.com/1424-8220/25/11/3254cuffless blood pressure estimationmulti-sourcefeature selectionphotoplethysmographybiomedical signals |
| spellingShingle | Yiliu Xu Zhaoming He Hao Wang Multi-Source Causal Invariance for Cuffless Blood Pressure Estimation Based on Photoplethysmography Signal Features Sensors cuffless blood pressure estimation multi-source feature selection photoplethysmography biomedical signals |
| title | Multi-Source Causal Invariance for Cuffless Blood Pressure Estimation Based on Photoplethysmography Signal Features |
| title_full | Multi-Source Causal Invariance for Cuffless Blood Pressure Estimation Based on Photoplethysmography Signal Features |
| title_fullStr | Multi-Source Causal Invariance for Cuffless Blood Pressure Estimation Based on Photoplethysmography Signal Features |
| title_full_unstemmed | Multi-Source Causal Invariance for Cuffless Blood Pressure Estimation Based on Photoplethysmography Signal Features |
| title_short | Multi-Source Causal Invariance for Cuffless Blood Pressure Estimation Based on Photoplethysmography Signal Features |
| title_sort | multi source causal invariance for cuffless blood pressure estimation based on photoplethysmography signal features |
| topic | cuffless blood pressure estimation multi-source feature selection photoplethysmography biomedical signals |
| url | https://www.mdpi.com/1424-8220/25/11/3254 |
| work_keys_str_mv | AT yiliuxu multisourcecausalinvarianceforcufflessbloodpressureestimationbasedonphotoplethysmographysignalfeatures AT zhaominghe multisourcecausalinvarianceforcufflessbloodpressureestimationbasedonphotoplethysmographysignalfeatures AT haowang multisourcecausalinvarianceforcufflessbloodpressureestimationbasedonphotoplethysmographysignalfeatures |