Benchmarking and Enhancing PPG-Based Cuffless Blood Pressure Estimation Methods
Preprint
Abstract
Cuffless blood pressure screening based on easily acquired photoplethysmography (PPG) signals offers a practical pathway toward scalable cardiovascular health assessment. Despite rapid progress, existing PPG-based blood pressure estimation models have not consistently achieved the established clinical numerical limits such as AAMI/ISO 81060-2, and prior evaluations often lack the rigorous experimental controls necessary for valid clinical assessment. Moreover, the publicly available datasets commonly used are heterogeneous and lack physiologically controlled conditions for fair benchmarking. To enable fair benchmarking under physiologically controlled conditions, we created a standardized benchmarking subset NBPDB comprising 101,453 high-quality PPG segments from 1,103 healthy adults, derived from MIMIC-III and VitalDB. Using this dataset, we systematically benchmarked several state-of-the-art PPG-based models. The results showed that none of the evaluated models met the AAMI/ISO 81060-2 accuracy requirements (mean error $<$ 5 mmHg and standard deviation $<$ 8 mmHg). To improve model accuracy, we modified these models and added patient demographic data such as age, sex, and body mass index as additional inputs. Our modifications consistently improved performance across all models. In particular, the MInception model reduced error by 23\% after adding the demographic data and yielded mean absolute errors of 4.75 mmHg (SBP) and 2.90 mmHg (DBP), achieves accuracy comparable to the numerical limits defined by AAMI/ISO accuracy standards. Our results show that existing PPG-based BP estimation models lack clinical practicality under standardized conditions, while incorporating demographic information markedly improves their accuracy and physiological validity.
Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Generalizable deep learning for photoplethysmography-based blood pressure estimation – A Benchmarking StudyMachine Learning: Health, 2025
- Examining the challenges of blood pressure estimation via photoplethysmogramScientific Reports, 2024
- A review: Blood pressure monitoring based on PPG and circadian rhythmAPL Bioengineering, 2024
- Interference source-based quality assessment method for postauricular photoplethysmography signalsBiomedical Signal Processing and Control, 2023
- VitalDB, a high-fidelity multi-parameter vital signs database in surgical patientsScientific Data, 2022
- MLP-BP: A novel framework for cuffless blood pressure measurement with PPG and ECG signals based on MLP-Mixer neural networksBiomedical Signal Processing and Control, 2022
- Deep learning models for cuffless blood pressure monitoring from PPG signals using attention mechanismBiomedical Signal Processing and Control, 2021
- Effect of Systolic and Diastolic Blood Pressure on Cardiovascular OutcomesNew England Journal of Medicine, 2019
- The use of photoplethysmography for assessing hypertensionnpj Digital Medicine, 2019
- MIMIC-III, a freely accessible critical care databaseScientific Data, 2016