Benchmarking and Enhancing PPG-Based Cuffless Blood Pressure Estimation Methods

2026-02-04

AI Summary

This study addresses the limitations of current cuffless blood pressure estimation algorithms based on photoplethysmography (PPG), which often fail to meet the AAMI/ISO 81060-2 clinical accuracy standards under standardized, physiologically controlled conditions and lack a fair evaluation benchmark. To this end, we construct NBPDB, a standardized benchmark dataset comprising 101,453 high-quality PPG segments by integrating MIMIC-III and VitalDB, and present the first systematic evaluation of multiple deep learning models under physiologically controlled settings. By incorporating demographic features—such as age, sex, and BMI—into an enhanced MInception architecture, our approach significantly improves performance, achieving mean absolute errors of 4.75 mmHg for systolic and 2.90 mmHg for diastolic blood pressure, thereby meeting clinical standards and reducing error by 23% compared to baseline models. This demonstrates the critical role of multimodal modeling in enhancing physiological plausibility and clinical applicability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Large-scale security measurements

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.

Problem

• cuffless blood pressure estimation
• photoplethysmography
• clinical accuracy
• benchmarking
• AAMI/ISO standard

Innovation

• cuffless blood pressure estimation
• photoplethysmography (PPG)
• standardized benchmarking
• demographic information fusion
• MInception model