Blood Pressure Estimation from PPG: A Comparative Study of Direct and ECG-Mediated Deep Learning Pipelines

2026-07-25

AI Summary

This study addresses the accuracy limitations of cuffless wearable devices for continuous blood pressure (BP) monitoring by challenging the conventional paradigm that relies on electrocardiography (ECG) as an intermediate representation. Leveraging 1.74 million segments of multimodal physiological signals from the MIMIC-III database, the work systematically compares two deep learning approaches: direct prediction of BP from photoplethysmography (PPG) versus ECG-mediated estimation. For the first time through large-scale data analysis, it demonstrates that PPG exhibits significantly stronger correlation with arterial blood pressure than ECG. The end-to-end PPG-to-BP model achieves superior performance, with mean absolute errors of 4.82 mmHg for systolic and 4.31 mmHg for diastolic BP—meeting Grade A accuracy according to the British Hypertension Society protocol—outperforming all ECG-mediated methods, which only attain Grade B. This finding establishes a new, simplified paradigm for wearable BP monitoring.

Abstract

Continuous cuffless blood pressure (BP) monitoring is essential for connected health systems and wearable devices, enabling early detection, longitudinal tracking, and personalized management of cardiovascular disease. Many prior approaches attempt to estimate BP indirectly by reconstructing electrocardiography (ECG) from photoplethysmography (PPG), assuming ECG provides a stronger physiological link to BP. However, ECG sensing is less accessible in wearable settings and may introduce unnecessary complexity. In this work, we first perform a large-scale physiological correlation analysis on the MIMIC-III waveform database, revealing that PPG exhibits substantially stronger coupling with arterial blood pressure (ABP) ($|r|=0.247$, $p<0.001$) than ECG does ($r=0.018$, $p=0.187$), challenging the assumption that ECG provides a superior intermediate representation. Motivated by this insight, we conduct a systematic comparison between direct PPG-to-BP prediction and ECG-mediated pipelines using multiple state-of-the-art deep learning models. Across 1.74M segments from 3,127 patients, direct PPG-to-BP prediction achieves British Hypertension Society Grade A performance ($\mathrm{MAE}_{\mathrm{SBP}} = 4.82 mmHg$, $\mathrm{MAE}_{\mathrm{DBP}} = 4.31 mmHg$), outperforming all ECG-mediated approaches, which achieve only Grade B accuracy. Our findings suggest that accurate continuous BP monitoring can be achieved directly from wearable PPG signals, enabling simpler, more efficient pipelines for real-world connected health systems.

Problem

• blood pressure estimation
• PPG
• cuffless monitoring
• wearable devices
• ECG-mediated

Innovation

• PPG-based blood pressure estimation
• ECG-mediated pipeline
• deep learning
• cuffless BP monitoring
• physiological correlation analysis