PMB-NN: Physiology-Centred Hybrid AI for Personalized Hemodynamic Monitoring from Photoplethysmography

TL;DR

This paper introduces PMB-NN, a hybrid AI model that combines deep learning with physiological models to accurately and interpretably monitor blood pressure and hemodynamic parameters using PPG data.

Contribution

The paper presents a novel physiology-centered hybrid AI model that unifies deep learning with Windkessel-based physiological constraints for personalized blood pressure estimation.

Findings

PMB-NN achieves systolic BP MAE of 7.2 mmHg, comparable to deep learning models.

PMB-NN has lower diastolic BP MAE (3.9 mmHg) than deep learning benchmarks.

The model accurately estimates resistance and compliance, enhancing interpretability.

Abstract

Continuous monitoring of blood pressure (BP) and hemodynamic parameters such as peripheral resistance (R) and arterial compliance (C) are critical for early vascular dysfunction detection. While photoplethysmography (PPG) wearables has gained popularity, existing data-driven methods for BP estimation lack interpretability. We advanced our previously proposed physiology-centered hybrid AI method-Physiological Model-Based Neural Network (PMB-NN)-in blood pressure estimation, that unifies deep learning with a 2-element Windkessel based model parameterized by R and C acting as physics constraints. The PMB-NN model was trained in a subject-specific manner using PPG-derived timing features, while demographic information was used to infer an intermediate variable: cardiac output. We validated the model on 10 healthy adults performing static and cycling activities across two days for model's day-to-day robustness, benchmarked against deep learning (DL) models (FCNN, CNN-LSTM, Transformer) and standalone Windkessel based physiological model (PM). Validation was conducted on three perspectives: accuracy, interpretability and plausibility. PMB-NN achieved systolic BP accuracy (MAE: 7.2 mmHg) comparable to DL benchmarks, diastolic performance (MAE: 3.9 mmHg) lower than DL models. However, PMB-NN exhibited higher physiological plausibility than both DL baselines and PM, suggesting that the hybrid architecture unifies and enhances the respective merits of physiological principles and data-driven techniques. Beyond BP, PMB-NN identified R (ME: 0.15 mmHg$\cdot$s/ml) and C (ME: -0.35 ml/mmHg) during training with accuracy similar to PM, demonstrating that the embedded physiological constraints confer interpretability to the hybrid AI framework. These results position PMB-NN as a balanced, physiologically grounded alternative to purely data-driven approaches for daily hemodynamic monitoring.