# An Ensemble-Based AI Approach for Continuous Blood Pressure Estimation in Health Monitoring Applications

## TL;DR

This paper introduces an AI framework that estimates continuous blood pressure using PPG signals and demographic data, achieving high accuracy for cardiovascular health monitoring.

## Contribution

A novel ensemble AI framework combining Tab-Transformer and gradient boosting models for accurate, non-invasive blood pressure estimation.

## Key findings

- The model achieved MAE of 3.87 mmHg for systolic and 2.50 mmHg for diastolic blood pressure.
- The framework meets BHS Grade A and AAMI standards for accuracy in blood pressure monitoring.
- Incorporating demographic data improved model robustness across diverse populations.

## Abstract

Continuous blood pressure (BP) monitoring provides valuable insight into the body’s dynamic cardiovascular regulation across various physiological states such as physical activity, emotional stress, postural changes, and sleep. Continuous BP monitoring captures different variations in systolic and diastolic pressures, reflecting autonomic nervous system activity, vascular compliance, and circadian rhythms. This enables early identification of abnormal BP trends and allows for timely diagnosis and interventions to reduce the risk of cardiovascular diseases (CVDs) such as hypertension, stroke, heart failure, and chronic kidney disease as well as chronic stress or anxiety disorders. To facilitate continuous BP monitoring, we propose an AI-powered estimation framework. The proposed framework first uses an expert-driven feature engineering approach that systematically extracts physiological features from photoplethysmogram (PPG)-based arterial pulse waveforms (APWs). Extracted features include pulse rate, ascending/descending times, pulse width, slopes, intensity variations, and waveform areas. These features are fused with demographic data (age, gender, height, weight, BMI) to enhance model robustness and accuracy across diverse populations. The framework utilizes a Tab-Transformer to learn rich feature embeddings, which are then processed through an ensemble machine learning framework consisting of CatBoost, XGBoost, and LightGBM. Evaluated on a dataset of 1000 subjects, the model achieves Mean Absolute Errors (MAE) of 3.87 mmHg (SBP) and 2.50 mmHg (DBP), meeting British Hypertension Society (BHS) Grade A and Association for the Advancement of Medical Instrumentation (AAMI) standards. The proposed architecture advances non-invasive, AI-driven solutions for dynamic cardiovascular health monitoring.