Related Experiment Video
Updated: Aug 5, 2026

Simultaneous Electrocardiography Recording and Invasive Blood Pressure Measurement in Rats
Published on: January 31, 2019
A Dual-Output Physiology-Informed Neural Network Architecture for Continuous Cuffless Blood Pressure Waveform
Zaineb Aloui1,2, Cederick Landry1,2
1Department of Mechanical Engineering, Université de Sherbrooke, Sherbrooke, QC Canada.
This study presents a new AI model that accurately estimates blood pressure (BP) waveforms using ECG and PPG signals. The physiology-informed approach improves continuous BP monitoring accuracy with less data.
Area of Science:
- Biomedical Engineering
- Artificial Intelligence in Healthcare
- Physiological Monitoring
Background:
- Continuous blood pressure (BP) monitoring is crucial for cardiovascular health management.
- Existing cuffless BP estimation methods often lack physiological accuracy or require extensive training data.
- Subject-specific, data-driven approaches are needed for reliable BP waveform estimation.
Purpose of the Study:
- To introduce and evaluate a novel subject-specific, physiology-informed neural network (NARXphysio) for accurate full blood pressure (BP) waveform estimation.
- To compare the performance of the NARXphysio model against traditional NARX models using reduced training data.
- To assess the model's ability to ensure internal physiological consistency and provide interpretable parameters.
Main Methods:
- Development of a nonlinear autoregressive model with exogenous inputs (NARX) implemented via artificial neural networks.
- Training models on subject-specific electrocardiography (ECG) and photoplethysmography (PPG) signals.
- Incorporation of a personalized four-parameter BP-PPG sigmoidal layer into the NARXphysio model, utilizing a dual-output loss function for simultaneous BP and PPG waveform estimation.
Main Results:
- The physiology-informed NARXphysio model, trained on 15 minutes of data, maintained accurate BP estimation comparable to a reference NARX model trained on 30 minutes.
- The NARXphysio model demonstrated internal physiological consistency by embedding BP-PPG physiology directly into the training process.
- Physiologically interpretable parameters, such as arterial compliance and PPG contact pressure, were derived from the sigmoidal layer.
Conclusions:
- The NARXphysio model enables effective personalization of cuffless BP waveform estimation with limited training data.
- This approach has the potential to significantly improve the reliability and clinical relevance of continuous cuffless BP monitoring.
- The integration of physiological principles into AI models offers a promising direction for advancing medical diagnostics.
Related Concept Videos
Equipments Used To Measure Blood Pressure
This invasive approach involves cannulating a peripheral artery. During each cardiac contraction, pressure generates mechanical motion within the catheter, transmitted through rigid, fluid-filled tubing to a transducer. This transducer converts mechanical motion into electrical signals displayed as waveforms on a monitor. An automatic flushing system prevents blood backflow. Due to the potential risk of unexpected arterial blood loss, this method is primarily used in intensive...
Sites for measuring blood pressure
The Brachial Artery: Primary Site for Blood Pressure Measurement
Assessing Blood pressure using a doppler ultrasound
Pre-Procedural Guidelines for Doppler Ultrasound Blood Pressure Assessment:
Preparation of Equipment:
Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac muscle...
Special considerations while measuring blood pressure
Monitoring Both Arms:
Monitoring BP in both arms during the initial assessment is advisable, as the systolic value may differ by five to ten mm Hg between arms. For subsequent BP assessments, use the arm with the higher reading.
Pre-Procedural Guidelines for Assessing Blood Pressure
