Machine Learning Prediction of Mean Arterial Pressure from the Photoplethysmography Waveform During Hemorrhagic Shock and Fluid Resuscitation

Gonzalez, Jose M.; Vega, Saul J.; Mosely, Shakayla V.; Pascua, Stefany V.; Rodgers, Tina M.; Snider, Eric J.

doi:10.3390/s25165035

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Machine Learning Prediction of Mean Arterial Pressure from the Photoplethysmography Waveform During Hemorrhagic Shock and Fluid Resuscitation

by

Jose M. Gonzalez

,

Saul J. Vega

,

Shakayla V. Mosely

,

Stefany V. Pascua

,

Tina M. Rodgers

and

Eric J. Snider

^*

U.S. Army Institute of Surgical Research, JBSA Fort Sam Houston, San Antonio, TX 78234, USA

^*

Author to whom correspondence should be addressed.

Sensors 2025, 25(16), 5035; https://doi.org/10.3390/s25165035

Submission received: 4 July 2025 / Revised: 5 August 2025 / Accepted: 11 August 2025 / Published: 13 August 2025

(This article belongs to the Special Issue AI on Biomedical Signal Sensing and Processing for Health Monitoring)

Download

Browse Figure

Review Reports Versions Notes

Abstract

We aimed to evaluate the non-invasive photoplethysmography waveform as a means to predict mean arterial pressure using artificial intelligence models. This was performed using datasets captured in large animal hemorrhage and resuscitation studies. An initial deep learning model trained using a subset of large animal data and was then evaluated for real-time blood pressure prediction. With the successful proof-of-concept experiment, we further tested different feature extraction approaches as well as different machine learning and deep learning methodologies to examine how various combinations of these methods can improve the accuracy of mean arterial pressure predictions from a non-invasive photoplethysmography sensor. Different combinations of feature extraction and artificial intelligence models successfully predicted mean arterial pressure throughout the study. Overall, manual feature extraction fed into a long short-term memory network tracked the mean arterial pressure through hemorrhage and resuscitation with the highest accuracy.

Keywords: deep learning; feature extraction; hemorrhage; machine learning; resuscitation

Graphical Abstract

Share and Cite

MDPI and ACS Style

Gonzalez, J.M.; Vega, S.J.; Mosely, S.V.; Pascua, S.V.; Rodgers, T.M.; Snider, E.J. Machine Learning Prediction of Mean Arterial Pressure from the Photoplethysmography Waveform During Hemorrhagic Shock and Fluid Resuscitation. Sensors 2025, 25, 5035. https://doi.org/10.3390/s25165035

AMA Style

Gonzalez JM, Vega SJ, Mosely SV, Pascua SV, Rodgers TM, Snider EJ. Machine Learning Prediction of Mean Arterial Pressure from the Photoplethysmography Waveform During Hemorrhagic Shock and Fluid Resuscitation. Sensors. 2025; 25(16):5035. https://doi.org/10.3390/s25165035

Chicago/Turabian Style

Gonzalez, Jose M., Saul J. Vega, Shakayla V. Mosely, Stefany V. Pascua, Tina M. Rodgers, and Eric J. Snider. 2025. "Machine Learning Prediction of Mean Arterial Pressure from the Photoplethysmography Waveform During Hemorrhagic Shock and Fluid Resuscitation" Sensors 25, no. 16: 5035. https://doi.org/10.3390/s25165035

APA Style

Gonzalez, J. M., Vega, S. J., Mosely, S. V., Pascua, S. V., Rodgers, T. M., & Snider, E. J. (2025). Machine Learning Prediction of Mean Arterial Pressure from the Photoplethysmography Waveform During Hemorrhagic Shock and Fluid Resuscitation. Sensors, 25(16), 5035. https://doi.org/10.3390/s25165035

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Machine Learning Prediction of Mean Arterial Pressure from the Photoplethysmography Waveform During Hemorrhagic Shock and Fluid Resuscitation

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI