EUVIMEDSkopri EUVIMED
Crossref

Blood Pressure Estimation for Hemodynamic Monitoring Using Reduced Photoplethysmography Features in Intensive Care Units: Prospective Machine Learning Study

Jieun Lee, Saurabh Ashok Sujanyal, Surbhi Dadwal, Elcin Omercikoglu, Heba M Alazab, Megha Shashidhar Handral, Mohammed Naveed Shariff, Muhammed Asil Nechooli, Saravanabhavan Chandrasekar, Suganti Shivaram, Vidhya C M, Shivaram P Arunachalam and 1 more

JMIR AI · 2026-11-17 · 5 · e105057-e105057

DOI: 10.2196/105057 ↗

At a glance

Journal article in JMIR AI, published online on 2026-11-17. Written by Jieun Lee and 12 co-authors. 34 references.

AstrattDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Continuous, noninvasive blood pressure (BP) monitoring is clinically important for managing hemodynamic instability in the intensive care unit (ICU). However, current ICU practice primarily relies on invasive arterial catheterization. While this is the clinical gold standard for continuous measurement, it carries risks such as infection and thrombosis and is typically limited to select critical care settings.

Objective

To reduce reliance on invasive arterial lines, we developed an interpretable estimation framework for systolic blood pressure (SBP), mean arterial pressure (MAP), and diastolic blood pressure (DBP) from single-sensor photoplethysmography (PPG).

Methods

Synchronized PPG and arterial line 10-minute recordings from 100 patients in the ICU were analyzed. Using a hybrid feature selection strategy (RReliefF and intrinsic model–specific rankings), we reduced 201 initial features to an optimized subset of 30 core features. Model development and evaluation were designed to minimize information leakage and overfitting, incorporating nested cross-validation and patient-wise testing to assess generalizability across heterogeneous ICU populations. We developed and validated predictive models using machine learning techniques, specifically XGBoost (XGB), random forest, and support vector regression, with XGB serving as our primary model.

Results

Among the evaluated models, the Hybrid Top 30 XGB configuration provided the best balance between estimation performance, model compactness, and computational efficiency. The model achieved mean absolute errors of 8.61 mm Hg (SBP), 3.50 mm Hg (MAP), and 2.62 mm Hg (DBP). For MAP and DBP, mean difference (SD) values of −0.09 (4.54) mm Hg and −1.07 (3.51) mm Hg, respectively, satisfied the Association for the Advancement of Medical Instrumentation numerical criteria, while performance corresponded to Grade A according to the British Hypertension Society grading criteria. Although SBP exhibited greater variability, estimation performance was largely preserved using a physiologically informed subset of 30 features (approximately 15% of the original feature set). Feature importance analysis revealed distinct physiological feature patterns across SBP, MAP, and DBP estimation.

Conclusions

Interpretability analysis identified key predictors associated with wave reflection, systolic timing, low-frequency vasomotor activity, and autonomic regulation. By explicitly linking predictive features to underlying cardiovascular physiology, the proposed framework addresses a key limitation of existing black-box cuffless BP models. Ultimately, this study demonstrates that an optimized XGB framework using physiologically informed PPG features can provide accurate and computationally efficient BP estimation in ICU settings and may support the assessment of clinically relevant hemodynamic states using a single-sensor PPG platform. These findings provide a foundation for future development of more robust and generalizable interpretable BP estimation models and cuffless monitoring technologies.

Cite

APA

Lee, J., Sujanyal, S. A., Dadwal, S., Omercikoglu, E., Alazab, H. M., Handral, M. S., Shariff, M. N., Nechooli, M. A., Chandrasekar, S., Shivaram, S., M, V. C., Arunachalam, S. P., & Helgeson, S. A. (2026). Blood Pressure Estimation for Hemodynamic Monitoring Using Reduced Photoplethysmography Features in Intensive Care Units: Prospective Machine Learning Study. JMIR AI, 5, e105057-e105057. https://doi.org/10.2196/105057

Vancouver

Lee J, Sujanyal SA, Dadwal S, Omercikoglu E, Alazab HM, Handral MS, et al. Blood Pressure Estimation for Hemodynamic Monitoring Using Reduced Photoplethysmography Features in Intensive Care Units: Prospective Machine Learning Study. JMIR AI. 2026;5:e105057-e105057. doi:10.2196/105057

BibTeX
@article{Lee2026,
  author = {Lee, Jieun and Sujanyal, Saurabh Ashok and Dadwal, Surbhi and Omercikoglu, Elcin and Alazab, Heba M and Handral, Megha Shashidhar and Shariff, Mohammed Naveed and Nechooli, Muhammed Asil and Chandrasekar, Saravanabhavan and Shivaram, Suganti and M, Vidhya C and Arunachalam, Shivaram P and Helgeson, Scott A},
  title = {Blood Pressure Estimation for Hemodynamic Monitoring Using Reduced Photoplethysmography Features in Intensive Care Units: Prospective Machine Learning Study},
  journal = {JMIR AI},
  year = {2026},
  volume = {5},
  pages = {e105057--e105057},
  doi = {10.2196/105057}
}
Start for free →