Multimodal Machine Learning for Intradialytic Hypotension Prediction Using Noncontact Radar-Derived Vital-Sign Summaries: A Single-Center Internal Validation Study
IEEE Journal of Translational Engineering in Health and Medicine · 2026 · 14 · 460-473
DOI: 10.1109/jtehm.2026.3744253 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Journal of Translational Engineering in Health and Medicine, 2026. Verfasst von Chia-Te Liao und 13 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council of Taiwan, Taipei Medical University, Taipei Medical University–Shuang Ho Hospital.
Abstract (Originalsprache)
Background
Intermittent blood-pressure (BP) and hemodialysis (HD) machine measurements limit continuously updated assessment of the intradialytic hypotension (IDH) risk. We developed and internally validated a multimodal machine-learning framework integrating noncontact radar-derived vital-sign summaries with HD machine parameters and demographics for 10-min-ahead IDH prediction.
Methods
This single-center study included 233 HD patients, 6,147 sessions, and 132,608 observation windows. Among these, 375 windows (0.28%) preceded clinically documented IDH within 10 min, corresponding to 325 episodes in 46 patients. Models were evaluated using patient-wise nested five-fold cross-validation. The primary early-fusion model combined demographic, HD machine, and radar-derived heart- and respiratory-rate features. Regression and permutation feature importance analyses were performed to evaluate the clinical associations and identify key contributors.
Results
The multimodal early-fusion model achieved an area under the receiver operating characteristic curve (AUROC) of 86.62% (95% confidence interval, 82.19%–89.49%), area under the precision-recall curve (AUPRC) of 3.33% (2.23%–6.09%), recall of 78.72% (67.81%–85.31%), specificity of 78.73% (72.90%–83.37%), and precision of 1.09% (0.71%–1.44%). It detected 260 of 325 IDH episodes (80.00%) with 4.53 false-positive prediction windows per session. A clinical baseline using recent systolic blood pressure and ultrafiltration-rate information achieved a higher AUPRC (4.21%). HD machine features accounted for most predictive information; incremental contributions from radar and demographics were modest and statistically uncertain.
Conclusions
Multimodal 10-min-ahead IDH risk estimation was feasible under internal validation, although most short-term predictive information was derived from HD machine parameters. Further work is needed to establish the incremental clinical value of continuous radar-derived monitoring.
Förderung
- National Science and Technology Council of Taiwan
- Taipei Medical University
- Taipei Medical University–Shuang Ho Hospital
Zitieren
APA
Liao, C., Liu, I., Liu, W., Chen, Y., Chen, Y., Huang, Y., Yeh, S., Cai, Z., Ho, S., Majumdar, A., Lee, K., Kang, J., Wu, M., & Tsai, C. (2026). Multimodal Machine Learning for Intradialytic Hypotension Prediction Using Noncontact Radar-Derived Vital-Sign Summaries: A Single-Center Internal Validation Study. IEEE Journal of Translational Engineering in Health and Medicine, 14, 460-473. https://doi.org/10.1109/jtehm.2026.3744253
Vancouver
Liao C, Liu I, Liu W, Chen Y, Chen Y, Huang Y, et al. Multimodal Machine Learning for Intradialytic Hypotension Prediction Using Noncontact Radar-Derived Vital-Sign Summaries: A Single-Center Internal Validation Study. IEEE Journal of Translational Engineering in Health and Medicine. 2026;14:460-473. doi:10.1109/jtehm.2026.3744253
BibTeX
@article{Liao2026,
author = {Liao, Chia-Te and Liu, I-Jung and Liu, Wen-Te and Chen, Ying-Ying and Chen, Yen-Ling and Huang, Yu-Wen and Yeh, Shang-Min and Cai, Zong-Lin and Ho, Shu-Shiuan and Majumdar, Arnab and Lee, Kang-Yun and Kang, Jiunn-Horng and Wu, Mai-Szu and Tsai, Cheng-Yu},
title = {Multimodal Machine Learning for Intradialytic Hypotension Prediction Using Noncontact Radar-Derived Vital-Sign Summaries: A Single-Center Internal Validation Study},
journal = {IEEE Journal of Translational Engineering in Health and Medicine},
year = {2026},
volume = {14},
pages = {460--473},
doi = {10.1109/jtehm.2026.3744253}
}
EUVIMED