Expert Augmented Prediction of Circulatory and Respiratory Instability from High Resolution Vital Signs
7 affiliations
- 1Department of Critical Care Medicine, the First Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China
- 2Guangdong Clinical Research Center for Critical Care Medicine, Guangzhou, Guangdong, China
- 3Shenzhen Mindray Bio-Medical Electronics Co., Ltd., Shenzhen, Guangdong, China
- 4Institute of Precision Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
- 5School of Computer Science, Wuhan University, Wuhan, China
- 6British Heart Foundation Cardiovascular Epidemiology Unit, Department of Public Health and Primary Care, University of Cambridge, Cambridge, UK
- 7Division of Pulmonary, Allergy, Critical Care & Sleep Medicine, Emory University School of Medicine, Atlanta, GA USA
Abstract
Timely detection of circulatory and respiratory instability (CRI) is critical in intensive care units (ICUs), yet existing early warning systems often rely on single-parameter indices that underutilize continuous vital-sign data or on delayed, difficult-to-interpret multimodal clinical data. Leveraging routinely collected high-frequency vital-sign monitoring, we developed an interpretable, expert-augmented early warning system based on 1-second-resolution heart rate, blood pressure, respiratory rate, and oxygen saturation data. Machine‑learning models were trained on 627,958 h of continuous vital‑sign data from 1702 ICU patients at the First Affiliated Hospital of Sun Yat‑sen University and externally validated in the MIMIC‑III cohort. Models incorporating trend-based, reference, and statistical features derived from vital-sign trajectories achieved strong predictive performance (AUROC > 0.8) in both internal and external validation, outperforming conventional single-parameter indices and achieving performance comparable to models incorporating laboratory and demographic variables. Increasing temporal resolution improved predictive accuracy, with trend-based features contributing most strongly to model predictions. To improve clinical interpretability, tree-based models were transformed into physiologically meaningful decision rules and refined through expert-augmented learning, resulting in the Expert-Augmented Early Warning System (EAEWS). EAEWS generated accurate, low-frequency alerts with transparent explanations aligned with bedside monitoring, and may provide a scalable framework for real-time CRI detection in ICUs.
Related
- Recognizing Nocturnal Respiratory Instability as a Key Component of Heart Failure Assessment
- Multidomain Polysomnographic Abnormalities in Cervical Dystonia: REM Suppression, Respiratory Instability, and Sensorimotor Dysregulation
- MDM-DDI: a drug–drug interaction prediction framework integrating multi-dimensional molecular features and memory-augmented networks
- Development and Internal Validation of a Prediction Model Incorporating Respiratory Muscle Function for CAT Score Deterioration in Stable COPD
- A deep learning-based model combining quantitative parameters of initial chest computed tomography and clinical variables for the prediction of posttraumatic acute respiratory distress syndrome
BibTeX
@article{wang2026expert,
title = {{Expert Augmented Prediction of Circulatory and Respiratory Instability from High Resolution Vital Signs}},
author = {Luhao Wang and Bin Gu and Yao Nie and Xingliang Jin and Chuanxi Chen and Fei Pei and Guangzhen Li and Ke Xiao and Xu Huang and Jin Liu and Hao Yan and Yu Xu and Sivasubramanium V. Bhavani and Jianfeng Wu and Xiangdong Guan},
journal = {NPJ Digital Medicine},
year = {2026},
month = jul,
doi = {10.1038/s41746-026-02993-9},
url = {https://doi.org/10.1038/s41746-026-02993-9},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Expert Augmented Prediction of Circulatory and Respiratory Instability from High Resolution Vital Signs
AU - Luhao Wang
AU - Bin Gu
AU - Yao Nie
AU - Xingliang Jin
AU - Chuanxi Chen
AU - Fei Pei
AU - Guangzhen Li
AU - Ke Xiao
AU - Xu Huang
AU - Jin Liu
AU - Hao Yan
AU - Yu Xu
AU - Sivasubramanium V. Bhavani
AU - Jianfeng Wu
AU - Xiangdong Guan
PY - 2026
DA - 2026/07/13
JO - NPJ Digital Medicine
DO - 10.1038/s41746-026-02993-9
UR - https://doi.org/10.1038/s41746-026-02993-9
AB - Timely detection of circulatory and respiratory instability (CRI) is critical in intensive care units (ICUs), yet existing early warning systems often rely on single-parameter indices that underutilize continuous vital-sign data or on delayed, difficult-to-interpret multimodal clinical data. Leveraging routinely collected high-frequency vital-sign monitoring, we developed an interpretable, expert-augmented early warning system based on 1-second-resolution heart rate, blood pressure, respiratory rate, and oxygen saturation data. Machine‑learning models were trained on 627,958 h of continuous vital‑sign data from 1702 ICU patients at the First Affiliated Hospital of Sun Yat‑sen University and externally validated in the MIMIC‑III cohort. Models incorporating trend-based, reference, and statistical features derived from vital-sign trajectories achieved strong predictive performance (AUROC > 0.8) in both internal and external validation, outperforming conventional single-parameter indices and achieving performance comparable to models incorporating laboratory and demographic variables. Increasing temporal resolution improved predictive accuracy, with trend-based features contributing most strongly to model predictions. To improve clinical interpretability, tree-based models were transformed into physiologically meaningful decision rules and refined through expert-augmented learning, resulting in the Expert-Augmented Early Warning System (EAEWS). EAEWS generated accurate, low-frequency alerts with transparent explanations aligned with bedside monitoring, and may provide a scalable framework for real-time CRI detection in ICUs.
SN - 2398-6352
ER -