Development and Prospective Validation of Predictive Model for Early Hemodynamic Deterioration in Critical Care: A Multicenter Study
Nagori, A.; Singh, P.; Firdos, S.; Devadiga, A.; Vats, V.; Gupta, A.; Bandhey, H.; Ailavadi, P.; Awasthi, R.; Narotam, N.; Mishra, A.; Lodha, R.; Sethi, T.
Show abstract
High-frequency physiological monitoring in ICUs can identify impending deterioration hours before clinical recognition yet extracting reliable early-warning signals from noisy vital-sign streams remains challenging. We present SIgnose, an interpretable prediction framework for early detection of abnormal shock index (SI), built from routinely monitored vital signs using physiologic variability and nonlinear time-series features. SIgnose was developed on the eICU Collaborative Research Database and externally validated on the MIMIC-III adult database and a pediatric SafeICU cohort (AIIMS New Delhi), with additional prospective validation in the pediatric ICU. We benchmarked three representation strategies: (i) engineered physiologic variability and nonlinear time-series features, (ii) deep learning, and (iii) Llama-3.1-8B embeddings with low-rank adaptation. Physiologic variability features consistently demonstrated superior cross-cohort generalization. The final model used 3,970 features from five vital signs to predict abnormal SI up to 8 hours ahead, achieving AUROC 0.861 (95% CI 0.859-0.863) and AUPRC 0.927 (95% CI 0.925-0.929) on eICU. External validation yielded AUROC 0.870 (95% CI 0.863-0.876) and AUPRC 0.935 (95% CI 0.930-0.940) on MIMIC-III, and AUROC 0.875 (95% CI 0.863-0.888) and AUPRC 0.915 (95% CI 0.898-0.930) on SafeICU; prospective pediatric validation (n = 88) achieved AUROC 0.885 (95% CI 0.868-0.902) and AUPRC 0.911 (95% CI 0.882-0.936). SHAP interpretability analysis identified heart rate variability, respiratory trend dynamics, and multi-scale blood pressure variability as key early-warning signatures. These findings establish SIgnose as a reproducible, low-compute, early-warning framework and demonstrate that physiologic variability features provide robust, generalizable representations for early deterioration detection across adult and pediatric critical care.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Identification of physiological adverse events using continuous vital signs monitoring during paediatric critical care transport: a novel data-driven approach 95%
- Generalizability Challenges of Mortality Risk Prediction Models: A Retrospective Analysis on a Multi-center Database 94%
- Identification of predictive patient characteristics for assessing the probability of COVID-19 in-hospital mortality 93%
Similar papers in this journal
- A comprehensive ML-based Respiratory Monitoring System for Physiological Monitoring & Resource Planning in the ICU 95%
- Development and Prospective Implementation of a Large Language Model based System for Early Sepsis Prediction 95%
- GLUCOSE: A Distributional Reinforcement Learning Model for Optimal Glucose Control After Cardiac Surgery 94%
Similar papers in this journal
- Predicting bloodstream infection outcome using machine learning 96%
- Evaluation of Domain Generalization and Adaptation on Improving Model Robustness to Temporal Dataset Shift in Clinical Medicine 95%
- Imputation of PaO2 from SpO2 values from the MIMIC-III Critical Care Database Using Machine-Learning Based Algorithms 95%
Similar papers in this journal
- Prospective validation of clinical deterioration predictive models prior to intensive care unit transfer among patients admitted to acute care cardiology wards 94%
- Age Prediction From 12-lead Electrocardiograms Using Deep Learning: A Comparison of Four Models on a Contemporary, Freely Available Dataset 93%
- External Validation Of A Novel Digital Signature In Continuous Cardiorespiratory Monitoring To Detect Early Respiratory Deterioration Of ICU Patients 92%
Similar papers in this journal
- SWIFT: A Deep Learning Approach to Prediction of Hypoxemic Events in Critically-Ill Patients Using SpO 2 Waveform Prediction 96%
- Contrasting factors associated with COVID-19-related ICU admission and death outcomes in hospitalised patients by means of Shapley values 93%
- Predicting the causative pathogen among children with pneumonia using a causal Bayesian network 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.