PhysioFusion: A Multi-Modal Ensemble using Static Preoperative Variables and Time Series Intraoperative Data to Predict Adverse Events Following Cardiothoracic Surgery
- 1Roux Institute, Northeastern University
Abstract
Accurate prediction of adverse events in the intensive care unit (ICU) following cardiothoracic surgery is crucial for timely interventions, improving patient outcomes and optimizing value in healthcare. By leveraging advanced machine learning techniques, this study demonstrates the transformative potential of predictive analytics to enhance postoperative care using a dataset from the Society of Thoracic Surgeons (STS) database [4] and time-series intraoperative data. We developed a multi-modal late fusion approach integrating static patient variables with intraoperative time-series data, utilizing an ensemble of models including residual neural networks for static features, CNN and Bidirectional GRU for time-series processing, XGBoost, logistic regression, SVM and Gradient Boosting. Through five-fold cross-validation, our ensemble model with balanced threshold selection achieved an AUC of 0.87, sensitivity of 0.76, specificity of 0.83, PPV of 0.40, and NPV of 0.96. Preoperative heart failure, IABP insertion, cardiopulmonary bypass (CPB) duration and white blood cell (WBC) count emerged as key predictors. Training the same pipeline on each modality separately showed that the static registry variables alone reached the same AUC of 0.87, and that the intraoperative signals alone reached 0.83, so on this cohort the two modalities act as substitutes rather than complements and fusion changed the sensitivity and precision trade-off rather than the amount of separable signal. A per-signal ablation found that no individual monitoring channel was load bearing, with mean arterial pressure and central venous pressure the least substitutable. This balanced approach optimizes the trade-off between sensitivity and specificity, providing a screening tool with high negative predictive value for monitoring high-risk patients, and the modality comparison indicates that comparable performance is attainable at sites holding registry data alone.
Related
- Biological aging measured from electronic health records is associated with recovery following cardiothoracic surgery
- Novel cardiac computed tomography-based preoperative indicator associated with intraoperative graft flow in coronary artery bypass grafting
- Development and validation of a machine learning model for preoperative prediction of intraoperative hypothermia in gynecological laparoscopic surgery: a two-center cohort study
- Intraoperative titanium clip localization versus preoperative medical glue localization for pulmonary nodules: a prospective cohort study.
- MRI-based radiomics models for the preoperative prediction of massive intraoperative blood loss in spinal metastases patients.
BibTeX
@misc{korutla2026physiofusion,
title = {{PhysioFusion: A Multi-Modal Ensemble using Static Preoperative Variables and Time Series Intraoperative Data to Predict Adverse Events Following Cardiothoracic Surgery}},
author = {R. Korutla and A. Hicks and M. Milosevic and D. Kulkarni and F. Mazhude and T. Kelting and J. B. Rabb and Q. Jin and R. Kramer and D. Sawyer and R. L. Winslow and S. Amal},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.24.26363920},
url = {https://www.medrxiv.org/content/10.64898/2026.09.24.26363920v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - PhysioFusion: A Multi-Modal Ensemble using Static Preoperative Variables and Time Series Intraoperative Data to Predict Adverse Events Following Cardiothoracic Surgery
AU - R. Korutla
AU - A. Hicks
AU - M. Milosevic
AU - D. Kulkarni
AU - F. Mazhude
AU - T. Kelting
AU - J. B. Rabb
AU - Q. Jin
AU - R. Kramer
AU - D. Sawyer
AU - R. L. Winslow
AU - S. Amal
PY - 2026
DA - 2026/09/24
PB - medRxiv
DO - 10.64898/2026.09.24.26363920
UR - https://www.medrxiv.org/content/10.64898/2026.09.24.26363920v1
AB - Accurate prediction of adverse events in the intensive care unit (ICU) following cardiothoracic surgery is crucial for timely interventions, improving patient outcomes and optimizing value in healthcare. By leveraging advanced machine learning techniques, this study demonstrates the transformative potential of predictive analytics to enhance postoperative care using a dataset from the Society of Thoracic Surgeons (STS) database [4] and time-series intraoperative data. We developed a multi-modal late fusion approach integrating static patient variables with intraoperative time-series data, utilizing an ensemble of models including residual neural networks for static features, CNN and Bidirectional GRU for time-series processing, XGBoost, logistic regression, SVM and Gradient Boosting. Through five-fold cross-validation, our ensemble model with balanced threshold selection achieved an AUC of 0.87, sensitivity of 0.76, specificity of 0.83, PPV of 0.40, and NPV of 0.96. Preoperative heart failure, IABP insertion, cardiopulmonary bypass (CPB) duration and white blood cell (WBC) count emerged as key predictors. Training the same pipeline on each modality separately showed that the static registry variables alone reached the same AUC of 0.87, and that the intraoperative signals alone reached 0.83, so on this cohort the two modalities act as substitutes rather than complements and fusion changed the sensitivity and precision trade-off rather than the amount of separable signal. A per-signal ablation found that no individual monitoring channel was load bearing, with mean arterial pressure and central venous pressure the least substitutable. This balanced approach optimizes the trade-off between sensitivity and specificity, providing a screening tool with high negative predictive value for monitoring high-risk patients, and the modality comparison indicates that comparable performance is attainable at sites holding registry data alone.
ER -