SHAP-Enabled Explainable ML for Early Sepsis Risk Prediction Using Tabular EHR Records
Main Article Content
Abstract
The sepsis condition is a severe syndrome that necessitates timely treatment. Electronic Health Records (EHRs) contain valuable information that can be used to predict disease early. Structured EHR data exhibit informative missingness, feature heterogeneity, and complex behavior in downstream machine learning (ML) models, thus presenting challenges for application. The current research aims to propose an ML framework for the early prediction of sepsis from structured tabular EHR data. The study will develop an ML framework for data pre-processing, handling missing data, conducting EDA, selecting clinical features, and class balancing. Using the developed framework, we will employ supervised machine learning algorithms to help predict the probability of developing sepsis over a particular period. The framework will be applied to the EHR data, with SHAP used to interpret the results. In addition, the study will examine the associations between input variables and model outcome at multiple levels. The proposed model’s performance is analyzed using different metrics, including AUROC, precision, recall, F1 score, sensitivity, and calibration. Additionally, this study will employ SHAP values to assess variable importance and provide patient-level explanations. The research hypothesizes that an interpretable ML framework can be used to create an early-warning system for timely detection of sepsis from structured EHR data
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
Islam, K. R., Prithula, J., Kumar, J., Tan, T., Reaz, M., Sumon, M. S. I., & Chowdhury, M. E. (2023). Machine learning-based early prediction of sepsis using electronic health records: A systematic review. Journal of Clinical Medicine, 12.
Yang, Z., Cui, X., & Song, Z. (2023). Predicting sepsis onset in ICU using machine learning models: A systematic review and meta-analysis. BMC Infectious Diseases, 23.
Lauritsen, S., et al. (2019). Early detection of sepsis utilizing deep learning on electronic health record event sequences. Artificial Intelligence in Medicine, 104, 101820.
Srimedha, B. C., Naveen Raj, R., & Mayya, V. (2022). A comprehensive machine learning based pipeline for an accurate early prediction of sepsis in ICU. IEEE Access, 10, 105120–105132.
Kijpaisalratana, N., et al. (2022). Machine learning algorithms for early sepsis detection in the emergency department: A retrospective study. International Journal of Medical Informatics, 160, 104689.
Su, L., et al. (2021). Early prediction of mortality, severity, and length of stay in the intensive care unit of sepsis patients based on Sepsis 3.0 by machine learning models. Frontiers in Medicine, 8.
Valik, J., et al. (2023). Predicting sepsis onset using a machine learned causal probabilistic network algorithm based on electronic health records data. Scientific Reports, 13.
Zhou, L., et al. (2024). An early sepsis prediction model utilizing machine learning and unbalanced data processing in a clinical context. Preventive Medicine Reports, 45.
Nesaragi, N., & Patidar, S. (2021). An explainable machine learning model for early prediction of sepsis using ICU data. Infectious Diseases and Sepsis.
Hu, C., et al. (2022). Interpretable machine learning for early prediction of prognosis in sepsis: A discovery and validation study. Infectious Diseases and Therapy, 11, 1117–1132.
Aygun, U., et al. (2024). Assessment of sepsis risk at admission to the emergency department: Clinical interpretable prediction model. Diagnostics, 14.
Zhang, T., et al. (2024). Development and validation of a machine learning-based interpretable model for predicting sepsis by complete blood cell parameters. Heliyon, 10.
Tang, Y., Zhang, Y., & Li, J. (2024). A time series driven model for early sepsis prediction based on transformer module. BMC Medical Research Methodology, 24.
Shi, X., et al. (2025). Accurate prediction of sepsis from pediatric emergency department to PICU using a machine-learning model. Frontiers in Pediatrics, 13.
Liu, Z., et al. (2025). Interpretable machine learning for predicting sepsis risk in emergency triage patients. Scientific Reports, 15.
Ma, X., et al. (2025). Constructing an early warning model for elderly sepsis patients based on machine learning. Scientific Reports, 15.
Gao, J., et al. (2024). Prediction of sepsis mortality in ICU patients using machine learning methods. BMC Medical Informatics and Decision Making, 24.
Desautels, T., et al. (2016). Prediction of sepsis in the intensive care unit with minimal electronic health record data: A machine learning approach. JMIR Medical Informatics, 4.
He, Z., et al. (2020). Early sepsis prediction using ensemble learning with deep features and artificial features extracted from clinical electronic health records. Critical Care Medicine.
Sadasivuni, S., et al. (2021). Fusion of fully integrated analog machine learning classifier with electronic medical records for real-time prediction of sepsis onset. Scientific Reports, 12.
Alam, M. U., & Rahmani, R. (2023). FedSepsis: A federated multi-modal deep learning-based Internet of Medical Things application for early detection of sepsis from electronic health records using Raspberry Pi and Jetson Nano devices. Sensors, 23.
Bomrah, S., et al. (2024). A scoping review of machine learning for sepsis prediction—feature engineering strategies and model performance: A step towards explainability. Critical Care, 28.
Prithula, J., et al. (2024). A novel classical machine learning framework for early sepsis prediction using electronic health record data from ICU patients. Computers in Biology and Medicine, 184, 109284.
Gupta, A., et al. (2024). Improving sepsis prediction in intensive care with SepsisAI: A clinical decision support system with a focus on minimizing false alarms. PLOS Digital Health, 3, e0000569.
Adams, R., et al. (2022). Prospective, multi-site study of patient outcomes after implementation of the TREWS machine learning-based early warning system for sepsis. Nature Medicine, 28, 1455–1460.
Persson, I., et al. (2024). Early prediction of sepsis in intensive care patients using the machine learning algorithm NAVOY® Sepsis, a prospective randomized clinical validation study. Journal of Critical Care, 80, 154400.
Zhou, H., Li, F., & Liu, X. (2025). Early prediction of septic shock in ICU patients using machine learning: Development, external validation, and explainability with SHAP. International Journal of Medical Informatics, 206, 106169.
Ogunwale, Y., et al. (2026). Explainable machine learning for multi-horizon early sepsis prediction in intensive care units. Cureus Journal of Computer Science.