Real-Time Sepsis Prediction in Intensive Care Units Using Temporal Deep Learning Models on Longitudinal Electronic Health Records

Davidson Ronaldo,

Authors

Davidson Ronaldo, Author

Keywords:

Sepsis prediction, Intensive Care Units (ICUs), Temporal Deep Learning, Longitudinal EHRs, LSTM, TCN, Transformer, Real-time monitoring

Abstract

Sepsis is a leading cause of mortality in Intensive Care Units (ICUs), demanding rapid diagnosis and intervention. The advent of longitudinal Electronic Health Records (EHRs) and advancements in temporal deep learning architectures offer new avenues for early, real-time prediction. This study explores the integration of Long Short-Term Memory (LSTM), Transformer-based models, and Temporal Convolutional Networks (TCNs) for sepsis prediction using dynamic ICU datasets. We synthesize findings from recent research and validate performance metrics including AUC, precision, and recall. Our review suggests that deep learning models utilizing temporal sequences in real-time outperform traditional static scoring systems, enhancing early intervention and clinical outcomes.

References

Lauritsen, S.M., Kalør, M.E., Kongsgaard, E.L., Lauritsen, K.M., Jørgensen, M.J., Lange, J., & Brunak, S. (2020). Early detection of sepsis utilizing deep learning on electronic health record event sequences. Artificial Intelligence in Medicine, 104, 101822.

Chaudhary, B.S. (2025). Automating system monitoring and management: Achieving significant time savings and reducing downtime. International Journal of Computer Science and Engineering Research and Development (IJCSERD), 15(1), 72–80. https://doi.org/10.5281/zenodo.14791930

Chunduru, V. K., Gonepally, S., Amuda, K. K., Kumbum, P. K., & Adari, V. K. (2024). Enhancing R&D project selection using grey relational analysis: A multi-criteria approach. Data Analytics and Artificial Intelligence, 4(3), 25–32. https://doi.org/10.46632/daai/4/3/4

Thorsen-Meyer, H.C., Nielsen, A.B., Nielsen, A.P., Kaas-Hansen, B.S., Toft, P., Schierbeck, J., Strøm, T., & Perner, A. (2020). Explainable machine learning prediction of mortality in patients in the intensive care unit: a retrospective study of high-frequency data in electronic patient records. The Lancet Digital Health, 2(4), e179–e191.

Shah, P.K., Ginestra, J.C., Ungar, L.H., Junker, C.L., Swedlow, D.B., & Bertsimas, D. (2021). A simulated prospective evaluation of a deep learning model for real-time prediction of clinical deterioration among ward patients. Critical Care Medicine, 49(8), 1200–1211.

Amuda, K. K., Kumbum, P. K., Adari, V. K., Chunduru, V. K., & Gonepally, S. (2024). Evaluation of crime rate prediction using machine learning and deep learning for GRA method. Data Analytics and Artificial Intelligence, 4(3). REST Publisher. https://doi.org/10.46632/daai/4/3/3

Chaudhary, B. S. (2025). Insights into cloud migration: (Migration to Azure/AWS). International Journal of Computer Engineering and Technology, 16(1), 1339–1349. https://doi.org/10.34218/IJCET_16_01_101

Valik, J.K., Ward, L., Tanushi, H., & Johansson, A.F. (2023). Predicting sepsis onset using a machine learned causal probabilistic network algorithm based on electronic health records data. Scientific Reports, 13, 10928.

Islam, K.R., Prithula, J., Kumar, J., & Tan, T.L. (2023). Machine learning-based early prediction of sepsis using electronic health records: a systematic review. Journal of Clinical Medicine, 12(17), 5658.

Kumbum, P. K., Adari, V. K., Chunduru, V. K., Gonepally, S., & Amuda, K. K. (2024). Optimizing network function virtualization: A comprehensive performance analysis of hardware-accelerated solutions. SOJ Materials Science & Engineering, 10(1), 1–10.

Lai, Y., Zhang, J., Chen, W., Wang, Y., & Zou, Q. (2022). DeepMPM: a mortality risk prediction model using longitudinal EHR data. BMC Bioinformatics, 23, 455.

Morid, M.A., Sheng, O.R.L., & Dunbar, J. (2023). Time series prediction using deep learning methods in healthcare. ACM Transactions on Management Information Systems, 14(1), 1–26.

Bajpai, S., & Kaul, M. (2025). DynEdges-TGN: Dynamic-Edges-Based Temporal Graph Network for Early Sepsis Prediction. SN Computer Science, 6, Article 45.

Gupta, A., Liu, T., & Crick, C. (2020). Utilizing time series data embedded in electronic health records to develop continuous mortality risk prediction models using hidden Markov models: a sepsis case study. Statistical Methods in Medical Research, 29(12), 3467–3484.

Adari, V. K. (2024). APIs and open banking: Driving interoperability in the financial sector. International Journal of Research in Computer Applications and Information Technology (IJRCAIT), 7(2), 2015–2024.

Moskovitch, R., Schvetz, M., Fuchs, L., & Novack, V. (2021). Outcomes prediction in longitudinal data: Study designs evaluation, use case in ICU acquired sepsis. Journal of Biomedical Informatics, 116, 103714.

Ge, W., Huh, J.W., Park, Y.R., Lee, J.H., Kim, Y.H., & Kim, J.H. (2022). Using deep learning with attention mechanism for identification of novel temporal data patterns for prediction of ICU mortality. Informatics in Medicine Unlocked, 28, 100835.

Lee, J.Y., Molani, S., Fang, C., & Jade, K. (2021). Ambulatory risk models for the long-term prevention of sepsis: Retrospective study. JMIR Medical Informatics, 9(7), e29986.

Li, F., Wang, S., Gao, Z., Qing, M., Pan, S., & Liu, Y. (2024). Harnessing artificial intelligence in sepsis care: advances in early detection, personalized treatment, and real-time monitoring. Frontiers in Medicine, 11, 1510792.

Cissoko, M.B.H. (2024). Adaptive time-aware LSTM for predicting and interpreting ICU patient trajectories from irregular data. Ph.D. Thesis, Université Paris-Saclay.

Sottile, P.D., Albers, D., DeWitt, P.E., & Kutner, J.S. (2021). Real-time electronic health record mortality prediction during the COVID-19 pandemic: a prospective cohort study. Journal of the American Medical Informatics Association, 28(11), 2354–2365.