IRO Journals
Journal of Innovative Image Processing

A Hybrid Deep Learning Model Combining Tabular Transformers and Temporal Convolutional Network for Sepsis Prediction

Open Access
Published: 24 April, 2026
Pages: 518-535
  • Sona G. , Sona G.
    Assistant Professor, Department of Computer Science and Engineering, Government College of Engineering, Tirunelveli, India
    Assistant Professor, Department of Computer Science and Engineering, Government College of Engineering, Tirunelveli, India
  • Anitha D. , Anitha D.
    Assistant Professor, Department of Computer Science and Engineering, Government College of Engineering, Tirunelveli, India
    Assistant Professor, Department of Computer Science and Engineering, Government College of Engineering, Tirunelveli, India
  • Narmatha B. Narmatha B.
    Assistant Professor, Department of Information Technology, Sri Krishna College of Engineering and Technology, Coimbatore, India
    Assistant Professor, Department of Information Technology, Sri Krishna College of Engineering and Technology, Coimbatore, India
PDF
PDF

How to Cite

G., Sona, Anitha D., and Narmatha B. 2026. “A Hybrid Deep Learning Model Combining Tabular Transformers and Temporal Convolutional Network for Sepsis Prediction”. Journal of Innovative Image Processing 8 (2): 518-35. https://doi.org/10.36548/jiip.2026.2.005.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Sepsis
Tabular Transformer
Temporal Convolutional Network
Clinical Time-Series Data
Early Detection

Abstract

Sepsis develops whenever our immune system's response to an infection becomes dysregulated, leading to extensive inflammation and organ damage. It is a severe immune system imbalance that, if ignored, can cause tissue damage, various organ failures, and death. Using multivariate clinical time-series data, a hybrid deep learning system combining a Temporal Convolutional Network (TCN) and a Tabular Transformer is developed for early prediction. The Sepsis Prediction Dataset is used in this work. The dataset consists of 40 clinical variables that have been gathered continuously in Intensive Care Unit (ICU) settings, which include vital signs, laboratory results, and demographic data. Two parallel branches are used for designing the proposed structure. The first branch, named the Tabular Transformer branch, learns the representations and interactions of variables through the handling of dynamic and categorical data. The Temporal Convolutional Network branch processes the sequential inputs by using dilated temporal convolution to detect long-range patterns within physiological signals. After concatenating both outputs and passing them into a fully connected layer, it makes predictions regarding the early phases of sepsis. With regard to its early predictions four to six hours before the clinical diagnoses, its sensitivity, specificity, accuracy, and F1-score were found to be 96.65%, 98.32%, 98.9%, and 96.3% respectively. These results indicate that the early detection of sepsis would improve as a result of integrating continuous patient data along with temporal patterns. Further validation of the developed model needs to be made on other clinical datasets.

References

  1. Rudd, Kristina E., Sarah Charlotte Johnson, Kareha M. Agesa, Katya Anne Shackelford, Derrick Tsoi, Daniel Rhodes Kievlan, Danny V. Colombara et al. "Global, Regional, And National Sepsis Incidence and Mortality, 1990–2017: Analysis for the Global Burden of Disease Study." The Lancet 395, no. 10219 (2020): 200-211.
  2. Singer, Mervyn, Clifford S. Deutschman, Christopher Warren Seymour, Manu Shankar-Hari, Djillali Annane, Michael Bauer, Rinaldo Bellomo et al. "The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3)." Jama 315, no. 8 (2016): 801-810.
  3. Seymour, Christopher W., Vincent X. Liu, Theodore J. Iwashyna, Frank M. Brunkhorst, Thomas D. Rea, André Scherag, Gordon Rubenfeld et al. "Assessment of Clinical Criteria for Sepsis: for the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3)." Jama 315, no. 8 (2016): 762-774.
  4. Kumar, Anand, Daniel Roberts, Kenneth E. Wood, Bruce Light, Joseph E. Parrillo, Satendra Sharma, Robert Suppes et al. "Duration of Hypotension Before Initiation of Effective Antimicrobial Therapy is the Critical Determinant of Survival in Human Septic Shock." Critical care medicine 34, no. 6 (2006): 1589-1596.
  5. Churpek, Matthew M., Frank J. Zadravecz, Christopher Winslow, Michael D. Howell, and Dana P. Edelson. "Incidence and Prognostic Value of the Systemic Inflammatory Response Syndrome and Organ Dysfunctions in Ward Patients." American journal of respiratory and critical care medicine 192, no. 8 (2015): 958-964.
  6. Fleuren, Lucas M., Thomas LT Klausch, Charlotte L. Zwager, Linda J. Schoonmade, Tingjie Guo, Luca F. Roggeveen, Eleonora L. Swart et al. "Machine Learning for the Prediction of Sepsis: A Systematic Review and Meta-Analysis of Diagnostic Test Accuracy." Intensive care medicine 46, no. 3 (2020): 383-400.
  7. Moor, Michael, Bastian Rieck, Max Horn, Catherine R. Jutzeler, and Karsten Borgwardt. "Early Prediction of Sepsis in the ICU Using Machine Learning: A Systematic Review." Frontiers in medicine 8 (2021): 607952.
  8. Reyna, Matthew A., Christopher S. Josef, Russell Jeter, Supreeth P. Shashikumar, M. Brandon Westover, Shamim Nemati, Gari D. Clifford, and Ashish Sharma. "Early Prediction of Sepsis from Clinical Data: The Physionet/Computing in Cardiology Challenge 2019." Critical care medicine 48, no. 2 (2020): 210-217.
  9. Tonekaboni, Sana, Shalmali Joshi, Melissa D. McCradden, and Anna Goldenberg. "What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use." In Machine learning for healthcare conference, PMLR, 2019, 359-380.
  10. Shashikumar, Supreeth P., Matthew D. Stanley, Ismail Sadiq, Qiao Li, Andre Holder, Gari D. Clifford, and Shamim Nemati. "Early Sepsis Detection in Critical Care Patients Using Multiscale Blood Pressure and Heart Rate Dynamics." Journal of electrocardiology 50, no. 6 (2017): 739-743.
  11. D. Banja, John, Yao Xie, Jeffrey R. Smith, Shaheen Rana, and Andre L. Holder. "Mitigating Bias in Machine Learning Models with Ethics-Based Initiatives: The Case of Sepsis." The American Journal of Bioethics 26, no. 2 (2026): 96-109.
  12. Johnson, Alistair EW, Tom J. Pollard, Lu Shen, Li-wei H. Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, and Roger G. Mark. "MIMIC-III, A Freely Accessible Critical Care Database." Scientific data 3, no. 1 (2016): 1-9.
  13. Athukorala, V. S., and W. M. K. S. Ilmini. "Explainable AI for Critical Care: A Systematic Review of Interpretable Models for Sepsis and ICU Mortality Prediction." BMC Medical Informatics and Decision Making (2026).
  14. Han, Yupeng, Xiyuan Xie, Jiapeng Qiu, Yijie Tang, Zhiwei Song, Wangyu Li, and Xiaodan Wu. "Early Prediction of Sepsis Associated Encephalopathy in Elderly ICU Patients Using Machine Learning Models: A Retrospective Study Based on the MIMIC-IV Database." Frontiers in Cellular and Infection Microbiology 15 (2025): 1545979.
  15. Kam, Hye Jin, and Ha Young Kim. "Learning Representations for the Early Detection of Sepsis with Deep Neural Networks." Computers in biology and medicine 89 (2017): 248-255.
  16. Lipton, Zachary C., David C. Kale, Charles Elkan, and Randall Wetzel. "Learning to Diagnose with LSTM Recurrent Neural Networks." arXiv preprint arXiv:1511.03677 (2015).
  17. Rajkomar, Alvin, Eyal Oren, Kai Chen, Andrew M. Dai, Nissan Hajaj, Michaela Hardt, Peter J. Liu et al. "Scalable and Accurate Deep Learning with Electronic Health Records." NPJ digital medicine 1, no. 1 (2018): 18.
  18. Faust, Oliver, U. Rajendra Acharya, Hojjat Adeli, and Amir Adeli. "Wavelet-based EEG Processing for Computer-Aided Seizure Detection and Epilepsy Diagnosis." Seizure 26 (2015): 56-64.
  19. Chicco, Davide, and Giuseppe Jurman. "The Advantages of the Matthews Correlation Coefficient (MCC) Over F1 Score and Accuracy in Binary Classification Evaluation." BMC genomics 21, no. 1 (2020): 6.
  20. Breiman, Leo. 2001. “Random Forests.” Machine Learning 45 (1): 5–32.
  21. Chen, Tianqi, and Carlos Guestrin. "Xgboost: A Scalable Tree Boosting System." In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, 785-794.
  22. Koller, Daphne, and Nir Friedman. Probabilistic Graphical Models: Principles and Techniques. MIT press, 2009.
  23. Vincent, Pascal, Hugo Larochelle, Yoshua Bengio, and Pierre-Antoine Manzagol. "Extracting and Composing Robust Features with Denoising Autoencoders." In Proceedings of the 25th international conference on Machine learning, 2008, 1096-1103.
  24. Komorowski, Matthieu, Leo A. Celi, Omar Badawi, Anthony C. Gordon, and A. Aldo Faisal. "The Artificial Intelligence Clinician Learns Optimal Treatment Strategies for Sepsis in Intensive Care." Nature medicine 24, no. 11 (2018): 1716-1720.
  25. Nemati, Shamim, Andre Holder, Fereshteh Razmi, Matthew D. Stanley, Gari D. Clifffrd, and Timothy G. Buchman. "An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU." Critical care medicine 46, no. 4 (2018): 547-553.
  26. Joshi, Yash. “Sepsis Prediction Dataset.”, Accessed March 17, 2026. https://www.kaggle.com/datasets/tea340yashjoshi/sepsis-prediction-dataset.