International Journal of
Advanced Multidisciplinary Application

Volume 3, Issue 5

• Author(s)Priya Mehta, Rajesh Kumar Sharma, Ananya Bose, Vikram Nair
• AffiliationDepartment of Computer Science and Engineering, Rajasthan Technical University, Kota, Rajasthan, India, Department of Biomedical Engineering, Uttar Pradesh Technical University, Lucknow, Uttar Pradesh, India
• Page No.67-71
• Volume, Issue & YearVolume 3, Issue 5, May 2026
• Published On2026/05/13
• JournalInternational Journal of Advanced Multidisciplinary Application (IJAMA)
• ISSN No.3048-9350
• DOIhttps://doi.org/10.5281/zenodo.20353287

Abstract

Sepsis is a life-threatening organ dysfunction caused by a dysregulated host response to infection, responsible for over 11 million deaths annually worldwide and constituting one of the most prevalent causes of ICU mortality. Early identification of sepsis from Electronic Health Records (EHRs) using machine learning approaches has attracted considerable research attention, but the inherent challenges of multivariate time-series clinical data — including irregular sampling, high missingness rates, inter-variable temporal dependencies, and clinical noise — continue to limit the translation of research models into real-world ICU deployment. This study proposes a Bidirectional Long Short-Term Memory (BiLSTM) network augmented with a multi-head attention mechanism for sepsis onset prediction from the MIMIC-III ICU dataset, using 18 clinical variables including vital signs, laboratory results, and Glasgow Coma Scale scores. The proposed architecture captures both forward and backward temporal dependencies in clinical sequences while the attention module dynamically weights clinically salient time steps. Compared to baseline models including Random Forest, SVM with radial basis function kernel, XGBoost, and standard LSTM, the proposed BiLSTM-Attention model achieves AUROC of 0.995, F1-Score of 0.981, sensitivity of 0.980, and specificity of 0.983 on the held-out test set. Ablation studies confirm the independent contributions of bidirectionality and attention. The model provides a 5.3-hour average early warning horizon before clinical sepsis criterion satisfaction, representing a clinically actionable prediction window for ICU intervention. SHAP-based feature importance analysis identifies lactate trend, heart rate variability, mean arterial pressure, and FiO₂/SpO₂ ratio as the most predictive variables, consistent with established sepsis pathophysiology.

Keywords: sepsis prediction, bidirectional LSTM, multi-head attention, electronic health records, ICU, MIMIC-III, time-series classification, SHAP, early warning system

References

1. [1] Singer, M., Deutschman, C. S., Seymour, C. W., et al. (2016). The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). JAMA, 315(8), 801-810.
2. [2] Rudd, K. E., Johnson, S. C., Agesa, K. M., et al. (2020). Global, regional, and national sepsis incidence and mortality, 1990–2017. The Lancet, 395(10219), 200-211.
3. [3] Johnson, A. E., Pollard, T. J., Shen, L., et al. (2016). MIMIC-III, a freely accessible critical care database. Scientific Data, 3, 160035.
4. [4] Rajpurkar, P., Irvin, J., Ball, R. L., et al. (2017). CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv preprint arXiv:1711.05225.
5. [5] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780.
6. [6] Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11), 2673-2681.
7. [7] Vaswani, A., Shazeer, N., Parmar, N., et al. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998-6008.
8. [8] Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30.
9. [9] Kam, H. J., & Kim, H. Y. (2017). Learning representations for the early detection of sepsis with deep neural networks. Computers in Biology and Medicine, 89, 248-255.
10. [10] Moor, M., Horn, M., Rieck, B., et al. (2021). Early warning of sepsis using deep learning of daily temporal patterns from electronic health record. Frontiers in Medicine, 8, 607502.
11. [11] Futoma, J., Hariharan, S., Heller, K., et al. (2017). An improved multi-output Gaussian process RNN with real-time validation for early sepsis detection. Machine Learning for Healthcare Conference, PMLR, 68, 243-254.
12. [12] Ye, C., Fu, T., Hao, S., et al. (2018). Prediction of incident hypertension within the next year. Journal of Medical Internet Research, 20(1), e22.
13. [13] Che, Z., Purushotham, S., Cho, K., et al. (2018). Recurrent neural networks for multivariate time series with missing values. Scientific Reports, 8, 6085.
14. [14] Lin, C., Zhang, Y., Ivy, J., et al. (2018). Early diagnosis of sepsis using serum biomarkers and clinical data. Critical Care Medicine, 46(3), 356-362.
15. [15] Gupta, M., Bhattacharya, A., Singh, R. P., et al. (2023). Transformer-based models for ICU outcome prediction: A systematic review. Biomedical Signal Processing and Control, 85, 104912.
16. [16] Mishra, A., & Verma, K. (2022). Attention-enhanced LSTM for sepsis severity scoring in resource-limited Indian hospitals. Journal of Healthcare Informatics Research, 6(2), 145-162.
17. [17] Dellinger, R. P., Levy, M. M., Rhodes, A., et al. (2013). Surviving Sepsis Campaign guidelines. Critical Care Medicine, 41(2), 580-637.

Explore Our Related Journals

Looking for the right journal for your next manuscript? Explore our international peer-reviewed journals covering engineering, management, computer science, artificial intelligence and multidisciplinary research.