Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{179154,
        author = {Ranjana Gore and Priyanshu Srivastava and Gresika Rai and Pranav Jain and Dheeraj Burli},
        title = {Sepsis Detection System using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {7645-7650},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179154},
        abstract = {The main cause of death in the intensive care units worldwide continues to be sepsis, due to its complex presentation and quick progression. Healthcare systems are always overwhelmed with patients and need to be more efficiently managed. Furthermore, measuring healthcare expenditure and survival rates needs improvement. This study describes the design and implementation of an early stage sepsis detection system using supervised machine learning methods on the PhysioNet Sepsis Challenge dataset. The dataset contains more than 40 clinical and physiological variables, such as vital signs, laboratory results and demographic data, gathered from ICU patients. A consistent pipeline for preprocessing was constructed to handle missing data, normalize the data, and overcome class imbalance problems through SMOTE. The selected model ('XGBoost') was trained to classify the time-series data of patients as septic or non-septic. Model performance was iteratively improved using hyper parameter tuning and cross validation. The model built achieved an impressive accuracy of 97% and a strong precision, recall and F1 score metrics which showcases the model's reliability in early detection while limiting false negative detections.},
        keywords = {Sepsis detection, machine learning, XGBoost, SMOTE, SHAP, healthcare AI, clinical decision support},
        month = {May},
        }