• Syed Sabreen
• Dr.K G Chiranjeevi

Sepsis is a life-threatening condition caused by the body’s abnormal response to infection, leading to organ failure and death if not detected early. Early identification is difficult due to overlapping symptoms and limitations in traditional diagnostic methods like SIRS, SOFA, and qSOFA, which rely on static thresholds and manual evaluation. This study proposes an Enhanced Gated Recurrent Unit (GRU) deep learning model for early sepsis prediction using clinical and physiological data from Kaggle. The data undergo preprocessing steps including cleaning, encoding, correlation filtering, and normalization. The Enhanced GRU model effectively captures temporal and nonlinear dependencies in patient data, enabling accurate early detection of sepsis. Experimental results show superior accuracy, precision, recall, F1-score, and AUC compared to traditional machine learning methods. The proposed model offers a reliable and efficient framework for real-time sepsis prediction and clinical decision support in intensive care units.

SEPSIS PREDICTION USING ENHANCED GRU DEEP LEARNING MODEL

"SEPSIS PREDICTION USING ENHANCED GRU DEEP LEARNING MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.a861-a870, November-2025, Available :http://www.jetir.org/papers/JETIR2511099.pdf

"SEPSIS PREDICTION USING ENHANCED GRU DEEP LEARNING MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppa861-a870, November-2025, Available at : http://www.jetir.org/papers/JETIR2511099.pdf