Development and Validation of SXI++ LNM Algorithm for Sepsis Prediction

Background Sepsis is a life - threatening condition affecting over 48.9 million people globally and causing 11 million deaths annually. Despite medical advancements, predicting sepsis remains a challenge due to non - specific symptoms and complex pathophysiology. The SXI++ LNM model is a machine learning - based scoring system that refines sepsis prediction by leveraging multiple algorithms and deep neural networks. The COMPOSER model, a de ep learning framework utilizing conformal prediction, aims to improve robustness in clinical applications. This study compares the predictive performance of SXI++ LNM and COMPOSER for sepsis prediction. Methods A dataset containing 1,552,210 rows with 43 columns was cleaned and refined to 964,355 rows and 14 key features for sepsis prediction. Data were sourced from ICU patients across three separate hospital systems, including two publicly available datasets fro m Kaggle and the Early Prediction of Sepsis from Clinical Data: The PhysioNet/Computing in Cardiology Challenge 2019.