Artificial intelligence based multispecialty mortality prediction models for septic shock in a multicenter retrospective study by Shurui Wang & Xinyi Liu & Shaohua Yuan & Yi Bian & Hong Wu & Qing Ye instant download

Artificial intelligence based multispecialty mortality prediction models for septic shock in a multicenter retrospective study by Shurui Wang & Xinyi Liu & Shaohua Yuan & Yi Bian & Hong Wu & Qing Ye instant download

Septic shock is one of the most lethal conditions in ICU, and early risk prediction may help reducemortality. We developed a TOPSIS-based Classification Fusion (TCF) model to predict mortality risk in1234567890():,;1234567890():,;septic shock patients using data from 4872 ICU patients from February 2003 to November 2023across three hospitals. The model integrates seven machine learning models via the Technique forOrder Preference by Similarity to an Ideal Solution (TOPSIS), achieving AUCs of 0.733 in internalvalidation, 0.808 in the pediatric ICU, 0.662 in the respiratory ICU, with external validation AUCs of0.784 and 0.786, respectively. It demonstrated high stability and accuracy in cross-specialty andmulti-center validation. This interpretable model provides clinicians with a reliable early-warning toolfor septic shock mortality risk, facilitating early intervention to reduce mortality.