Wang Shurui, Liu Xinyi, Yuan Shaohua, Bian Yi, Wu Hong, Ye Qing
Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
NPJ Digit Med. 2025 Apr 28;8(1):228. doi: 10.1038/s41746-025-01643-w.
Septic shock is one of the most lethal conditions in ICU, and early risk prediction may help reduce mortality. We developed a TOPSIS-based Classification Fusion (TCF) model to predict mortality risk in septic shock patients using data from 4872 ICU patients from February 2003 to November 2023 across three hospitals. The model integrates seven machine learning models via the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS), achieving AUCs of 0.733 in internal validation, 0.808 in the pediatric ICU, 0.662 in the respiratory ICU, with external validation AUCs of 0.784 and 0.786, respectively. It demonstrated high stability and accuracy in cross-specialty and multi-center validation. This interpretable model provides clinicians with a reliable early-warning tool for septic shock mortality risk, facilitating early intervention to reduce mortality.
感染性休克是重症监护病房（ICU）中最致命的病症之一，早期风险预测可能有助于降低死亡率。我们开发了一种基于逼近理想解排序法（TOPSIS）的分类融合（TCF）模型，利用2003年2月至2023年11月期间来自三家医院的4872例ICU患者的数据来预测感染性休克患者的死亡风险。该模型通过逼近理想解排序法（TOPSIS）整合了七个机器学习模型，内部验证的曲线下面积（AUC）为0.733，儿科ICU为0.808，呼吸ICU为0.662，外部验证的AUC分别为0.784和0.786。它在跨专业和多中心验证中表现出高稳定性和准确性。这个可解释的模型为临床医生提供了一个可靠的感染性休克死亡风险早期预警工具，有助于早期干预以降低死亡率。
