Personalized prediction of mortality in patients with acute ischemic stroke using explainable artificial intelligence

• Published in: European journal of medical research Vol. 29; no. 1; pp. 341 - 12
• Main Authors: Xu, Lingyu, Li, Chenyu, Zhang, Jiaqi, Guan, Chen, Zhao, Long, Shen, Xuefei, Zhang, Ningxin, Li, Tianyang, Yang, Chengyu, Zhou, Bin, Bu, Quandong, Xu, Yan
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 20.06.2024; BioMed Central; BMC
• Subjects: Acute ischemic stroke; Acute kidney disease; Acute Kidney Injury - mortality; Aged; Algorithms; Artificial Intelligence; Computational linguistics; Decision-making; Diuretics; Female; Humans; Ischemia; Ischemic Stroke - mortality; Kidney diseases; Language processing; Machine Learning; Male; Medical research; Medicine, Experimental; Middle Aged; Mortality; Natural language interfaces; Patient outcomes; Precision Medicine - methods; Prognosis; Retrospective Studies; Stroke (Disease); Acute ischemic stroke; Artificial intelligence; Mortality; Machine learning; Acute kidney disease
• ISSN: 2047-783X; 0949-2321; 2047-783X
• DOI: 10.1186/s40001-024-01940-2

Research into the acute kidney disease (AKD) after acute ischemic stroke (AIS) is rare, and how clinical features influence its prognosis remain unknown. We aim to employ interpretable machine learning (ML) models to study AIS and clarify its decision-making process in identifying the risk of mortality. We conducted a retrospective cohort study involving AIS patients from January 2020 to June 2021. Patient data were randomly divided into training and test sets. Eight ML algorithms were employed to construct predictive models for mortality. The performance of the best model was evaluated using various metrics. Furthermore, we created an artificial intelligence (AI)-driven web application that leveraged the top ten most crucial features for mortality prediction. The study cohort consisted of 1633 AIS patients, among whom 257 (15.74%) developed subacute AKD, 173 (10.59%) experienced AKI recovery, and 65 (3.98%) met criteria for both AKI and AKD. The mortality rate stood at 4.84%. The LightGBM model displayed superior performance, boasting an AUROC of 0.96 for mortality prediction. The top five features linked to mortality were ACEI/ARE, renal function trajectories, neutrophil count, diuretics, and serum creatinine. Moreover, we designed a web application using the LightGBM model to estimate mortality risk. Complete renal function trajectories, including AKI and AKD, are vital for fitting mortality in AIS patients. An interpretable ML model effectively clarified its decision-making process for identifying AIS patients at risk of mortality. The AI-driven web application has the potential to contribute to the development of personalized early mortality prevention.