Machine learning predicts the risk of hemorrhagic transformation of acute cerebral infarction and in-hospital death

• Published in: Computer methods and programs in biomedicine Vol. 237; p. 107582
• Main Authors: Li, Xuewen, Xu, Changyan, Shang, Chengming, Wang, Yiting, Xu, Jiancheng, Zhou, Qi
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.07.2023
• Subjects: Acute Disease; Big data; Brain Ischemia; Cerebral Hemorrhage; Cerebral Infarction; Death; Hemorrhagic transformation; Hospital Mortality; Humans; Machine Learning; Stroke; Cerebral infarction; Death; Hemorrhagic transformation; Big data; Machine learning
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2023.107582

•Extreme gradient Boosting algorithm outperforms logistic regression.•HF-Lab10 accurately predicts hemorrhagic transformation.•HF-Lab10 accurately predicts in-hospital mortality. The incidence of hemorrhagic transformation (HT) during thrombolysis after acute cerebral infarction (ACI) is very high. We aimed to develop a model to predict the occurrence of HT after ACI and the risk of death after HT. Cohort 1 is divided into HT and non-HT groups, to train the model and perform internal validation. All first laboratory test results of study subjects were used as features to be selected for machine learning, and the models built by four machine learning algorithms were compared to screen the best algorithm and model. Following that, the HT group was divided into death and non-death for subgroup analysis. Receiver operating characteristic (ROC) curves etc. to evaluate the model. ACI patients in cohort 2 for external validation. In cohort 1, the HT risk prediction model HT-Lab10 built by the XgBoost algorithm performed the best with AUCROC=0.95 (95% CI, 0.93-0.96). Ten features were included in the model, namely B-type natriuretic peptide precursor, ultrasensitive C-reactive protein, glucose, absolute neutrophil value, myoglobin, uric acid, creatinine, Ca2+, Thrombin time, and carbon dioxide combining power. The model also had the ability to predict death after HT with AUCROC=0.85 (95% CI, 0.78-0.91). The ability of HT-Lab10 to predict the occurrence of HT as well as death after HT was validated in cohort 2. The model HT-Lab10 built using the XgBoost algorithm showed excellent predictive ability in both the occurrence of HT and the risk of HT death, achieving a model with multiple uses.