Risk prediction of cholangitis after stent implantation based on machine learning

• Published in: Scientific reports Vol. 14; no. 1; pp. 13715 - 11
• Main Authors: Zhao, Rui, Gu, Lin, Ke, Xiquan, Deng, Xiaojing, Li, Dapeng, Ma, Zhenzeng, Wang, Qizhi, Zheng, Hailun, Yang, Yong
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 14.06.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 692/4020/4021; 692/4020/4021/1328; 692/4020/4021/44; Aged; Aged, 80 and over; Artificial intelligence; Cholangiopancreatography, Endoscopic Retrograde - adverse effects; Cholangitis; Cholangitis - etiology; Endoscopic retrograde cholangiopancreatography; Female; Humanities and Social Sciences; Humans; Implants; Jaundice; Jaundice, Obstructive - etiology; Jaundice, Obstructive - surgery; Learning algorithms; Machine Learning; Machine learning model; Male; Malignant obstructive jaundice; Middle Aged; multidisciplinary; Patients; Prediction models; Retrospective Studies; Risk Assessment - methods; Risk Factors; Science; Science (multidisciplinary); Stents - adverse effects; Endoscopic retrograde cholangiopancreatography; Machine learning model; Malignant obstructive jaundice; Cholangitis
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-64734-w

The risk of cholangitis after ERCP implantation in malignant obstructive jaundice patients remains unknown. To develop models based on artificial intelligence methods to predict cholangitis risk more accurately, according to patients after stent implantation in patients’ MOJ clinical data. This retrospective study included 218 patients with MOJ undergoing ERCP surgery. A total of 27 clinical variables were collected as input variables. Seven models (including univariate analysis and six machine learning models) were trained and tested for classified prediction. The model’ performance was measured by AUROC. The RFT model demonstrated excellent performances with accuracies up to 0.86 and AUROC up to 0.87. Feature selection in RF and SHAP was similar, and the choice of the best variable subset produced a high performance with an AUROC up to 0.89. We have developed a hybrid machine learning model with better predictive performance than traditional LR prediction models, as well as other machine learning models for cholangitis based on simple clinical data. The model can assist doctors in clinical diagnosis, adopt reasonable treatment plans, and improve the survival rate of patients.