Machine learning prediction model for treatment responders in patients with primary biliary cholangitis

• Published in: JGH open 2023-06, Vol.7 (6), p.431-438
• Main Authors: Kimura, Naruhiro, Takahashi, Kazuya, Setsu, Toru, Goto, Shu, Miida, Suguru, Takeda, Nobutaka, Kojima, Yuichi, Arao, Yoshihisa, Hayashi, Kazunao, Sakai, Norihiro, Watanabe, Yusuke, Abe, Hiroyuki, Kamimura, Hiroteru, Sakamaki, Akira, Yokoo, Takeshi, Kamimura, Kenya, Tsuchiya, Atsunori, Terai, Shuji
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Autoimmune diseases; Cholangitis; Datasets; Disease; Immunoglobulins; Liver; Machine learning; Original; Phosphatase; primary biliary cholangitis; Statistical analysis; treatment response; ursodeoxycholic acid
• ISSN: 2397-9070; 2397-9070
• DOI: 10.1002/jgh3.12915

Background and Aim Treatment response to ursodeoxycholic acid may predict the prognosis of patients with primary biliary cholangitis (PBC). Recent studies have suggested the benefits of using machine learning (ML) to forecast complex medical predictions. We aimed to predict treatment response in patients with PBC using ML and pretreatment data. Methods We conducted a single‐center retrospective study and collected data from 194 patients with PBC who were followed up for at least 12 months after treatment initiation. Patient data were analyzed with five ML models, namely random forest, extreme gradient boosting (XGB), decision tree, naïve Bayes, or logistic regression, to predict treatment response using the Paris II criteria. The established models were assessed using an out‐of‐sample validation. The area under the curve (AUC) was used to evaluate the efficacy of each algorithm. Overall survival and liver‐related deaths were analyzed using Kaplan–Meier analysis. Results Compared to logistic regression (AUC = 0.595, P = 0.0219, 0.031 models), ML analyses showed significantly high AUC in the random forest (AUC = 0.84) and XGB (AUC = 0.83) models; however, the AUC was not significantly high for decision tree (AUC = 0.633) or naïve Bayes (AUC = 0.584) models. Kaplan–Meier analysis showed significantly improved prognoses in patients predicted to achieve the Paris II criteria by XGB (log‐rank = 0.005 and 0.007). Conclusion ML algorithms could improve treatment response prediction using pretreatment data, which could lead to better prognoses. In addition, the ML model using XGB could predict the prognosis of patients before treatment initiation. Receiver operating characteristic curve analysis showed area under the curve (AUC) for predicting patients meeting the Paris II criteria using extreme gradient boosting tree (AUC = 0.830), random forest (AUC = 0.842), logistic regression (AUC = 0.595), Naïve Bayes (AUC = 0.584), and decision tree (AUC = 0.633).