Cumulative risk of developing a new symptom in patients with primary biliary cholangitis and its impact on prognosis

Kimura, Naruhiro; Setsu, Toru; Arao, Yoshihisa; Sakai, Norihiro; Watanabe, Yusuke; Abé, Hiroyuki; Kamimura, Hiroteru; Sakamaki, Akira; Yokoo, Takeshi; Kamimura, Kenya; Tsuchiya, Atsunori; Osaki, Akihiko; Igarashi, Kazumasa; Waguri, Nobuo; Yanagi, Masahiko; Takahashi, Toru; Sugitani, Soichi; Kobayashi, Yuka; Takamura, Masaaki; Yoshikawa, Akira; Ishikawa, Toru; Yoshida, Toshiaki; Watanabe, Toshiaki; Bannai, Hitoshi; Kubota, Tomoyuki; Funakoshi, Kazuhiro; Wakabayashi, Hiroto; Kurita, So; Ogata, Norio; Watanabe, Masashi; Mita, Yuhsaku; Mori, Shigeki; Sugiyama, Motoya; Miyajima, Toru; Takahashi, Sumio; Sato, Shuichi; Ishizuka, Kisei; Ohta, H; Aoyagi, Yoshinobu; Terai, Shuji

doi:10.1002/jgh3.12789

Cited by 2 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We adopted the Paris II criteria in the present study, as they could predict overall survival, liver-related death, and future prevalence of symptoms in patients with PBC. 4,6 The percentage of patients who met the requirements in this study was approximately equivalent to that in previous reports; therefore, we believe that the results from this study are reproducible.…”

Section: Discussionsupporting

confidence: 85%

“…23,24 These studies did not use the Paris II criteria, which have been reported to be the best for prognosis prediction, to determine treatment response. 4,6 We reported that prothrombin time % and AST were the independent predictors for the Paris II criteria; however, ROC was 0.695 and 0.669, respectively. 6 The AUC for data 1 and 2 was >0.8, sufficiently high for use in actual clinical practice.…”

Section: Discussionmentioning

confidence: 93%

“…[1][2][3] However, almost 20%-40% of patients fail to respond to treatment. 4,5 Furthermore, the treatment response after UDCA usage is one of the most critical factors in predicting outcomes in patients with PBC. 6 We had previously reported that the Paris II criteria are the best for predicting the outcome in patients with PBC, 6 and these criteria were used in the present study.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Development and validation of machine learning model for predicting treatment responders in patients with primary biliary cholangitis

Kimura,

Takahashi,

Setsu

et al. 2023

Hepatology Research

Self Cite

View full text Add to dashboard Cite

AimsUrsodeoxycholic acid is the first‐line treatment for primary biliary cholangitis, and treatment response is one of the factors predicting the outcome. To prescribe alternative therapies, clinicians might need additional information before deciphering the treatment response to ursodeoxycholic acid, contributing to a better patient prognosis. In this study, we developed and validated machine learning (ML) algorithms to predict treatment responses using pretreatment data.MethodsThis multicenter cohort study included collecting datasets from two data samples. Data 1 included 245 patients from 18 hospitals for ML development, and was divided into (i) training and (ii) development sets. Data 2 (iii: test set) included 51 patients from our hospital for validation. An extreme gradient boosted tree predicted the treatment response in the ML model. The area under the curve was used to evaluate the efficacy of the algorithm.ResultsData 1 showed that patients complying with the Paris II treatment response had significantly lower serum alkaline phosphatase and total bilirubin levels than those who did not respond. Three factors, total bilirubin, total protein, and alanine aminotransferase levels were selected as essential variables for prediction. Data 2 showed that patients complying with the Paris II criteria had significantly high prothrombin time and low total bilirubin levels. The area under the curve of extreme gradient boosted tree was good for (ii) (0.811) and (iii) (0.856).ConclusionsWe demonstrated the efficacy of ML in predicting the treatment response for patients with primary biliary cholangitis. Early identification of cases requiring additional treatment with our novel ML model may improve prognosis.

show abstract

Section: Discussionsupporting

confidence: 85%

Section: Discussionmentioning

confidence: 93%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development and validation of machine learning model for predicting treatment responders in patients with primary biliary cholangitis

Kimura,

Takahashi,

Setsu

et al. 2023

Hepatology Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…As these studies aimed to predict the Barcelona, Paris I, or Toronto criteria, it is difficult to compare our results with theirs. However, previous reports have shown that Paris II criteria could predict OS, LRD, and newly developed symptoms in patients with PBC 16,17 . From these data, we deduced that our prediction model could be more useful than previous prediction models.…”

Section: Discussionmentioning

confidence: 67%

“…Treatment response at 12 months after initial UDCA treatment is recognized as a surrogate marker for early detection of high‐risk patients as per the guidelines. Well‐known methods to detect good treatment response are the Paris I, Paris II, Barcelona, and Ehime criteria 2,8,16,27 . We have reported previously that the Paris II criteria may be able to predict overall survival (OS), liver‐related deaths (LRD), and newly developed symptoms 17,31 .…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2023

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Cumulative risk of developing a new symptom in patients with primary biliary cholangitis and its impact on prognosis

Cited by 2 publications

References 25 publications

Development and validation of machine learning model for predicting treatment responders in patients with primary biliary cholangitis

Development and validation of machine learning model for predicting treatment responders in patients with primary biliary cholangitis

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

Contact Info

Product

Resources

About