Machine learning prediction model for treatment responders in patients with primary biliary cholangitis
Abstract 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 respon...
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-06-01
|
| Series: | JGH Open |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/jgh3.12915 |
| _version_ | 1797796237538230272 |
|---|---|
| author | Naruhiro Kimura Kazuya Takahashi Toru Setsu Shu Goto Suguru Miida Nobutaka Takeda Yuichi Kojima Yoshihisa Arao Kazunao Hayashi Norihiro Sakai Yusuke Watanabe Hiroyuki Abe Hiroteru Kamimura Akira Sakamaki Takeshi Yokoo Kenya Kamimura Atsunori Tsuchiya Shuji Terai |
| author_facet | Naruhiro Kimura Kazuya Takahashi Toru Setsu Shu Goto Suguru Miida Nobutaka Takeda Yuichi Kojima Yoshihisa Arao Kazunao Hayashi Norihiro Sakai Yusuke Watanabe Hiroyuki Abe Hiroteru Kamimura Akira Sakamaki Takeshi Yokoo Kenya Kamimura Atsunori Tsuchiya Shuji Terai |
| author_sort | Naruhiro Kimura |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-03-13T03:30:04Z |
| format | Article |
| id | doaj.art-1d727ae04c9f49aa841a7010e16fa942 |
| institution | Directory Open Access Journal |
| issn | 2397-9070 |
| language | English |
| last_indexed | 2024-03-13T03:30:04Z |
| publishDate | 2023-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | JGH Open |
| spelling | doaj.art-1d727ae04c9f49aa841a7010e16fa9422023-06-24T09:50:22ZengWileyJGH Open2397-90702023-06-017643143810.1002/jgh3.12915Machine learning prediction model for treatment responders in patients with primary biliary cholangitisNaruhiro Kimura0Kazuya Takahashi1Toru Setsu2Shu Goto3Suguru Miida4Nobutaka Takeda5Yuichi Kojima6Yoshihisa Arao7Kazunao Hayashi8Norihiro Sakai9Yusuke Watanabe10Hiroyuki Abe11Hiroteru Kamimura12Akira Sakamaki13Takeshi Yokoo14Kenya Kamimura15Atsunori Tsuchiya16Shuji Terai17Division of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanDivision of Gastroenterology and Hepatology Niigata University Graduate School of Medical and Dental Sciences Niigata JapanAbstract 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.https://doi.org/10.1002/jgh3.12915machine learningprimary biliary cholangitistreatment responseursodeoxycholic acid |
| spellingShingle | Naruhiro Kimura Kazuya Takahashi Toru Setsu Shu Goto Suguru Miida Nobutaka Takeda Yuichi Kojima Yoshihisa Arao Kazunao Hayashi Norihiro Sakai Yusuke Watanabe Hiroyuki Abe Hiroteru Kamimura Akira Sakamaki Takeshi Yokoo Kenya Kamimura Atsunori Tsuchiya Shuji Terai Machine learning prediction model for treatment responders in patients with primary biliary cholangitis JGH Open machine learning primary biliary cholangitis treatment response ursodeoxycholic acid |
| title | Machine learning prediction model for treatment responders in patients with primary biliary cholangitis |
| title_full | Machine learning prediction model for treatment responders in patients with primary biliary cholangitis |
| title_fullStr | Machine learning prediction model for treatment responders in patients with primary biliary cholangitis |
| title_full_unstemmed | Machine learning prediction model for treatment responders in patients with primary biliary cholangitis |
| title_short | Machine learning prediction model for treatment responders in patients with primary biliary cholangitis |
| title_sort | machine learning prediction model for treatment responders in patients with primary biliary cholangitis |
| topic | machine learning primary biliary cholangitis treatment response ursodeoxycholic acid |
| url | https://doi.org/10.1002/jgh3.12915 |
| work_keys_str_mv | AT naruhirokimura machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT kazuyatakahashi machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT torusetsu machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT shugoto machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT sugurumiida machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT nobutakatakeda machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT yuichikojima machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT yoshihisaarao machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT kazunaohayashi machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT norihirosakai machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT yusukewatanabe machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT hiroyukiabe machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT hiroterukamimura machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT akirasakamaki machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT takeshiyokoo machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT kenyakamimura machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT atsunoritsuchiya machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis AT shujiterai machinelearningpredictionmodelfortreatmentrespondersinpatientswithprimarybiliarycholangitis |