Moon Haeng Hur, Terry Cheuk-Fung Yip, Seung Up Kim, Hyun Woong Lee, Han Ah Lee, Hyung-Chul Lee, Grace Lai-Hung Wong, Vincent Wai-Sun Wong, Jun Yong Park, Sang Hoon Ahn, Beom Kyung Kim, Hwi Young Kim, Yeon Seok Seo, Hyunjae Shin, Jeayeon Park, Yunmi Ko, Youngsu Park, Yun Bin Lee, Su Jong Yu, Sang Hyub Lee, Yoon Jun Kim, Jung-Hwan Yoon, Jeong-Hoon Lee
{"title":"A machine learning model to predict liver-related outcomes after the functional cure of chronic hepatitis B.","authors":"Moon Haeng Hur, Terry Cheuk-Fung Yip, Seung Up Kim, Hyun Woong Lee, Han Ah Lee, Hyung-Chul Lee, Grace Lai-Hung Wong, Vincent Wai-Sun Wong, Jun Yong Park, Sang Hoon Ahn, Beom Kyung Kim, Hwi Young Kim, Yeon Seok Seo, Hyunjae Shin, Jeayeon Park, Yunmi Ko, Youngsu Park, Yun Bin Lee, Su Jong Yu, Sang Hyub Lee, Yoon Jun Kim, Jung-Hwan Yoon, Jeong-Hoon Lee","doi":"10.1016/j.jhep.2024.08.016","DOIUrl":null,"url":null,"abstract":"<p><strong>Background & aims: </strong>The risk of hepatocellular carcinoma (HCC) and hepatic decompensation persists after hepatitis B surface antigen (HBsAg) seroclearance. This study aimed to develop and validate a machine learning model to predict the risk of liver-related outcomes (LROs) following HBsAg seroclearance.</p><p><strong>Methods: </strong>A total of 4,787 consecutive patients who achieved HBsAg seroclearance between 2000 and 2022 were enrolled from 6 centers in South Korea and a territory-wide database in Hong Kong, comprising the training (n=944), internal validation (n=1,102), and external validation (n=2,741) cohorts. Three machine learning-based models were developed and compared in each cohort. The primary outcome was the development of any LRO, including HCC, decompensation, and liver-related death.</p><p><strong>Results: </strong>During a median follow-up of 55.2 (interquartile range=30.1-92.3) months, 123 LROs were confirmed (1.1%/person-year) in the Korean cohort. A model with the best predictive performance in the training cohort was selected as the final model (designated as PLAN-B-CURE), which was constructed using a gradient boosting algorithm and 7 variables (age, sex, diabetes, alcohol consumption, cirrhosis, albumin, and platelet count). Compared to previous HCC prediction models, PLAN-B-CURE showed significantly superior accuracy in the training cohort (c-index: 0.82 vs. 0.63-0.70, all P<0.001; area under the receiver operating characteristic curve: 0.86 vs. 0.62-0.72, all P<0.01; area under the precision-recall curve: 0.53 vs. 0.13-0.29, all P<0.01). PLAN-B-CURE showed a reliable calibration function (Hosmer-Lemeshow test P>0.05) and these results were reproduced in the internal and external validation cohorts.</p><p><strong>Conclusion: </strong>This novel machine learning model consisting of 7 variables provides reliable risk prediction of LRO after HBsAg seroclearance that can be used for personalized surveillance.</p>","PeriodicalId":15888,"journal":{"name":"Journal of Hepatology","volume":null,"pages":null},"PeriodicalIF":26.8000,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Hepatology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.jhep.2024.08.016","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GASTROENTEROLOGY & HEPATOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Background & aims: The risk of hepatocellular carcinoma (HCC) and hepatic decompensation persists after hepatitis B surface antigen (HBsAg) seroclearance. This study aimed to develop and validate a machine learning model to predict the risk of liver-related outcomes (LROs) following HBsAg seroclearance.
Methods: A total of 4,787 consecutive patients who achieved HBsAg seroclearance between 2000 and 2022 were enrolled from 6 centers in South Korea and a territory-wide database in Hong Kong, comprising the training (n=944), internal validation (n=1,102), and external validation (n=2,741) cohorts. Three machine learning-based models were developed and compared in each cohort. The primary outcome was the development of any LRO, including HCC, decompensation, and liver-related death.
Results: During a median follow-up of 55.2 (interquartile range=30.1-92.3) months, 123 LROs were confirmed (1.1%/person-year) in the Korean cohort. A model with the best predictive performance in the training cohort was selected as the final model (designated as PLAN-B-CURE), which was constructed using a gradient boosting algorithm and 7 variables (age, sex, diabetes, alcohol consumption, cirrhosis, albumin, and platelet count). Compared to previous HCC prediction models, PLAN-B-CURE showed significantly superior accuracy in the training cohort (c-index: 0.82 vs. 0.63-0.70, all P<0.001; area under the receiver operating characteristic curve: 0.86 vs. 0.62-0.72, all P<0.01; area under the precision-recall curve: 0.53 vs. 0.13-0.29, all P<0.01). PLAN-B-CURE showed a reliable calibration function (Hosmer-Lemeshow test P>0.05) and these results were reproduced in the internal and external validation cohorts.
Conclusion: This novel machine learning model consisting of 7 variables provides reliable risk prediction of LRO after HBsAg seroclearance that can be used for personalized surveillance.
期刊介绍:
The Journal of Hepatology is the official publication of the European Association for the Study of the Liver (EASL). It is dedicated to presenting clinical and basic research in the field of hepatology through original papers, reviews, case reports, and letters to the Editor. The Journal is published in English and may consider supplements that pass an editorial review.