Literature DB >> 24169273

Machine learning algorithms outperform conventional regression models in predicting development of hepatocellular carcinoma.

Amit G Singal1, Ashin Mukherjee, B Joseph Elmunzer, Peter D R Higgins, Anna S Lok, Ji Zhu, Jorge A Marrero, Akbar K Waljee.   

Abstract

OBJECTIVES: Predictive models for hepatocellular carcinoma (HCC) have been limited by modest accuracy and lack of validation. Machine-learning algorithms offer a novel methodology, which may improve HCC risk prognostication among patients with cirrhosis. Our study's aim was to develop and compare predictive models for HCC development among cirrhotic patients, using conventional regression analysis and machine-learning algorithms.
METHODS: We enrolled 442 patients with Child A or B cirrhosis at the University of Michigan between January 2004 and September 2006 (UM cohort) and prospectively followed them until HCC development, liver transplantation, death, or study termination. Regression analysis and machine-learning algorithms were used to construct predictive models for HCC development, which were tested on an independent validation cohort from the Hepatitis C Antiviral Long-term Treatment against Cirrhosis (HALT-C) Trial. Both models were also compared with the previously published HALT-C model. Discrimination was assessed using receiver operating characteristic curve analysis, and diagnostic accuracy was assessed with net reclassification improvement and integrated discrimination improvement statistics.
RESULTS: After a median follow-up of 3.5 years, 41 patients developed HCC. The UM regression model had a c-statistic of 0.61 (95% confidence interval (CI) 0.56-0.67), whereas the machine-learning algorithm had a c-statistic of 0.64 (95% CI 0.60-0.69) in the validation cohort. The HALT-C model had a c-statistic of 0.60 (95% CI 0.50-0.70) in the validation cohort and was outperformed by the machine-learning algorithm. The machine-learning algorithm had significantly better diagnostic accuracy as assessed by net reclassification improvement (P<0.001) and integrated discrimination improvement (P=0.04).
CONCLUSIONS: Machine-learning algorithms improve the accuracy of risk stratifying patients with cirrhosis and can be used to accurately identify patients at high-risk for developing HCC.

Entities:  

Mesh:

Year:  2013        PMID: 24169273      PMCID: PMC4610387          DOI: 10.1038/ajg.2013.332

Source DB:  PubMed          Journal:  Am J Gastroenterol        ISSN: 0002-9270            Impact factor:   10.864


  23 in total

1.  Evaluating the added predictive ability of a new marker: from area under the ROC curve to reclassification and beyond.

Authors:  Michael J Pencina; Ralph B D'Agostino; Ralph B D'Agostino; Ramachandran S Vasan
Journal:  Stat Med       Date:  2008-01-30       Impact factor: 2.373

Review 2.  Validation, updating and impact of clinical prediction rules: a review.

Authors:  D B Toll; K J M Janssen; Y Vergouwe; K G M Moons
Journal:  J Clin Epidemiol       Date:  2008-11       Impact factor: 6.437

3.  Natural history of untreated nonsurgical hepatocellular carcinoma: rationale for the design and evaluation of therapeutic trials.

Authors:  J M Llovet; J Bustamante; A Castells; R Vilana; M del C Ayuso; M Sala; C Brú; J Rodés; J Bruix
Journal:  Hepatology       Date:  1999-01       Impact factor: 17.425

Review 4.  Recent advances in the treatment of hepatocellular carcinoma.

Authors:  Amit G Singal; Jorge A Marrero
Journal:  Curr Opin Gastroenterol       Date:  2010-05       Impact factor: 3.287

5.  Use and misuse of the receiver operating characteristic curve in risk prediction.

Authors:  Nancy R Cook
Journal:  Circulation       Date:  2007-02-20       Impact factor: 29.690

6.  Assessing the performance of prediction models: a framework for traditional and novel measures.

Authors:  Ewout W Steyerberg; Andrew J Vickers; Nancy R Cook; Thomas Gerds; Mithat Gonen; Nancy Obuchowski; Michael J Pencina; Michael W Kattan
Journal:  Epidemiology       Date:  2010-01       Impact factor: 4.822

7.  Algorithms outperform metabolite tests in predicting response of patients with inflammatory bowel disease to thiopurines.

Authors:  Akbar K Waljee; Joel C Joyce; Sijian Wang; Aditi Saxena; Margaret Hart; Ji Zhu; Peter D R Higgins
Journal:  Clin Gastroenterol Hepatol       Date:  2009-10-14       Impact factor: 11.382

8.  Artificial neural networks for the prediction of response to interferon plus ribavirin treatment in patients with chronic hepatitis C.

Authors:  P A Maiellaro; R Cozzolongo; P Marino
Journal:  Curr Pharm Des       Date:  2004       Impact factor: 3.116

9.  Meta-analysis: surveillance with ultrasound for early-stage hepatocellular carcinoma in patients with cirrhosis.

Authors:  A Singal; M L Volk; A Waljee; R Salgia; P Higgins; M A M Rogers; J A Marrero
Journal:  Aliment Pharmacol Ther       Date:  2009-04-08       Impact factor: 8.171

10.  Disease-free survival after hepatic resection in hepatocellular carcinoma patients: a prediction approach using artificial neural network.

Authors:  Wen-Hsien Ho; King-Teh Lee; Hong-Yaw Chen; Te-Wei Ho; Herng-Chia Chiu
Journal:  PLoS One       Date:  2012-01-03       Impact factor: 3.240

View more
  67 in total

Review 1.  Biomarker development for hepatocellular carcinoma early detection: current and future perspectives.

Authors:  Shreya Sengupta; Neehar D Parikh
Journal:  Hepat Oncol       Date:  2017-11-17

2.  Predicting Inpatient Length of Stay After Brain Tumor Surgery: Developing Machine Learning Ensembles to Improve Predictive Performance.

Authors:  Whitney E Muhlestein; Dallin S Akagi; Jason M Davies; Lola B Chambless
Journal:  Neurosurgery       Date:  2019-09-01       Impact factor: 4.654

Review 3.  The effect of PNPLA3 on fibrosis progression and development of hepatocellular carcinoma: a meta-analysis.

Authors:  Amit G Singal; Hema Manjunath; Adam C Yopp; Muhammad S Beg; Jorge A Marrero; Purva Gopal; Akbar K Waljee
Journal:  Am J Gastroenterol       Date:  2014-01-21       Impact factor: 10.864

4.  Differences in hepatocellular carcinoma risk, predictors and trends over time according to etiology of cirrhosis.

Authors:  George N Ioannou; Pamela Green; Elliott Lowy; Elijah J Mun; Kristin Berry
Journal:  PLoS One       Date:  2018-09-27       Impact factor: 3.240

5.  A genomic and clinical prognostic index for hepatitis C-related early-stage cirrhosis that predicts clinical deterioration.

Authors:  Lindsay Y King; Claudia Canasto-Chibuque; Kara B Johnson; Shun Yip; Xintong Chen; Kensuke Kojima; Manjeet Deshmukh; Anu Venkatesh; Poh Seng Tan; Xiaochen Sun; Augusto Villanueva; Angelo Sangiovanni; Venugopalan Nair; Milind Mahajan; Masahiro Kobayashi; Hiromitsu Kumada; Massimo Iavarone; Massimo Colombo; Maria Isabel Fiel; Scott L Friedman; Josep M Llovet; Raymond T Chung; Yujin Hoshida
Journal:  Gut       Date:  2014-08-20       Impact factor: 23.059

6.  For Whom is Hepatocellular Carcinoma Surveillance After Sustained Virologic Response Cost-Effective?

Authors:  Amit G Singal; George N Ioannou
Journal:  Clin Gastroenterol Hepatol       Date:  2019-02-14       Impact factor: 11.382

7.  Racial, social, and clinical determinants of hepatocellular carcinoma surveillance.

Authors:  Amit G Singal; Xilong Li; Jasmin Tiro; Pragathi Kandunoori; Beverley Adams-Huet; Mahendra S Nehra; Adam Yopp
Journal:  Am J Med       Date:  2014-08-10       Impact factor: 4.965

8.  Factors that affect accuracy of α-fetoprotein test in detection of hepatocellular carcinoma in patients with cirrhosis.

Authors:  Purva Gopal; Adam C Yopp; Akbar K Waljee; Jason Chiang; Mahendra Nehra; Pragathi Kandunoori; Amit G Singal
Journal:  Clin Gastroenterol Hepatol       Date:  2013-10-02       Impact factor: 11.382

Review 9.  Hepatocellular Carcinoma From Epidemiology to Prevention: Translating Knowledge into Practice.

Authors:  Amit G Singal; Hashem B El-Serag
Journal:  Clin Gastroenterol Hepatol       Date:  2015-08-15       Impact factor: 11.382

Review 10.  Automated Quantitative Nuclear Cardiology Methods.

Authors:  Manish Motwani; Daniel S Berman; Guido Germano; Piotr Slomka
Journal:  Cardiol Clin       Date:  2015-10-20       Impact factor: 2.213

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.