{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T21:09:02Z","timestamp":1791839342136,"version":"4.3.4"},"reference-count":30,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T00:00:00Z","timestamp":1709164800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Innovative Medicines Initiative 2 Joint Undertaking","award":["777377"],"award-info":[{"award-number":["777377"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Aims<\/jats:title>\n<jats:p>Metabolic dysfunction Associated Steatotic Liver Disease (MASLD) outcomes such as MASH (metabolic dysfunction associated steatohepatitis), fibrosis and cirrhosis are ordinarily determined by resource-intensive and invasive biopsies. We aim to show that routine clinical tests offer sufficient information to predict these endpoints.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>Using the LITMUS Metacohort derived from the European NAFLD Registry, the largest MASLD dataset in Europe, we create three combinations of features which vary in degree of procurement including a 19-variable feature set that are attained through a routine clinical appointment or blood test. This data was used to train predictive models using supervised machine learning (ML) algorithm XGBoost, alongside missing imputation technique MICE and class balancing algorithm SMOTE. Shapley Additive exPlanations (SHAP) were added to determine relative importance for each clinical variable.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>Analysing nine biopsy-derived MASLD outcomes of cohort size ranging between 5385 and 6673 subjects, we were able to predict individuals at training set AUCs ranging from 0.719-0.994, including classifying individuals who are At-Risk MASH at an AUC = 0.899. Using two further feature combinations of 26-variables and 35-variables, which included composite scores known to be good indicators for MASLD endpoints and advanced specialist tests, we found predictive performance did not sufficiently improve. We are also able to present local and global explanations for each ML model, offering clinicians interpretability without the expense of worsening predictive performance.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusions<\/jats:title>\n<jats:p>This study developed a series of ML models of accuracy ranging from 71.9\u201499.4% using only easily extractable and readily available information in predicting MASLD outcomes which are usually determined through highly invasive means.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0299487","type":"journal-article","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T18:26:33Z","timestamp":1709231193000},"page":"e0299487","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":39,"title":["Machine learning approaches to enhance diagnosis and staging of patients with MASLD using routinely available clinical information"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2889-030X","authenticated-orcid":true,"given":"Matthew","family":"McTeer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8322-4672","authenticated-orcid":true,"given":"Douglas","family":"Applegate","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5624-6726","authenticated-orcid":true,"given":"Peter","family":"Mesenbrink","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vlad","family":"Ratziu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00f6rn M.","family":"Schattenberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisabetta","family":"Bugianesi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Geier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manuel","family":"Romero Gomez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean-Francois","family":"Dufour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5590-8601","authenticated-orcid":true,"given":"Mattias","family":"Ekstedt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7527-4714","authenticated-orcid":true,"given":"Sven","family":"Francque","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hannele","family":"Yki-Jarvinen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Allison","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8909-0345","authenticated-orcid":true,"given":"Luca","family":"Valenti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Miele","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9882-8874","authenticated-orcid":true,"given":"Michael","family":"Pavlides","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeremy","family":"Cobbold","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgios","family":"Papatheodoridis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adriaan G.","family":"Holleboom","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dina","family":"Tiniakos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clifford","family":"Brass","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9518-0088","authenticated-orcid":true,"given":"Quentin M.","family":"Anstee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Missier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"on behalf of the LITMUS Consortium investigators","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,2,29]]},"reference":[{"key":"pone.0299487.ref001","first-page":"101133","article-title":"A multi-society Delphi consensus statement on new fatty liver disease nomenclature","author":"ME Rinella","year":"2023","journal-title":"Annals of Hepatology"},{"issue":"1","key":"pone.0299487.ref002","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1038\/nrgastro.2017.109","article-title":"Global burden of NAFLD and NASH: trends, predictions, risk factors and prevention","volume":"15","author":"Z Younossi","year":"2018","journal-title":"Nature reviews Gastroenterology & hepatology"},{"key":"pone.0299487.ref003","doi-asserted-by":"crossref","DOI":"10.21037\/tgh-2020-15","article-title":"Liver transplantation in patients with non-alcoholic steatohepatitis and alcohol-related liver disease: the dust is yet to settle","volume":"7","author":"SK Satapathy","year":"2022","journal-title":"Translational Gastroenterology and Hepatology"},{"issue":"7","key":"pone.0299487.ref004","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1038\/s41575-019-0145-7","article-title":"From NASH to HCC: current concepts and future challenges","volume":"16","author":"QM Anstee","year":"2019","journal-title":"Nature reviews Gastroenterology & hepatology"},{"issue":"6","key":"pone.0299487.ref005","doi-asserted-by":"crossref","first-page":"1611","DOI":"10.1053\/j.gastro.2020.01.043","article-title":"Association between fibrosis stage and outcomes of patients with nonalcoholic fatty liver disease: a systematic review and meta-analysis","volume":"158","author":"RS Taylor","year":"2020","journal-title":"Gastroenterology"},{"issue":"6","key":"pone.0299487.ref006","doi-asserted-by":"crossref","first-page":"1313","DOI":"10.1002\/hep.20701","article-title":"Design and validation of a histological scoring system for nonalcoholic fatty liver disease","volume":"41","author":"DE Kleiner","year":"2005","journal-title":"Hepatology"},{"issue":"12","key":"pone.0299487.ref007","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1136\/jclinpath-2013-201620","article-title":"Non-alcoholic fatty liver disease: non-invasive investigation and risk stratification","volume":"66","author":"J Dyson","year":"2013","journal-title":"Journal of clinical pathology"},{"issue":"5","key":"pone.0299487.ref008","doi-asserted-by":"crossref","first-page":"1030","DOI":"10.1016\/j.jhep.2022.01.011","article-title":"Complexity of ballooned hepatocyte feature recognition: Defining a training atlas for artificial intelligence-based imaging in NAFLD","volume":"76","author":"EM Brunt","year":"2022","journal-title":"Journal of hepatology"},{"issue":"6","key":"pone.0299487.ref009","doi-asserted-by":"crossref","first-page":"1322","DOI":"10.1016\/j.jhep.2020.06.025","article-title":"Suboptimal reliability of liver biopsy evaluation has implications for randomized clinical trials","volume":"73","author":"BA Davison","year":"2020","journal-title":"Journal of hepatology"},{"issue":"6","key":"pone.0299487.ref010","doi-asserted-by":"crossref","first-page":"1362","DOI":"10.1016\/j.jhep.2022.03.026","article-title":"Impact of non-invasive biomarkers on hepatology practice: past, present and future","volume":"76","author":"QM Anstee","year":"2022","journal-title":"Journal of hepatology"},{"issue":"3","key":"pone.0299487.ref011","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1038\/s41591-021-01652-8","article-title":"Non-invasive biomarkers of nonalcoholic steatohepatitis: the FNIH NIMBLE project","volume":"28","author":"AJ Sanyal","year":"2022","journal-title":"Nature medicine"},{"key":"pone.0299487.ref012","doi-asserted-by":"crossref","first-page":"106175","DOI":"10.1016\/j.cct.2020.106175","article-title":"The European NAFLD Registry: a real-world longitudinal cohort study of nonalcoholic fatty liver disease","volume":"98","author":"T Hardy","year":"2020","journal-title":"Contemporary clinical trials"},{"key":"pone.0299487.ref013","article-title":"Biomarkers for staging fibrosis and non-alcoholic steatohepatitis in non-alcoholic fatty liver disease (the LITMUS project): a comparative diagnostic accuracy study","author":"Y Vali","year":"2023","journal-title":"The Lancet Gastroenterology & Hepatology"},{"issue":"10","key":"pone.0299487.ref014","doi-asserted-by":"crossref","first-page":"e0240867","DOI":"10.1371\/journal.pone.0240867","article-title":"Selecting the best machine learning algorithm to support the diagnosis of Non-Alcoholic Fatty Liver Disease: A meta learner study","volume":"15","author":"P Sorino","year":"2020","journal-title":"PLoS One"},{"issue":"3","key":"pone.0299487.ref015","doi-asserted-by":"crossref","first-page":"e0214436","DOI":"10.1371\/journal.pone.0214436","article-title":"Non-invasive assessment of NAFLD as systemic disease\u2014a machine learning perspective","volume":"14","author":"A Canbay","year":"2019","journal-title":"PloS one"},{"issue":"1","key":"pone.0299487.ref016","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1093\/gastro\/goaa035","article-title":"A novel model for predicting fatty liver disease by means of an artificial neural network","volume":"9","author":"YS Chen","year":"2021","journal-title":"Gastroenterology report"},{"issue":"1","key":"pone.0299487.ref017","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1097\/HEP.0000000000000364","article-title":"Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study","volume":"78","author":"J Lee","year":"2023","journal-title":"Hepatology"},{"issue":"6","key":"pone.0299487.ref018","doi-asserted-by":"crossref","first-page":"e1003149","DOI":"10.1371\/journal.pmed.1003149","article-title":"Predicting and elucidating the etiology of fatty liver disease: A machine learning modeling and validation study in the IMI DIRECT cohorts","volume":"17","author":"N Atabaki-Pasdar","year":"2020","journal-title":"PLoS medicine"},{"key":"pone.0299487.ref019","article-title":"Application of machine learning techniques for clinical predictive modeling: a cross-sectional study on nonalcoholic fatty liver disease in China","volume":"2018","author":"H Ma","year":"2018","journal-title":"BioMed research international"},{"issue":"4","key":"pone.0299487.ref020","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1111\/apt.14172","article-title":"Laboratory parameter-based machine learning model for excluding non-alcoholic fatty liver disease (NAFLD) in the general population","volume":"46","author":"TF Yip","year":"2017","journal-title":"Alimentary pharmacology & therapeutics"},{"issue":"1","key":"pone.0299487.ref021","doi-asserted-by":"crossref","first-page":"5573","DOI":"10.1038\/s41598-023-32551-2","article-title":"NASHmap: clinical utility of a machine learning model to identify patients at risk of NASH in real-world settings","volume":"13","author":"JM Schattenberg","year":"2023","journal-title":"Scientific Reports"},{"issue":"2","key":"pone.0299487.ref022","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1002\/hep.21984","article-title":"Noninvasive markers of fibrosis in nonalcoholic fatty liver disease: Validating the European Liver Fibrosis Panel and exploring simple markers","volume":"47","author":"IN Guha","year":"2008","journal-title":"Hepatology"},{"issue":"2","key":"pone.0299487.ref023","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1016\/j.jhep.2020.03.036","article-title":"Enhanced liver fibrosis test for the non-invasive diagnosis of fibrosis in patients with NAFLD: a systematic review and meta-analysis","volume":"73","author":"Y Vali","year":"2020","journal-title":"Journal of hepatology"},{"issue":"3","key":"pone.0299487.ref024","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1016\/j.jhepr.2019.06.004","article-title":"Performance of the PRO-C3 collagen neo-epitope biomarker in non-alcoholic fatty liver disease","volume":"1","author":"M Boyle","year":"2019","journal-title":"Jhep Reports"},{"issue":"12","key":"pone.0299487.ref025","doi-asserted-by":"crossref","first-page":"1920","DOI":"10.3390\/biomedicines9121920","article-title":"Systematic review with meta-analysis: diagnostic accuracy of pro-C3 for hepatic fibrosis in patients with non-alcoholic fatty liver disease","volume":"9","author":"AL Mak","year":"2021","journal-title":"Biomedicines"},{"key":"pone.0299487.ref026","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining; 2016. p. 785\u2013794.","DOI":"10.1145\/2939672.2939785"},{"key":"pone.0299487.ref027","first-page":"1","article-title":"mice: Multivariate imputation by chained equations in R","volume":"45","author":"S Van Buuren","year":"2011","journal-title":"Journal of statistical software"},{"key":"pone.0299487.ref028","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"NV Chawla","year":"2002","journal-title":"Journal of artificial intelligence research"},{"key":"pone.0299487.ref029","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"SM Lundberg","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"pone.0299487.ref030","unstructured":"Lundberg SM, Lee SI. Consistent feature attribution for tree ensembles. arXiv preprint arXiv:170606060. 2017;."}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0299487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T18:27:04Z","timestamp":1709231224000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0299487"}},"subtitle":[],"editor":[{"given":"Pavel","family":"Strnad","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,2,29]]},"references-count":30,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,2,29]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0299487","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,29]]}}}