{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:07:03Z","timestamp":1790273223946,"version":"4.1.0"},"reference-count":43,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100011614","name":"University of Kelaniya","doi-asserted-by":"publisher","award":[".RC\/2024\/G03"],"award-info":[{"award-number":[".RC\/2024\/G03"]}],"id":[{"id":"10.13039\/501100011614","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The European Association for the Study of the Liver (EASL) metabolic dysfunction-associated steatotic liver disease (MASLD) screening algorithm involves two steps: initial screening with FIB-4, followed by referral for vibration-controlled transient elastography (VCTE) in patients likely to have significant fibrosis (SF). However, VCTE is not widely available in resource-limited settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Aim<\/jats:title>\n                    <jats:p>To optimise the EASL MASLD screening algorithm for resource-poor settings using machine learning (ML).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We analysed data from 964 adults aged \u226535 years who underwent VCTE at a tertiary referral centre in Sri Lanka between November 2024 and 2025. Multiple ML models using different methods and variable combinations were trained on 80% of the dataset and tested on the remaining 20%. The best models were selected based on performance and externally validated on data from 430 patients who underwent VCTE before November 2024. Model performance was compared with that of the FIB-4 score using confusion matrices.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A Random Forest model incorporating age, AST, ALT, and platelet count separately, rather than using the FIB-4 score, outperformed in predicting SF. The model using all variables showed the best predictive performance for SF, with an AUC-ROC of 0.808. The variables used in the model, in descending order of feature importance, were AST, platelet count, BMI, diabetes mellitus, ALT, age, hypertension, dyslipidaemia, sex, family history, diabetes complication, hypothyroidism, and smoking. External validation of the all-variable model demonstrated an AUC of 0.795 and predicted SF in 9.0% more patients without increasing negative VCTE referrals compared with using the FIB-4 score as the screening tool in the first step of the MASLD screening algorithm.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec005\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>ML-based models were more effective than the FIB-4 score as the first-line screening tool for VCTE referrals, substantially improving the identification of patients with significant fibrosis in this South Asian cohort.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0352231","type":"journal-article","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:27:56Z","timestamp":1790270876000},"page":"e0352231","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimisation of metabolic dysfunction-associated steatotic liver disease (MASLD) screening algorithm for resource-poor settings using machine learning"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3328-1553","authenticated-orcid":true,"given":"Chamila","family":"Mettananda","sequence":"first","affiliation":[{"name":"University of Kelaniya","place":["Ragama, Sri Lanka"],"department":["Faculty of Medicine"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6343-0755","authenticated-orcid":true,"given":"Kaveesha","family":"Sivasumithran","sequence":"additional","affiliation":[{"name":"University of Colombo","place":["Colombo, Sri Lanka"],"department":["Faculty of Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lakmali","family":"Ranaweera","sequence":"additional","affiliation":[{"name":"North Colombo Teaching Hospital","place":["Ragama, Sri Lanka"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anjalika","family":"Madhubhashini","sequence":"additional","affiliation":[{"name":"North Colombo Teaching Hospital","place":["Ragama, Sri Lanka"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chamila","family":"Ranawaka","sequence":"additional","affiliation":[{"name":"North Colombo Teaching Hospital","place":["Ragama, Sri Lanka"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4065-2639","authenticated-orcid":true,"given":"Arunasalam","family":"Pathmeswaran","sequence":"additional","affiliation":[{"name":"University of Kelaniya","place":["Ragama, Sri Lanka"],"department":["Faculty of Medicine"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anuradha","family":"Dassanayake","sequence":"additional","affiliation":[{"name":"University of Kelaniya","place":["Ragama, Sri Lanka"],"department":["Faculty of Medicine"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,24]]},"reference":[{"issue":"9","key":"pone.0352231.ref001","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1016\/S2468-1253(22)00165-0","article-title":"The prevalence and incidence of NAFLD worldwide: a systematic review and meta-analysis","volume":"7","author":"K Riazi","year":"2022","journal-title":"Lancet Gastroenterol Hepatol"},{"issue":"2","key":"pone.0352231.ref002","doi-asserted-by":"crossref","first-page":"519","DOI":"10.2337\/dc20-1778","article-title":"High Prevalence of Advanced Liver Fibrosis Assessed by Transient Elastography Among U.S. Adults With Type 2 Diabetes","volume":"44","author":"S Ciardullo","year":"2021","journal-title":"Diabetes Care"},{"issue":"4","key":"pone.0352231.ref003","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1016\/j.jhep.2019.06.021","article-title":"The global epidemiology of NAFLD and NASH in patients with type 2 diabetes: A systematic review and meta-analysis","volume":"71","author":"ZM Younossi","year":"2019","journal-title":"J Hepatol"},{"issue":"2","key":"pone.0352231.ref004","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1053\/j.gastro.2018.04.034","article-title":"Fibrosis Severity as a Determinant of Cause-Specific Mortality in Patients With Advanced Nonalcoholic Fatty Liver Disease: A Multi-National Cohort Study","volume":"155","author":"E Vilar-Gomez","year":"2018","journal-title":"Gastroenterology"},{"issue":"21","key":"pone.0352231.ref005","doi-asserted-by":"crossref","first-page":"2063","DOI":"10.1056\/NEJMra1503519","article-title":"Cause, Pathogenesis, and Treatment of Nonalcoholic Steatohepatitis","volume":"377","author":"AM Diehl","year":"2017","journal-title":"N Engl J Med"},{"key":"pone.0352231.ref006","doi-asserted-by":"crossref","DOI":"10.1016\/j.jhep.2014.12.012","article-title":"NAFLD: a multisystem disease","volume":"62","author":"CD Byrne","year":"2015","journal-title":"J Hepatol"},{"issue":"17","key":"pone.0352231.ref007","doi-asserted-by":"crossref","first-page":"1559","DOI":"10.1056\/NEJMoa2029349","article-title":"Prospective Study of Outcomes in Adults with Nonalcoholic Fatty Liver Disease","volume":"385","author":"AJ Sanyal","year":"2021","journal-title":"N Engl J Med"},{"issue":"2","key":"pone.0352231.ref008","doi-asserted-by":"crossref","DOI":"10.1053\/j.gastro.2023.04.025","article-title":"Fibrosis Progression Rate in Biopsy-Proven Nonalcoholic Fatty Liver Disease Among People With Diabetes Versus People Without Diabetes: A Multicenter Study","volume":"165","author":"DQ Huang","year":"2023","journal-title":"Gastroenterology"},{"issue":"2","key":"pone.0352231.ref009","doi-asserted-by":"crossref","first-page":"399","DOI":"10.2337\/dc20-1997","article-title":"Advanced Liver Fibrosis Is Common in Patients With Type 2 Diabetes Followed in the Outpatient Setting: The Need for Systematic Screening","volume":"44","author":"R Lomonaco","year":"2021","journal-title":"Diabetes Care"},{"issue":"3","key":"pone.0352231.ref010","article-title":"Steatotic liver disease and cancer: from pathogenesis to therapeutic targets. eGastroenterology","volume":"3","author":"Z Yang","year":"2025"},{"issue":"1","key":"pone.0352231.ref011","article-title":"Liver fibrosis with persistently normal alanine transaminase levels exhibits a distinct treatment response in MASLD","volume":"12","author":"L Luo","year":"2025","journal-title":"BMJ Open Gastroenterol"},{"key":"pone.0352231.ref012","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1111\/dom.70545","article-title":"Providing holistic care for patients with metabolic dysfunction-associated steatotic liver disease\/metabolic dysfunction-associated steatohepatitis: Key aspects of clinical assessment and how to develop individualised care plans for surveillance and interventions","author":"L Chen","year":"2026","journal-title":"Diabetes Obes Metab"},{"issue":"6","key":"pone.0352231.ref013","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":"5","key":"pone.0352231.ref014","doi-asserted-by":"crossref","first-page":"1557","DOI":"10.1002\/hep.29085","article-title":"Increased risk of mortality by fibrosis stage in nonalcoholic fatty liver disease: Systematic review and meta-analysis","volume":"65","author":"PS Dulai","year":"2017","journal-title":"Hepatology"},{"issue":"7","key":"pone.0352231.ref015","doi-asserted-by":"crossref","first-page":"1375","DOI":"10.1136\/gutjnl-2020-322786","article-title":"Mortality in biopsy-confirmed nonalcoholic fatty liver disease: results from a nationwide cohort","volume":"70","author":"TG Simon","year":"2021","journal-title":"Gut"},{"issue":"5","key":"pone.0352231.ref016","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1016\/j.eprac.2022.03.010","article-title":"American Association of Clinical Endocrinology Clinical Practice Guideline for the Diagnosis and Management of Nonalcoholic Fatty Liver Disease in Primary Care and Endocrinology Clinical Settings: Co-Sponsored by the American Association for the Study of Liver Diseases (AASLD)","volume":"28","author":"K Cusi","year":"2022","journal-title":"Endocr Pract"},{"issue":"5","key":"pone.0352231.ref017","doi-asserted-by":"crossref","first-page":"1797","DOI":"10.1097\/HEP.0000000000000323","article-title":"AASLD Practice Guidance on the clinical assessment and management of nonalcoholic fatty liver disease","volume":"77","author":"ME Rinella","year":"2023","journal-title":"Hepatology"},{"issue":"11","key":"pone.0352231.ref018","doi-asserted-by":"crossref","first-page":"2375","DOI":"10.1007\/s00125-024-06196-3","article-title":"EASL\u2013EASD\u2013EASO Clinical Practice Guidelines on the management of metabolic dysfunction-associated steatotic liver disease (MASLD): Executive Summary","volume":"67","author":"European Association for the Study of the Liver, European Association for the Study of Diabetes, European Association for the Study of Obesity","year":"2024","journal-title":"Diabetologia"},{"issue":"1","key":"pone.0352231.ref019","doi-asserted-by":"crossref","first-page":"14","DOI":"10.2337\/cd21-as01","article-title":"Standards of Medical Care in Diabetes\u20142021 Abridged for Primary Care Providers","volume":"39","author":"American Diabetes Association","year":"2021","journal-title":"Clinical Diabetes"},{"key":"pone.0352231.ref020","article-title":"Introduction and Methodology: Standards of Care in Diabetes\u20142023","volume":"46","author":"NA ElSayed","year":"2023","journal-title":"Diabetes Care"},{"issue":"10","key":"pone.0352231.ref021","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1016\/j.gastrohep.2022.12.002","article-title":"NAFLD and type 2 diabetes: A practical guide for the joint management","volume":"46","author":"I Genua","year":"2023","journal-title":"Gastroenterol Hepatol"},{"issue":"1","key":"pone.0352231.ref022","doi-asserted-by":"crossref","first-page":"29","DOI":"10.2337\/dsi23-0014","article-title":"Making Sense of the Nonalcoholic Fatty Liver Disease Clinical Practice Guidelines: What Clinicians Need to Know","volume":"37","author":"K Cusi","year":"2024","journal-title":"Diabetes Spectrum"},{"issue":"3","key":"pone.0352231.ref023","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1016\/j.jhep.2021.05.025","article-title":"EASL Clinical Practice Guidelines on non-invasive tests for evaluation of liver disease severity and prognosis - 2021 update","volume":"75","author":"Liver European Association for the Study of the","year":"2021","journal-title":"J Hepatol"},{"issue":"1","key":"pone.0352231.ref024","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1111\/jgh.13857","article-title":"Asia-Pacific Working Party on Non-alcoholic Fatty Liver Disease guidelines 2017-Part 1: Definition, risk factors and assessment","volume":"33","author":"VW-S Wong","year":"2018","journal-title":"J Gastroenterol Hepatol"},{"issue":"1","key":"pone.0352231.ref025","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1002\/cld.1045","article-title":"Nonalcoholic Fatty Liver Disease and Recent Guideline Updates","volume":"17","author":"Y Ando","year":"2021","journal-title":"Clin Liver Dis"},{"issue":"2","key":"pone.0352231.ref026","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1002\/hep.32655","article-title":"Machine learning models are superior to noninvasive tests in identifying clinically significant stages of NAFLD and NAFLD-related cirrhosis","volume":"77","author":"D Chang","year":"2023","journal-title":"Hepatology"},{"key":"pone.0352231.ref027","first-page":"4304376","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 Res Int"},{"issue":"10","key":"pone.0352231.ref028","doi-asserted-by":"crossref","first-page":"1417","DOI":"10.4254\/wjh.v13.i10.1417","article-title":"Machine learning models for predicting non-alcoholic fatty liver disease in the general United States population: NHANES database","volume":"13","author":"A Atsawarungruangkit","year":"2021","journal-title":"World J Hepatol"},{"issue":"7","key":"pone.0352231.ref029","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.3390\/jpm12071026","article-title":"Machine-Learning Algorithm for Predicting Fatty Liver Disease in a Taiwanese Population","volume":"12","author":"Y-Y Chen","year":"2022","journal-title":"J Pers Med"},{"issue":"3","key":"pone.0352231.ref030","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1002\/jgh3.12716","article-title":"Machine learning to predict progression of non-alcoholic fatty liver to non-alcoholic steatohepatitis or fibrosis","volume":"6","author":"S Ghandian","year":"2022","journal-title":"JGH Open"},{"issue":"10","key":"pone.0352231.ref031","doi-asserted-by":"crossref","first-page":"551","DOI":"10.34172\/aim.31269","article-title":"Machine-Learning Application for Predicting Metabolic Dysfunction-Associated Steatotic Liver Disease Using Laboratory and Body Composition Indicators","volume":"27","author":"F Masaebi","year":"2024","journal-title":"Arch Iran Med"},{"issue":"2","key":"pone.0352231.ref032","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0299487","article-title":"Machine learning approaches to enhance diagnosis and staging of patients with MASLD using routinely available clinical information","volume":"19","author":"M McTeer","year":"2024","journal-title":"PLoS One"},{"issue":"1","key":"pone.0352231.ref033","doi-asserted-by":"crossref","first-page":"2442","DOI":"10.1038\/s41598-024-51741-0","article-title":"Machine learning approaches for early detection of non-alcoholic steatohepatitis based on clinical and blood parameters","volume":"14","author":"AR Naderi Yaghouti","year":"2024","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0352231.ref034","doi-asserted-by":"crossref","first-page":"4942","DOI":"10.1038\/s41598-023-32129-y","article-title":"Application of machine learning in predicting non-alcoholic fatty liver disease using anthropometric and body composition indices","volume":"13","author":"F Razmpour","year":"2023","journal-title":"Sci Rep"},{"issue":"6","key":"pone.0352231.ref035","doi-asserted-by":"crossref","first-page":"774","DOI":"10.1111\/apt.17891","article-title":"Machine learning improves the prediction of significant fibrosis in Asian patients with metabolic dysfunction-associated steatotic liver disease - The Gut and Obesity in Asia (GO-ASIA) Study","volume":"59","author":"N Verma","year":"2024","journal-title":"Aliment Pharmacol Ther"},{"key":"pone.0352231.ref036","doi-asserted-by":"crossref","first-page":"107932","DOI":"10.1016\/j.cmpb.2023.107932","article-title":"Application of artificial intelligence techniques for non-alcoholic fatty liver disease diagnosis: A systematic review (2005-2023)","volume":"244","author":"H Zamanian","year":"2024","journal-title":"Comput Methods Programs Biomed"},{"issue":"6","key":"pone.0352231.ref037","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1002\/hep.21178","article-title":"Development of a simple noninvasive index to predict significant fibrosis in patients with HIV\/HCV coinfection","volume":"43","author":"RK Sterling","year":"2006","journal-title":"Hepatology"},{"issue":"1","key":"pone.0352231.ref038","doi-asserted-by":"crossref","first-page":"8589","DOI":"10.1038\/s41598-024-59183-4","article-title":"An explainable machine learning model for prediction of high-risk nonalcoholic steatohepatitis","volume":"14","author":"B Njei","year":"2024","journal-title":"Sci Rep"},{"key":"pone.0352231.ref039","doi-asserted-by":"crossref","first-page":"100753","DOI":"10.1016\/j.lansea.2026.100753","article-title":"A multicentre survey of liver fibrosis burden in type 2 diabetes in India: the DiaFib-Liver Study","volume":"47","author":"A Kumar","year":"2026","journal-title":"Lancet Reg Health Southeast Asia"},{"issue":"2","key":"pone.0352231.ref040","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1016\/j.jhep.2016.03.011","article-title":"PNPLA3 gene in liver diseases","volume":"65","author":"E Tr\u00e9po","year":"2016","journal-title":"J Hepatol"},{"issue":"7","key":"pone.0352231.ref041","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1007\/s00439-012-1141-y","article-title":"A multi-ethnic study of a PNPLA3 gene variant and its association with disease severity in non-alcoholic fatty liver disease","volume":"131","author":"SM Zain","year":"2012","journal-title":"Hum Genet"},{"issue":"12","key":"pone.0352231.ref042","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1038\/ng.257","article-title":"Genetic variation in PNPLA3 confers susceptibility to nonalcoholic fatty liver disease","volume":"40","author":"S Romeo","year":"2008","journal-title":"Nat Genet"},{"issue":"26","key":"pone.0352231.ref043","doi-asserted-by":"crossref","first-page":"1101","DOI":"10.4254\/wjh.v9.i26.1101","article-title":"Regional differences in genetic susceptibility to non-alcoholic liver disease in two distinct Indian ethnicities","volume":"9","author":"G Bale","year":"2017","journal-title":"World J Hepatol"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0352231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:28:01Z","timestamp":1790270881000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0352231"}},"subtitle":[],"editor":[{"given":"Lanlan","family":"Chen","sequence":"first","affiliation":[{"name":"Charite Universitatsmedizin Berlin","place":["GERMANY"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,24]]},"references-count":43,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0352231","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,24]]}}}