{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T15:11:20Z","timestamp":1772205080937,"version":"3.50.1"},"reference-count":27,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T00:00:00Z","timestamp":1772150400000},"content-version":"unspecified","delay-in-days":26,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"LaunchTN SBIR\/STTR Matching Fund","award":["Not applicable"],"award-info":[{"award-number":["Not applicable"]}]},{"name":"Decode Health, Inc.","award":["Not applicable"],"award-info":[{"award-number":["Not applicable"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Health Care Inform"],"accepted":{"date-parts":[[2026,2,10]]},"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To develop and evaluate a machine learning (ML) model that predicts Crohn\u2019s disease (CD) patients responsible for the top quartile of healthcare spending.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>De-identified commercial claims (2016\u20132018) from ~267\u2009000 continuously enrolled members in a Midwestern state were analysed, including 994\u2009CD cases. Monthly data for each patient was aggregated into data points that included healthcare spending amounts, encounter interactions, demographics and binary flags for diagnoses, procedures and drug codes. Seven algorithm families were tuned using five-fold cross-validation (January 2016 to September 2017) and tested prospectively (November 2017 to February 2018). Monthly performance evaluations assessed the accuracy of predicting high-cost healthcare spending, using 4-month and 1-month historical cost analyses for comparison.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>ML models predicted an average of 80% of the dollars spent by top-quartile members during the 4-month evaluation period, compared with 67% for the 4-month baseline and 62% for the prior-month benchmark. The models identified an average of 51 new members entering the high-cost group each month, nearly double the yield of the 4-month historical method. These ML models more accurately anticipated inpatient encounters that drove excess spending.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Claims-based ML offers actionable lead time for payers and clinicians to enhance monitoring, adjust biological therapy or schedule elective care before emergency admissions occur. Because this framework relies exclusively on standard claim fields, it can be quickly extended to other episodic, high-variance conditions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Prospectively tested, claims-only ML models enhance short-term risk stratification in CD by identifying future high-cost patients. Future studies should confirm the clinical impact, cost savings and ensure equitable performance across diverse populations.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjhci-2025-101761","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T14:25:19Z","timestamp":1772202319000},"page":"e101761","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning framework for early identification of high-spending Crohn\u2019s disease patients using administrative claims"],"prefix":"10.1136","volume":"33","author":[{"given":"Lukasz S","family":"Wylezinski","sequence":"first","affiliation":[{"name":"Decode Health Inc, Nashville, Tennessee, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jamieson D","family":"Gray","sequence":"additional","affiliation":[{"name":"Decode Health Inc, Nashville, Tennessee, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9015-6321","authenticated-orcid":false,"suffix":"III","given":"Charles F","family":"Spurlock","sequence":"additional","affiliation":[{"name":"Decode Health Inc, Nashville, Tennessee, USA"},{"name":"Department of Medicine, Vanderbilt University School of Medicine, Nashville, Tennessee, USA"},{"name":"Wagner School of Public Service, New York University, New York, NY, USA"},{"name":"Thomas F. Frist, Jr. College of Medicine, Belmont University, Nashville, TN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"239","published-online":{"date-parts":[[2026,2,27]]},"reference":[{"key":"2026022706251054000_33.1.e101761.1","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2022.01.024"},{"key":"2026022706251054000_33.1.e101761.2","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1038\/s41572-020-0156-2","article-title":"Crohn\u2019s disease","volume":"6","author":"Roda","year":"2020","journal-title":"Nat Rev Dis Primers"},{"key":"2026022706251054000_33.1.e101761.3","first-page":"661","article-title":"Crohn\u2019s Disease: Diagnosis and Management","volume":"98","author":"Veauthier","year":"2018","journal-title":"Am Fam Physician"},{"key":"2026022706251054000_33.1.e101761.4","article-title":"Prevalence of Bowel Damage Assessed by Cross-Sectional Imaging in Early Crohn\u2019s Disease and its Impact on Disease Outcome","volume":"11","author":"Fiorino","year":"2017","journal-title":"ECCOJC"},{"key":"2026022706251054000_33.1.e101761.5","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2020.18936"},{"key":"2026022706251054000_33.1.e101761.6","doi-asserted-by":"crossref","first-page":"1515","DOI":"10.1016\/j.cgh.2018.07.032","article-title":"Early Initiation of Tumor Necrosis Factor Antagonist-Based Therapy for Patients With Crohn\u2019s Disease Reduces Costs Compared With Late Initiation","volume":"17","author":"Beilman","year":"2019","journal-title":"Clin Gastroenterol Hepatol"},{"key":"2026022706251054000_33.1.e101761.7","doi-asserted-by":"publisher","DOI":"10.1093\/ibd\/izz104"},{"key":"2026022706251054000_33.1.e101761.8","doi-asserted-by":"crossref","first-page":"1092","DOI":"10.1080\/13696998.2020.1789649","article-title":"Burden of Crohn\u2019s disease in the United States: long-term healthcare and work-loss related costs","volume":"23","author":"Manceur","year":"2020","journal-title":"J Med Econ"},{"key":"2026022706251054000_33.1.e101761.9","doi-asserted-by":"publisher","DOI":"10.1093\/ibd\/izz059"},{"key":"2026022706251054000_33.1.e101761.10","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1038\/ajg.2015.207","article-title":"Health Insurance Paid Costs and Drivers of Costs for Patients With Crohn\u2019s Disease in the United States","volume":"111","author":"Park","year":"2016","journal-title":"Am J Gastroenterol"},{"key":"2026022706251054000_33.1.e101761.11","doi-asserted-by":"crossref","first-page":"2607","DOI":"10.1016\/j.cgh.2022.02.021","article-title":"Earlier Anti-TNF Initiation Leads to Long-term Lower Health Care Utilization in Crohn\u2019s Disease but Not in Ulcerative Colitis","volume":"20","author":"Targownik","year":"2022","journal-title":"Clin Gastroenterol Hepatol"},{"key":"2026022706251054000_33.1.e101761.12","doi-asserted-by":"publisher","DOI":"10.1370\/afm.2124"},{"key":"2026022706251054000_33.1.e101761.13","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1093\/eurpub\/ckz168","article-title":"Benefits and challenges of Big Data in healthcare: an overview of the European initiatives","volume":"29","author":"Pastorino","year":"2019","journal-title":"Eur J Public Health"},{"key":"2026022706251054000_33.1.e101761.14","doi-asserted-by":"crossref","DOI":"10.1186\/2047-2501-2-3","article-title":"Big data analytics in healthcare: promise and potential","volume":"2","author":"Raghupathi","year":"2014","journal-title":"Health Inf Sci Syst"},{"key":"2026022706251054000_33.1.e101761.15","doi-asserted-by":"crossref","DOI":"10.1186\/s40537-021-00553-4","article-title":"The use of Big Data Analytics in healthcare","volume":"9","author":"Batko","year":"2022","journal-title":"J Big Data"},{"key":"2026022706251054000_33.1.e101761.16","doi-asserted-by":"crossref","first-page":"1330","DOI":"10.1038\/s41551-022-00898-y","article-title":"Shifting machine learning for healthcare from development to deployment and from models to data","volume":"6","author":"Zhang","year":"2022","journal-title":"Nat Biomed Eng"},{"key":"2026022706251054000_33.1.e101761.17","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-021-91580-x","article-title":"A machine learning approach to predict healthcare cost of breast cancer patients","volume":"11","author":"Rakshit","year":"2021","journal-title":"Sci Rep"},{"key":"2026022706251054000_33.1.e101761.18","doi-asserted-by":"crossref","first-page":"e288","DOI":"10.1016\/S2589-7500(23)00025-0","article-title":"The impact of commercial health datasets on medical research and health-care algorithms","volume":"5","author":"Alberto","year":"2023","journal-title":"Lancet Digit Health"},{"key":"2026022706251054000_33.1.e101761.19","doi-asserted-by":"crossref","DOI":"10.1186\/s12938-018-0568-3","article-title":"Machine learning approaches for predicting high cost high need patient expenditures in health care","volume":"17","author":"Yang","year":"2018","journal-title":"Biomed Eng Online"},{"key":"2026022706251054000_33.1.e101761.20","first-page":"1312","article-title":"Supervised Learning Methods for Predicting Healthcare Costs: Systematic Literature Review and Empirical Evaluation","volume":"2017","author":"Morid","year":"2017","journal-title":"AMIA Annu Symp Proc"},{"key":"2026022706251054000_33.1.e101761.21","doi-asserted-by":"crossref","DOI":"10.14309\/ctg.0000000000000507","article-title":"Simplified Machine Learning Models Can Accurately Identify High-Need High-Cost Patients With Inflammatory Bowel Disease","volume":"13","author":"Nguyen","year":"2022","journal-title":"Clin Transl Gastroenterol"},{"key":"2026022706251054000_33.1.e101761.22","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1016\/S2468-1253(19)30173-6","article-title":"Comorbidities in inflammatory bowel disease: a call for action","volume":"4","author":"Argollo","year":"2019","journal-title":"Lancet Gastroenterol Hepatol"},{"key":"2026022706251054000_33.1.e101761.23","doi-asserted-by":"publisher","DOI":"10.1111\/j.1572-0241.2001.03943.x"},{"key":"2026022706251054000_33.1.e101761.24","doi-asserted-by":"crossref","DOI":"10.1093\/crocol\/otaa080","article-title":"Management of Inflammatory Bowel Disease Patients With Clinical Care Pathways Reduces Emergency Department Utilization","volume":"2","author":"Lytvyak","year":"2020","journal-title":"Crohns Colitis 360"},{"key":"2026022706251054000_33.1.e101761.25","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0266464","article-title":"Telemonitoring for patients with inflammatory bowel disease amid the COVID-19 pandemic-A cost-effectiveness analysis","volume":"17","author":"Yao","year":"2022","journal-title":"PLoS One"},{"key":"2026022706251054000_33.1.e101761.26","doi-asserted-by":"crossref","first-page":"1763","DOI":"10.1007\/s11606-021-07333-z","article-title":"Prediction Models for Future High-Need High-Cost Healthcare Use: a Systematic Review","volume":"37","author":"de Ruijter","year":"2022","journal-title":"J Gen Intern Med"},{"key":"2026022706251054000_33.1.e101761.27","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"}],"container-title":["BMJ Health &amp; Care Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjhci-2025-101761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T14:25:22Z","timestamp":1772202322000},"score":1,"resource":{"primary":{"URL":"https:\/\/informatics.bmj.com\/lookup\/doi\/10.1136\/bmjhci-2025-101761"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,2,27]]},"published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1136\/bmjhci-2025-101761"],"URL":"https:\/\/doi.org\/10.1136\/bmjhci-2025-101761","relation":{},"ISSN":["2632-1009"],"issn-type":[{"value":"2632-1009","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}