{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T14:25:09Z","timestamp":1787235909933,"version":"build-2736575974"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Josephine Hughes Sterling Foundation and Inflammatory Bowel Disease Innovative Research Funds at Houston Methodist Hospital"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Dig Dis Sci"],"DOI":"10.1007\/s10620-026-10180-9","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T10:16:07Z","timestamp":1787220967000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond ICD-10 Codes: A Multi-class Machine-Learning Approach to Identify True IBD Cases in Electronic Medical Records"],"prefix":"10.1007","author":[{"given":"Oscar","family":"Noble","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Poojasree","family":"Pasupuleti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fadi","family":"Shehadeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dheeraj","family":"Reddy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claire","family":"Sweeney","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rasha","family":"Bara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Megan","family":"Lewis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eamonn M. M.","family":"Quigley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bincy P.","family":"Abraham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"key":"10180_CR1","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1093\/ibd\/izab187","volume":"28","author":"A Javaid","year":"2022","unstructured":"Javaid A, Shahab O, Adorno W, Fernandes P, May E, Syed S. Machine learning predictive outcomes modeling in inflammatory bowel diseases. Inflamm Bowel Dis. 2022;28:819\u2013829. https:\/\/doi.org\/10.1093\/ibd\/izab187.","journal-title":"Inflamm Bowel Dis."},{"key":"10180_CR2","doi-asserted-by":"publisher","DOI":"10.3390\/jcm10204745","author":"S Kraszewski","year":"2021","unstructured":"Kraszewski S, Szczurek W, Szymczak J, Regula M, Neubauer K. Machine learning prediction model for inflammatory bowel disease based on laboratory markers: working model in a discovery cohort study. J Clin Med. 2021. https:\/\/doi.org\/10.3390\/jcm10204745.","journal-title":"J Clin Med."},{"key":"10180_CR3","doi-asserted-by":"publisher","first-page":"1411","DOI":"10.1097\/MIB.0b013e31828133fd","volume":"19","author":"AN Ananthakrishnan","year":"2013","unstructured":"Ananthakrishnan AN, Cai T, Savova G et al. Improving case definition of Crohn\u2019s disease and ulcerative colitis in electronic medical records using natural language processing: a novel informatics approach. Inflamm Bowel Dis. 2013;19:1411\u20131420. https:\/\/doi.org\/10.1097\/MIB.0b013e31828133fd.","journal-title":"Inflamm Bowel Dis."},{"key":"10180_CR4","doi-asserted-by":"publisher","first-page":"e000378","DOI":"10.1136\/bmjgast-2020-000378","volume":"7","author":"M Singla","year":"2020","unstructured":"Singla M, Hutfless S, Al Kazzi E, Rodriguez B, Betteridge J, Brant S. Clinical codes combined with procedure codes increase diagnostic accuracy of Crohn\u2019s disease in a US Military health record. BMJ Open Gastroenterol. 2020;7:e000378. https:\/\/doi.org\/10.1136\/bmjgast-2020-000378.","journal-title":"BMJ Open Gastroenterol."},{"key":"10180_CR5","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1093\/ibd\/izac131","volume":"29","author":"S Hutfless","year":"2023","unstructured":"Hutfless S, Jasper RA, Tilak A et al. A systematic review of Crohn\u2019s disease case definitions in administrative or claims databases. Inflamm Bowel Dis. 2023;29:705\u2013715. https:\/\/doi.org\/10.1093\/ibd\/izac131.","journal-title":"Inflamm Bowel Dis."},{"key":"10180_CR6","doi-asserted-by":"publisher","first-page":"e0136651","DOI":"10.1371\/journal.pone.0136651","volume":"10","author":"KP Liao","year":"2015","unstructured":"Liao KP, Ananthakrishnan AN, Kumar V et al. Methods to develop an electronic medical record phenotype algorithm to compare the risk of coronary artery disease across 3 chronic disease cohorts. PLoS One. 2015;10:e0136651. https:\/\/doi.org\/10.1371\/journal.pone.0136651.","journal-title":"PLoS One."},{"key":"10180_CR7","doi-asserted-by":"publisher","first-page":"671","DOI":"10.2147\/CLEP.S151339","volume":"10","author":"MY Friedman","year":"2018","unstructured":"Friedman MY, Leventer-Roberts M, Rosenblum J et al. Development and validation of novel algorithms to identify patients with inflammatory bowel diseases in Israel: an epi-IIRN group study. Clin Epidemiol. 2018;10:671\u2013681. https:\/\/doi.org\/10.2147\/CLEP.S151339.","journal-title":"Clin Epidemiol."},{"key":"10180_CR8","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.1093\/ibd\/izaa263","volume":"27","author":"G Chen","year":"2021","unstructured":"Chen G, Lissoos T, Dieyi C, Null KD. Development and validation of an inflammatory bowel disease severity index using US administrative claims data: a retrospective cohort study. Inflamm Bowel Dis. 2021;27:1177\u20131183. https:\/\/doi.org\/10.1093\/ibd\/izaa263.","journal-title":"Inflamm Bowel Dis."},{"key":"10180_CR9","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1111\/jgh.15732","volume":"37","author":"H Ogino","year":"2022","unstructured":"Ogino H, Morikubo H, Fukaura K et al. Validation of a claims-based algorithm to identify cases of ulcerative colitis in Japan. J Gastroenterol Hepatol. 2022;37:499\u2013506. https:\/\/doi.org\/10.1111\/jgh.15732.","journal-title":"J Gastroenterol Hepatol."},{"key":"10180_CR10","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1093\/ibd\/izad053","volume":"29","author":"GK Dawwas","year":"2023","unstructured":"Dawwas GK, Weiss A, Constant BD et al. Development and validation of claims-based definitions to identify incident and prevalent inflammatory bowel disease in administrative healthcare databases. Inflamm Bowel Dis. 2023;29:1993\u20131996. https:\/\/doi.org\/10.1093\/ibd\/izad053.","journal-title":"Inflamm Bowel Dis."},{"key":"10180_CR11","doi-asserted-by":"publisher","first-page":"309","DOI":"10.2147\/CLEP.S383738","volume":"15","author":"Y Ingrasciotta","year":"2023","unstructured":"Ingrasciotta Y, Isgro V, Foti SS et al. Testing of coding algorithms for inflammatory bowel disease identification, as indication for use of biological drugs, using a claims database from Southern Italy. Clin Epidemiol. 2023;15:309\u2013321. https:\/\/doi.org\/10.2147\/CLEP.S383738.","journal-title":"Clin Epidemiol."},{"key":"10180_CR12","doi-asserted-by":"publisher","first-page":"46958019887816","DOI":"10.1177\/0046958019887816","volume":"56","author":"Y Ye","year":"2019","unstructured":"Ye Y, Manne S, Bennett D. Identifying patients with inflammatory bowel diseases in an administrative health claims database: do algorithms generate similar findings? Inquiry 2019;56:46958019887816. https:\/\/doi.org\/10.1177\/0046958019887816.","journal-title":"Inquiry"},{"key":"10180_CR13","doi-asserted-by":"publisher","first-page":"e1002683","DOI":"10.1371\/journal.pmed.1002683","volume":"15","author":"JR Zech","year":"2018","unstructured":"Zech JR, Badgeley MA, Liu M, Costa AB, Titano JJ, Oermann EK. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Med. 2018;15:e1002683. https:\/\/doi.org\/10.1371\/journal.pmed.1002683.","journal-title":"PLoS Med."},{"key":"10180_CR14","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","volume":"20","author":"J Cohen","year":"1960","unstructured":"Cohen J. A coefficient of agreement for nominal scales. Educ Psychol Measure. 1960;20:37\u201346. https:\/\/doi.org\/10.1177\/001316446002000104.","journal-title":"Educ Psychol Measure."},{"key":"10180_CR15","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/s41664-018-0068-2","volume":"2","author":"Y Xu","year":"2018","unstructured":"Xu Y, Goodacre R. On splitting training and validation set: a comparative study of cross-validation, bootstrap and systematic sampling for estimating the generalization performance of supervised learning. J Anal Test. 2018;2:249\u2013262. https:\/\/doi.org\/10.1007\/s41664-018-0068-2.","journal-title":"J Anal Test."},{"key":"10180_CR16","doi-asserted-by":"publisher","first-page":"12","DOI":"10.11613\/BM.2014.003","volume":"24","author":"S Sperandei","year":"2014","unstructured":"Sperandei S. Understanding logistic regression analysis. Biochem Med (Zagreb). 2014;24:12\u201318. https:\/\/doi.org\/10.11613\/BM.2014.003.","journal-title":"Biochem Med (Zagreb)."},{"key":"10180_CR17","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1080\/10888438.2015.1107073","volume":"20","author":"K Matsuki","year":"2016","unstructured":"Matsuki K, Kuperman V, Van Dyke JA. The random forests statistical technique: an examination of its value for the study of reading. Sci Stud Read. 2016;20:20\u201333. https:\/\/doi.org\/10.1080\/10888438.2015.1107073.","journal-title":"Sci Stud Read."},{"key":"10180_CR18","doi-asserted-by":"publisher","first-page":"117954682211336","DOI":"10.1177\/11795468221133611","volume":"16","author":"A Moore","year":"2022","unstructured":"Moore A, Bell M. XGBoost, a novel explainable AI technique, in the prediction of myocardial infarction: A UK biobank cohort study. Clin Med Insights Cardiol. 2022;16:11795468221133612. https:\/\/doi.org\/10.1177\/11795468221133611.","journal-title":"Clin Med Insights Cardiol."},{"key":"10180_CR19","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1089\/neur.2020.0009","volume":"1","author":"T Inoue","year":"2020","unstructured":"Inoue T, Ichikawa D, Ueno T et al. XGBoost, a machine learning method, predicts neurological recovery in patients with cervical spinal cord injury. Neurotrauma Rep. 2020;1:8\u201316. https:\/\/doi.org\/10.1089\/neur.2020.0009.","journal-title":"Neurotrauma Rep."},{"key":"10180_CR20","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.ejim.2024.11.022","volume":"132","author":"Y Takefuji","year":"2025","unstructured":"Takefuji Y. Evaluating feature importance biases in logistic regression: recommendations for robust statistical methods. Eur J Intern Med. 2025;132:135\u2013136. https:\/\/doi.org\/10.1016\/j.ejim.2024.11.022.","journal-title":"Eur J Intern Med."},{"key":"10180_CR21","doi-asserted-by":"publisher","first-page":"e10243","DOI":"10.1002\/lrh2.10243","volume":"4","author":"R Khare","year":"2020","unstructured":"Khare R, Kappelman MD, Samson C et al. Development and evaluation of an EHR-based computable phenotype for identification of pediatric Crohn\u2019s disease patients in a National Pediatric Learning Health System. Learn Health Syst. 2020;4:e10243. https:\/\/doi.org\/10.1002\/lrh2.10243.","journal-title":"Learn Health Syst."},{"key":"10180_CR22","doi-asserted-by":"publisher","first-page":"e70056","DOI":"10.1111\/cts.70056","volume":"17","author":"AV Ponce-Bobadilla","year":"2024","unstructured":"Ponce-Bobadilla AV, Schmitt V, Maier CS, Mensing S, Stodtmann S. Practical guide to SHAP analysis: explaining supervised machine learning model predictions in drug development. Clin Transl Sci. 2024;17:e70056. https:\/\/doi.org\/10.1111\/cts.70056.","journal-title":"Clin Transl Sci."},{"key":"10180_CR23","doi-asserted-by":"publisher","first-page":"2406","DOI":"10.1007\/s10620-014-3174-7","volume":"59","author":"JK Hou","year":"2014","unstructured":"Hou JK, Tan M, Stidham RW et al. Accuracy of diagnostic codes for identifying patients with ulcerative colitis and crohn\u2019s disease in the veterans affairs health care system. Dig Dis Sci. 2014;59:2406\u20132410. https:\/\/doi.org\/10.1007\/s10620-014-3174-7.","journal-title":"Dig Dis Sci."},{"key":"10180_CR24","doi-asserted-by":"publisher","first-page":"765474","DOI":"10.3389\/fmed.2021.765474","volume":"8","author":"Z Cai","year":"2021","unstructured":"Cai Z, Wang S, Li J. Treatment of inflammatory bowel disease: a comprehensive review. Front Med. 2021;8:765474. https:\/\/doi.org\/10.3389\/fmed.2021.765474.","journal-title":"Front Med."},{"key":"10180_CR25","doi-asserted-by":"publisher","first-page":"e51003","DOI":"10.2196\/51003","volume":"25","author":"J Chishtie","year":"2023","unstructured":"Chishtie J, Sapiro N, Wiebe N et al. Use of epic electronic health record system for health care research: scoping review. J Med Internet Res. 2023;25:e51003. https:\/\/doi.org\/10.2196\/51003.","journal-title":"J Med Internet Res."}],"container-title":["Digestive Diseases and Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10620-026-10180-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10620-026-10180-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10620-026-10180-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T10:16:08Z","timestamp":1787220968000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10620-026-10180-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":25,"alternative-id":["10180"],"URL":"https:\/\/doi.org\/10.1007\/s10620-026-10180-9","relation":{},"ISSN":["0163-2116","1573-2568"],"issn-type":[{"value":"0163-2116","type":"print"},{"value":"1573-2568","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]},"assertion":[{"value":"3 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"BP is a consultant for AbbVie, Canon, Celltrion, Ironwood, Lilly, Pfizer, Takeda, Johnson & Johnson, Prometheus, and Sanofi, and a speaker for AbbVie, Janssen, Takeda, Lilly. The rest of the author list reports no disclosures. All other authors disclose no conflicts.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study was conducted under approval of the Houston Methodist Institutional Review Board (IRB protocol #PRO00018644).","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}}]}}