{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:56:28Z","timestamp":1791568588657,"version":"4.3.4"},"reference-count":18,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"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>Unplanned readmissions in neurology signify care gaps, increasing costs, and morbidity. This study aimed to develop and internally validate an AI model to predict unplanned readmissions among neurological patients in Jordan.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Method and materials<\/jats:title>\n                    <jats:p>We conducted a retrospective analysis of 2,795 adult neurology admissions (2022\u20132024). Patients\u2019 diagnosis was grouped and analyzed based on the International Classification of Diseases and Related Health Problems, Tenth Revision. Nine prediction models were compared using Electronic Health Record (EHR) data. The Chi-square Automatic Interaction Detection (CHAID) decision tree was selected for optimal performance and interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The unplanned readmission rate was 8.9%, highest in the neoplasm group (24%). The CHAID model demonstrated modest discriminative ability (AUC\u2009=\u20090.671). For risk stratification, it achieved a balanced accuracy of 0.63, sensitivity of 0.52, and specificity of 0.74. Key predictors were Charlson Comorbidity Index (CCI\u2009\u2265\u20095), age, geographic region, length of stay, and sex. Risk-stratification metrics were calculated descriptively from the complete cohort, whereas independent model validation was based on the held-out test-set AUC. Subgroup analysis revealed distinct risk profiles: vascular patients with high CCI (p\u2009&lt;\u2009.001, \u03c72\u2009=\u200966.368), young females of whom 37.3% had neoplasms (p\u2009=\u2009.037, \u03c72\u2009=\u20094.367), and functional disorder patients from northern regions (p\u2009=\u2009.009, \u03c72\u2009=\u20098.897).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This is one of the first studies from the Middle East to demonstrate the potential of the CHAID model for risk stratification in neurology readmissions. The model offers an interpretable framework to identify high-risk patient subgroups but requires external validation before clinical application. Its poor-to-fair discriminative performance (AUC\u2009=\u20090.671) supports population-level risk stratification rather than individual-level prediction.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0360077","type":"journal-article","created":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:27:42Z","timestamp":1791566862000},"page":"e0360077","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting unplanned readmissions in neurological patients: A large-scale AI-driven analysis using CHAID decision trees"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0632-7146","authenticated-orcid":true,"given":"Randa","family":"Al-Kharabsheh","sequence":"first","affiliation":[{"name":"University of Jordan","place":["Amman, Jordan"],"department":["Critical Care Nursing, Clinical Nursing Department, School of Nursing"]},{"name":"King Hussein Medical Hospital, Jordanian Royal Medical Services\/Army Forces","place":["Amman, Jordan"],"department":["Department of Training and Continuing Education"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4388-8332","authenticated-orcid":true,"given":"Muayyad","family":"Ahmad","sequence":"additional","affiliation":[{"name":"University of Jordan","place":["Amman, Jordan"],"department":["Clinical Nursing Department, School of Nursing"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,9]]},"reference":[{"issue":"5","key":"pone.0360077.ref001","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2019-034728","article-title":"Understanding the patient experience of early unplanned hospital readmission following acute care discharge: A qualitative descriptive study","volume":"10","author":"J Considine","year":"2020","journal-title":"BMJ Open"},{"issue":"11","key":"pone.0360077.ref002","doi-asserted-by":"crossref","first-page":"4291","DOI":"10.1111\/jan.14893","article-title":"Unplanned readmission for older persons: A concept analysis","volume":"77","author":"R Coatsworth-Puspoky","year":"2021","journal-title":"J Adv Nurs"},{"key":"pone.0360077.ref003","doi-asserted-by":"crossref","first-page":"2163","DOI":"10.2147\/CIA.S544949","article-title":"Interpretable machine Learning model for predicting 1-year unplanned readmissions in ischemic stroke patients with diabetes: A synergistic view of inflammation and metabolism","volume":"20","author":"Y Hu","year":"2025","journal-title":"Clin Interv Aging"},{"issue":"2","key":"pone.0360077.ref004","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1080\/20479700.2022.2099337","article-title":"The length of stay and readmissions of THA and TKA patients: A longitudinal analysis using a nationwide readmissions data","volume":"16","author":"S Muchiri","year":"2022","journal-title":"International Journal of Healthcare Management"},{"key":"pone.0360077.ref005","doi-asserted-by":"crossref","DOI":"10.1016\/j.wneu.2018.07.136","article-title":"Clinical risk factors and postoperative complications associated with unplanned hospital readmissions after cranial neurosurgery","volume":"119","author":"C Lopez Ramos","year":"2018","journal-title":"World Neurosurg"},{"issue":"11","key":"pone.0360077.ref006","doi-asserted-by":"crossref","first-page":"2647","DOI":"10.1007\/s00701-020-04521-4","article-title":"Early unplanned readmission of neurosurgical patients after treatment of intracranial lesions: A comparison between surgical and non-surgical intervention group","volume":"162","author":"C Sander","year":"2020","journal-title":"Acta Neurochir (Wien)"},{"issue":"1","key":"pone.0360077.ref007","doi-asserted-by":"crossref","first-page":"22152","DOI":"10.1038\/s41598-021-01641-4","article-title":"Factors associated with unplanned readmissions and costs following resection of brain metastases in the United States","volume":"11","author":"R Tonse","year":"2021","journal-title":"Sci Rep"},{"issue":"7","key":"pone.0360077.ref008","first-page":"1481","article-title":"Readmission risk prediction model for patients with chronic heart failure: A systematic review and meta-analysis","volume":"51","author":"J Liu","year":"2022","journal-title":"Iran J Public Health"},{"issue":"10","key":"pone.0360077.ref009","doi-asserted-by":"crossref","first-page":"11083","DOI":"10.21037\/apm-21-2884","article-title":"Risk factors for 30-day readmission in patients with ischemic stroke: A systematic review and meta-analysis","volume":"10","author":"Z Deng","year":"2021","journal-title":"Ann Palliat Med"},{"issue":"1","key":"pone.0360077.ref010","doi-asserted-by":"crossref","first-page":"189","DOI":"10.3171\/2014.12.JNS14447","article-title":"Cranial neurosurgical 30-day readmissions by clinical indication","volume":"123","author":"N Moghavem","year":"2015","journal-title":"J Neurosurg"},{"key":"pone.0360077.ref011","doi-asserted-by":"crossref","first-page":"154925","DOI":"10.1016\/j.jcrc.2024.154925","article-title":"Hospital readmission after surviving sepsis: A systematic review of readmission reasons and meta-analysis of readmission rates","volume":"85","author":"K Ackermann","year":"2025","journal-title":"J Crit Care"},{"issue":"11","key":"pone.0360077.ref012","doi-asserted-by":"crossref","first-page":"1046","DOI":"10.1136\/thoraxjnl-2017-210822","article-title":"Predicting risk of unplanned hospital readmission in survivors of critical illness: A population-level cohort study","volume":"74","author":"NI Lone","year":"2019","journal-title":"Thorax"},{"issue":"3","key":"pone.0360077.ref013","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s12028-018-0557-1","article-title":"Preventable readmissions and predictors of readmission after subarachnoid hemorrhage","volume":"29","author":"JW Liang","year":"2018","journal-title":"Neurocrit Care"},{"issue":"3","key":"pone.0360077.ref014","doi-asserted-by":"crossref","DOI":"10.1002\/brb3.3456","article-title":"Predictive model for identifying mild cognitive impairment in patients with type 2 diabetes mellitus: A CHAID decision tree analysis","volume":"14","author":"R Maimaitituerxun","year":"2024","journal-title":"Brain Behav"},{"key":"pone.0360077.ref015","article-title":"High mortality among 30-day readmission after stroke: Predictors and etiologies of readmission","volume":"8","author":"AM Nouh","year":"2017","journal-title":"Frontiers in Neurology"},{"issue":"11","key":"pone.0360077.ref016","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1007\/s11940-022-00734-3","article-title":"Quality improvement in neurocritical care: A review of the current landscape and best practices","volume":"24","author":"N Karanjia","year":"2022","journal-title":"Current Treatment Options in Neurology"},{"issue":"11","key":"pone.0360077.ref017","doi-asserted-by":"crossref","first-page":"2558","DOI":"10.3390\/math11112558","article-title":"Performance analysis of the CHAID algorithm for accuracy","volume":"11","author":"Y Yang","year":"2023","journal-title":"Mathematics"},{"key":"pone.0360077.ref018","doi-asserted-by":"crossref","first-page":"242717","DOI":"10.1155\/2014\/242717","article-title":"Use of CHAID decision trees to formulate pathways for the early detection of metabolic syndrome in young adults","volume":"2014","author":"B Miller","year":"2014","journal-title":"Comput Math Methods Med"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0360077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:27:45Z","timestamp":1791566865000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0360077"}},"subtitle":[],"editor":[{"given":"Yangming","family":"Ou","sequence":"first","affiliation":[{"name":"Harvard Medical School","place":["UNITED STATES OF AMERICA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,9]]},"references-count":18,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0360077","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,9]]}}}