{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T20:57:57Z","timestamp":1787345877607,"version":"build-2736575974"},"reference-count":63,"publisher":"BMJ","issue":"4","license":[{"start":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T00:00:00Z","timestamp":1775174400000},"content-version":"unspecified","delay-in-days":2,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100015339","name":"ACCP Foundation","doi-asserted-by":"publisher","award":["Meds for Optimization"],"award-info":[{"award-number":["Meds for Optimization"]}],"id":[{"id":"10.13039\/100015339","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2026,2,19]]},"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To develop and evaluate an explainable machine learning framework enhanced with synthetic data generation to predict unplanned 30-day hospital readmissions among patients with chronic obstructive pulmonary disease (COPD), heart failure (HF) and type 2 diabetes mellitus (T2DM), and to identify key clinical and social predictors of readmission.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>A retrospective cohort study using electronic health record data incorporating both structured variables and information extracted from unstructured clinical notes. Synthetic data were generated using advanced resampling and deep learning-based techniques to address outcome imbalance and improve model training.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>Intensive care unit and general ward admissions at a single tertiary academic medical centre included in the MIMIC-IV (Medical Information Mart for Intensive Care IV) database.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>Adult patients (\u226518 years) were admitted with a primary diagnosis of COPD (n=14\u2009050), HF (n=7097) or T2DM (n=12\u2009735) between 2008 and 2019, with complete 30-day follow-up and no in-hospital mortality during the index admission.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Primary and secondary outcome measures<\/jats:title>\n                    <jats:p>The primary outcome was unplanned all-cause hospital readmission within 30-days of discharge. Predictors were drawn from six domains, including demographics, comorbidities, clinical acuity, therapies, behavioural factors and care continuity. Predictive performance was evaluated using multiple machine learning methods and fivefold cross-validation, with model interpretability assessed using established goal and local explanation approaches.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Ensemble-based machine learning models demonstrated the strongest predictive performance across all three disease cohorts. Key predictors of readmission included higher illness severity, greater comorbidity burden, medication non-adherence, gaps in preventive care and limited social support. Models incorporating synthetic data augmentation showed improved discrimination compared with models trained on original data alone.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>An explainable synthetic-data driven framework incorporating clinical, behavioural and social data can support prediction of 30-day readmissions among patients with common chronic conditions using routinely available electronic health record data.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2025-108273","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T02:31:07Z","timestamp":1775442667000},"page":"e108273","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":2,"title":["Synthetic data-augmented machine learning for 30-day readmission prediction in patients with chronic conditions: a retrospective real-world study"],"prefix":"10.1136","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1799-7233","authenticated-orcid":false,"given":"Todd","family":"Brothers","sequence":"first","affiliation":[{"name":"Pharmacy Practice, University of Rhode Island - College of Pharmacy, Kingston, Rhode Island, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keyuri","family":"Adhikari","sequence":"additional","affiliation":[{"name":"Pharmaceutical Systems and Policy, West Virginia University, Morgantown, West Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maryam","family":"Ramazani","sequence":"additional","affiliation":[{"name":"Industrial and Management Systems Engineering, West Virginia University, Morgantown, West Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"Imtiaz","sequence":"additional","affiliation":[{"name":"Industrial and Management Systems Engineering, West Virginia University, Morgantown, West Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Al-Mamun","sequence":"additional","affiliation":[{"name":"Pharmaceutical Systems and Policy, West Virginia University, Morgantown, West Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,4,3]]},"reference":[{"key":"2026040308201324000_16.4.e108273.1","unstructured":"Bailey MK , Weiss AJ , Barrett ML , et al . Characteristics of 30-day all-cause hospital readmissions, 2010\u20132016. Agency for Healthcare Research and \u01eauality; 2018. Available: https:\/\/www.hcup-us.ahrq.gov\/reports\/statbriefs\/sb248-Hospital-Readmissions-2010- 2016.jsp [Accessed 3 Apr 2025]."},{"key":"2026040308201324000_16.4.e108273.2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMsa0803563"},{"key":"2026040308201324000_16.4.e108273.3","unstructured":"Centers for Medicare C Medicaid Services (CMS) . Hospital readmissions reduction program (HRRP). Available: https:\/\/www.cms.gov\/medicare\/medicare-fee-for-service- payment\/acuteinpatientpps\/readmissions-reduction-program [Accessed 3 Apr 2025]."},{"key":"2026040308201324000_16.4.e108273.4","unstructured":"Medicare Payment Advisory Commission (MedPAC) . Report to the congress: medicare and the health care delivery system. 2023."},{"key":"2026040308201324000_16.4.e108273.5","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2017-020325","article-title":"National trends in emergency readmission rates: a longitudinal analysis of administrative data for England between 2006 and 2016","volume":"8","author":"Friebel","year":"2018","journal-title":"BMJ Open"},{"key":"2026040308201324000_16.4.e108273.6","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0233457","article-title":"Reasons for readmission after hospital discharge in patients with chronic diseases-Information from an international dataset","volume":"15","author":"Brunner-La Rocca","year":"2020","journal-title":"PLoS One"},{"key":"2026040308201324000_16.4.e108273.7","doi-asserted-by":"publisher","DOI":"10.1378\/chest.13-0809"},{"key":"2026040308201324000_16.4.e108273.8","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1016\/j.chest.2016.05.002","article-title":"COPD Readmissions: Addressing COPD in the Era of Value-based Health Care","volume":"150","author":"Shah","year":"2016","journal-title":"Chest"},{"key":"2026040308201324000_16.4.e108273.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2021.12.012"},{"key":"2026040308201324000_16.4.e108273.10","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2012.216476"},{"key":"2026040308201324000_16.4.e108273.11","doi-asserted-by":"crossref","DOI":"10.1007\/s11892-015-0584-7","article-title":"Hospital readmission of patients with diabetes","volume":"15","author":"Rubin","year":"2015","journal-title":"Curr Diab Rep"},{"key":"2026040308201324000_16.4.e108273.12","doi-asserted-by":"publisher","DOI":"10.2337\/diacare.26.5.1421"},{"key":"2026040308201324000_16.4.e108273.13","doi-asserted-by":"crossref","unstructured":"Rubin DJ , Donnell-Jackson K , Jhingan R , et al . Early readmission among patients with diabetes: a qualitative study of patients\u2019 perspectives. J Diabetes Complications 2014. doi:10.1016\/j.jdiacomp.2014.06.013","DOI":"10.1016\/j.jdiacomp.2014.06.013"},{"key":"2026040308201324000_16.4.e108273.14","first-page":"110","article-title":"Multimorbidity patterns and hospital readmission risk among older adults: A retrospective cohort study","volume":"22","author":"Nguyen","year":"2022","journal-title":"BMC Geriatr"},{"key":"2026040308201324000_16.4.e108273.15","article-title":"Patterns and trends in comorbidity and multimorbidity: A systematic review of the literature","volume":"12","author":"Mounce","year":"2022","journal-title":"BMJ Open"},{"key":"2026040308201324000_16.4.e108273.16","first-page":"2560","article-title":"Impact of multimorbidity on 30-day readmission: A population-based study","volume":"20","author":"Zhao","year":"2023","journal-title":"Int J Environ Res Public Health"},{"key":"2026040308201324000_16.4.e108273.17","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2011.1515"},{"key":"2026040308201324000_16.4.e108273.18","doi-asserted-by":"publisher","DOI":"10.1503\/cmaj.091117"},{"key":"2026040308201324000_16.4.e108273.19","doi-asserted-by":"publisher","DOI":"10.1093\/geront\/48.4.495"},{"key":"2026040308201324000_16.4.e108273.20","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1300122"},{"key":"2026040308201324000_16.4.e108273.21","doi-asserted-by":"publisher","DOI":"10.1377\/hlthaff.2013.0816"},{"key":"2026040308201324000_16.4.e108273.22","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.hjdsi.2017.06.001","article-title":"It takes a village: exploring the impact of social determinants on delivery system outcomes for heart failure patients","volume":"6","author":"Knighton","year":"2018","journal-title":"Healthc (Amst)"},{"key":"2026040308201324000_16.4.e108273.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ahj.2005.12.002"},{"key":"2026040308201324000_16.4.e108273.24","doi-asserted-by":"publisher","DOI":"10.7326\/M13-2946"},{"key":"2026040308201324000_16.4.e108273.25","unstructured":"Johnson AEW , Pollard TJ , Shen L , et al . MIMIC-IV (version 2.2). PhysioNet 2022;16. doi:10.13026\/s6n6-xd98"},{"key":"2026040308201324000_16.4.e108273.26","first-page":"317","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"8","author":"Johnson","year":"2021","journal-title":"Sci Data"},{"key":"2026040308201324000_16.4.e108273.27","doi-asserted-by":"publisher","DOI":"10.1097\/01.mlr.0000182534.19832.83"},{"key":"2026040308201324000_16.4.e108273.28","doi-asserted-by":"crossref","DOI":"10.3390\/jcm9092788","article-title":"What Is the Effectiveness of Different Duration Interdisciplinary Treatment Programs in Patients with Chronic Pain? A Large-Scale Longitudinal Register Study","volume":"9","author":"Tseli","year":"2020","journal-title":"J Clin Med"},{"key":"2026040308201324000_16.4.e108273.29","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1109\/JPROC.2015.2501978","article-title":"Machine Learning and Decision Support in Critical Care","volume":"104","author":"Johnson","year":"2016","journal-title":"Proc IEEE"},{"key":"2026040308201324000_16.4.e108273.30","unstructured":"Xu L , Skoularidou M , Cuesta-Infante A , et al . Modeling tabular data using conditional gan. Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS); 2019"},{"key":"2026040308201324000_16.4.e108273.31","unstructured":"Choi E , Biswal S , Malin B , et al . Generating multi-label discrete patient records using generative adversarial networks. Machine Learning for Healthcare Conference; 2017"},{"key":"2026040308201324000_16.4.e108273.32","first-page":"103725","article-title":"Synthesizing EHR with variational autoencoders: improving robustness and privacy in predictive modeling","volume":"116","author":"Xu","year":"2021","journal-title":"J Biomed Inform"},{"key":"2026040308201324000_16.4.e108273.33","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"2026040308201324000_16.4.e108273.34","unstructured":"Fang H , Zhang Y , Liu J , et al . DP-CTGAN: Differentially Private Synthetic Data and Federated Learning with Conditional GANs. Adv Neural Inf Process Syst 2022."},{"key":"2026040308201324000_16.4.e108273.35","doi-asserted-by":"crossref","first-page":"13690","DOI":"10.3390\/su151813690","article-title":"Synthetic Data as a Proxy for Real-World Electronic Health Records in the Patient Length of Stay Prediction","volume":"15","author":"Bietsch","year":"2023","journal-title":"Sustainability"},{"key":"2026040308201324000_16.4.e108273.36","unstructured":"Wadstr\u00f6m J . Synthetic EHR data generation using generative models: A comparative analysis of CTGAN, TVAE, and GaussianCopula. Uppsala University; 2023. Available: https:\/\/www.diva-portal.org\/smash\/record.jsf?pid=diva2%3A1955597"},{"key":"2026040308201324000_16.4.e108273.37","doi-asserted-by":"crossref","unstructured":"Hosmer DW , Lemeshow S , Sturdivant RX . Applied Logistic Regression. 3rd edn. Hoboken, NJ: Wiley, 2013.","DOI":"10.1002\/9781118548387"},{"key":"2026040308201324000_16.4.e108273.38","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2026040308201324000_16.4.e108273.39","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203450"},{"key":"2026040308201324000_16.4.e108273.40","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C . XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD); 2016:785\u201394. doi:10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"2026040308201324000_16.4.e108273.41","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v045.i05"},{"key":"2026040308201324000_16.4.e108273.42","doi-asserted-by":"crossref","unstructured":"Moerschbacher A , He Z . Building Prediction Models for 30-Day Readmissions Among ICU Patients Using Both Structured and Unstructured Data in Electronic Health Records. Proceedings (IEEE Int Conf Bioinformatics Biomed 2023;2023:4368\u201373. doi:10.1109\/bibm58861.2023.10385612","DOI":"10.1109\/BIBM58861.2023.10385612"},{"key":"2026040308201324000_16.4.e108273.43","doi-asserted-by":"crossref","DOI":"10.1186\/s12874-021-01284-z","article-title":"Application of machine learning in predicting hospital readmissions: a scoping review of the literature","volume":"21","author":"Huang","year":"2021","journal-title":"BMC Med Res Methodol"},{"key":"2026040308201324000_16.4.e108273.44","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1080\/20476965.2018.1510040","article-title":"Analysing repeated hospital readmissions using data mining techniques","volume":"7","author":"Ben-Assuli","year":"2018","journal-title":"Health Syst (Basingstoke)"},{"key":"2026040308201324000_16.4.e108273.45","unstructured":"Caruana R , Baluja S , Mitchell T . Using the future to \u201csort out\u201d the present: rankprop and multitask learning for medical risk evaluation. In: Advances in Neural Information Processing Systems 8. Denver, Colorado: MIT Press, 1996: 959\u201365."},{"key":"2026040308201324000_16.4.e108273.46","doi-asserted-by":"publisher","DOI":"10.1097\/00003246-200102000-00012"},{"key":"2026040308201324000_16.4.e108273.47","doi-asserted-by":"crossref","first-page":"138","DOI":"10.3390\/jpm2040138","article-title":"A Database-driven Decision Support System: Customized Mortality Prediction","volume":"2","author":"Celi","year":"2012","journal-title":"J Pers Med"},{"key":"2026040308201324000_16.4.e108273.48","doi-asserted-by":"crossref","DOI":"10.1136\/bmjdrc-2020-001227","article-title":"Predictors of 30-day unplanned hospital readmission among adult patients with diabetes mellitus: a systematic review with meta-analysis","volume":"8","author":"Soh","year":"2020","journal-title":"BMJ Open Diab Res Care"},{"key":"2026040308201324000_16.4.e108273.49","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0235064","article-title":"Assessing the impact of social determinants of health on predictive models for potentially avoidable 30-day readmission or death","volume":"15","author":"Zhang","year":"2020","journal-title":"PLoS ONE"},{"key":"2026040308201324000_16.4.e108273.50","first-page":"514","article-title":"Predicting outcome in older ICU patients: development and validation of the COVIP score","volume":"48","author":"Flaatten","year":"2022","journal-title":"Intensive Care Med"},{"key":"2026040308201324000_16.4.e108273.51","doi-asserted-by":"crossref","DOI":"10.1038\/s41597-019-0103-9","article-title":"Multitask learning and benchmarking with clinical time series data","volume":"6","author":"Harutyunyan","year":"2019","journal-title":"Sci Data"},{"key":"2026040308201324000_16.4.e108273.52","doi-asserted-by":"publisher","DOI":"10.7326\/M18-1990"},{"key":"2026040308201324000_16.4.e108273.53","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000003148"},{"key":"2026040308201324000_16.4.e108273.54","doi-asserted-by":"crossref","first-page":"632","DOI":"10.1001\/jamainternmed.2013.3023","article-title":"Potentially avoidable 30-day hospital readmissions in medical patients: derivation and validation of a prediction model","volume":"173","author":"Donz\u00e9","year":"2013","journal-title":"JAMA Intern Med"},{"key":"2026040308201324000_16.4.e108273.55","first-page":"290","article-title":"Association of the HOSPITAL score with potentially avoidable readmissions: a multicentre international study","volume":"30","author":"Aubert","year":"2021","journal-title":"BMJ Qual Saf"},{"key":"2026040308201324000_16.4.e108273.56","doi-asserted-by":"crossref","first-page":"109","DOI":"10.2147\/COPD.S147796","article-title":"Examining 30-day COPD readmissions through the emergency department","volume":"13","author":"Rezaee","year":"2018","journal-title":"Int J Chron Obstruct Pulmon Dis"},{"key":"2026040308201324000_16.4.e108273.57","doi-asserted-by":"publisher","DOI":"10.2147\/IJGM.S150676"},{"key":"2026040308201324000_16.4.e108273.58","doi-asserted-by":"crossref","first-page":"14240","DOI":"10.1038\/s41598-019-50751-7","article-title":"High Glucose Variability Increases 30-Day Readmission Rates in Patients with Type 2 Diabetes Hospitalized in Department of Surgery","volume":"9","author":"Hsieh","year":"2019","journal-title":"Sci Rep"},{"key":"2026040308201324000_16.4.e108273.59","doi-asserted-by":"crossref","DOI":"10.1097\/MD.0000000000032953","article-title":"The Charlson comorbidity index and short-term readmission in patients with heart failure: A retrospective cohort study","volume":"102","author":"Wei","year":"2023","journal-title":"Medicine (Baltimore)"},{"key":"2026040308201324000_16.4.e108273.60","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1097\/MS9.0000000000002852","article-title":"Short-term mortality and readmission rate prediction by the sequential organ failure assessment score in acute decompensated heart failure","volume":"87","author":"Hoang","year":"2025","journal-title":"Ann Med Surg (Lond)"},{"key":"2026040308201324000_16.4.e108273.61","doi-asserted-by":"publisher","DOI":"10.1001\/jama.1990.03450220076026"},{"key":"2026040308201324000_16.4.e108273.62","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1111\/joim.12984","article-title":"Higher frequency of hospitalization but lower relative mortality for pandemic influenza in people with type 2 diabetes","volume":"287","author":"Ruiz","year":"2020","journal-title":"J Intern Med"},{"key":"2026040308201324000_16.4.e108273.63","doi-asserted-by":"crossref","first-page":"1168","DOI":"10.1007\/s00125-024-06102-x","article-title":"Diabetes and infection: review of the epidemiology, mechanisms and principles of treatment","volume":"67","author":"Holt","year":"2024","journal-title":"Diabetologia"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2025-108273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T02:31:15Z","timestamp":1775442675000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2025-108273"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":63,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4,3]]},"published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1136\/bmjopen-2025-108273"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2025-108273","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}