{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:26:08Z","timestamp":1780053968130,"version":"3.54.0"},"reference-count":30,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T00:00:00Z","timestamp":1643155200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100006098","name":"Radiological Society of North America","doi-asserted-by":"publisher","award":["RSCH2028"],"award-info":[{"award-number":["RSCH2028"]}],"id":[{"id":"10.13039\/100006098","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Informatics"],"abstract":"<jats:p>Predicting ICU readmission risk will help physicians make decisions regarding discharge. We used discharge summaries to predict ICU 30-day readmission risk using text mining and machine learning (ML) with data from the Medical Information Mart for Intensive Care III (MIMIC-III). We used Natural Language Processing (NLP) and the Bag-of-Words approach on discharge summaries to build a Document-Term-Matrix with 3000 features. We compared the performance of support vector machines with the radial basis function kernel (SVM-RBF), adaptive boosting (AdaBoost), quadratic discriminant analysis (QDA), least absolute shrinkage and selection operator (LASSO), and Ridge Regression. A total of 4000 patients were used for model training and 6000 were used for validation. Using the bag-of-words determined by NLP, the area under the receiver operating characteristic (AUROC) curve was 0.71, 0.68, 0.65, 0.69, and 0.65 correspondingly for SVM-RBF, AdaBoost, QDA, LASSO, and Ridge Regression. We then used the SVM-RBF model for feature selection by incrementally adding features to the model from 1 to 3000 bag-of-words. Through this exhaustive search approach, only 825 features (words) were dominant. Using those selected features, we trained and validated all ML models. The AUROC curve was 0.74, 0.69, 0.67, 0.70, and 0.71 respectively for SVM-RBF, AdaBoost, QDA, LASSO, and Ridge Regression. Overall, this technique could predict ICU readmission relatively well.<\/jats:p>","DOI":"10.3390\/informatics9010010","type":"journal-article","created":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T11:02:53Z","timestamp":1643194973000},"page":"10","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Predictive Model for ICU Readmission Based on Discharge Summaries Using Machine Learning and Natural Language Processing"],"prefix":"10.3390","volume":"9","author":[{"given":"Negar","family":"Orangi-Fard","sequence":"first","affiliation":[{"name":"Mathematics, School of Science and Technology, Georgia Gwinnett College, Lawrenceville, GA 30043, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alireza","family":"Akhbardeh","sequence":"additional","affiliation":[{"name":"Department of Radiology, School of Medicine, The Johns Hopkins University, Baltimore, MD 21205, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2909-6793","authenticated-orcid":false,"given":"Hersh","family":"Sagreiya","sequence":"additional","affiliation":[{"name":"Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,1,26]]},"reference":[{"key":"ref_1","first-page":"5452683","article-title":"Characteristics, Outcomes, and Cost Patterns of High-Cost Patients in the Intensive Care Unit","volume":"2018","author":"Reardon","year":"2018","journal-title":"Crit. Care Res. Pract."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1001\/jama.2011.1515","article-title":"Risk prediction models for hospital readmission: A systematic review","volume":"306","author":"Kansagara","year":"2011","journal-title":"JAMA"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.iccn.2013.10.005","article-title":"Intensive care readmission: A contemporary review of the literature","volume":"30","author":"Elliott","year":"2014","journal-title":"Intensive Crit. Care Nurs."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1097\/CCM.0b013e31822d751e","article-title":"Intensive care unit readmissions in U.S. hospitals: Patient characteristics, risk factors, and outcomes","volume":"40","author":"Kramer","year":"2012","journal-title":"Crit. Care Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1097\/CCM.0000000000003002","article-title":"The Utility of ICU Readmission as a Quality Indicator and the Effect of Selection","volume":"46","author":"Maharaj","year":"2018","journal-title":"Crit. Care Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1097\/CCM.0b013e3182657b8a","article-title":"The association between ICU readmission rate and patient outcomes","volume":"41","author":"Kramer","year":"2013","journal-title":"Crit. Care Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1312","DOI":"10.1513\/AnnalsATS.201611-851OC","article-title":"Readmission to the Intensive Care Unit: Incidence, Risk Factors, Resource Use, and Outcomes. A Retrospective Cohort Study","volume":"14","author":"Ponzoni","year":"2017","journal-title":"Ann. Am. Thorac Soc."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e202044","DOI":"10.1001\/jamanetworkopen.2020.2044","article-title":"Association Between Financial Incentives in Medicare\u2019s Hospital Readmissions Reduction Program and Hospital Readmission Performance","volume":"3","author":"Hoffman","year":"2020","journal-title":"JAMA Netw. Open"},{"key":"ref_9","unstructured":"CMS.gov (2022, January 17). Hospital Readmissions Reduction Program (HRRP), Available online: https:\/\/www.cms.gov\/Medicare\/Medicare-Fee-for-Service-Payment\/AcuteInpatientPPS\/Readmissions-Reduction-Program."},{"key":"ref_10","unstructured":"Henriksen, K., Battles, J.B., Keyes, M.A., and Grady, M.L. (2008). Documentation of Mandated Discharge Summary Components in Transitions from Acute to Subacute Care. Advances in Patient Safety: New Directions and Alternative Approaches (Vol. 2: Culture and Redesign), Advances in Patient Safety."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1093\/bja\/aen069","article-title":"Predicting death and readmission after intensive care discharge","volume":"100","author":"Campbell","year":"2008","journal-title":"Br. J. Anaesth"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Badawi, O., and Breslow, M.J. (2012). Readmissions and death after ICU discharge: Development and validation of two predictive models. PLoS ONE, 7.","DOI":"10.1371\/journal.pone.0048758"},{"key":"ref_13","first-page":"83","article-title":"Readmission to intensive care: Development of a nomogram for individualising risk","volume":"12","author":"Frost","year":"2010","journal-title":"Crit. Care Resusc."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"13158","DOI":"10.1016\/j.eswa.2012.05.086","article-title":"Data mining using clinical physiology at discharge to predict ICU readmissions","volume":"39","author":"Fialho","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1016\/j.jbi.2014.08.006","article-title":"The effects of data sources, cohort selection, and outcome definition on a predictive model of risk of thirty-day hospital readmissions","volume":"52","author":"Walsh","year":"2014","journal-title":"J. Biomed. Inform."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Curto, S., Carvalho, J.P., Salgado, C., Vieira, S.M., and Sousa, J.M.C. (2016, January 24\u201329). Predicting ICU readmissions based on bedside medical text notes. Proceedings of the 2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Vancouver, BC, Canada.","DOI":"10.1109\/FUZZ-IEEE.2016.7737956"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e921","DOI":"10.1038\/tp.2015.182","article-title":"Predicting early psychiatric readmission with natural language processing of narrative discharge summaries","volume":"6","author":"Rumshisky","year":"2016","journal-title":"Transl. Psychiatry"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"22","DOI":"10.11648\/j.bsi.20190403.11","article-title":"Early Prediction of 30-Day ICU Re-admissions Using Natural Language Processing and Machine Learning","volume":"4","author":"Li","year":"2019","journal-title":"Biomed. Stat. Inform."},{"key":"ref_19","unstructured":"Huang, K., Altosaar, J., and Ranganath, R. (2020, January 2\u20134). ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission. Proceedings of the Conference on Health, Inference, and Learning, Toronto, ON, Canada."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1038\/505612a","article-title":"Policy: NIH plans to enhance reproducibility","volume":"505","author":"Collins","year":"2014","journal-title":"Nature"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"E215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"160035","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci. Data"},{"key":"ref_23","unstructured":"Johnson, A.E., Pollard, T., and Mark, R. (2016). MIMIC-III Clinical Database (version 1.4). PhysioNet."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2758","DOI":"10.1109\/78.650102","article-title":"Comparing support vector machines with Gaussian kernels to radial basis function classifiers","volume":"45","author":"Sung","year":"1997","journal-title":"IEEE Trans. Signal. Process."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1006\/jcss.1997.1504","article-title":"A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting","volume":"55","author":"Freund","year":"1997","journal-title":"J. Comput. Syst. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1504\/IJAPR.2016.079050","article-title":"Linear vs. quadratic discriminant analysis classifier: A tutorial","volume":"3","author":"Tharwat","year":"2016","journal-title":"Int. J. Appl. Pattern Recognit."},{"key":"ref_27","unstructured":"Dobson, A.J., and Barnett, A.G. (2018). An Introduction to Generalized Linear Models, CRC Press. [4th ed.]."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","article-title":"Ridge Regression: Biased Estimation for Nonorthogonal Problems","volume":"12","author":"Hoerl","year":"1970","journal-title":"Technometrics"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression Shrinkage and Selection Via the Lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J. R. Stat. Soc. Ser. B (Methodol.)"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R., and Friedman, J.H. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer. [2nd ed.].","DOI":"10.1007\/978-0-387-84858-7"}],"container-title":["Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2227-9709\/9\/1\/10\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:08:11Z","timestamp":1760134091000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2227-9709\/9\/1\/10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,26]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,3]]}},"alternative-id":["informatics9010010"],"URL":"https:\/\/doi.org\/10.3390\/informatics9010010","relation":{},"ISSN":["2227-9709"],"issn-type":[{"value":"2227-9709","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,26]]}}}