{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T05:37:22Z","timestamp":1740202642608,"version":"3.37.3"},"reference-count":0,"publisher":"IOS Press","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"abstract":"<jats:p>Hospital readmissions receive increasing interest, since they are burdensome for patients and costly for healthcare providers. For the calculation of reimbursement fees, in Germany there is the German-Diagnosis Related Groups (G-DRG) system. For every hospital stay, data are collected as a so-called &amp;ldquo;case&amp;rdquo;, as the basis for the subsequent reimbursement calculations (&amp;ldquo;&amp;sect;21 dataset&amp;rdquo;). Merging rules lead to a loss of information in &amp;sect;21 datasets. We applied machine learning to &amp;sect;21 datasets and evaluated the influence of case merging for the resulting accuracy of readmission risk prediction. Data from 478,966 cases were analysed by applying a random forest. Many cases with readmissions within 30 days had been merged and thus their prediction required additional data. Using 10-fold cross validation, the prediction for readmissions within 31&amp;ndash;60 days showed no notable difference in the area under the ROC curves comparing unedited &amp;sect;21 datasets with &amp;sect;21 datasets with restored original cases. The achieved AUC values of 0.69 lie in a similar range as the values of comparable state-of-the-art models. We conclude that dealing with merged cases, i.e. adding data, is required for 30-day-readmission prediction, whereas un-merging brings no improvement for the readmission prediction of period beyond 30 days.<\/jats:p>","DOI":"10.3233\/978-1-61499-896-9-170","type":"book-chapter","created":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T17:13:02Z","timestamp":1740157982000},"source":"Crossref","is-referenced-by-count":0,"title":["Prediction of Readmissions in the German DRG System Based on &amp;sect;21 Datasets"],"prefix":"10.3233","author":[{"family":"Eggerth Alphons","sequence":"additional","affiliation":[]},{"family":"Hayn Dieter","sequence":"additional","affiliation":[]},{"family":"Veeranki Sai","sequence":"additional","affiliation":[]},{"family":"Stieg J&ouml;rg","sequence":"additional","affiliation":[]},{"family":"Schreier G&uuml;nter","sequence":"additional","affiliation":[]}],"member":"7437","container-title":["Studies in Health Technology and Informatics","German Medical Data Sciences: A Learning Healthcare System"],"original-title":[],"deposited":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T18:02:15Z","timestamp":1740160935000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.medra.org\/servlet\/aliasResolver?alias=iospressISBN&isbn=978-1-61499-895-2&spage=170&doi=10.3233\/978-1-61499-896-9-170"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/978-1-61499-896-9-170","relation":{},"ISSN":["0926-9630"],"issn-type":[{"value":"0926-9630","type":"print"}],"subject":[],"published":{"date-parts":[[2018]]}}}