Also in the Article



Administrative data of 86 Helios hospitals in Germany were retrospectively analysed. Patient cases with inpatient treatment within 1 January 2016 to 31 December 2018 and a main discharge diagnosis of HF defined in accordance to prior publications were identified. 12 Types of admission and discharge were gathered from administrative data, and only cases with both urgent (non‐elective) hospital admission and hospital discharge type other than hospital transfer were further studied. In‐hospital death as the outcome of interest has been defined based on hospital discharge type. Discharge diagnoses were encoded by the International Statistical Classification of Diseases and Related Health Problems [ICD‐10‐GM (German Modification)]. Relevant co‐morbidities were identified from encoded secondary diagnoses within hospital discharge data according to the Elixhauser co‐morbidity score as defined previously without a distinction being made between pre‐existing co‐morbidities and new medical conditions. 13 , 14 Cases with missing information for New York Heart Association (NYHA) class (n = 5315 cases) were discarded due to adequate calibration of ML models. Detailed information regarding used ICD codes and a comparison of datasets with and without the exclusion of cases with missing NYHA class is provided in the Supporting Information, Tables S1–S3 . The investigation conforms with the principles outlined in the Declaration of Helsinki. Given the anonymized data analysis of administrative data, ethics committee approval was determined not to be required in accordance with German law [Professional Code for Physicians (Saxony) §15]. Due to the retrospective study of anonymized data, informed consent has not been obtained.

Note: The content above has been extracted from a research article, so it may not display correctly.



Also in the Article

Q&A
Please log in to submit your questions online.
Your question will be posted on the Bio-101 website. We will send your questions to the authors of this protocol and Bio-protocol community members who are experienced with this method. you will be informed using the email address associated with your Bio-protocol account.



We use cookies on this site to enhance your user experience. By using our website, you are agreeing to allow the storage of cookies on your computer.