Difference between revisions of "Case Description"
| Line 17: | Line 17: | ||
All cases are cross-matched with a second database. This method excludes more than 99% of test patients. In rare cases (invalid synchronization, patient id merge, ...) valid patients get excluded. In a tertiary validation process about 50 of these cases were identified but discarded nevertheless as some data (i.e. mortality) is unreliable. | All cases are cross-matched with a second database. This method excludes more than 99% of test patients. In rare cases (invalid synchronization, patient id merge, ...) valid patients get excluded. In a tertiary validation process about 50 of these cases were identified but discarded nevertheless as some data (i.e. mortality) is unreliable. | ||
The dataset is in constant development. Feel free to contact us when you find a significant amount of invalid data. | |||
== Pseudoanonymization == | == Pseudoanonymization == | ||
Data is pseudoanonymized according to HIPAA and the European General Data Protection Regulation. Please note that any efforts to reidentify cases are illegal. | Data is pseudoanonymized according to HIPAA and the European General Data Protection Regulation. Please note that any efforts to reidentify cases are illegal. | ||
Revision as of 10:37, 16 February 2022
Case Selection
With Version 1.0.0 all admissions to participating intensiv care units are included, as long as following conditions do not apply:
- Less the 10 Minutes of Stay
- Missing mandatory admission data
- No monitor signals
- No medication data
- hospital number mismatch
Unit Description
The participating metavision enabled wards are CWIN, INBD, INIC, and INIC. INCV and CWCV are used for cases associated with SARS-COV-2, this includes SARS-COV-2 ARDS and patients with coincidental positive test and other cause of intensive care. CWIN and INBD are high level intensive care units, INIC and INID low level (intermediate care or patients that do not need advanced therapies like CRRT or invasive ventilation).
Validation
All cases are cross-matched with a second database. This method excludes more than 99% of test patients. In rare cases (invalid synchronization, patient id merge, ...) valid patients get excluded. In a tertiary validation process about 50 of these cases were identified but discarded nevertheless as some data (i.e. mortality) is unreliable.
The dataset is in constant development. Feel free to contact us when you find a significant amount of invalid data.
Pseudoanonymization
Data is pseudoanonymized according to HIPAA and the European General Data Protection Regulation. Please note that any efforts to reidentify cases are illegal.