Predicting Clinical Outcomes of Critically Ill Patients in Intensive Care Units With De-identification Database
Predicting Clinical Outcomes of Critically Ill Patients in Intensive Care Units With De-identification Database
Australian and New Zealand Intensive Care Society (ANZICS) has built a Center of Outcome and Resource Evaluation (CORE) adult patients database (APD) of adult critically ill patients. ANZICS CORE APD has built an international collaboration of ICU database. National Taiwan University Hospital has joined this international collaboration and built the data according to the APD data dictionary with same value domain attributes and data element attributes. We retrospectively collected the data of patients discharged from the March 1, 2019 to June 30, 2022. Data of this database are permitted to study clinical problems and predict the clinical outcomes of these critically ill patients using statistical methods and machine learning techniques.
Data of this database are permitted to study the following clinical issues: including delirium, sepsis, acute kidney injury, acute respiratory distress syndrome, disseminated intravascular coagulation, multiple organ injuries, nutrition, survival status, number of days on ventilators, need for renal replacement therapy, length of stays in intensive care unit, length of stay in hospital, and other relevant clinical outcomes. It is also planned to analyze the clinical prognosis of special disease subgroups and establish a prediction model according to the type of patient's disease.
Inclusion Criteria:
Exclusion Criteria:
tonyyeh@ntuh.gov.tw+886-9-10513711