Introduction

The SICdb dataset provides insight to over 27 thousand intensive care admissions, including therapy and data of their preceding surgery. Data was collected between 2013 and 2021 from 4 of the intensive care units at the University Hospital Salzburg, having more than 3 thousand intensive care admissions per year on 37 beds. The dataset is deidentified and contains, amongst others, case information, laboratory, medication, monitor and respirator signal data.SICdb provides aggregated once-per-hour and highly granular once-per-minute data.

Reference Table

Nominal data is encoded, the reference table d_references provides information associated with a reference. Referenced fields of all data tables relate to the primary key of the reference table, d_references.ReferenceGlobalID. The value field d_references.ReferenceValue gives the variables value, the unit field d_references.ReferenceUnit holds the unit or measurement if applicable. Refer to chapter d_references for further information.

Data Description

The SICdb dataset contains billions of data entries, provided in 6 data tables. The base table is “cases”, which contains one entry per intensive care admission. The table contains, amongst others, infomration about the patient, like age, weight and sex, and case information like diagnosis, scores and ICD10 codes. All other data table relate to this table, where x.CaseID is associated with cases.CaseID. Most data has timing information, where the field x.offset is the amount of seconds from admission to event time.

Table laboratory contains laboratory values, table medication provides data about applied drugs. There are several generic data tables, which contain data sorted by their type. In table data_ref additional nominal/categorical data, one per admission, is found. In data_range items with a begin and end time are documented, this includes for example data about central lines or drainages. Table data_float_h contains float data, aggregated once per hour. To decrease table size minute data is serialized as a stream of IEEE 754 floats in data_float_h.rawdata

The database contains pseudoanonymized data of intensive care patients and has to be handled with appropriate care and respect.