HiRID, a time-resolution that is high dataset. Anonymization procedure

Posted Variation: 1.0


HiRID is a easily available critical care dataset containing data associated with very nearly 34 thousand patient admissions to your Department of Intensive Care Medicine associated with the Bern University Hospital, Switzerland (ICU), an interdisciplinary 60-bed product admitting >6,500 clients each year. The ICU provides the complete array of contemporary interdisciplinary intensive care medication for adult clients. The dataset was created in cooperation amongst the Swiss Federal Institute of tech (ETH) ZГјrich, Switzerland in addition to ICU.

The dataset contains de-identified demographic information and a total of 681 regularly gathered physiological factors, diagnostic test outcomes and therapy parameters from nearly 34 thousand admissions throughout the duration. Information is kept having an uniquely about time quality of 1 entry every 120 seconds.


Critical infection is described as the existence or threat of developing deadly organ dysfunction. Critically sick clients are generally taken care of in intensive care units (ICUs), which concentrate on supplying monitoring that is continuous advanced therapeutic and diagnostic technologies. This dataset ended up being gathered during routine care during the Department of Intensive Care Medicine regarding the Bern University Hospital, Switzerland (ICU), an interdisciplinary unit that is 60-bed >6,500 clients each year. It absolutely was initially removed to guide a research in the very early forecast of circulatory failure within the intensive care product machine learning 1 that is using. The latest documents for the dataset is available2.


The HiRID database includes a selection that is large of routinely gathered data relating to patient admissions towards the Department of Intensive Care Medicine regarding the Bern University Hospital, Switzerland (ICU). The information ended up being obtained from the ICU individual information Management System that will be familiar with register that is prospectively wellness information, dimensions of organ function parameters, outcomes of laboratory tests and therapy parameters from ICU admission to discharge.

Dimensions from bedside monitoring

Dimensions and settings of medical products such as for instance technical air flow

Findings by healthcare providers e.g.: GCS, RASS, urine along with other output that is fluid

Administered drugs, liquids and nourishment

HiRID has an increased time quality than many other posted datasets, above all for bedside monitoring with many parameters recorded every 120 seconds.

So that the anonymization of an individual within the information set, we used the procedures effectively sent applications for the MIMIC-IIwe and Amsterdam UMC db dataset, which adopted the wellness Insurance Portability and Accountability Act (HIPAA) secure Harbor demands and, when it comes to Amsterdam UMC db, additionally europe’s General information Protection Regulation (GDPR) standards 3,4.

Elimination of all eighteen determining information elements placed in HIPAA

Times were shifted by a random offset such that the admission date lies. We made certain to protect the seasonality, time of time plus the day’s week.

Individual age, weight and height are binned into containers of size 5. The max bin is 90 years and contains also all older patients for patient age.

Dimensions and medicines with changing devices in the long run had been standardised to your unit that is latest utilized. This standardization ended up being essential to create a conclusion about predicted admission times, in line with the devices utilized in a certain patient, impossible.

Complimentary text had been taken from the database

k-anonymization had been applied on patient age, fat, height and intercourse.

Ethical approval and client permission

The institutional review board (IRB) associated with Canton of Bern authorized the research. The necessity for acquiring informed client consent ended up being waived due to the retrospective and observational nature for the research.

Information Description

The data that are overall for sale in two states: as natural information and/or as pre-processed information. Also you can find three guide tables for adjustable lookup.

Guide tables

adjustable guide – guide dining dining dining table for factors (for natural phase)

ordinal guide that is adjustable guide dining dining table for categorical/ordinal variables for string value lookup

pre-processed adjustable guide – guide dining dining dining table for factors (for merged and stage that is imputed

Natural information

The raw information was just processed if it was necessary for patient de-identification and otherwise left unchanged set alongside the initial supply. The foundation information offers the set that is complete of factors (685 factors). It consist of the after tables:

Preprocessed information

The pre-processed information is comprised of intermediary pipeline phases from the accompanying book by Hyland et al 1. Supply factors representing exactly the same medical ideas had been merged into one meta-variable per concept. The info contains the 18 many meta-variables that are predictive, as defined within our book. Two various phases associated with pipeline can be found

Merged phase supply factors are merged into meta-variables by medical ideas e.g. non-opioid-analgesics. The full time grid is kept unchanged and it is sparse.

Imputed stage the info through the merged stage is down sampled up to a five-minute time grid. Enough time grid is filled up with imputed values. The imputation strategy is complex and it is discussed when you look at the initial book.

The rule utilized to build these phases are available in this GitHub repository beneath the folder 5 that is preprocessing.

Which information to make use of?

The pre-processed information is intended primarily being a fast option to jump-start a task or even for use within a evidence of concept. We advice with the supply data whenever feasible for regular tasks. This is the many versatile type and possesses the whole pair of factors within the time resolution that is original.

Information platforms

Information is for sale in two platforms: CSV for wide compatibility and Apache Parquet for convenience and gratification.

Considering that the information sets are fairly big, they’ve been divided in to partitions, so that they could be prepared in parallel in a simple means. The lookup dining table mapping patient id to partition id is supplied when you look at the file called combined with the information. The partitions are aligned between your various information sets and tables, in a way that the information of an individual can invariably be located when you look at the partition aided by the exact same id. Note however, that an individual might not take place in all data sets, e.g. a patient may be lacking within the data that are preprocessed because an individual did not meet with the demographic requirements become within the research.

Patient ID / ICU admission

The dataset treats each ICU admission uniquely and it’s also difficult to recognize numerous ICU admissions as originating from the patient that is same. A unique “Patient ID” is generated for each ICU ( re-)admission.

Information schemata

The schemata of each and every dining table are located in the *schemata.pdf* file.

Use Records

Because the database contains detailed information about the medical care of clients, it should be addressed with appropriate care and respect.

Scientists have to formally request access via PhysioNet. The user has to be a credentialed PhysioNet user, digitally sign the Data Use Agreement and provide a specific research question to be granted access.

Conflicts of Interest

The writers declare no disputes of great interest


Access Policy: Only PhysioNet credentialed users whom signal the specified DUA have access to the files.