MIMIC-IV, a freely accessible electronic health record dataset

Abstract

Digital data collection during routine clinical practice is now ubiquitous within hospitals. The data contains valuable information on the care of patients and their response to treatments, offering exciting opportunities for research. Typically, data are stored within archival systems that are not intended to support research. These systems are often inaccessible to researchers and structured for optimal storage, rather than interpretability and analysis. Here we present MIMIC-IV, a publicly available database sourced from the electronic health record of the Beth Israel Deaconess Medical Center. Information available includes patient measurements, orders, diagnoses, procedures, treatments, and deidentified free-text clinical notes. MIMIC-IV is intended to support a wide array of research studies and educational material, helping to reduce barriers to conducting clinical research.

Fig. 1

An overview of the development process for MIMIC. Data are acquired from the BIDMC data warehouse, the ICU information system (MetaVision), and external sources (“acquisition”). Structured Query Language (SQL) scripts merge the various data sources into a single schema (“transformation”). Finally, deidentification algorithms are applied to selectively remove protected health information from the reformatted schema. Tables present in MIMIC-IV are provided on the far right of the figure under their respective module. Issues raised on the MIMIC Code Repository are assessed and used to improve the build process as appropriate.

Fig. 2

MIMIC-IV follows a modular structure. Modules can be linked by identifiers including subject_id, hadm_id, and deidentified date and time. Example content of each module is shown.

Fig. 3

Visualization of data within MIMIC-IV for a single patient’s hospitalization: hadm_id 28503629. Three vertically stacked panels highlight the variety of information available. Vital signs are shown in the top panel: note the frequency of data collection for temperature is much higher at the start of the ICU stay due to the use of targeted temperature management. Procedures from multiple sources are shown in the middle panel, including from billing information, the provider order entry system, as well as the ICU information system. The bottom panel displays patient laboratory measurements. Note that while frequent vital signs are only available when the patient is in the ICU, laboratory measures are available throughout their hospitalization.

Fig. 4

Visualization of medication information documented within MIMIC-IV for a single patient’s hospitalization: hadm_id 28503629. The annotated grey line indicates care units for the patient throughout their stay. Bolus medications are indicated by markers, continuous infusions as lines, and range doses as filled boxes. For example, on day 5 of their hospital stay, the patient had two active prescriptions for heparin (one for 1600–3500 units of heparin, brown filled box, and one for 1000 units of heparin, pink line with triangles). Additionally on day 5, the patient continued to received heparin according to emar (orange circle), and was imminently transferred to the medicine/cardiology intermediate ward.