MIMIC-IV, a freely accessible electronic health record dataset
By Alistair E. W. Johnson, Lucas Bulgarelli, Lu Shen, Alvin Gayles, Ayad Shammout, Steven Horng, Tom J. Pollard, Benjamin Moody, B. Gow, Li-wei H. Lehman and 2 more. Scientific Data, 2023
3,152 citations recorded by the source corpus.
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. Measurement(s) Homo sapiens Technology Type(s) Electronic Health Record Sample Characteristic - Organism Homo sapiens Sample Characteristic - Environment hospital Sample Characteristic - Location Commonwealth of Massachusetts
Subfields: Artificial Intelligence, Health Information Management
View Paper: https://www.semanticscholar.org/paper/5425de16356015c2f26d2a50684c6c46d6998f51
Citations in the corpus
- Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook (2024, neutral): “Existing multimodal medical data sets available for public use [84,85,148] are often relatively small in scale and demand the consolidation of numerous resources.”
- TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion (2026, unknown): “Tabular data is one of the most fundamental data types in modern machine learning and is indispensable across domains such as finance (Sattarov et al., 2023), health-care (Johnson et al., 2023), and social media (Lakkaraju et al., 2013).”
- “Small” Large Language Models in the Hospital: Evaluation Study on Real-World Data in a Resource-Constrained Setting (2025, unknown): “Existing research has largely focused on evaluating LLMs (often exceeding 70 billion parameters) available through APIs as a service across various health care applications and on simulated or publicly available datasets [11,12].”
- Towards Domain Specification of Embedding Models in Medicine (2025, unknown): “To capture authentic clinical language we incorporate MIMIC-IV [33], a de-identified EHR dataset rich in clinical notes, discharge summaries, and structured patient data reflective of bedside documentation.”