MIMIC-III, a freely accessible critical care database
By Alistair E. W. Johnson, Tom J. Pollard, Lu Shen, Li-wei H. Lehman, Mengling Feng, Marzyeh Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, R. Mark. 2016
8,772 citations recorded by the source corpus.
MIMIC-III (‘Medical Information Mart for Intensive Care’) is a large, single-center database comprising information relating to patients admitted to critical care units at a large tertiary care hospital. Data includes vital signs, medications, laboratory measurements, observations and notes charted by care providers, fluid balance, procedure codes, diagnostic codes, imaging reports, hospital length of stay, survival data, and more. The database supports applications including academic and industrial research, quality improvement initiatives, and higher education coursework. Design Type(s) data integration objective Measurement Type(s) Demographics • clinical measurement • intervention • Billing • Medical History Dictionary • Pharmacotherapy • clinical laboratory test • medical data Technology Type(s) Electronic Medical Record • Medical Record • Electronic Billing System • Medical Coding Process Document • Free Text Format Factor Type(s) Sample Characteristic(s) Homo sapiens Design Type(s) data integration objective Measurement Type(s) Demographics • clinical measurement • intervention • Billing • Medical History Dictionary • Pharmacotherapy • clinical laboratory test • medical data Technology Type(s) Electronic Medical Record • Medical Record • Electronic Billing System • Medical Coding Process Document • Free Text Format Factor Type(s) Sample Characteristic(s) Homo sapiens Machine-accessible metadata file describing the reported data (ISA-Tab format)
Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Epidemiology, Surgery, Evaluation & Benchmarks
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Biomedical Engineering
- Chao Yu
- Jimeng Sun
- Fei Wang
- Mihaela van der Schaar
- Dianbo Liu
- Finale Doshi-Velez
- Shamim Nemati
- Jiming Liu
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Xiaogang Wang
- Trevor Darrell
- Jitendra Malik
- Yi Yang
- Ming-Hsuan Yang
- Andrew Zisserman
In Epidemiology
In Surgery
- Dianbo Liu
- Fei Wang
- Jimeng Sun
- Chao Yu
- Mihaela van der Schaar
- Finale Doshi-Velez
- Shamim Nemati
- Marzyeh Ghassemi
In Evaluation & Benchmarks
- Hannaneh Hajishirzi
- Noah A. Smith
- Sergey Levine
- Luke S. Zettlemoyer
- Mohit Bansal
- Kyunghyun Cho
- Yejin Choi
- Eric Wallace
Citations in the corpus
- SciBERT: A Pretrained Language Model for Scientific Text (2019, methodology): “BIOBERT is trained on PubMed abstracts and PMC full text articles, and CLINICALBERT is trained on clinical text from the MIMIC-III database (Johnson et al., 2016).”
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (2022, methodology): “Training Transformers with longer sequences with F LASH A T - TENTION improves performance on the MIMIC-III [49] and ECtHR [6, 7] datasets.”
- Privacy-Preserving Generative Deep Neural Networks Support Clinical Data Sharing (2017, methodology): “Predicting Heart Failure in the MIMIC Critical Care Database We applied the method to the MIMIC Critical Care Database (36) to demonstrate its generality.”
- Attention is not Explanation (2019, background): “MIMIC ICD9 (Diabetes) (Johnson et al., 2016).”
- Attention is not not Explanation (2019, methodology): “The tasks are as follows: to predict positive or negative sentiment from sentences (SST) and movie reviews (IMDB), to predict the topic of news articles as either baseball (neg.) or hockey (pos.) in 20 NEWSGROUPS and either world (neg.) or business (pos.) in AG NEWS, to predict whether a patient is ”
- Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems (2020, methodology): “The MIMIC-III dataset (Johnson et al., 2016), which contains approximately 60K medical records from ICUs, has been influential in enabling data-driven research in healthcare treatment.”
- A Communication Efficient Vertical Federated Learning Framework (2019, background): “MIMIC-III [16] is a large database comprising information related to patients admitted to critical care units at a large tertiary care hospital.”
- Privacy-Preserving Tensor Factorization for Collaborative Health Data Analysis (2019, methodology): “We choose the per-epoch privacy budget under the zCDP definition for each factor matrix as ρ = 10−3 for MIMIC-III, CMS, and synthetic dataset.”
- Beyond Sparsity: Tree Regularization of Deep Models for Interpretability (2017, methodology): “• Sepsis Critical Care: We study time-series data for 11 786 septic ICU patients from the public MIMIC III dataset (Johnson et al. 2016).”
- Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders (2019, methodology): “Experiments on MIMIC III Using the Medical Information Mart for Intensive Care (MIMIC III) (Johnson et al., 2016) database consisting of electronic health records from patients in the ICU, we show how the Time Series Deconfounder can be applied on a real dataset.”
- AutoScore: A Machine Learning–Based Automatic Clinical Score Generator and Its Application to Mortality Prediction Using Electronic Health Records (2020, methodology): “The BIDMC data set was obtained from the Medical Information Mart for Intensive Care III [23] database compiled by the Massachusetts Institute of Technology Laboratory for Computational Physiology.”
- Reinforcement Learning in Healthcare: A Survey (2019, methodology): “With the available data obtained from freely accessible critical care databases such as the Multiparameter Intelligent Monitoring in Intensive Care (MIMIC) [227], recent years have seen an increasing number of studies that applied RL”
- Interpretable and Steerable Sequence Learning via Prototypes (2019, background): “ork, NY, USA, 11 pages. https: //doi.org/10.1145/3292500.3330908 1 INTRODUCTION Event sequence data is becoming pervasive in a variety of domains, e.g., electronic health records (EHR) in health care [10, 15], click streams in software applications and vehicle fault logs in automobiles. In general, ”
- Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations (2020, methodology): “We provide experimental results based on the Medical Information Mart for Intensive Care (MIMIC III) database (Johnson et al., 2016) consisting of electronic health records from patients in the ICU.”
- Joint Embedding of Words and Labels for Text Classification (2018, methodology): “Specifically, we consider an open-access dataset, MIMIC-III (Johnson et al., 2016), which”