Multiparameter Intelligent Monitoring in Intensive Care Ii (Mimic-Ii): A Public-Access Intensive Care Unit Database

By Mohammed Saeed. 2011

Subfields: Evaluation & Benchmarks, Medical & Health AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Evaluation & Benchmarks

In Medical & Health AI

Citations in the corpus

Federated Tensor Factorization for Computational Phenotyping (2017, methodology): “We use a large publicly available dataset MIMIC-III containing de-identified health-related data associated with over forty thousand patients who stayed in critical care units of the Beth Israel Dea-coness Medical Center between 2001 and 2012 [26].”
Machine Learning Model Interpretability for Precision Medicine (2016, methodology): “We extracted features from the Multi-Parameter Intelligent Monitoring in Intensive Care (MIMIC-II) dataset [4] containing 8,315 patients who exhibited mortality and 23,974 patients who did not.”
Distilling Knowledge from Deep Networks with Applications to Healthcare Domain (2015, methodology): “We will also apply our proposed approaches on a larger healthcare dataset, such as MIMIC-II [38] which is derived from multiple clinical sources, to further verify our methods.”
Doctor AI: Predicting Clinical Events via Recurrent Neural Networks (2015, methodology): “MIMIC II [39], a publicly available clinical dataset collected from ICU patients over 7 years of observation was chosen to conduct the experiment.”
Clinical Natural Language Processing in languages other than English: opportunities and challenges (2018, methodology): “However, there are currently no sharable clinical datasets comparable to the i2b2 datasets [142, 143], the ShARe corpus [144], the THYME corpus [145, 146] or the MIMIC corpus [147] in languages other than English except the Turku Clinical TreeBank and PropBank [32, 38, 148] in Finnish and the small ”
Machine Learning and Decision Support in Critical Care (2016, methodology): “The creation of openly available databases such as MIMIC [22] is a key step toward this goal, and the recent announcement that a subset of the eICU database [30] will be made open to the public demonstrates that this practice is becoming more common.”
A Multivariate Timeseries Modeling Approach to Severity of Illness Assessment and Forecasting in ICU with Sparse, Heterogeneous Clinical Data (2015, methodology): “6 database (Saeed et al. 2011), which includes electronic medical records (EMRs) for 26, 870 ICU patients at the Beth Israel Deaconess Medical Center (BIDMC).”
Bidirectional LSTM-CRF for Clinical Concept Extraction (2016, methodology): “Moreover, Wu et al. (Wu et al., 2015) have jointly used word embeddings derived from the entire English Wikipedia (Collobert et al., 2011) and binarized word embeddings derived from domain-speciﬁc corpora (e.g. the MIMIC-II corpus (Saeed et al., 2011)).”
What-If Reasoning with Counterfactual Gaussian Processes (2017, methodology): “To demonstrate how the CGP can be used as a decision support tool, we extract observational creatinine traces from the publicly available MIMIC-II database [Saeed et al., 2011].”
De-identification of patient notes with recurrent neural networks (2016, methodology): “As a matter of comparison, the MIMIC dataset (Goldberger et al., 2000; Saeed et al., 2011), which contains data from 50,000 intensive care unit (ICU) stays, consists of 100 million words.”
State of the art review: the data revolution in critical care (2015, background): “Over the past decade, the MIMIC database has collected clinical data from over 60,000 stays in Beth Israel Deaconess Medical Center ICUs, including clinical notes, physiological waveforms, laboratory measurements, and nurse-verified numerical data [10].”
Optimal medication dosing from suboptimal clinical examples: A deep reinforcement learning approach (2016, methodology): “[8], we extracted data for 4470 patients from the publicly available Multiparameter Intelligent Monitoring in Intensive Care (MIMIC) II database [9] that received a heparin intravenous infusion at some point during their ICU stay (randomly assigned to 80% training”
A Survey on Causal Inference (2020, methodology): “MVICU The data is sourced from the publicly available MIMIC III database [130].”