The Medical Information Mart for Intensive Care (MIMIC)-IV database is comprised of deidentified electronic health records for patients admitted to the Beth Israel Deaconess Medical Center. Access to MIMIC-IV is limited to credentialed users. Here, we have provided an openly-available demo of MIMIC-IV containing a subset of 100 patients. The dataset includes similar content to MIMIC-IV, but excludes free-text clinical notes. The demo may be useful for running workshops and for assessing whether the MIMIC-IV is appropriate for a study before making an access request.

The advent of large, open access text databases has driven advances in state-of-the-art model performance in natural language processing (NLP). The relatively limited amount of clinical data available for NLP has been cited as a significant barrier to the field's progress. Here we describe MIMIC-IV-Note: a collection of deidentified free-text clinical notes for patients included in the MIMIC-IV clinical database. MIMIC-IV-Note contains 331,794 deidentified discharge summaries from 145,915 patients admitted to the hospital and emergency department at the Beth Israel Deaconess Medical Center in Boston, MA, USA. The database also contains 2,321,355 deidentified radiology reports for 237,427 patients. All notes have had protected health information removed in accordance with the Health Insurance Portability and Accountability Act (HIPAA) Safe Harbor provision. All notes are linkable to MIMIC-IV providing important context to the clinical data therein. The database is intended to stimulate research in clinical natural language processing and associated areas.

Large language models (LLMs) have recently demonstrated remarkable capabilities across a broad spectrum of tasks and applications, including the medical field. Models like GPT-4 excel in medical question answering but encounter challenges in interpretability when managing complex tasks in real clinical settings. To address this, we introduce the Diagnostic Reasoning Dataset for Clinical Notes (DiReCT), designed to evaluate the reasoning ability and interpretability of LLMs compared to human doctors. The dataset comprises 511 clinical notes (sourced from MIMIC-IV), each meticulously annotated by physicians, detailing the diagnostic reasoning process from initial observations to the final diagnosis.

MIMIC-IV ICD-10 contains 122,279 discharge summaries—free-text medical documents—annotated with ICD-10 diagnosis and procedure codes. It contains data for patients admitted to the Beth Israel Deaconess Medical Center emergency department or ICU between 2008-2019. All codes with fewer than ten examples have been removed, and the train-val-test split was created using multi-label stratified sampling. The dataset is described further in Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study, and the code to use the dataset is found here.

The dataset is intended for medical code prediction and was created using MIMIC-IV v2.2 and MIMIC-IV-NOTE v2.2. Using the two datasets requires a license obtained in Physionet; this can take a couple of days.

The MIMIC-IV-ECG module contains approximately 800,000 diagnostic electrocardiograms across nearly 160,000 unique patients. These diagnostic ECGs use 12 leads and are 10 seconds in length. They are sampled at 500 Hz. This subset contains all of the ECGs for patients who appear in the MIMIC-IV Clinical Database. When a cardiologist report is available for a given ECG, we provide the needed information to link the waveform to the report. The patients in MIMIC-IV-ECG have been matched against the MIMIC-IV Clinical Database, making it possible to link to information across the MIMIC-IV modules.

The number of publicly available ECG datasets has increased tremendously in the past few years and several of these datasets have developed into widely used benchmarking datasets. However, most of them exhibit a common limitation, namely the reliance on retrospective annotation and a lack of clinical ground truth. This represents a serious limitation compared to closed in-hospital datasets. To circumvent this issue, we propose the MIMIC-IV-ECG-Ext-ICD dataset by linking the samples from the MIMIC-IV-ECG dataset to clinical ground truth from the MIMIC-IV dataset, in the form of ED and hospital discharge diagnoses. We release this derived dataset to foster further research on ECG-based prediction models with clinical ground truth and build a resource for benchmarking clinical ECG prediction models.

Fast Healthcare Interoperability Resources (FHIR) has emerged as a robust standard for healthcare data exchange. To explore the use of FHIR for the process of data harmonization, we converted the Medical Information Mart for Intensive Care IV (MIMIC-IV) and MIMIC-IV Emergency Department (MIMIC-IV-ED) databases into FHIR. We extended base FHIR to encode information in MIMIC-IV and aimed to retain the data in FHIR with minimal additional processing, aligning to US Core v4.0.0 where possible. A total of 24 profiles were created for MIMIC-IV data, and an additional 6 profiles were created for MIMIC-IV-ED data. Code systems and value sets were created from MIMIC terminology. We hope MIMIC-IV in FHIR provides a useful restructuring of the data to support applications around data harmonization, interoperability, and other areas of research.

In this work, we extract an event log from the MIMIC-IV-ED dataset by adopting a well-established event log generation methodology, and we name this event log MIMICEL. The data tables in the MIMIC-IV-ED dataset relate to each other based on the existing relational database schema, and each table records the individual activities of patients along their journey in the emergency department (ED). While the data tables in the MIMIC-IV-ED dataset catch snapshots of a patient journey in the ED, the extracted event log MIMICEL aims to capture an end-to-end process of the patient journey. This will enable us to analyse the existing patient flows, thereby improving the efficiency of an ED process.

The MIMIC-IV-ICD9 dataset, featuring the top 50 most frequently occurring labels.

BackgroundExisting research suggests that using statins may reduce the incidence of enteritis caused by C. difficile and improve the prognosis of patients. This study aimed to explore the relation between Clostridium difficile-induced enteritis (CDE) and statin use.MethodsData were collected from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database. Multivariate logistic regression analysis was employed to assess the impact of statin use on CDE incidence in patients in intensive care units (ICUs) and its effect on in-hospital mortality among them. The research findings were validated by performing propensity score matching (PSM), inverse probability of treatment weighting (IPTW), and subgroup analyses.ResultsThe study enrolled the data of 51,978 individuals to assess the effect of statin usage on the occurrence of CDE in patients admitted to the ICU. The results indicate that statins can decrease the prevalence of CDE in patients in ICU (odds ratio (OR): 0.758, 95% confidence interval (CI): 0.666–0.873, P < 0.05), which was further confirmed through PSM (OR: 0.760, 95% CI: 0.661–0.873, P < 0.05) and IPTW (OR: 0.818, 95% CI: 0.754–0.888, P < 0.05) analyses. For most subgroups, statins’ favorable effect in reducing CDE remained constant. A total of 1,208 patients were included in the study to evaluate whether statins could lower the risk of death in patients in ICU with enteritis caused by C. difficile. Statins did not reduce in-hospital mortality of patients in ICU with CDE (OR: 0.911, 95% CI: 0.667–1.235, P = 0.553). The results were validated following PSM (OR: 0.877, 95% CI: 0.599–1.282, P = 0.499) and IPTW (OR: 0.781, 95% CI: 0.632–1.062, P = 0.071) analyses, and all subgroups demonstrated consistent results.ConclusionStatin administration can reduce the incidence of CDE in patients in the ICU; however, it does not decrease the in-hospital mortality rate for individuals with CDE.

AimTo compare the effects of midazolam, propofol, and dexmedetomidine monotherapy and combination therapy on the prognosis of intensive care unit (ICU) patients receiving continuous mechanical ventilation (MV).Methods11,491 participants from the Medical Information Mart for Intensive Care (MIMIC)-IV database 2008–2019 was included in this retrospective cohort study. The primary outcome was defined as incidence of ventilator-associated pneumonia (VAP), in-hospital mortality, and duration of MV. Univariate and multivariate logistic regression analyses were utilized to evaluate the association between sedation and the incidence of VAP. Univariate and multivariate Cox analyses were performed to investigate the correlation between sedative therapy and in-hospital mortality. Additionally, univariate and multivariate linear analyses were conducted to explore the relationship between sedation and duration of MV.ResultsCompared to patients not receiving these medications, propofol alone, dexmedetomidine alone, combination of midazolam and dexmedetomidine, combination of propofol and dexmedetomidine, combination of midazolam, propofol and dexmedetomidine were all association with an increased risk of VAP; dexmedetomidine alone, combination of midazolam and dexmedetomidine, combination of propofol and dexmedetomidine, combination of midazolam, propofol and dexmedetomidine may be protective factor for in-hospital mortality, while propofol alone was risk factor. There was a positive correlation between all types of tranquilizers and the duration of MV. Taking dexmedetomidine alone as the reference, all other drug groups were found to be associated with an increased risk of in-hospital mortality. The administration of propofol alone, in combination with midazolam and dexmedetomidine, in combination with propofol and dexmedetomidine, in combination with midazolam, propofol and dexmedetomidine were associated with an increased risk of VAP compared to the use of dexmedetomidine alone.ConclusionDexmedetomidine alone may present as a favorable prognostic option for ICU patients with mechanical ventilation MV.

Data used for research.

Emergency department (ED) overcrowding leads to delayed care, increased patient risk, and inefficient resource use. The MIMIC-IV-Ext Triage Instruction Corpus (MIETIC) addresses this by providing 9,629 structured triage cases from MIMIC-IV, aligned with the Emergency Severity Index (ESI). MIETIC supports large language model (LLM) training for AI-assisted triage, improving accuracy, consistency, and risk assessment. The dataset includes chief complaints, vital signs, demographics, and medical history, ensuring realistic triage decision-making. Developed through automated quality control and expert validation, MIETIC enhances model performance in high-risk and moderate-risk classification. Available in CSV formats, MIETIC enables research in clinical NLP, AI-driven triage, and decision-support tools. The dataset module includes:

Structured triage cases with ESI labels. Triage case generation prompts for instruction tuning. Expert-validated samples for quality control. SQL scripts for data extraction and validation, hosted on GitHub.

MIETIC provides a standardized, reproducible dataset to advance AI-driven emergency triage, optimizing accuracy, efficiency, and resource allocation.

The authors of the paper collected the dataset.

ObjectiveThis study aimed to evaluate the predictive capability of glycolipid metabolism index (triglyceride-glucose index, TyG; atherogenic index of plasma, AIP; triglyceride to high-density lipoprotein cholesterol ratio, TG/HDL-C; and non-HDL-C to HDL-C ratio, NHHR) for complications and ventilator use in patients with intracerebral hemorrhage (ICH) admitted to the intensive care unit (ICU).MethodsPatients with ICH requiring ICU admission were selected from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Outcomes assessed included incidence of complications and use of ventilator support. Multivariate logistic regression, receiver operating characteristic (ROC) analysis, and restricted cubic spline were employed to investigate the relationship between glycolipid metabolism index and clinical outcomes in ICH patients.ResultsA total of 733 patients were included. Multivariate logistic regression analysis revealed that elevated TyG, AIP, and TG/HDL-C levels were associated with increased incidence of complications and prolonged ventilator use. ROC curve analysis demonstrated that TyG (AUC 0.646) exhibited the strongest predictive ability for multiple complications in ICH patients. Further multiple regression analysis identified TG/HDL-C as an independent predictor of deep vein thrombosis, while TyG, AIP, and TG/HDL-C independently predicted pulmonary embolism, and TyG, AIP, NHHR, and TG/HDL-C independently predicted acute kidney injury. Moreover, ventilator use further heightened the risk of multiple complications in ICU patients with elevated glycolipid metabolism index.ConclusionGlycolipid metabolism index represent promising and readily accessible biomarkers for predicting multiple complications and ventilator use in ICU patients with ICH.

Objective: Congestive heart failure (CHF) is a clinical syndrome in which heart disease progresses to a severe stage. Risk assessment and early diagnosis of death in patients with CHF are critical to patient prognosis and treatment. The purpose of this study was to establish a nomogram predicting in-hospital death for CHF patients in the ICU.

Design: A retrospective observational cohort study.

Setting and participants: The data of study from 30,411 CHF patients in the Medical Information Mart for Intensive Care (MIMIC-IV) database and the eICU Collaborative Research Database (eICU-CRD).

Primary outcome: In-hospital mortality.

Results: The inclusion criteria were met by 15983 subjects, whose in-hospital mortality rate was 12.4%. Multivariate analysis determined that the independent risk factors were age, race, norepinephrine, dopamine, phenylephrine, vasopressin, mechanical ventilation, intubation, HepF, heart rate, respiratory rate, temperature, SBP, AG, BUN, creatinine, chloride, MCV, RDW, and WBC. The C-index of the nomogram (0.767, 95%CI: 0.759–0.779) was superior to that of the traditional SOFA, APSIII and GWTGHF score, indicating its discrimination power. Calibration plots demonstrated that the predicted results are in good agreement with the observed results. The decision curves of the derivation and validation sets both had net benefits.

Conclusion: The twenty independent risk factors for in-hospital mortality of CHF patients were age, race, norepinephrine, dopamine, phenylephrine, vasopressin, mechanical ventilation, intubation, HepF, heart rate, respiratory rate, temperature, SBP, AG, BUN, creatinine, chloride, MCV, RDW, and WBC. The nomogram that included these factors accurately predicted the in-hospital mortality of CHF patients. The novel nomogram has the potential to be a clinical practice aided predictive tool for predicting and assessing mortality in CHF patients in the ICU.

BackgroundAcute respiratory distress syndrome (ARDS) is a severe condition associated with high morbidity, mortality, and healthcare costs. Despite extensive research, treatment options for ARDS are suboptimal.MethodsThis study encompassed patients diagnosed with ARDS from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database. Pre-intensive care unit (ICU) statin use was assessed as the exposure variable. Kaplan–Meier survival analysis was conducted to evaluate mortality at 30 and 90 days. Adjusted multivariable Cox models were utilized to estimate hazard ratios. Subgroup analyses and propensity score-matching (PSM) were undertaken for further validation.ResultsOur study comprised 10,042 participants diagnosed with ARDS, with an average age of 61.8 ± 15.3 years. Kaplan–Meier survival analysis demonstrated a significantly lower prevalence of mortality at 30 and 90 days in individuals who used statins before ICU admission. Adjusted multivariable Cox models consistently showed a significant decrease in mortality prevalence associated with pre-ICU statin use. After accounting for confounding factors, patients who used statins before ICU admission experienced a 39% reduction in 30-day mortality and 38% reduction in 90-day mortality. We found a significant decrease in ICU stay (0.84 days) for those who used statins before ICU admission. These results were supported by subgroup analyses and PSM.ConclusionThis large cohort study provides evidence supporting the association between pre-ICU statin use, reduced risk of death, and shorter ICU stay in patients with ARDS, thereby suggesting the potential benefits of statin use in critically ill patients.

Abstract

👂💉 EHRSHOT is a dataset for benchmarking the few-shot performance of foundation models for clinical prediction tasks. EHRSHOT contains de-identified structured data (e.g., diagnosis and procedure codes, medications, lab values) from the electronic health records (EHRs) of 6,739 Stanford Medicine patients and includes 15 prediction tasks. Unlike MIMIC-III/IV and other popular EHR datasets, EHRSHOT is longitudinal and includes data beyond ICU and emergency department patients.

⚡️Quickstart 1. To recreate the original EHRSHOT paper, download the EHRSHOT_ASSETS.zip file from the "Files" tab 2. To work with OMOP CDM formatted data, download all the tables in the "Tables" tab

⚙️ Please see the "Methodology" section below for details on the dataset and downloadable files.

Methodology

1. 📖 Overview

EHRSHOT is a benchmark for evaluating models on few-shot learning for patient classification tasks. The dataset contains:

• **6,739 **patients
• 41.6 million clinical events
• 921,499 visits
• 15 prediction tasks

%3C!-- --%3E

2. 💽 Dataset

EHRSHOT is sourced from Stanford’s STARR-OMOP database.

• Data follows the OMOP CDM and is fully de-identified.
• Unlike most other EHR research datasets, EHRSHOT is not restricted to ED/ICU visits and instead includes longitudinal patient data for all hospital encounter types.
• EHRSHOT does not contain clinical notes or images.

%3C!-- --%3E

We provide two versions of the dataset:

• EHRSHOT-Original is the same exact dataset used in the original EHRSHOT paper.
• EHRSHOT-OMOP is a more complete version of the EHRSHOT dataset which includes all OMOP CDM tables and additional OMOP metadata.

%3C!-- --%3E

To access the raw data, please see the "Tables" and "Files"** **tabs above:

3. 💽 Data Files and Formats

We provide EHRSHOT in two file formats:

• OMOP CDM v5.4
• Medical Event Data Standard (MEDS)

%3C!-- --%3E

Within the "Tables" tab...

1. %3Cu%3EEHRSHOT-OMOP%3C/u%3E

* Dataset Version: EHRSHOT-OMOP

* Notes: Contains all OMOP CDM tables for the EHRSHOT patients. Note that this dataset is slightly different than the original EHRSHOT dataset, as these tables contain the full OMOP schema rather than a filtered subset.

Within the "Files" tab...

1. %3Cu%3EEHRSHOT_ASSETS.zip%3C/u%3E

* Dataset Version: EHRSHOT-Original

* Data Format: FEMR 0.1.16

* Notes: The original EHRSHOT dataset as detailed in the paper. Also includes model weights.

2. %3Cu%3EEHRSHOT_MEDS.zip%3C/u%3E

* Dataset Version: EHRSHOT-Original

* Data Format: MEDS 0.3.3

* Notes: The original EHRSHOT dataset as detailed in the paper. It does not include any models.

3. %3Cu%3EEHRSHOT_OMOP_MEDS.zip%3C/u%3E

* Dataset Version: EHRSHOT-OMOP

* Data Format: MEDS 0.3.3 + MEDS-ETL 0.3.8

* Notes: Converts the dataset from EHRSHOT-OMOP into MEDS format via the `meds_etl_omop`command from MEDS-ETL.

4. %3Cu%3EEHRSHOT_OMOP_MEDS_Reader.zip%3C/u%3E

* Dataset Version: EHRSHOT-OMOP

* Data Format: MEDS Reader 0.1.9 + MEDS 0.3.3 + MEDS-ETL 0.3.8

* Notes: Same data as EHRSHOT_OMOP_MEDS.zip, but converted into a MEDS-Reader database for faster reads.

4. 🤖 Model

We also release the full weights of **CLMBR-T-base, **a 141M parameter clinical foundation model pretrained on the structured EHR data of 2.57M patients. Please download from https://huggingface.co/StanfordShahLab/clmbr-t-base

**5. 🧑‍💻 Code **

Please see our Github repo to obtain code for loading the dataset and running a set of pretrained baseline models: https://github.com/som-shahlab/ehrshot-benchmark/

Usage

**NOTE: You must authenticate to Redivis using your formal affiliation's email address. If you use gmail or other personal email addresses, you will not be granted access. **

Access to the EHRSHOT dataset requires the following:

• Verified Affiliation with an **Academic, Government, **o

Background/ObjectiveThis study was conducted to investigate the clinical characteristics and outcomes of patients with acute ischemic stroke and atrial fibrillation (AF) in intensive care units (ICUs).MethodsIn the Medical Information Mart for Intensive Care IV database, 1,662 patients with acute ischemic stroke were identified from 2008 to 2019. Of the 1,662 patients, 653 had AF. The clinical characteristics and outcomes of patients with and without AF were compared using propensity score matching (PSM). Furthermore, univariate and multivariate Cox regression analyzes were performed.ResultsOf the 1,662 patients, 39.2% had AF. The prevalence of AF in these patients increased in a stepwise manner with advanced age. Patients with AF were older and had higher Charlson Comorbidity Index, CHA2DS2-VASc Score, HAS-BLED score, and Acute Physiology Score III than those without AF. After PSM, 1,152 patients remained, comprising 576 matched pairs in both groups. In multivariate analysis, AF was not associated with higher ICU mortality [hazard ratio (HR), 0.95; 95% confidence interval (CI), 0.64–1.42] or in-hospital mortality (HR, 1.08; 95% CI, 0.79–1.47). In Kaplan–Meier analysis, no difference in ICU or in-hospital mortality was observed between patients with and without AF.ConclusionsAF could be associated with poor clinical characteristics and outcomes; however, it does not remain an independent short-term predictor of ICU and in-hospital mortality among patients with acute ischemic stroke after PSM with multivariate analysis.

Clinical management decisions for patients with acutely decompensated heart failure and many other diseases are often based on grades of pulmonary edema severity, rather than its mere absence or presence. Chest radiographs are commonly performed to assess pulmonary edema. The MIMIC-CXR dataset that consists of 377,110 chest radiographs with free-text radiology reports offers a tremendous opportunity to study this subject.

This dataset is curated based on MIMIC-CXR, containing 3 metadata files that consist of pulmonary edema severity grades extracted from the MIMIC-CXR dataset through different means: 1) by regular expression (regex) from radiology reports, 2) by expert labeling from radiology reports, and 3) by consensus labeling from chest radiographs.

This dataset aims to support the algorithmic development of pulmonary edema assessment from chest x-ray images and benchmark its performance. The metadata files have subject IDs, study IDs, DICOM IDs, and the numerical grades of pulmonary edema severity. The IDs listed in this dataset have the same mapping structure as in MIMIC-CXR.