Skip to main content
. 2022 Oct 21;22(20):8068. doi: 10.3390/s22208068

Table 6.

Publicly available dataset for medical experiments.

Dataset Source Medical Domain Category Size
RSNA(Radiological Society of North America) and NIH [72] Pneumonia NIH chest X-ray dataset with initial annotation. 26,601 CXR Images
Kermany [73] Pneumonia Chest X-rays 5856 CXR Images
Chest radiographs (SCR) dataset X-ray images [74] Pneumonia Chest radiographs 247 frontal viewed
posterior-anterior (PA)
Central Line-Associated Bloodstream infections (CLABSI) in California Hospitals [75] Blood Stream Infections (BSI) The CLABSI (text/csv) dataset contains reported infections, baseline data predictions, days count for central line, standard infection ratio (SIR), associated confidence interval of 95%, and grading with respect to national baseline. Details from 461 hospitals.
MIMIC Clinical Database [76,77] Epidemics (HER Data) The MIMIC dataset consists of ICU data with high patient’s count including vital signs, laboratory test, and medication courses. The MIMIC-III database has 26 relational tables containing patient’s data (SUBJECT_ID), hospital admissions (HADM_ID), and ICU admissions(ICUSTAY_ID).
ICES Data Repository [78] EHR Data EHR Data recorded from the health services of Ontario. 13 million people.
Veterans Health Administration [79,80] EHR Data EHR data from US Veteran’s Affairs (VA) dataset 1293 health care facilities with 171 medical center and 1112 outpatient sites.