Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
14,748 datasets
WMS on the development plan Groß Brunsrode III Original of the municipality of Lehr in the original data format. The dataset is provided by the Bundesamt für Kartographie und Geodäsie. It was last updated on 2025-11-25.
WFS on the development plan Birkenfeld - Ost II 3. partially simplified change of the municipality of Lehr in the original data format. The dataset is provided by the Bundesamt für Kartographie und Geodäsie (Federal Agency for Cartography and Geodesy) and was last updated on 2025-11-25.
June 1 price lists from California hospitals detail average charges for 25 common outpatient procedures and estimated revenue impacts. The dataset is compiled by the State of California's Department of Health Care Access and Information and was last updated in December 2025.
Qualitative data from a multi-site feasibility study assessing a traumatic brain injury prognostic model as a clinical decision support tool. The study involved co-design sessions with 21 healthcare providers from Kilimanjaro Christian Medical Center in Tanzania and Duke Hospital in the USA. Paige O'Leary collected the data for her Master's thesis at Duke.
Data collection began in 1992 for firearm-related injuries and expanded in July 2000 to include all injury types. The dataset provides the basis for national estimates of nonfatal injuries treated in U.S. hospital emergency departments. It is an ongoing surveillance study managed by the CDC and CPSC.
A multimodal dataset linking chest X-ray images with radiologist gaze patterns and report ground truth. The data includes fixation lists, static gaze heatmaps, segmentation masks, and a full JSON file with report annotations. It was created by phamtrongthang and last updated on Hugging Face in November 2025.
Enterococci measurements from water samples collected at New York City beaches by the DOHMH Office of Public Health Engineering. Monitoring is conducted from April through September each year as part of the Beach Surveillance and Monitoring Program. The data is hosted by data.cityofnewyork.us and was last updated on October 6, 2025.
TCGA-UniformTumor-8K contains 25,495 high-resolution regions of interest (ROIs) extracted from 9,662 H&E-stained diagnostic histopathology slides. Created by MahmoodLab using TCGA data and updated in 2025, the dataset features manual annotations from two expert pathologists for pan-cancer subtyping tasks.
Healthcare Payments Data (HPD) Services report details individual procedures from California healthcare claims, categorized using the Restructured Berenson-Eggers Type of Services (BETOS) Classification System. It provides three main metrics—total services, member count, and service rate per 1,000 members—groupable by year, age, sex, county, region, and payer. Data is available at two aggregation levels: eight main RBCS categories and their more specific subcategories.
ReXVQA provides 653,834 visual question-answering pairs linked to 160,000 radiological studies and 273,004 chest X-ray images. Created by the Rajpurkar Lab, the data originates from 109,487 patients across 79 medical sites within three U.S. health systems.
Khayelitsha township in Cape Town, Western Cape Province, South Africa, is the geographic scope. This qualitative dataset contains transcripts from in-depth interviews exploring the lived experiences of patients managing HIV and type 2 diabetes multimorbidity. The study recruited 10 patient-participants and 6 healthcare workers from two public clinics, and interviews were guided by semi-structured questionnaires based on Shippee's Complex Cumulative Model.
31 patient records from a mixed-methods study assessing a nurse-led psychosocial intervention for fear of progression in advanced gynecologic or lung cancer. The dataset includes quantitative questionnaire responses at baseline, eight, and twelve weeks, and qualitative exit interview transcripts analyzed with N-Vivo 12. The study was conducted by Anne Reb and harvested by QDR.
77 Samsung INR21700-50E lithium-ion cells were experimentally evaluated to develop state-of-health diagnostic methods. The dataset results from the REBELION project, part of a Horizon Europe program, and was last updated in October 2025. It contains data from three novel diagnostic methods—electrochemical noise analysis, current steps, and high-frequency current steps—contrasted with conventional techniques.
The Netherlands-based TOPICS-MDS Memorabel 1-4 database contains pooled cross-sectional and longitudinal data from 11 research projects. It includes information on 919 care receiver-caregiver dyads, covering older persons with dementia and their informal caregivers. The dataset was developed for the National Care for the Elderly Programme and the Memorabel programme, with data collected from 2014 onward.
Zhang, Cherri externally validated the Smart Triage clinical prediction model for critically ill children. The analysis included 11,595 participants under the age of five from three hospitals in Uganda and two in Kenya, evaluating model performance by age group. The dataset was last updated on October 13, 2025.
Case Mix Index (CMI) data from the State of California's Department of Health Care Access and Information provides the average relative DRG weight for hospital inpatient discharges. The CMI reflects patient diversity, clinical complexity, and resource needs, calculated using Medicare Severity-Diagnosis Related Group (MS-DRG) weights from CMS applied to all discharges. The dataset was last updated in November 2025.
565 whole-body PET/CT image-report pairs comprise this benchmark dataset for evaluating vision-language models in radiology report generation. The dataset offers coverage of dozens of organs with metabolic information, reflecting real-world clinical PET imaging in oncology. It was authored by r1pples and last updated on November 14, 2025.
A dataset for predicting clinical trial outcomes in drug development, presented in the paper 'Automatically Labeling Clinical Trial Outcomes: A Large-Scale Benchmark for Drug Development'. It includes a manually annotated subset called 'human_labels'. The dataset was created by author chufangao and was last updated on 2025-10-27.
MedSynth is a dataset of synthetic medical dialogue-note pairs created by Ahmad Rezaie Mianroodi and colleagues, as described in a 2025 arXiv paper. The dataset is hosted on HuggingFace by the author Ahmad0067 and was last updated in November 2025. It likely contains paired conversational text and structured clinical notes.
SCOPE-MRI is a musculoskeletal imaging dataset released by Sethi et al. in 2025 to facilitate deep learning research in orthopedics. It includes MRI and CT scans designed for computer vision tasks as detailed in the accompanying NPJ AI publication.