Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
13,593 datasets
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.
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.
Chicago Department of Public Health (CDPH) Environmental Health program collects and sorts mosquitoes for West Nile Virus surveillance. The dataset currently contains counts for Aedes albopictus, with plans to include additional species. Data is organized by SEASON YEAR and WEEK, with totals broken down by MALE and FEMALE counts.
19 curated medical datasets across categories such as historical clinical trials, oncology, and cardiology. The collection includes standardized data from landmark studies, ranging from the 1747 scurvy trial to modern observational studies on blood storage and cancer recurrence.
Emergency Department ratio data from the State of California represents ED burden by comparing encounters to available treatment stations. The dataset breaks down encounters by 16 health-related conditions including Active COVID-19, Asthma, Cardiac, and Substance Abuse. It was last updated in November 2025.
Annual Excel pivot tables summarize patients treated in California Emergency Departments. Data includes number of visits, expected payer, discharge disposition, age groups, sex, preferred language, race groups, principal diagnosis groups, and principal external cause of injury groups. The State of California aggregates this data from the ED Treat-and-Release and Inpatient Databases.
California county data contains hospitalization rates for seven prevention quality indicators and supply rates for physicians treating those conditions. Anticipated retirement of practicing physician specialists is also provided by county. Rates are calculated per 100,000 population.
Clara Virbel-Fleischman's qualitative study includes interview data from 22 patients with Parkinson's disease and 9 healthcare professionals regarding their perceptions of body-worn sensor monitoring. The data likely contains interview transcripts and thematic analysis documents, including usability scores and user experience feedback from a one-week sensor experiment. It was harvested by QDR and last updated on October 20, 2025.
A qualitative study conducted through the Palliative Care Research Cooperative Group (PCRC) interviewed 42 participants, including 20 clinical investigators and 22 patients or family caregivers. The research, authored by Matthew DeCamp and harvested by QDR, identified 8 ethical challenges and 11 potential solutions specific to end-of-life and palliative care research engagement. Data includes transcripts from participants who provided enthusiastic consent for sharing.
Eleonore Baum and colleagues conducted 20 semi-structured interviews with Somali pastoralists in Ethiopia between July 2020 and January 2021. The interviews explore perceptions of chronic pain across primary, secondary, and tertiary care facilities and pastoralist communities. Audio recordings were transcribed and translated from Somali to English for analysis using the Framework Method.
MMOral-OPG-Bench consists of 100 panoramic X-ray images paired with 491 closed-ended and 578 open-ended questions for dental diagnostic evaluation. Created by OralGPT and released in 2025, it serves as a manually curated benchmark for multimodal dental AI.
A qualitative study interviewed patients with metastatic lung cancer admitted to a 52-bed chest ward in a central Taiwan medical center. Participants were selected based on criteria including being over 20 years old, having exercise habits, and speaking Chinese or Taiwanese. Interview transcripts were de-identified and analyzed by a group of qualitative research experts to extract main themes.
Medical Encyclopedia is a text dataset hosted on HuggingFace by author amalsp. The dataset was last updated on December 18, 2025. Its specific content and scale are not detailed in the available metadata.