Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
14,756 datasets
5000 time series recordings of electrocardiogram (ECG) heartbeats, each 140 data points long, sourced from the OpenML platform. The dataset is designed for classification tasks, distinguishing between normal and arrhythmic heart rhythms. The original collection methodology and time period are not specified in the provided metadata.
Beginning in 2009, this dataset contains hospital discharge counts and calculated rates for Patient Safety Indicators (PSIs) developed by the Agency for Healthcare Research and Quality (AHRQ). It is produced by health.data.ny.gov using New York's Statewide Planning and Research Cooperative System (SPARCS) inpatient data and US Census data for area-level measures. The data includes observed, expected, and risk-adjusted rates with confidence intervals for potential in-hospital complications and adverse events.
Patient Safety Indicators (PSI) developed by the Agency for Healthcare Research and Quality (AHRQ) track potential in-hospital complications and adverse events. The dataset contains hospital discharge counts, observed, expected, and risk-adjusted rates with 95% confidence intervals for New York State hospitals beginning in 2009. Data originates from the Statewide Planning and Research Cooperative System (SPARCS) inpatient records and is published by health.data.ny.gov.
Hospital discharge data from New York State's SPARCS system provides counts, observed, expected, and risk-adjusted rates for Patient Safety Indicators (PSIs) developed by the Agency for Healthcare Research and Quality (AHRQ). The dataset includes measures for potential in-hospital complications and adverse events following surgeries, procedures, and childbirth, calculated from inpatient data beginning in 2009. Data is presented by hospital and county, with rates and confidence intervals.
A WMS service provides the urban development plan ‘Zentrales Feuerwehrgerätehaus und Bauhof - 1st Amendment’ for the municipality of Auenwald. The dataset is transformed according to the INSPIRE directive and is based on an XPlanung dataset in version 6.0. The Bundesamt für Kartographie und Geodäsie is listed as the organization, and the record was last updated on 2025-10-22.
MedSG-Bench is the first benchmark for medical image sequences grounding, accepted as a Spotlight at NeurIPS 2025. The dataset is associated with MedSG-188K, a grounding instruction-tuning dataset, and the MedSeq-Grounder model. It was last updated on Hugging Face on October 24, 2025.
A behavioral psychology experiment by H. Scholten, last updated in October 2025, investigates the effect of inhibitory control training on smoking-related cues. The dataset likely contains pre- and post-training evaluations from 39 smokers and 43 nonsmokers who underwent a go/no-go task. Results show that not responding to smoking stimuli decreased their subsequent valuation, extending a known devaluation effect to smoking cues.
I.M.G Schouwenaars from DANS Data Station Social Sciences and Humanities Collection published this dataset on 2025-10-24. It describes lessons learned from the school-partnered development of a sleep intervention for autistic students, focusing on the first three phases of the CeHReS roadmap. The iterative development involved active stakeholder participation to identify important factors like limited burden and clear guidance.
78 Tension-Type Headache patients participated in a randomized clinical trial analyzed via Structural Equation Modeling. The dataset supports a study exploring how headache presenteeism relates to health-related productivity loss through anxiety and headache severity. The data was authored by L. Monzani and last updated in October 2025.
508 respondents from a representative Dutch sample participated in a cross-sectional, internet-based survey. The data supports a 2018 publication investigating how expected effectiveness of medication varies by administration route (oral, injection, topical) and targeted symptom (pain, itch). K.J. Peerdeman and colleagues authored the original study.
AbdomenAtlas 3.0 Mini is a public dataset containing more than 9,000 high-quality abdominal CT scans paired with radiology reports. It includes per-voxel annotations for tumors in the liver, kidney, and pancreas. The dataset was created by AbdomenAtlas and was last updated on Hugging Face in October 2025.
289 completed survey records from two cohorts of third- and fourth-year medical students, collected at three time points: pre-workshop, post-workshop, and one year after. The data examines concept retention from an implicit bias classroom workshop using a self-developed seven-item, seven-point Likert-scale survey. The dataset was contributed by Y. Zhou and is hosted by the DANS Data Station Social Sciences and Humanities Collection.
Sickle cell disease is one of the most common monogenic disorders globally. This dataset, created by M. A. Timmer, compares movement behavior in adults with SCD to healthy controls, addressing a hypothesized lack of physical activity information. It was last updated on November 4, 2025.
900 de-identified electronic medical records (EMRs) from psychiatric inpatients used to evaluate LLM performance in clinical practice. The data consists of real-world clinical resources without synthetic augmentation or paraphrasing to ensure professional-grade benchmarking.
Derm1M is a large-scale vision-language dataset for dermatology containing 1,029,761 image-text pairs from 403,563 unique images. The dataset covers 390 skin conditions organized in a four-level expert ontology and includes 130 clinical concepts. It was created by author redlessone and last updated on the Hugging Face platform in October 2025.
Primary sources document expressed support or rejection of terrorist Anders Behring Breivik by far-right actors between 2011 and 2021. The dataset likely contains letters, blog posts, videos, and archived message board posts. Lars Erik Berntzen authored this study, which was harvested by QDR and updated in October 2025.
7,041 dermatologic cases combine SkinCAP dermatologist-authored captions with SkinCoT clinician-certified diagnostic narratives. The dataset bridges the gap between visual observations and clinical reasoning. It was created by yuhos16 and last updated in October 2025.
New York City's Taxi and Limousine Commission (TLC) approved LabCorp drug test locations. The dataset includes addresses, geographic coordinates, and administrative boundaries for each site. It was last updated on October 8, 2025, and is hosted on the NYC Open Data platform.
10,000 text-based conversations provide a corpus for analyzing mental health discourse. The dataset was created by author LasagnaS and last updated in December 2025. Its content is derived from conversational text, focusing on mental health topics.
MTBBench is a benchmark designed to evaluate multimodal large language models in complex clinical oncology scenarios. It focuses on multimodal integration of data like pathology and radiology, and longitudinal reasoning across patient timelines. The benchmark was authored by EeshaanJain and last updated on October 23, 2025.