Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
13,115 datasets
Shuting Yang's study evaluates open-source large language models on 11,329 adult diabetes patient records from a Chinese tertiary center (2010–2020). The analysis measures F1-scores for multi-class diabetes subtyping and binary classification of diabetic kidney disease and metabolic syndrome. It tests various model sizes, four prompting strategies, and performance in both English and Chinese.
Shuting Yang's 2026 study evaluates open-source large language models for diagnosing diabetes subtypes and comorbidities from unstructured clinical text. The analysis uses 11,329 adult diabetes patient records from a Chinese tertiary center spanning 2010-2020. It measures model performance via F1-scores for multi-class subtyping and binary classification of diabetic kidney disease and metabolic syndrome.
11,329 adult diabetes patient records from a Chinese tertiary center (2010–2020) were used to evaluate open-source LLMs. The dataset supports analysis of model performance metrics like F1-scores for diabetes subtyping and comorbidity classification. It captures results from testing various LLMs using different prompting strategies in English and Chinese.
ACT Government Open Data provides the proportion of Aboriginal and Torres Strait Islander children aged 60–63 months fully immunised from 2010 to 2017. This dataset, sourced from Australian Government Department of Health historical tables, tracks annual immunization coverage percentages for this specific demographic cohort.
Data and R analysis scripts for a study on the diagnostic accuracy of a milk pregnancy-associated glycoprotein ELISA test in Holstein cows. The study was submitted for publication in Preventive Veterinary Medicine. The dataset was authored by Simon Dufour and is hosted on the Borealis Harvested Dataverse.
Data from the Slovak Pancreas Registry includes 95 patients with metastatic pancreatic ductal adenocarcinoma treated with third-line systemic therapy. The study analyzes survival outcomes and the prognostic value of nutritional and inflammatory markers, such as the Prognostic Nutritional Index and Glasgow Prognostic Score. It reports a median overall survival of 5.55 months and a median progression-free survival of 3.29 months.
MedMisBench is a benchmark for evaluating large language models on medical question-answering tasks when misleading context is introduced. It is built from five medical QA sources covering standard reasoning, expert reasoning, patient-journey scenarios, and agentic biomedical capability. The dataset was created by AI4HealthResearch and was last updated on Hugging Face in May 2026.
Simulation data from DKOsim Run 139, mimicking the methodology of Fong 2024. The dataset includes dLFC scores and was published by Yue Gu on figshare in April 2026. The file size is 163 bytes, indicating a very small sample or summary.
Qualitative data from an exploratory study using online mini-focus groups with healthcare professionals and patients. The dataset, 29.5 KB in size, was created by Maria de Lacerda Machado and last updated on March 17, 2026. It synthesizes results on discrepancies in perceived importance of safety outcome measures.
Qualitative codes from a study exploring discrepancies in how patients and healthcare professionals perceive perioperative patient safety measures. The 5.5 KB XLS file, authored by Maria de Lacerda Machado and last updated in March 2026, contains thematic categories derived from online mini-focus group analysis. Findings highlight communication failure as a predominant cross-cutting issue and differing priorities between patient experiences and professional system-level concerns.
Maria de Lacerda Machado's dataset contains qualitative focus group data used to build graphs for a study on patient safety in perioperative care. The data, stored in an XLSX file of 103.6 KB, was collected via online mini-focus groups with healthcare professionals and patients. It was last updated on March 17, 2026, and is shared under a CC-BY-4.0 license.
A 60.7 KB document authored by Long Guo in March 2026, reviewing advancements in surgical nanorobotics. The text critically evaluates magnetic, acoustic, optical, and chemical actuation modalities for navigating physiological fluids. It analyzes the integration of propulsion systems with medical imaging for real-time feedback in oncology and ophthalmology.
A single-center retrospective cohort study of 48 valvular heart disease patients undergoing valve surgery. The dataset, authored by Chengyao Xu and last updated in March 2026, compares outcomes for patients on quadruple therapy with SGLT2 inhibitors versus triple therapy without, assessing mobility, stress ulcer risk, and fall risk at multiple perioperative timepoints.
A matrix dataset on the acceptability of medical illustrations, authored by Ruth Dede Tuwor. The dataset is stored in an XLS file and was last updated on April 22, 2026. Its small size of 5.5 KB suggests a limited scope.
A matrix analysis of challenges associated with using real-life imagery in health communication materials. The dataset is a 5.5 KB Excel file authored by Ruth Dede Tuwor and last updated on April 22, 2026. It is shared under a CC-BY-4.0 license on the figshare platform.
Ruth Dede Tuwor published a matrix for theme 1 on the current role of imagery in health communication tools on figshare in April 2026. The dataset is a 5.5 KB Excel file released under a CC-BY-4.0 license. Its specific row count and column details are not provided in the metadata.
A small dataset (9.5 KB) containing anthropometric and clinical characteristics for a group of studied subjects, presented as mean values with standard error of the mean. The data was authored by Nur Hasnah Maamor and last updated on April 15, 2026. It is available in XLS format under a CC-BY-4.0 license.
A dataset of 688 endometriosis patients used to compare the mean age of diagnosis based on symptom severity via multiple linear regression analysis. The data was authored by Soha Wahab and is available on figshare. The dataset was last updated on 2026-04-15.
A clinical dataset of 688 endometriosis patients compares the mean age of diagnosis based on the severity of their symptoms. The data is provided in an XLS format and was authored by Soha Wahab. It was last updated on April 15, 2026.
688 endometriosis patients are represented in this dataset, which provides frequency and percentage distributions of Symptom Severity Scores (SSS). The data was authored by Soha Wahab and last updated on April 15, 2026. It is available for download in XLS format under a CC-BY-4.0 license.