Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
12,212 datasets
Five large language models were evaluated on 15 high-fidelity cardiac surgery scenarios by senior surgeons. O1 achieved the highest median normalized score (0.896), while patient safety and hallucination avoidance were the lowest-scoring dimensions across models. The dataset, authored by Marc Leon and last updated in May 2026, documents the evaluation framework and results, concluding that LLMs are not yet ready for safe use in complex surgical settings.
113 cancer patients experienced immune-related adverse events in a cohort of 297 patients receiving immune checkpoint inhibitor combination therapy. Yao Qiu published this clinical study on figshare in 2026, analyzing incidence, severity, onset time, and risk factors for adverse events. The findings suggest corticosteroid use is a protective factor and combination with targeted therapy increases risk for endocrine adverse events.
787 patient records from a retrospective two-center cohort study conducted between January 2021 and October 2025. The dataset was used to develop an interpretable machine-learning model for identifying comorbid atrial fibrillation in patients with diabetic kidney disease. The model was created by Xiaoran Li and is shared under a CC-BY-4.0 license.
23 randomized controlled trials involving 1,384 patients with multiple sclerosis were analyzed to compare eight acupoint stimulation therapies. Ruiou Chen published this supplementary document on figshare in May 2026 under a CC-BY-4.0 license. The analysis ranks interventions for improving neurological function, fatigue, and activities of daily living using Bayesian network meta-analysis.
A retrospective two-center cohort study from January 2021 to October 2025, comprising 787 unique patient records with diabetic kidney disease. The dataset was used to develop and internally validate a machine-learning model for identifying comorbid atrial fibrillation. The model, created by Xiaoran Li, achieved an AUC of 0.927 on the test set and was last updated in May 2026.
579 adult paralytic ileus patient records from the MIMIC-IV database (2008–2022) and an external hospital cohort, used to develop a sepsis prediction model. The dataset includes seven clinical predictors identified through feature selection, such as pneumonia and red cell distribution width. It was created by Qingzhou Song and last updated on June 2, 2026.
A retrospective cohort study of 123 patients with type 2 diabetes and non-diabetic renal disease, with a median follow-up of 80 months. The dataset includes supplementary material analyzing clinicopathological profiles and prognostic factors for renal outcomes. It was authored by figshare admin karger and last updated on 2026-06-01.
60 high-bleeding-risk patients were randomized between 2019 and 2020 to compare two intermittent hemodialysis techniques. The supplementary material includes results on session success rates, adequacy (KT/V), dialyzer status, costs, and nursing workload. This document dataset was authored by figshare admin karger and is licensed under CC-BY-4.0.
Anita Muglia's dataset contains serum cytokine and chemokine measurements from 103 RT-PCR-confirmed COVID-19 patients hospitalized during the first pandemic wave in Italy from January to May 2020. The data includes concentrations of IL-1β, IL-6, IL-8, IL-10, TNF-α, CCL3, and CXCL10 (IP-10) and their associations with in-hospital mortality and ICU admission. It was last updated on 2026-05-25.
A retrospective study of 103 RT-PCR-confirmed COVID-19 patients hospitalized during the first pandemic wave in Italy from January to May 2020. It contains serum cytokine and chemokine measurements, including IL-1β, IL-6, IL-8, IL-10, TNF-α, CCL3, and CXCL10, linked to clinical outcomes like ICU admission and mortality. The dataset was authored by Anita Muglia and shared under a CC-BY-4.0 license.
A systematic review and meta-analysis of 11 risk prediction models for Peristomal Moisture-associated Skin Damage (PMASD), identified from 10 studies. The work was authored by Haijia Liu and last updated on June 4, 2026. It synthesizes model performance metrics, including Area Under the Curve (AUC) values ranging from 0.812 to 0.914, and evaluates predictors like radiotherapy history and stoma type.
A single-center retrospective cohort study of 917 hormone replacement frozen embryo transfer (HRT-FET) cycles from 2017 to 2023. The dataset, authored by Goksu Goc and shared under CC-BY-4.0, compares outcomes for patients grouped by receipt of a single-dose progesterone rescue injection, with pre-transfer progesterone levels measured by Cobas e411 ECLIA. It explores the association between very low pre-transfer progesterone levels and live birth rates.
A retrospective cohort study analyzed 62 pediatric patients with newly diagnosed acute myeloid leukemia from January 2015 to December 2024. The dataset likely contains longitudinal measurements of weight Z-score, BMI Z-score, and serum albumin, tracked from pre-induction chemotherapy through 30 days post-treatment. The study, authored by Chun-lei Liu and shared on figshare, correlates nutritional indicator changes with treatment outcomes like remission rates and mortality.
A retrospective cohort study of 917 hormone replacement frozen embryo transfer cycles from a single center between 2017 and 2023. The data describes patient groups based on receipt of a single-dose progesterone rescue and analyzes live birth and miscarriage rates relative to pre-transfer progesterone levels. The dataset was authored by Goksu Goc and shared under a CC-BY-4.0 license.
917 hormone replacement frozen embryo transfer cycles from a single-center retrospective cohort study conducted between 2017 and 2023. The data, shared by Goksu Goc, explores the association between pre-transfer progesterone levels and live birth rates under a specific rescue protocol. Results indicate a live birth rate of 19.2% for cycles with pre-transfer progesterone below 5 ng/mL, compared to 43.8% for levels between 5–7.49 ng/mL.
A supplementary document from a single-arm, single-center Phase II prospective clinical trial evaluating a combination therapy for advanced pancreatic cancer. The study enrolled 16 patients and reports outcomes including an objective response rate of 68.75%, median progression-free survival of 6.0 months, and median overall survival of 12.0 months. The document was authored by Lin Lin and uploaded to figshare in 2026.
128 patient records from a pooled individual-patient data systematic review characterize the rare condition of intestinal ulceration with pancytopenia. The dataset, created by Song Su and last updated in May 2026, includes clinical features, mortality outcomes, and prognostic factors from 60 studies. Overall mortality was substantial, ranging from 31.3% to 44.4% across patient subgroups.
128 individual patient records from 60 studies, pooled for a systematic review on intestinal ulceration with pancytopenia. The dataset was created by Song Su and last updated in May 2026. It analyzes clinical features and mortality, which ranged from 31.3% to 44.4%.
128 patient records from a pooled individual-patient data systematic review characterize a rare condition with high mortality. The dataset, created by Song Su and last updated in May 2026, includes clinical features, diagnoses, and mortality outcomes for patients with intestinal ulcers and concurrent hematologic diseases like myelodysplastic syndrome. Overall mortality ranged from 31.3% to 44.4%, with analyses exploring prognostic factors such as sex and MDS evolution.
69 bleeding episodes in 56 severe acute pancreatitis patients were analyzed to compare contrast-enhanced CT and angiographic findings. The dataset, authored by Yinshan Wu and last updated in June 2026, shows only fair agreement (weighted κ=0.29) between the two imaging modalities. It includes outcomes such as embolization success, rebleeding, and surgical rescue.