Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
12,224 datasets
A meta-learning framework for predicting drug combination responses, developed by Congcong Guo and last updated in June 2026. It uses drug structures and gene expression profiles from cell lines and patient ex vivo samples to train a model that adapts to data-scarce patient scenarios. The method reportedly improved prediction AUROC by 8.5% for data-poor cell lines and 7.4% for patient ex vivo samples compared to conventional transfer learning.
66 healthcare professionals participated in a series of communication workshops from May to July 2025. The dataset contains pre- and post-workshop questionnaires measuring self-confidence, anxiety, burnout, and professional fulfillment. Data includes study-specific and validated instruments like the GHQ-12 and Stanford Professional Fulfillment Index.
Skin thickness measurements from 42 bedridden patients with pressure injuries, comparing injury sites to adjacent normal sites using high-frequency ultrasound (18 MHz). The data was collected by Lin Tang in a prospective comparative study and published on figshare under a CC-BY-4.0 license. The dataset includes results from a mixed-design ANOVA analyzing the effects of tissue type, pressure injury risk status, and body mass index.
A 104-week observational extension of a randomized clinical trial involving 61 youth with recent type 1 diabetes diagnosis. The dataset includes secondary analysis of continuous glucose monitoring (CGM) data, comparing time in range (TIR) and hemoglobin A1c between intensive care and standard care groups. The supplementary material was authored by figshare admin karger and last updated in June 2026.
90 participants with symptomatic knee osteoarthritis from Tehran, Iran, were recruited for a randomized controlled trial. The study protocol, authored by Maryam Bagheri Mahmoudi, investigates the effect of pre-exercise expectation framing on pain and functional outcomes. The document was last updated on 2026-05-26.
213 participants from the Program to Improve Mobility in Aging (PRIMA) cohort trial were analyzed to evaluate walking cadence as a digital outcome measure. Change in median walking cadence predicted improvement in usual-pace gait speed with an AUC of 0.90 and identified a threshold of ≥3 steps/min. The data supports research into scalable, digitally measurable alternatives to in-person mobility assessments.
32 ICU staff members from a private general hospital in Hanoi, Vietnam, completed a 46-question survey on Candida auris. The dataset, created by Lê Phan Khánh Huy and last updated in May 2026, includes quantitative survey data and qualitative interview insights. It covers demographic, knowledge, attitude, and practice domains using Likert-type and ranking scales.
A retrospective study of 839 hospitalized pneumonia patients admitted between January 2020 and December 2023. The dataset was used to develop and validate a nomogram integrating inflammatory-nutritional-metabolic composite indices for predicting short-term adverse outcomes. The model was created by Jing Zhao and published on figshare.
A retrospective cohort study by Benfan Yin analyzed 218 consecutive patients who underwent modified TROPIS surgery combined with Parks’ fistulotomy with seton for high anal fistula between May 2022 and May 2024. The dataset likely contains patient-level data used to identify risk factors for a composite postoperative adverse outcome, which occurred in 22.5% of cases. The study identified five independent risk factors, including diabetes mellitus and horseshoe extension, using Firth’s penalized logistic regression.
1,086 breast cancer patient samples from Seoul National University Hospital cohorts were analyzed for ALDH1L1 expression via immunostaining. The dataset includes clinical data on tumor size, grade, lymphatic invasion, and lymph node metastasis, and links expression levels to survival outcomes. It was authored by Han Suk Ryu and last updated on 2026-05-25.
South Korean clinical data from Seoul National University Hospital analyzed ALDH1L1 expression across 1,086 breast cancer cases. The research combined three cohorts, including a tissue microarray of 1,001 invasive ductal carcinoma patients, to assess correlations with tumor aggressiveness and survival. Han Suk Ryu published the findings on figshare in 2026 under a CC-BY-4.0 license.
A 2026 study analyzes ALDH1L1 expression in breast cancer using data from Seoul National University Hospital and the METABRIC database. The dataset includes clinical and survival outcomes for over 1,000 invasive ductal carcinoma patients. It was authored by Han Suk Ryu and published on figshare under a CC-BY-4.0 license.
A clinical research dataset from Seoul National University Hospital analyzes ALDH1L1 expression across 1,086 breast cancer cases. The study correlates protein expression levels with tumor characteristics and patient survival outcomes, particularly in hormone receptor-positive subtypes. Author Han Suk Ryu published the findings on figshare under a CC-BY-4.0 license.
130 patients with suspected pulmonary tuberculosis were enrolled to evaluate a novel non-sputum diagnostic method. The ExoNA-based saliva assay reduced turnaround time from 16 hours to 3 hours and achieved a limit of detection of 10 CFU/mL. This dataset, authored by Jun Ma and last updated in June 2026, contains the results of this molecular diagnosis study.
A 2026 clinical study by Jun Ma evaluating a non-sputum tuberculosis diagnostic method. The dataset includes results from 130 patients with suspected pulmonary tuberculosis, assessing the sensitivity and specificity of a dual-gene qPCR assay on salivary exosomal DNA. It is hosted on figshare under a CC-BY-4.0 license.
270 patient records from a retrospective cohort study at the First Hospital of Shanxi Medical University between January 2018 and December 2024. The dataset was used to develop and validate a multidimensional nomogram predicting postoperative sepsis, ICU admission, and complications in small bowel obstruction patients. It was authored by Yanan Shi and last updated on June 1, 2026.
A pilot study from October 2020 to December 2023 developed an AI model using clinical data from 67 pancreatic cancer patients discussed in multidisciplinary tumor boards. The model's recommendations were compared against expert decisions for 15 independent patients from 2024, showing an 80% concordance rate. Author Samet Yigman published the findings under a CC-BY-4.0 license.
A 5-year prospective observational cohort study of 1,732 people with chronic kidney disease (CKD) category G3, investigating associations between body composition biomarkers and clinical outcomes. The dataset, published on figshare under CC-BY-4.0, includes data on mortality, cardiovascular events, and CKD progression linked to Creatinine Muscle Index and waist-hip ratio. The supplementary material was last updated in June 2026.
Northwest China dentists were surveyed on antibiotic use during dental implant surgery from April to December 2021. The dataset contains responses from 318 dentists regarding their awareness, prescription habits, and concerns about antibiotic prophylaxis. It was created by Yao Lin and published on figshare under a CC-BY-4.0 license.
35 pregnant women at high-risk for preeclampsia from a hospital in Istanbul, Türkiye, were stratified by BMI to assess aspirin dosing. The dataset includes blood salicylate levels, 11-dehydrothromboxane B2 levels, and uterine artery Doppler measurements taken at two time points during pregnancy. It was authored by Fulya Sultan Karaduman and shared on figshare under a CC-BY-4.0 license.