Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
12,594 datasets
178 pertussis cough recordings from three Kaggle datasets were used to evaluate an interpretable deep learning framework. The proposed method achieved AUC scores up to 0.996 and demonstrated noise robustness with performance degradation below 3%. This 5.5 KB XLS file, authored by Siheng Zhang and last updated in May 2026, contains the experimental configuration details under a CC-BY-4.0 license.
88 patients with type 2 diabetes and 93 healthy controls provided 30-minute Lead II ECG recordings for this study. Xuwei Liao developed a novel automated algorithm to detect Q and T points across five T-wave morphological types, validated by two electrophysiologists. The resulting data, last updated in April 2026, introduces a new RQT_diff parameter that improved HRV analysis AUCs by up to 27%.
583 colonies of Acropora hyacinthus were measured for acute heat stress responses across the Great Barrier Reef. The dataset includes physiological response variables, host genomic cluster assignments, Symbiodiniaceae ITS2 variants, and environmental predictors. It was collected under the Reef Restoration and Adaptation Program's Genetic Basis of Coral Traits project.
More than 16,000 rotavirus isolates from children under five hospitalized with acute watery diarrhea are included in this dataset. The data originates from 40 countries participating in the Global Rotavirus Surveillance Network. Country results are weighted by their estimated rotavirus disease burden to estimate regional genotype distributions.
A matrix representation of primary headache diagnoses from the International Classification of Headache Disorders (ICHD3). The dataset encodes headache phenotypes and characteristics as a binary matrix, enabling automated diagnosis and analysis. It was created by Pengfei Zhang and last updated on 2026-05-11.
A matrix representation of primary headache diagnoses from the International Classification of Headache Disorders (ICHD-3) encodes phenotypes and characteristics as true/false statements. The analysis yields 63 basis vectors spanning the headache phenotype space and identifies 64 clusters via Markov clustering, demonstrating the mathematical structure of the classification. Author Pengfei Zhang published this 19.2 KB PDF document under a CC-BY-4.0 license on figshare.
63 basis vectors span the space of all primary headache phenotypes in the ICHD3 classification, enabling automated diagnosis. The dataset encodes headache diagnoses as a matrix where rows are phenotypes and columns are characteristics, derived from the International Classification of Headache Disorders. Pengfei Zhang published this analysis on figshare in 2026.
A 12.7 KB matrix representation of primary headache syndromes from the International Classification of Headache Disorders (ICHD3). Pengfei Zhang published this dataset on figshare in 2026, demonstrating that all headache diagnoses can be represented in a 63-dimensional vector space. The matrix encodes phenotypes and characteristics to enable automated diagnosis and analysis.
A matrix representation of primary headache diagnoses from the International Classification of Headache Disorders (ICHD3) encodes phenotypes and characteristics as true/false statements. The 198.3 KB PDF by Pengfei Zhang, last updated in May 2026, demonstrates that all headache diagnoses can be represented as linear combinations of 63 basis characteristics. This mathematical embodiment allows for automated diagnosis and systematic analysis of relationships between headache phenotypes.
A matrix representation of primary headache syndromes from the International Classification of Headache Disorders (ICHD3) enables automated diagnosis. The dataset encodes headache phenotypes and characteristics as a biadjacency matrix, with results showing diagnoses can be represented in a 63-dimensional vector space. It was created by Pengfei Zhang and last updated on 2026-05-11.
Wei Wei's retrospective study includes data from 1,128 patients admitted for acute pancreatitis between November 2019 and December 2025. The dataset was used to develop and validate a nomogram model for predicting severe acute pancreatitis (SAP), achieving an AUC of 0.88. The model incorporates clinical characteristics, laboratory results, and non-contrast CT signs.
A retrospective study of 533 patients with acute appendicitis admitted between January 2018 and December 2024. The dataset was used to develop and validate a diagnostic nomogram based on peripheral blood composite inflammatory markers to distinguish complicated from simple appendicitis. The model was created by author Menghao Li and published on figshare under a CC-BY-4.0 license.
A dataset of 1,336 preterm infants with gestational age under 32 weeks, collected prospectively from 28 hospitals in Shenzhen, China, between January 2022 and December 2023. The data was used to develop and validate a nomogram model for predicting the risk of bronchopulmonary dysplasia based on six perinatal and postnatal factors available within the first week of life. The model achieved area under the curve (AUC) scores between 0.783 and 0.812 across training and validation cohorts.
A dataset of 1,336 preterm infants with gestational age under 32 weeks, collected prospectively from 28 hospitals in Shenzhen from January 2022 to December 2023. The data was used to develop and validate a nomogram model for predicting bronchopulmonary dysplasia risk based on six perinatal and postnatal factors available within the first week of life. The model was created by Yanping Guo and shows an area under the curve of 0.810 in external validation.
Shenzhen, China, provided data for 1,336 preterm infants with gestational age under 32 weeks, collected prospectively from 28 hospitals between January 2022 and December 2023. Author Yanping Guo developed and validated a nomogram model for predicting bronchopulmonary dysplasia risk based on six perinatal factors available within the first week of life. The model achieved area under the curve values between 0.783 and 0.812 across training and validation cohorts.
12 randomized controlled trials involving 802 colorectal cancer patients were analyzed. The meta-analysis, authored by Jing Yang and uploaded to figshare in May 2026, synthesized evidence on the effects of home-based exercise on anxiety, depression, fatigue, and quality of life.
A document summarizes anatomical details and surgical techniques for robot-assisted laparoscopic prostatectomy (RALP). It includes a systematic literature review of 604 articles, with 27 focused on individual operation techniques. The work was authored by J. Rassweiler and last updated in May 2026.
390 patient records from Ningbo No.2 Hospital were used to develop a multidimensional prediction model for futile reperfusion after endovascular thrombectomy. The model integrates nine clinical, imaging, and laboratory variables and demonstrated a pooled test AUC of 0.795. This dataset, authored by Sisi Jiang and last updated in April 2026, contains the supplementary file for the study.
35 patients with atypical psychiatric presentations had serum and cerebrospinal fluid markers measured and compared against cohorts of non-inflammatory neurological disease controls (n=18), CNS viral infection patients (n=22), and autoimmune encephalitis patients (n=40). The dataset, authored by Jocelyn X. Jiang and last updated in May 2026, contains results suggesting a subset of patients may have an immune contribution to their condition.
Supplementary file 3 from a 2026 multilevel meta-analysis by Burcu Yuksel, synthesizing preclinical evidence on ferroptosis inhibition for renoprotection. The dataset likely contains extracted data from 58 preclinical studies, including 265 effect sizes on renal function and ferroptotic biomarkers. It was published on figshare under a CC-BY-4.0 license.