COVID-19 datasets
COVID-19 datasets are public databases for sharing case data and medical information related to the COVID-19 pandemic.
Testing and case tracking stats
Databases of testing and case tracking for COVID-19 include:
- Johns Hopkins Coronavirus Resource Center: Global aggregated data including cases, testing, contact tracing, and vaccine development[1]
- World Health Organization (WHO) Coronavirus Disease Dashboard: a database of confirmed cases and deaths reported globally and broken down by region.[2] This database is part of the WHO Health Data Platform.[3]
- COVID Tracking Project: a volunteer-run database of testing and medical stats in the United States[4]
- COVID-19 Africa Open Data Project: a volunteer-run database and dashboard reporting region, country and district level case counts, deaths, healthcare worker infections, healthcare services and urgent needs.[5]
Hospitalizations (United States)
Datasets of hospital utilization for the United States:
- COVID-19 Reported Patient Impact and Hospital Capacity by Facility
- COVID-19 Estimated Patient Impact and Hospital Capacity by State
- COVID-19 Reported Patient Impact and Hospital Capacity by State
- COVID-19 Reported Patient Impact and Hospital Capacity by State Timeseries
Open Access Research
- COVID-19 Open Research Dataset (CORD-19): The Semantic Scholar project of the Allen Institute for AI hosts CORD-19, a public dataset of academic articles about COVID-19 and related research.[6] The dataset is updated daily and includes both peer-reviewed articles and preprints.[7] CORD-19 was originally released on March 16, 2020 by researchers and leaders from the Allen Institute for AI, Chan Zuckerburg Initiative, Georgetown University's Center for Security and Emerging Technhology, Microsoft, and the National Library of Medicine.[8] The dataset is created through the use of text mining of the current research literature.[9]
- NIH Open Access Datasets: The National Institutes of Health provide open-access data an computational resources related to COVID-19.[10]
Imaging
Radiology
Characteristic imaging features on chest radiographs and computed tomography (CT) of people who are symptomatic include asymmetric peripheral ground-glass opacities without pleural effusions.[11] The University of Montreal and Mila created the "COVID-19 Image Data Collection" in March which is a public data repository of chest imaging.[12][13][14] The Medical Imaging Databank in Valencian Region released a large dataset of chest imaging from Spain.[15][16] The Italian Radiological Society is compiling an international online database of imaging findings for confirmed cases.[17] Online radiology case sharing platforms such as Eurorad and Radiopaedia serve as platforms for sharing COVID-19 case data and imaging.[18][19]
Genetics
Open access Gene sequencing data for SARS-CoV-2 is provided by GISAID[20] and included in an interactive Phylogenetic tree dashboard [21] on Nextstrain, an open-source pathogen genome data project.[22]
References
- ^ "Home". Johns Hopkins Coronavirus Resource Center. Retrieved 2020-09-18.
- ^ "WHO Coronavirus Disease (COVID-19) Dashboard". covid19.who.int. Retrieved 2020-09-18.
- ^ "World Health Data Platform - WHO". www.who.int. Retrieved 2020-09-18.
- ^ Stephens, Autumn. "Tracking Star in Oakland". Diablo Magazine. Retrieved 2020-09-18.
- ^ "COVID-19 Africa Open Data". Retrieved 16 November 2020.
- ^ "CORD-19 | Semantic Scholar". www.semanticscholar.org. Retrieved 2020-10-13.
- ^ "Analysis of COVID-19 publications identifies research gaps". EurekAlert!. Retrieved 2020-10-13.
- ^ "Call to Action to the Tech Community on New Machine Readable COVID-19 Dataset". The White House. Retrieved 2020-10-13.
- ^ "NLM Leverages Data, Text Mining to Sharpen COVID-19 Research Databases". governmentciomedia.com. Retrieved 2020-10-13.
- ^ "Open-Access Data and Computational Resources to Address COVID-19 | Data Science at NIH". datascience.nih.gov. Retrieved 2020-10-13.
- ^ Li Y, Xia L (March 2020). "Coronavirus Disease 2019 (COVID-19): Role of Chest CT in Diagnosis and Management". American Journal of Roentgenology. 214 (6): 1280–1286. doi:10.2214/AJR.20.22954. PMID 32130038. S2CID 212416282.
- ^ "COVID-19 related projects". Mila. COVID-19 image data collection. Retrieved 12 July 2020.
- ^ "COVID-19 image data collection". GitHub. Retrieved 12 July 2020.
- ^ Cohen, Joseph (25 March 2020). "COVID-19 image data collection". arXiv:2003.11597 [eess.IV].
- ^ "BIMCV-COVID19, Datasets related to COVID19's pathology course". Medical Imaging Databank in Valencian Region Medical. Retrieved 12 July 2020.
- ^ de la Iglesia Vayá, Maria (1 June 2020). "BIMCV COVID-19+: a large annotated dataset of RX and CT images from COVID-19 patients". arXiv:2006.01174 [eess.IV].
- ^ "COVID-19 Database". Società Italiana di Radiologia Medica e Interventistica (in Italian). Retrieved 2020-03-11.
- ^ "Pneumothorax and pneumomediastinum: a rare complication in the evolution of COVID-19 pneumonia". Eurorad. Retrieved 12 July 2020.
- ^ Bell, Daniel; Knipe, Henry. "COVID-19 (summary)". Radiopaedia. Retrieved 12 July 2020.
- ^ "GISAID".
- ^ "Nexstrain SARS-CoV-2 Dashboard".
- ^ "Nextstrain".