Compared to most of the existing
databases on COVID-19, focused on demographic data, this clinical dataset collects the different interactions in the
COVID-19 treatment process, including detailed information on diagnoses, treatments, admissions, ICU admissions, diagnostic imaging tests, laboratory results, discharge or death, among many other records.
With the opening of this dataset, we intend to take the first step and serve as an example for other institutions to be encouraged to share their information and thus, together, be able to offer the medical and scientific community clinical data with which to obtain predictive models of evolution, epidemiological models, information on the response to the various treatments applied,
knowledge of virus for the creation of a vaccine, and sociodemographic data on the impact on the population of the virus.
Dataset “Covid Data Save lives”
The information in this data set comes from the HM Hospitales EHR system. It contains the anonymized records of 2,310 patients, admitted with a diagnosis of COVID POSITIVE or COVID PENDING, since the beginning of the epidemic to date. The information is organized in tables according to their content, all of them linked by a unique admission identifier. This identifier is the de-anonymization key, explicitly created for this purpose, and has nothing to do with the actual identifier of each admission.
- The main table includes data on the admission and the patient (age and sex), data on the previous emergency if there has been one (2,226 records), data on their stay in the ICU if there has been one and records of the first and last set of emergency constants.
- The medication table shows all the medication administered to each patient during admission (more than 60,000 records), with the dates corresponding to the first and last administration of each drug, identified by their brand name and classification in the ATC5/ATC7.
- In the table of vital signs, there are all the basic records of constants (54,000 records so far) collected during admission with their date and time of registration.
- The laboratory table contains the results of the determinations (398,884 records) of all the requests made to each patient during admission and in the previous emergency, if any.
- And finally, the ICD10 coding tables show the records of diagnostic and procedural information coded according to the international ICD10 classification in its latest distributed version (does not include COVID), for the patients referred, both for episodes of hospital admission (more than 1,600) and for the emergency (more than 1,900) prior to those episodes, if any.
How to access
HM Hospitales makes this
clinical dataset available to researchers from academic, university and healthcare institutions who request it, and whose project is approved. The content is expected to be expanded and updated periodically and its update will not be completed until this pandemic is terminated.
To obtain the data it will be necessary to send the following request to the email
coviddatasavelives@hmhospitales.com or
data_science@hmhospitales.com in order to be evaluated by the Data Science Commission and, where appropriate, by the Research Ethics Committee of HM Hospitales or any other accredited research ethics committee.
Request Form COVIDDATASAVELIVES
Aplication_for_acces_to_Dataset_V3 - English.docx
National and International Institutions
Since the announcement on April 15th of the availability of this clinical dataset to the international medical and scientific community, 68 Institutions from 15 different countries have been interested in it. Research groups, universities and health corporations that from India, the United States or Russia have presented projects in massive data analysis and that are being analyzed by the different Committees for the immediate delivery of the dataset.
HM Hospitales wants to thank the interest of the
National and International Scientific Community for this initiative and especially the emails of gratitude received by the work team. In our vocation to serve society, there is no other way to deal with this devastating pandemic.