Dataset Open Access

Detection of COVID-19 Infection from Routine Blood Exams with Machine Learning: a Feasibility Study

Brinati, Davide; Campagner, Andrea; Ferrari, Davide; Locatelli, Massimo; Banfi, Giuseppe; Cabitza, Federico

This upload consists of the dataset employed in the publication "Detection of COVID-19 Infection from Routine Blood Exams with Machine Learning: a Feasibility Study". The paper was accepted for publication at Journal of Medical Systems (Springer), and a pre-print version is also available on MedRXiv and has been attached to the upload for further reference. If you decide to use or reference this dataset (or the related work) please cite the journal version (details will be added as soon as available).

The dataset consists of 280 records of patients admitted to the San Raffaele Hospital (Milan, Italy), annotated with a collection of  hematochemical values from routine blood exams (namely: white blood cells counts, and the platelets, CRP, AST, ALT, GGT, ALP, LDH plasma levels), and a target variable that describes COVID-19 positivity/negativity (in the target column, class 2 and class 1 can both be treated as COVID-19 positive patients)

 

The abstract of the supporting publication follows:

 

Background - The COVID-19 pandemia due to the SARS-CoV-2 coronavirus, in its first 4 months since its outbreak, has to date reached more than 200 countries worldwide with more than 2 million confirmed cases (probably a much higher number of infected), and almost 200,000 deaths. Amplification of viral RNA by (real time) reverse transcription polymerase chain reaction (rRT-PCR) is the current gold standard test for confirmation of infection, although it presents known shortcomings: long turnaround times (3-4 hours to generate results), potential shortage of reagents, false-negative rates as large as 15-20%, the need for certified laboratories, expensive equipment and trained personnel. Thus there is a need for alternative, faster, less expensive and more accessible tests.

Material and methods - We developed two machine learning classification models using hematochemical values from routine blood exams (namely: white blood cells counts, and the platelets, CRP, AST, ALT, GGT, ALP, LDH plasma levels) drawn from 279 patients who, after being admitted to the San Raffaele Hospital (Milan, Italy) emergency-room with COVID-19 symptoms, were screened with the rRT-PCR test performed on respiratory tract specimens. Of these patients, 177 resulted positive, whereas 102 received a negative response.

Results - We have developed two machine learning models, to discriminate between patients who are either positive or negative to the SARS-CoV-2: their accuracy ranges between 82% and 86%, and sensitivity between 92% e 95%, so comparably well with respect to the gold standard. We also developed an interpretable Decision Tree model as a simple decision aid for clinician interpreting blood tests (even off-line) for COVID-19 suspect cases.

Discussion - This study demonstrated the feasibility and clinical soundness of using blood tests analysis and machine learning as an alternative to rRT-PCR for identifying COVID-19 positive patients. This is especially useful in those countries, like developing ones, suffering from shortages of rRT-PCR reagents and specialized laboratories. We made available a Web-based tool for clinical reference and evaluation. This tool is available at https://covid19-blood-ml.herokuapp.com.

Files (5.4 MB)
Name Size
2020.04.22.20075143v1.full.pdf
md5:26296d94d35ae37dcaeb80d30502e62b
5.4 MB Download
covid_study.xlsx
md5:1f97fec0fc90dbf4d85fceb22368c16e
30.9 kB Download
covid_study_v2.xlsx
md5:9fe7bcbc5cb41bca47f4cf3b260e902b
31.0 kB Download
1,647
2,206
views
downloads
Views 1,647
Downloads 2,206
Data volume 6.7 GB
Unique views 1,454
Unique downloads 1,293

Share

Cite as