TY - JOUR
T1 - Detection of COVID-19 Infection from Routine Blood Exams with Machine Learning: A Feasibility Study
T2 - Journal of Medical Systems
AU - Brinati, D.
AU - Campagner, A.
AU - Ferrari, D.
AU - Locatelli, M.
AU - Banfi, G.
AU - Cabitza, F.
N1 - Cited By :17
Export Date: 11 March 2021
CODEN: JMSYD
Correspondence Address: Cabitza, F.; DISCo, Viale Sarca 336, Italy; email: federico.cabitza@unimib.it
Chemicals/CAS: alanine aminotransferase, 9000-86-6, 9014-30-6; aspartate aminotransferase, 9000-97-9; C reactive protein, 9007-41-4; gamma glutamyltransferase, 85876-02-4; lactate dehydrogenase, 9001-60-9; lactate dehydrogenase A
Funding details: National Natural Science Foundation of China, NSFC, 61727809
Funding text 1: This research was sponsered by the Research on the Major Scientific Instrument of National Natural Science Foundation of China (61727809).
PY - 2020
Y1 - 2020
N2 - 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. 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. 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. 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/). © 2020, Springer Science+Business Media, LLC, part of Springer Nature.
AB - 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. 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. 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. 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/). © 2020, Springer Science+Business Media, LLC, part of Springer Nature.
KW - Blood tests
KW - COVID-19
KW - Machine learning
KW - Random forest
KW - RT-PCR test
KW - Three-way
KW - alanine aminotransferase
KW - aspartate aminotransferase
KW - C reactive protein
KW - gamma glutamyltransferase
KW - lactate dehydrogenase
KW - adult
KW - Article
KW - blood examination
KW - coronavirus disease 2019
KW - feasibility study
KW - female
KW - human
KW - human cell
KW - leukocyte count
KW - machine learning
KW - major clinical study
KW - male
KW - respiratory system
KW - reverse transcription polymerase chain reaction
KW - thrombocyte
KW - turnaround time
KW - Betacoronavirus
KW - Coronavirus infection
KW - pandemic
KW - procedures
KW - real time polymerase chain reaction
KW - virus pneumonia
KW - Coronavirus Infections
KW - Hematologic Tests
KW - Humans
KW - Machine Learning
KW - Pandemics
KW - Pneumonia, Viral
KW - Real-Time Polymerase Chain Reaction
U2 - 10.1007/s10916-020-01597-4
DO - 10.1007/s10916-020-01597-4
M3 - Article
VL - 44
JO - J. Med. Syst.
JF - J. Med. Syst.
SN - 0148-5598
IS - 8
ER -