Skip to main content
Erschienen in: Journal of Medical Systems 8/2020

02.07.2020 | COVID-19 | Image & Signal Processing Zur Zeit gratis

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

verfasst von: Davide Brinati, Andrea Campagner, Davide Ferrari, Massimo Locatelli, Giuseppe Banfi, Federico Cabitza

Erschienen in: Journal of Medical Systems | Ausgabe 8/2020

Einloggen, um Zugang zu erhalten

Abstract

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/​).
Fußnoten
1
A qualitative estimation of the cost of the exams used for this study is 15 euros per test, approximately five times cheaper than rt-PCR testing.
 
2
IRCCS is the Italian acronym for Scientific Institute for Research, Hospitalization and Healthcare
 
3
We recall that balanced accuracy is defined as the average of sensitivity and specificity. If accuracy and balanced accuracy significantly differ, the data could be interpreted as unbalanced with respect to class prevalence.
 
4
We recall here that PPV represents the probability that subjects with a positive screening test truly have the disease.
 
Literatur
1.
Zurück zum Zitat Ai T., Yang Z., Hou H., Zhan C., Chen C., Lv W., Tao Q., Sun Z., Xia L. (2020) Correlation of chest ct and rt-pcr testing in coronavirus disease 2019 (covid-19) in china: a report of 1014 cases. Radiology p 200642 Ai T., Yang Z., Hou H., Zhan C., Chen C., Lv W., Tao Q., Sun Z., Xia L. (2020) Correlation of chest ct and rt-pcr testing in coronavirus disease 2019 (covid-19) in china: a report of 1014 cases. Radiology p 200642
2.
Zurück zum Zitat Altman N.S.: An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician 46 (3): 175–185, 1992 Altman N.S.: An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician 46 (3): 175–185, 1992
4.
Zurück zum Zitat Apostolopoulos I.D., Mpesiana T.A. (2020) Covid-19: automatic detection from x-ray images utilizing transfer learning with convolutional neural networks. Physical and Engineering Sciences in Medicine 1 Apostolopoulos I.D., Mpesiana T.A. (2020) Covid-19: automatic detection from x-ray images utilizing transfer learning with convolutional neural networks. Physical and Engineering Sciences in Medicine 1
6.
Zurück zum Zitat Cabitza F., Zeitoun J.D. (2019) The proof of the pudding: in praise of a culture of real-world validation for medical artificial intelligence. Annals of translational medicine 7(8) Cabitza F., Zeitoun J.D. (2019) The proof of the pudding: in praise of a culture of real-world validation for medical artificial intelligence. Annals of translational medicine 7(8)
7.
Zurück zum Zitat Campagner A., Cabitza F., Ciucci D.: The three-way-in and three-way-out framework to treat and exploit ambiguity in data. International Journal of Approximate Reasoning 119: 292–312, 2020CrossRef Campagner A., Cabitza F., Ciucci D.: The three-way-in and three-way-out framework to treat and exploit ambiguity in data. International Journal of Approximate Reasoning 119: 292–312, 2020CrossRef
8.
Zurück zum Zitat Cascella M., Rajnik M., Cuomo A., Dulebohn S.C., Di Napoli R.: Features, evaluation and treatment coronavirus (covid-19).. In: StatPearls [Internet], StatPearls Publishing, 2020 Cascella M., Rajnik M., Cuomo A., Dulebohn S.C., Di Napoli R.: Features, evaluation and treatment coronavirus (covid-19).. In: StatPearls [Internet], StatPearls Publishing, 2020
9.
Zurück zum Zitat Cawley G.C., Talbot N.L.: On over-fitting in model selection and subsequent selection bias in performance evaluation. Journal of Machine Learning Research 11 (Jul): 2079–2107, 2010 Cawley G.C., Talbot N.L.: On over-fitting in model selection and subsequent selection bias in performance evaluation. Journal of Machine Learning Research 11 (Jul): 2079–2107, 2010
10.
Zurück zum Zitat Chen N., Zhou M., Dong X., Qu J., Gong F., Han Y., Qiu Y., Wang J., Liu Y., Wei Y., et al.: Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in wuhan, china: a descriptive study. The Lancet 395 (10223): 507–513, 2020CrossRef Chen N., Zhou M., Dong X., Qu J., Gong F., Han Y., Qiu Y., Wang J., Liu Y., Wei Y., et al.: Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in wuhan, china: a descriptive study. The Lancet 395 (10223): 507–513, 2020CrossRef
11.
Zurück zum Zitat Corman V.M., Landt O., Kaiser M., Molenkamp R., Meijer A., Chu D.K., Bleicker T., Brünink S, Schneider J., Schmidt M.L., at al.: Detection of 2019 novel coronavirus (2019-ncov) by real-time rt-pcr. Eurosurveillance 25 (3): 2000045, 2020CrossRef Corman V.M., Landt O., Kaiser M., Molenkamp R., Meijer A., Chu D.K., Bleicker T., Brünink S, Schneider J., Schmidt M.L., at al.: Detection of 2019 novel coronavirus (2019-ncov) by real-time rt-pcr. Eurosurveillance 25 (3): 2000045, 2020CrossRef
12.
Zurück zum Zitat Day M.: Covid-19: identifying and isolating asymptomatic people helped eliminate virus in italian village. BMJ 368: m1165, 2020CrossRef Day M.: Covid-19: identifying and isolating asymptomatic people helped eliminate virus in italian village. BMJ 368: m1165, 2020CrossRef
13.
Zurück zum Zitat Ferrari D., Lombardi G., Strollo M., Pontillo M., Motta A., Locatelli M.: Association between solar ultraviolet doses and vitamin d clinical routine data in european mid-latitude population between 2006 and 2018. Photochemical & Photobiological Sciences 18 (11): 2696–2706, 2019CrossRef Ferrari D., Lombardi G., Strollo M., Pontillo M., Motta A., Locatelli M.: Association between solar ultraviolet doses and vitamin d clinical routine data in european mid-latitude population between 2006 and 2018. Photochemical & Photobiological Sciences 18 (11): 2696–2706, 2019CrossRef
15.
Zurück zum Zitat Ferretti L., Wymant C., Kendall M., Zhao L., Nurtay A., Abeler-Dörner L, Parker M., Bonsall D., Fraser C. (2020) Quantifying sars-cov-2 transmission suggests epidemic control with digital contact tracing. Science Ferretti L., Wymant C., Kendall M., Zhao L., Nurtay A., Abeler-Dörner L, Parker M., Bonsall D., Fraser C. (2020) Quantifying sars-cov-2 transmission suggests epidemic control with digital contact tracing. Science
16.
Zurück zum Zitat Ferri C., Hernández-Orallo J: Cautious classifiers. ROCAI 4: 27–36, 2004 Ferri C., Hernández-Orallo J: Cautious classifiers. ROCAI 4: 27–36, 2004
17.
Zurück zum Zitat Geurts P., Ernst D., Wehenkel L.: Extremely randomized trees. Machine learning 63 (1): 3–42, 2006CrossRef Geurts P., Ernst D., Wehenkel L.: Extremely randomized trees. Machine learning 63 (1): 3–42, 2006CrossRef
18.
Zurück zum Zitat Goebel R., Chander A., Holzinger K., Lecue F., Akata Z., Stumpf S., Kieseberg P., Holzinger A.: Explainable ai: the new 42? In: International Cross-Domain Conference for Machine Learning and Knowledge Extraction New York: Springer, 2018, pp 295–303CrossRef Goebel R., Chander A., Holzinger K., Lecue F., Akata Z., Stumpf S., Kieseberg P., Holzinger A.: Explainable ai: the new 42? In: International Cross-Domain Conference for Machine Learning and Knowledge Extraction New York: Springer, 2018, pp 295–303CrossRef
19.
Zurück zum Zitat Gozes O., Frid-Adar M., Sagie N., Zhang H., Ji W., Greenspan H. (2020) Coronavirus detection and analysis on chest ct with deep learning. arXiv:200402640 Gozes O., Frid-Adar M., Sagie N., Zhang H., Ji W., Greenspan H. (2020) Coronavirus detection and analysis on chest ct with deep learning. arXiv:200402640
20.
Zurück zum Zitat Hastie T., Tibshirani R., Friedman J. (2009) The elements of statistical learning: data mining, inference, and prediction. Springer Science & Business Media Hastie T., Tibshirani R., Friedman J. (2009) The elements of statistical learning: data mining, inference, and prediction. Springer Science & Business Media
21.
Zurück zum Zitat Hosmer DW Jr., Lemeshow S., Sturdivant R.X.: Applied logistic regression, vol 398 New York: John Wiley & Sons, 2013CrossRef Hosmer DW Jr., Lemeshow S., Sturdivant R.X.: Applied logistic regression, vol 398 New York: John Wiley & Sons, 2013CrossRef
22.
Zurück zum Zitat Hunter J.D.: Matplotlib: a 2d graphics environment. Computing in science & engineering 9 (3): 90–95, 2007CrossRef Hunter J.D.: Matplotlib: a 2d graphics environment. Computing in science & engineering 9 (3): 90–95, 2007CrossRef
23.
Zurück zum Zitat Kam H.T.: Random decision forest.. In: Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, Canada, August, vol 1416, p 278282, 1995 Kam H.T.: Random decision forest.. In: Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, Canada, August, vol 1416, p 278282, 1995
24.
Zurück zum Zitat Kim S., Kim D.M., Lee B. (2020) Insufficient sensitivity of rna dependent rna polymerase gene of sars-cov-2 viral genome as confirmatory test using korean covid-19 cases Kim S., Kim D.M., Lee B. (2020) Insufficient sensitivity of rna dependent rna polymerase gene of sars-cov-2 viral genome as confirmatory test using korean covid-19 cases
25.
Zurück zum Zitat Lewis D.D.: Naive (bayes) at forty: The independence assumption in information retrieval.. In: European conference on machine learning. Springer, New York, 1998, pp 4–15 Lewis D.D.: Naive (bayes) at forty: The independence assumption in information retrieval.. In: European conference on machine learning. Springer, New York, 1998, pp 4–15
26.
Zurück zum Zitat Li D., Wang D., Dong J., Wang N., Huang H., Xu H., Xia C.: False-negative results of real-time reverse-transcriptase polymerase chain reaction for severe acute respiratory syndrome coronavirus 2: Role of deep-learning-based ct diagnosis and insights from two cases. Korean journal of radiology 21 (4): 505–508, 2020aCrossRef Li D., Wang D., Dong J., Wang N., Huang H., Xu H., Xia C.: False-negative results of real-time reverse-transcriptase polymerase chain reaction for severe acute respiratory syndrome coronavirus 2: Role of deep-learning-based ct diagnosis and insights from two cases. Korean journal of radiology 21 (4): 505–508, 2020aCrossRef
27.
Zurück zum Zitat Li L., Qin L., Xu Z., Yin Y., Wang X., Kong B., Bai J., Lu Y., Fang Z., Song Q., et al. (2020b) Artificial intelligence distinguishes covid-19 from community acquired pneumonia on chest ct. Radiology p 200905 Li L., Qin L., Xu Z., Yin Y., Wang X., Kong B., Bai J., Lu Y., Fang Z., Song Q., et al. (2020b) Artificial intelligence distinguishes covid-19 from community acquired pneumonia on chest ct. Radiology p 200905
28.
Zurück zum Zitat Li Z., Yi Y., Luo X., Xiong N., Liu Y., Li S., Sun R., Wang Y., Hu B., Chen W., et al. (2020c) Development and clinical application of a rapid igm-igg combined antibody test for sars-cov-2 infection diagnosis. Journal of medical virology Li Z., Yi Y., Luo X., Xiong N., Liu Y., Li S., Sun R., Wang Y., Hu B., Chen W., et al. (2020c) Development and clinical application of a rapid igm-igg combined antibody test for sars-cov-2 infection diagnosis. Journal of medical virology
29.
Zurück zum Zitat Lippi G., Plebani M. (2020) Laboratory abnormalities in patients with covid-2019 infection. Clinical Chemistry and Laboratory Medicine (CCLM)1(ahead-of-print) Lippi G., Plebani M. (2020) Laboratory abnormalities in patients with covid-2019 infection. Clinical Chemistry and Laboratory Medicine (CCLM)1(ahead-of-print)
30.
Zurück zum Zitat Lippi G., Simundic A.M., Plebani M. (2020) Potential preanalytical and analytical vulnerabilities in the laboratory diagnosis of coronavirus disease 2019 (covid-19). Clinical Chemistry and Laboratory Medicine (CCLM) 1(ahead-of-print) Lippi G., Simundic A.M., Plebani M. (2020) Potential preanalytical and analytical vulnerabilities in the laboratory diagnosis of coronavirus disease 2019 (covid-19). Clinical Chemistry and Laboratory Medicine (CCLM) 1(ahead-of-print)
31.
Zurück zum Zitat McKinney W., et al. (2011) Pandas: a foundational python library for data analysis and statistics. Python for High Performance and Scientific Computing 14(9) McKinney W., et al. (2011) Pandas: a foundational python library for data analysis and statistics. Python for High Performance and Scientific Computing 14(9)
32.
Zurück zum Zitat Mei X., Lee H.C., Ky D., Huang M., Lin B., Liu C., Xie Z., Ma Y., Robson P.M., Chung M., et al. (2020) Artificial intelligence–enabled rapid diagnosis of patients with covid-19. Nature Medicine pp 1–55 Mei X., Lee H.C., Ky D., Huang M., Lin B., Liu C., Xie Z., Ma Y., Robson P.M., Chung M., et al. (2020) Artificial intelligence–enabled rapid diagnosis of patients with covid-19. Nature Medicine pp 1–55
34.
Zurück zum Zitat Pan F., Ye T., Sun P., Gui S., Liang B., Li L., Zheng D., Wang J., Hesketh R.L., Yang L., et al. (2020) Time course of lung changes on chest ct during recovery from 2019 novel coronavirus (covid-19) pneumonia. Radiology p 200370 Pan F., Ye T., Sun P., Gui S., Liang B., Li L., Zheng D., Wang J., Hesketh R.L., Yang L., et al. (2020) Time course of lung changes on chest ct during recovery from 2019 novel coronavirus (covid-19) pneumonia. Radiology p 200370
35.
Zurück zum Zitat Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., et al.: Scikit-learn:, Machine learning in python. The Journal of machine Learning research 12: 2825–2830, 2011 Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., et al.: Scikit-learn:, Machine learning in python. The Journal of machine Learning research 12: 2825–2830, 2011
36.
Zurück zum Zitat Qi Y.: Random forest for bioinformatics.. In: Ensemble machine learning. Springer, New York, 2012, pp 307–323 Qi Y.: Random forest for bioinformatics.. In: Ensemble machine learning. Springer, New York, 2012, pp 307–323
37.
Zurück zum Zitat Qin C., Zhou L., Hu Z., Zhang S., Yang S., Tao Y., Xie C., Ma K., Shang K., Wang W., et al. (2020) Dysregulation of immune response in patients with covid-19 in wuhan, china. China (February 17, 2020) Qin C., Zhou L., Hu Z., Zhang S., Yang S., Tao Y., Xie C., Ma K., Shang K., Wang W., et al. (2020) Dysregulation of immune response in patients with covid-19 in wuhan, china. China (February 17, 2020)
38.
Zurück zum Zitat Rubin D.B.: Multiple imputation for nonresponse in surveys, vol 81 New York: John Wiley & Sons, 2004 Rubin D.B.: Multiple imputation for nonresponse in surveys, vol 81 New York: John Wiley & Sons, 2004
39.
Zurück zum Zitat Rubino S., Kelvin N., Bermejo-Martin J.F., Kelvin D.: As covid-19 cases, deaths and fatality rates surge in italy, underlying causes require investigation. The Journal of Infection in Developing Countries 14 (03): 265–267, 2020CrossRef Rubino S., Kelvin N., Bermejo-Martin J.F., Kelvin D.: As covid-19 cases, deaths and fatality rates surge in italy, underlying causes require investigation. The Journal of Infection in Developing Countries 14 (03): 265–267, 2020CrossRef
40.
Zurück zum Zitat Safavian S.R., Landgrebe D.: A survey of decision tree classifier methodology. IEEE transactions on systems, man, and cybernetics 21 (3): 660–674, 1991CrossRef Safavian S.R., Landgrebe D.: A survey of decision tree classifier methodology. IEEE transactions on systems, man, and cybernetics 21 (3): 660–674, 1991CrossRef
41.
Zurück zum Zitat Schölkopf B, Smola A.J., Bach F., et al., 2002 Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT press Schölkopf B, Smola A.J., Bach F., et al., 2002 Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT press
42.
Zurück zum Zitat Skurichina M., Duin R.P.W.: Stabilizing classifiers for very small sample sizes.. In: Proceedings of ICPR-1996, vol 2, 1996, pp 891–896 Skurichina M., Duin R.P.W.: Stabilizing classifiers for very small sample sizes.. In: Proceedings of ICPR-1996, vol 2, 1996, pp 891–896
43.
Zurück zum Zitat Varma S., Simon R.: Bias in error estimation when using cross-validation for model selection. BMC bioinformatics 7 (1): 91, 2006CrossRef Varma S., Simon R.: Bias in error estimation when using cross-validation for model selection. BMC bioinformatics 7 (1): 91, 2006CrossRef
44.
Zurück zum Zitat Wang D., Hu B., Hu C., Zhu F., Liu X., Zhang J., Wang B., Xiang H., Cheng Z., Xiong Y., et al: Clinical characteristics of 138 hospitalized patients with 2019 novel coronavirus–infected pneumonia in wuhan, china. Jama 323 (11): 1061–1069, 2020CrossRef Wang D., Hu B., Hu C., Zhu F., Liu X., Zhang J., Wang B., Xiang H., Cheng Z., Xiong Y., et al: Clinical characteristics of 138 hospitalized patients with 2019 novel coronavirus–infected pneumonia in wuhan, china. Jama 323 (11): 1061–1069, 2020CrossRef
45.
Zurück zum Zitat Mea W. (2020) Chest x-ray findings in 636 ambulatory patients with covid-19 presenting to an urgent care center: a normal chest x-ray is no guarantee. The Journal of Urgent Care Medicin (2):1–9 Mea W. (2020) Chest x-ray findings in 636 ambulatory patients with covid-19 presenting to an urgent care center: a normal chest x-ray is no guarantee. The Journal of Urgent Care Medicin (2):1–9
46.
Zurück zum Zitat Wynants L., Van Calster B., Bonten M.M., Collins G.S., Debray T.P., De Vos M., Haller M.C., Heinze G., Moons K.G., Riley R.D., et al. (2020) Prediction models for diagnosis and prognosis of covid-19 infection: systematic review and critical appraisal. bmj 369 Wynants L., Van Calster B., Bonten M.M., Collins G.S., Debray T.P., De Vos M., Haller M.C., Heinze G., Moons K.G., Riley R.D., et al. (2020) Prediction models for diagnosis and prognosis of covid-19 infection: systematic review and critical appraisal. bmj 369
47.
Zurück zum Zitat Xie X., Zhong Z., Zhao W., Zheng C., Wang F., Liu J. (2020) Chest ct for typical 2019-ncov pneumonia: relationship to negative rt-pcr testing. Radiology p 200343 Xie X., Zhong Z., Zhao W., Zheng C., Wang F., Liu J. (2020) Chest ct for typical 2019-ncov pneumonia: relationship to negative rt-pcr testing. Radiology p 200343
48.
Zurück zum Zitat Zhang C., Shi L., Wang F.S. (2020) Liver injury in covid-19: management and challenges. The Lancet Gastroenterology & Hepatology Zhang C., Shi L., Wang F.S. (2020) Liver injury in covid-19: management and challenges. The Lancet Gastroenterology & Hepatology
50.
Zurück zum Zitat Zheng M., Gao Y., Wang G., Song G., Liu S., Sun D., Xu Y., Tian Z. (2020) Functional exhaustion of antiviral lymphocytes in covid-19 patients. Cellular & Molecular Immunology 1–3 Zheng M., Gao Y., Wang G., Song G., Liu S., Sun D., Xu Y., Tian Z. (2020) Functional exhaustion of antiviral lymphocytes in covid-19 patients. Cellular & Molecular Immunology 1–3
Metadaten
Titel
Detection of COVID-19 Infection from Routine Blood Exams with Machine Learning: A Feasibility Study
verfasst von
Davide Brinati
Andrea Campagner
Davide Ferrari
Massimo Locatelli
Giuseppe Banfi
Federico Cabitza
Publikationsdatum
02.07.2020
Verlag
Springer US
Erschienen in
Journal of Medical Systems / Ausgabe 8/2020
Print ISSN: 0148-5598
Elektronische ISSN: 1573-689X
DOI
https://doi.org/10.1007/s10916-020-01597-4

Weitere Artikel der Ausgabe 8/2020

Journal of Medical Systems 8/2020 Zur Ausgabe