Italian 
English Identificazione di positività al SARS-CoV-2 attraverso metodi di Machine Learning sui dati dell’esame emocromocitometrico: validazione esterna di modelli allo stato dell’arte
Identification of SARS-CoV-2 positivity using machine learning methods on blood count data: external validation of state-of-the-art models.
AUTORI
1IRCCS Istituto Scientifico Ospedale San Raffaele, Milano
2DISCo, Università degli Studi di Milano-Bicocca, Milano
3Laboratorio di chimica clinica, Ospedale di Desio e Monza, ASST-Monza, Dipartimento di medicina e chirurgia, Università di Milano-Bicocca, Monza
4Laboratorio di chimica clinica, Ospedale Papa Giovanni XXIII, Bergamo
5Centro regionale di riferimento per la qualità, ASST Grande Ospedale Metropolitano Niguarda, Milano
Questo lavoro è stato in parte presentato al 52° Congresso Nazionale SIBioC, 6-8 Ottobre 2020, Virtual Edition, quale Comunicazione Orale
ABSTRACT
Identification of SARS-CoV-2 positivity using machine learning methods on blood count data: external validation of state-of-the-art models.
Introduction: The aim of the paper is to present the results from the process of external validation of a number of machine learning (ML) models that had been previously developed to detect SARS-CoV-2 virus positivity on both symptomatic and asymptomatic patients on the basis of the complete blood count (CBC) test.
Methods: Briefly, models were trained using a dataset of 816 COVID-19 positive and 920 negative cases collected at the emergency departments of IRCCS Hospital San Raffaele and IRCCS Istituto Ortopedico Galeazzi. 21 parameters, including the results of the CBC analysis, age [60.9 (0.9) years], gender (57% males) and the presence of COVID-19 related symptoms were used. The validation regarded the evaluation of the error rate (through different metrics, including accuracy, sensitivity, specificity and the area under the curve (AUC)) of the models considered. This external validation was conducted on two well balanced datasets coming from two different hospitals in Northern Italy: Desio hospital and Bergamo Papa Giovanni XXIII hospital. 163 positive and 174 true negative patients from Desio, and 104 positive and 145 true negative from Bergamo were included in the validation.
Results: The performance of the predictive models is satisfactory as we can report an average AUC of 95% for both external datasets.
Conclusion: ML models have been applied to hematological parameters for a more rapid and cost-effective detection of the COVID-19 disease. We make the point that validated models may be useful in the management and early detection of potential COVID-19 patients.