Use of Machine Learning and Artificial Intelligence to predict SARS-CoV-2 infection from Full Blood Counts in a population

Abstract

Since December 2019 the novel coronavirus SARS-CoV-2 has been identified as the cause of the pandemic COVID-19. Early symptoms overlap with other common conditions such as common cold and Influenza, making early screening and diagnosis are crucial goals for health practitioners. The aim of the study was to use machine learning (ML), an artificial neural network (ANN) and a simple statistical test to identify SARS-CoV-2 positive patients from full blood counts without knowledge of symptoms or history of the individuals. The dataset included in the analysis and training contains anonymized full blood counts results from patients seen at the Hospital Israelita Albert Einstein, at São Paulo, Brazil, and who had samples collected to perform the SARS-CoV-2 rt-PCR test during a visit to the hospital. Patient data was anonymised by the hospital, clinical data was standardized to have a mean of zero and a unit standard deviation. This data was made public with the aim to allow researchers to develop ways to enable the hospital to rapidly predict and potentially identify SARS-CoV-2 positive patients. We find that with full blood counts random forest, shallow learning and a flexible ANN model predict SARS-CoV-2 patients with high accuracy between populations on regular wards (AUC = 94-95%) and those not admitted to hospital or in the community (AUC = 80-86%). Here, AUC is the Area Under the receiver operating characteristics Curve and a measure for model performance. Moreover, a simple linear combination of 4 blood counts can be used to have an AUC of 85% for patients within the community. The normalised data of different blood parameters from SARS-CoV-2 positive patients exhibit a decrease in platelets, leukocytes, eosinophils, basophils and lymphocytes, and an increase in monocytes. SARS-CoV-2 positive patients exhibit a characteristic immune response profile pattern and changes in different parameters measured in the full blood count that are detected from simple and rapid blood tests. While symptoms at an early stage of infection are known to overlap with other common conditions, parameters of the full blood counts can be analysed to distinguish the viral type at an earlier stage than current rt-PCR tests for SARS-CoV-2 allow at present. This new methodology has potential to greatly improve initial screening for patients where PCR based diagnostic tools are limited.

Keywords: Artificial Neural Network (ANN); Full blood count; Leukocytes; Machine Learning; Monocytes; SARS-CoV-2; Screening.

Fig. 1

Box plots showing median and 1st/3rd quartile of individual parameters of the full blood counts categorized by whether tested positive (red box) or negative (blue box) by the rt-PCR test for SARS-CoV-2 and by whether they remained in the community or were admitted in the regular ward. MPV; mean platelet volume, RBC; red blood cells, RBCDW; red blood cell distribution width. The p-values are tests of equality of population using the Wilcoxon rank sum test, where p < 0.05 implies statistically significant difference between the populations. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)

Fig. 2

a. The ROC curve of the defined ANN model over patients admitted to regular ward; b. The normalized confusion matrix, corresponding to fold 2 (corresponds to the worst value of AUC). ROC: Receiver operating characteristic; AUC: area under the curve.

Fig. 3

a. The ROC curve of the defined ANN model over patients not admitted to the hospital (community); b. The normalized confusion matrix, corresponding to fold 8 (corresponds to the worst value of AUC). ROC: Receiver operating characteristic; AUC: area under the curve.

Fig. 4

Variable importance plot of (a) random forest and (b) glmnet classification of SARS-CoV-2 positive patients who are in the regular hospital ward. The plot shows the importance of variables in building the respective predictive model. MPV; mean platelet volume, RBC; red blood cells, MCHC; mean corpuscular haemoglobin concentration, MCH; mean corpuscular haemoglobin, MCV; mean corpuscular volume, RBCDW; red blood cell distribution width. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)

Fig. 5

Box plots of blood characteristics: a. monocytes - leukocytes (m-l) b. monocytes - leukocytes - eosinophils (m-l-e) and c. monocytes - leukocytes - eosinophils - platelets (m-l-e-p); all normalized values, categorized by whether tested negative (blue box) or positive (red box) to rt-PCR SARS-CoV-2 test, and whether they remained in the community or were admitted in the regular ward. All p-values are tests of equality of population using Wilcoxon rank sum test and suggest statistically significant difference. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)