The sudden outbreak of coronavirus disease 2019 (COVID-19) revealed the need for fast and reliable automatic tools to help health teams. This paper aims to present understandable solutions based on Machine Learning (ML) techniques to deal with COVID-19 screening in routine blood tests. We tested different ML classifiers in a public dataset from the Hospital Albert Einstein, São Paulo, Brazil. After cleaning and pre-processing the data has 608 patients, of which 84 are positive for COVID-19 confirmed by RT-PCR. To understand the model decisions, we introduce (i) a local Decision Tree Explainer (DTX) for local explanation and (ii) a Criteria Graph to aggregate these explanations and portrait a global picture of the results. Random Forest (RF) classifier achieved the best results (accuracy 0.88, F1–score 0.76, sensitivity 0.66, specificity 0.91, and AUROC 0.86). By using DTX and Criteria Graph for cases confirmed by the RF, it was possible to find some patterns among the individuals able to aid the clinicians to understand the interconnection among the blood parameters either globally or on a case-by-case basis. The results are in accordance with the literature and the proposed methodology may be embedded in an electronic health record system.

No abstract

No abstract

No abstract

Leukemia is a rare and lethal blood cancer. One of the factors that increase the patient's chances of better treatment results is early diagnosis. The best attempt to discover leukemia usually is the image analysis exams, but this is costly, and sometimes it is late. Thus, this paper uses attributes of a complete blood count as input to Machine Learning algorithms to predict earlier and cheaper leukemia diagnoses. In this paper, we collected actual exam results. We developed a synthetic dataset with 1000 examples based on the distribution and limits of each attribute to classify a patient in positive or negative for leukemia. We tested different classifiers (Logistic Regression, Random Forest, XGBoost, and SVM) to predict sample classes. We show that it is possible with an accuracy of 96% to predict if a patient is likely to have leukemia based on its blood count.