Machine Learning Applied to COVID-19: A Review of the Initial Pandemic Period

Diagnostic and decision-making processes in the 2019 Coronavirus treatment have combined new standards using patient chest images, clinical and laboratory data. This work presents a systematic review aimed at studying the Artificial Intelligence (AI) approaches to the patients' diagnosis or evolution with Coronavirus 2019. Five electronic databases were searched, from December 2019 to October 2020, considering the beginning of the pandemic when there was no vaccine influencing the exploration of Artificial Intelligence-based techniques. The first search collected 839 papers. Next, the abstracts were reviewed, and 138 remained after the inclusion/exclusion criteria was performed. After thorough reading and review by a second group of reviewers, 64 met the study objectives. These papers were carefully analyzed to identify the AI techniques used to interpret the images, clinical and laboratory data, considering a distribution regarding two variables: (i) diagnosis or outcome and (ii) the type of data: clinical, laboratory, or imaging (chest computed tomography, chest X-ray, or ultrasound). The data type most used was chest CT scans, followed by chest X-ray. The chest CT scan was the only data type that was used for diagnosis, outcome, or both. A few works combine Clinical and Laboratory data, and the most used laboratory tests were C-reactive protein. AI techniques have been increasingly explored in medical image annotation to overcome the need for specialized manual work. In this context, 25 machine learning (ML) techniques with a highest frequency of usage were identified, ranging from the most classic ones, such as Logistic Regression, to the most current ones, such as those that explore Deep Learning. Most imaging works explored convolutional neural networks (CNN), such as VGG and Resnet. Then transfer learning which stands out among the techniques related to deep learning has the second highest frequency of use. In general, classification tasks adopted two or three datasets. COVID-19 related data is present in all papers, while pneumonia is the most common non-COVID-19 class among them.