Artificial intelligence (AI) and innovative technology offer opportunities for enhanced health care during the COVID-19 pandemic. Populations living in low-income countries do not have access to reverse transcription polymerase chain reaction (RT-PCR) testing for COVID-19 and, thus, depend on the scarce resources of their health system. In this context, an automated screening system for COVID-19 based on AI for a telemedicine platform could be directed towards alleviating the current lack of trained radiologists who can interpret computed tomography images at countryside hospitals.

This descriptive study was carried out in Paraguay by the Telemedicine Unit of the Ministry of Public Health and Social Welfare in collaboration with the Department of Biomedical Engineering and Imaging of the Health Science Research Institute and the University of the Basque Country. The utility of the screening system for COVID-19 was analyzed by dividing the results from two tailored AI systems implemented in 14 public hospitals into four likelihood levels for COVID-19.

Between March and October 2020, 911 COVID-19 diagnoses were performed in 14 regional hospitals (62.6% were men and 37.4% were women). The average age of the patients diagnosed with COVID-19 was 50.7 years; 59.1% were aged 19 to 59 years. The two AI systems used have different background information for detecting COVID-19. The most common findings were severe pneumonia and bilateral pneumonia with pleural effusions. The role of computed tomography was to find lesions and evaluate the effects of treatment. The sensitivity of AI for detecting COVID-19 was 93%.

AI technology could help in developing a screening system for COVID-19 and other respiratory pathologies. It could speed up medical imaging diagnosis at regional hospitals for patients with suspected infection during the COVID-19 pandemic and rationalize scarce RT-PCR and specialized human resources in low-income countries. These results must be contextualized with the local or regional epidemiological profile before widespread implementation.