DeepPathCOVIDx (DeepPathCOVIDx)

Type: National Project Project

Duration: from 2020 Mar 01 to 2021 Feb 03

Financed by: Agência Nacional de Inovação

Prime Contractor: GLSMED LEARNING HEALTH, S.A (Company)

The pandemic caused by the SARS-CoV-2 coronavirus has introduced new procedures in the provision of health care, with the creation of specific circuits and procedures for patients with suspected COVID-19. The early identification and characterization of patients is crucial to provide the best health care and to prevent the spread of the virus within health facilities. In this context, it is essential to have the ability to identify and characterize these patients quickly, to trigger the most appropriate clinical protocols and prevent the spread of the virus. The project aims to develop a solution, consisting of AI models for the analysis of chest radiography, designed jointly by health and engineering professionals, which indicates (i) the probability of the patient concerned having COVID-19, (ii ) how severe the disease is. Thus, it is intended to respond to the following needs: (1) optimize the work of radiologists, identifying and prioritizing the suspected X-rays of COVID-19 in the work list; (2) assisting doctors in an emergency context when radiologists are not available, with a tool for analyzing radiographs and (3) increasing efficiency in an emergency context, facilitating professionals' decision making.


  • Hospital da Luz (Company)
  • INESC-ID (Other)
  • Instituto Superior Técnico (University)

Principal Investigators