In his capacity as a corresponding author, Professor Weimin Li of West China Hospital (WCH) published in Cell, on April 25, an online article titled “Clinically Applicable AI System for Accurate Diagnosis, Quantitative Measurements and Prognosis of COVID-19 Pneumonia Using Computed Tomography”. The article is the research achievement of a cooperation project among West China Hospital, Macau University of Science and Technology, Tsinghua University, and Sun Yat-Sen University.

Using a large computed Tomography (CT) database from 4,154 patients, the researchers have developed an AI system that can diagnose NCP and differentiate it from other common pneumonia and normal controls. “The AI system can assist radiologists and physicians in performing a quick diagnosis especially when the health system is overloaded. Significantly, our AI system identified important clinical markers that correlated with the NCP lesion properties. Together with the clinical data, our AI system was able to provide accurate clinical prognosis that can aid clinicians to consider appropriate early clinical management and allocate resources appropriately. We have made this AI system available globally to assist the clinicians to combat COVID-19.” (Summary)

Studies have shown that over 60% of patients died once they progressed into the severe/critical illness stage. “Therefore, identifying risk factors and parameters that can allow the creation of an accurate prognosis predictive model are critical in such a pandemic in the planning of early intervention and intense monitoring and hopefully will lead to improved clinical outcomes.” “Recent new and exciting advances in the applications of AI in many healthcare areas have inspired innovations in the development of novel AI-based radiological diagnostic technology. —- various quantitative models of thin-section CT of the chest showed effectiveness of quantitative tools in both accurate diagnosis and longitudinal follow-up. — Therefore, with a more accurate tool in CT scans, we hypothesized that an AI system can be established that can accurately diagnose NCP and this will assist radiologists and clinicians in the management of patients with symptoms suggestive of COVID-19 NCP.” The researchers “have constructed a large CT dataset on NCP, other common pneumonia and normal controls and developed an AI diagnostic system for assisting the accurate diagnosis for application of an epidemic area and two in non-epidemic areas in China.” (Introduction)

Macau University of Science and Technology is the first work unit of this research paper, and Sichuan University West China Hospital is the second work unit. Kang Zhang is the co first author (listed in the first place) and the co corresponding author and Weimin Li is the co corresponding author. In addition to Macao University of Science and Technology and West China Hospital, the other corresponding work units also include Tsinghua University and the First Affiliated Hospital of Guangzhou Medical University.

Article link: https://www.cell.com/pb-assets/products/coronavirus/CELL_CELL-D-20-00656.pdf