Researchers have developed an artificial intelligence (AI) technology capable of assessing the severity of Covid-19 cases with a promising degree of accuracy, and researchers from the University of Waterloo and Alexander Wong, professor of systems design engineering and co-founder of the software company DarwinAI, said the technology could provide clinicians An important tool to help them manage cases.
Assessing the severity of a patient with Covid-19 is a critical step in the clinical workflow to determine the best course of treatment and care, whether that is by admitting the patient to the intensive care unit, giving the patient oxygen therapy, or putting the patient in good health.
For the study published in Scientific Reports, the deep-learning AI was trained to analyze the extent and transparency of infection in the lungs of Covid-19 patients based on chest X-rays, and the team said its scores were then compared to evaluations of the same X-rays by radiologists.
For both range and opacity, which are important indicators of infection severity, the predictions made by the AI software were in good agreement with the scores provided by human experts. The promising results in this study show that AI has strong potential to be an effective tool to support Healthcare workers are on the front lines in their decisions and improve clinical efficiency.