Artificial Intelligence at Mount Sinai capable of diagnosing COVID-19

Published by:
Posted on: May 19, 2020 9:23 pm EDT

In a Nature Medicine research paper released today, Mount Sinai researchers revealed how they are using artificial intelligence to diagnose COVID-19. By using chest CT scans in conjunction with bloodwork, demographic data, and knowledge of possible contact, Mount Sinai is now the first American health agency capable of detecting COVID-19 using AI.

Zahi Fayad, who co-authored the research paper and serves as the director of the BioMedical Engineering and Imaging Institute (BMEII) at the Icahn School of Medicine noted, “We were able to show that the AI model was as accurate as an experienced radiologist in diagnosing the disease, and even better in some cases where there was no clear sign of lung disease on CT.”

The paper’s authors note that scans alone don’t always reveal lung diseases on their own, especially when symptoms are first present. In addition, lab tests can take several days. Mount Sinai’s AI bridges this gap.

In a press release Zahi Fayad stated, “The high sensitivity of our AI model can provide a ‘second opinion’ to physicians in cases where CT is either negative (in the early course of infection) or shows nonspecific findings, which can be common. It’s something that should be considered on a wider scale, especially in the United States, where currently we have more spare capacity for CT scanning than in labs for genetic tests.”

The researchers at Mount Sinai trained the artificial intelligence algorithm using 900 scans from Chinese medical centers. These included both 419 positive and 486 negative COVID-19 cases. These scans were used with patient information, including blood test results that revealed abnormalities in either lymphocyte of white blood cell count.

Mount Sinai’s AI algorithm mirror a typical doctor’s workflow when diagnosing COVID-19. The AI is capable of revealing the likelihood of the patient testing positive based on the clinical data, CT images, or both together.

“This is an early proof concept that we can apply to our own patient data to further develop algorithms that are more specific to our region and diverse populations,” said Mount Sinai Health System’s Clinical Data Science Team Director Matthew Levin.