By LUKE OAKDEN-RAYNER, MBBS
I got asked the other day to comment for Wired on the role of AI in Covid-19 detection, in particular for use with CT scanning. Since I didn’t know exactly what resources they had on the ground in China, I could only make some generic vaguely negative statements. I thought it would be worthwhile to expand on those ideas here, so I am writing two blog posts on the topic, on CT scanning for Covid-19, and on using AI on those CT scans.
As background, the pro-AI argument goes like this:
- CT screening detects 97% of Covid-19, viral PCR only detects 70%!
- A radiologist takes 5-10 minutes to read a CT chest scan. AI can do it in a second or two.
- If you use CT for screening, there will be so many studies that radiologists will be overwhelmed.
In this first post, I will explain why CT, with or without AI, is not worthwhile for Covid-19 screening and diagnosis, and why that 97% sensitivity report is unfounded and unbelievable.
Next post, I will address the use of AI for this task specifically.
In 2011, the New England Journal of Medicine reported results of the National Lung Screening Trial (NLST). Screening trials have to be big, because almost all the people who are screened don’t have the disease being investigated, and screening only helps people with silent disease.
The NLST had over 50,000 participants, all with a history of abusing their lungs through heavy smoking. Half were randomly assigned to have three annual low-dose helical chest computed tomography (CT) exams, and half were assigned to have three annual chest x-rays
All earlier trials had shown screening with x-rays to be ineffective, so many of us were surprised when CT screening proved to be effective, reducing death from lung cancer by 20 percent over the six years of the trial. Apparently, the CT proved to be effective at finding much smaller tumors than could x-ray.
Since publication of this study, the American Society of Clinical Oncology and other medical organizations have recommended screening for those at similarly high risk for lung cancer. The United States Preventive Services Task Force gave such CT screening a grade B recommendation, making coverage by private insurers mandatory and by public insurers likely.