As the novel coronavirus that causes COVID-19 spreads across the globe, innovative thinking is needed more than ever to counter the devastating effects on the physical and socioeconomic health of individuals and communities. Innovations in healthcare delivery not yet fully realized prior to the pandemic, such as the adoption of telehealth, are moving to the mainstream. Artificial intelligence (AI) and machine learning are other important tools being adopted to manage and process massive amounts of data on the virus.
One specific application of AI during COVID-19 has been an attempt to use it to diagnose the disease with computed tomography (CT) imaging. Although the accuracy of AI in this setting is still being explored, as discussed in correspondence to the Lancet Digital Health on May 1, 2020, and in a blog from the Brookings Institute, the interest in, and research on, using AI in medical imaging during the pandemic may accelerate its use for medical imaging in general.1,2
Berend Stoel, PhD, a computer scientist in the division of medical image processing, Radiology, at Leiden University Medical Center, The Netherlands, thinks so. “There are already several research projects ongoing to apply AI in interpreting chest CTs of patients suspected of having COVID-19,” says Dr. Stoel, who published a review of current and potential uses of AI and machine learning in imaging in rheumatology in the January 2020 issue of RMD Open.3
“This will boost the AI development in imaging in general, and rheumatologic applications of AI will benefit from this as well,” Dr. Stoel says.
Along with imaging, AI and machine learning are being looked at for an array of potential applications within rheumatology, such as disease detection and stratification, prediction of disease flares, prediction of disease progression and use of genetic biomarkers to personalize treatment, as discussed in a 2020 review by Hügle et al.4
This is just a sampling of potential applications opening up for rheumatologists as physicians grapple with how to harness the power of big data and sophisticated technological processing tools.
Given the broad scope of research on AI and machine learning, this article focuses on the area in which these tools may first be applied in rheumatology practices—imaging.
“I think imaging is the entry for AI in rheumatology,” says Thomas Hügle, MD, PhD, head of, and professor in, the Department of Rheumatology, University Hospital, Lausanne, Switzerland. Crucial among the reasons for this is the wide availability of data in radiology on which AI and machine learning depends to create algorithms.
“Imaging is data driven, and data are what we really need for machine learning,” he says.
