What changes could AI bring to oncology?

Even as AI is being thrust into efforts such as the battle against COVID-19, researchers in specialties such as oncology are examining the new technologies for their potential for deeper, more fundamental advances in medicine.

Jeff Rowe | May 22, 2020 01:14 pm

While AI has been widely enlisted almost overnight to combat the coronavirus pandemic, stakeholders in healthcare specialties are more in the midst of a long-term vetting process to see how the new technologies can be applied to their fields.

For example, medical writer Andrea Blevins Primeau recently wrote an article surveying the prospects of AI in oncology, and she says that while AI is not yet being used broadly by oncologists, its use is being studied in several areas pertaining to treating myriad cancers. 

Take screening and diagnosis.  According to Primeau, the FDA has approved a number of AI platforms to help evaluate medical images, particularly when it comes to identifying potentially cancerous lesions.

“Some platforms help to visualize and manipulate images from magnetic resonance imaging (MRI) or computed tomography (CT) and flag suspicious areas,” she explains. “For example, there are several AI platforms for evaluating mammography images and, in some cases, help to diagnose breast abnormalities. There is also an AI platform that helps to analyze lung nodules in individuals who are being screened for lung cancer.”

Other screening and diagnosis uses under consideration include tapping AI to either supplement or replace clinicians when it comes to running biopsies of lesions, primarily in the name of making the process more efficient.

As in much of the healthcare sector, Big Data looms large on the horizon for oncology given the potential for researchers to collect and analyze vast amounts of data in the search for meaningful patterns.

“Such tools would be useful in the research setting,” she notes, “as scientists look for novel targets for new anticancer therapies or to further their understanding of underlying disease processes. AI would also be useful in the clinical setting, especially now that electronic health records are being used and real-world data are being generated from patients.”

Finally, there’s clinical decision. As an example, she points to an AI platform that provides clinical decision-making support by basing suggestions for clinicians “on clinical practice guideline recommendations, analysis of the scientific literature, learning from experts and test cases, and the patient’s characteristics. An early study of this platform showed that the AI technology chose treatments that were highly concordant with what prostate cancer specialists would select.”

The bottom line is that even as AI is being snatched into the battle against the coronavirus, slower, but potentially more transformative, changes are being painstakingly researched and developed in critical fields such as oncology.


Resource Center VIEW MORE