When many of us think of artificial intelligence (AI) we think of robots, or various smart assistants like Alexa. But AI is used in many fields, including medicine, where it has helped doctors and researchers make important advancements.
Early cancer detection often increases a person’s chances of survival. As data is collected, AI can begin to see patterns that help in early detection. AI also is being used by a major tech company to help more quickly diagnose and treat glaucoma.
AI and detecting cancer
As we learn more about AI, the word algorithm is moving from research centers and universities to mainstream America. Many people know that Facebook, Netflix and other streaming and social media apps collect our data to try to find patterns and build algorithms on what kinds of product we buy or movies we watch.
But few of us think about how that data is being used in other fields. In medicine, finding a cure for cancer is the holy grail.
The more we learn about the disease, the more information we can put into databases that artificial intelligence uses to build algorithms. It shows patterns on how people react to certain treatments, what treatments should be used and helps with early cancer detection.
MRIs, CT scanners, biopsy samples and more contain complex information that is difficult for humans to sort out. That’s where AI comes in.
Health IT Analytics reports that AI and deep machine learning, or deep learning network, already have shown promise for supplementing and verifying work of clinicians mired in complex imaging analytics.
In a 2017 study from Case Western Reserve University, researchers said that a deep learning network found invasive forms of breast cancer in pathology images with 100% accuracy.
“Artificial intelligence algorithms have tremendous potential to help health care providers diagnose and treat medical conditions,” Robert Ochs of the FDA’s Center for Devices and Radiological Health told Health IT Analytics.
AI also can substantially weed out false positives without having patients go through invasive tests, according to researchers at the University of Pittsburgh and UPMH Hillman Cancer Center.
Despite the promise AI and deep machine learning have shown, trust is a major obstacle with doctors and patients.
In a personal essay for TNW, Yessi Bello Perez wrote, “AI shouldn’t be seen as a standalone solution for diagnosing or treating patients in a completely unsupervised environment. Rather it’s a solution created to be a smart, and helpful assistant to physicians, who have an invaluable, and holistic view, of the patient’s condition and past medical history.”
IBM developing AI solution for glaucoma
Numerous tests are needed to gauge accurate vision loss from glaucoma. But IBM is working on how to use AI and computers to take on that task.
According to Engadget, IBM’s research wing used AI to discover retina imaging data that can be used to detect and manage the eye disease. By using a deep learning system, IBM was able to estimate the degree of visual function based on a single 3D scan of the optic nerve.
IBM said that while it’s only at the groundwork state, machine learning has shown that it’s possible to predict the results of future vision tests, and how glaucoma will evolve in a patient over time. This could help doctors in using treatments based on what’s likely to happen to a patient with glaucoma.