No-contact blood pressure and diabetes screening with AI shows promise
Artificial intelligence (AI) could help physicians deliver no-contact screening for high blood pressure and diabetes, according to new data to be presented at the American Heart Association’s Scientific Sessions 2024 conference in Chicago.
The screening device uses a high-speed video camera to capture face and palm recording of patients at a rate of 150 images per second. Advanced AI algorithms then process the recordings and identify signs of hypertension, type 1 diabetes or type 2 diabetes.
The team behind this new-look technology tracked data from 215 patients with an average age of 64 years old. Overall, their design was associated with an accuracy of 94% for detecting stage 1 hypertension and an accuracy of 86% for detecting above-average blood pressure. It also delivered an accuracy of 75% for identifying patients with diabetes when compared to traditional hemoglobin A1c blood test results.
“This method may someday allow people to monitor their own health at home and could lead to early detection and treatment of high blood pressure and diabetes in people who avoid medical exams and blood tests,” Ryoko Uchida, BSc, a researcher with the department of advanced cardiology at the University of Tokyo, said in a statement.
Uchida also noted that her team still has a significant amount of work to do before this technology is ready to be used outside of a research setting. More algorithms needs to be incorporated, for example, and the sensors need to be updated so they are more affordable. Once those steps have been taken—and the accuracy for diabetes detection is improved—she hopes her team will be able to gain approval from the U.S. Food and Drug Administration (FDA) and gets its screening tool on smartphones all over the United States.
“Currently, the only way to confirm the diagnosis of diabetes is invasive blood tests, however, if it were to require only a noninvasive photo or video, that could be a game-changer,” Uchida said.
In the same statement, Eugene Yang, MD, MS, a professor of cardiology with the University of Washington School of Medicine in Seattle, emphasized that it will still take some time before this no-contact screening system is ready for prime time.
“While the results are promising, it is important to recognize that validation of these technologies is lacking,” Yang said. “The referenced blood pressure monitor device used in this study, while cleared by the FDA, has not gone through appropriate validation protocols to ensure accuracy. Until we have approved validation protocols for these technologies, including wearable devices like smartwatches, we must use validated devices for measuring blood pressure and glucose levels.”
Uchida et al. plan to share their progress Sunday, Nov. 17, at 11:10 a.m. during a digital poster presentation moderated by cardiologists Sneha Shah Jain, MD, MBA, from Stanford University and Rohan Khera, MD, MS, from Yale School of Medicine.
Michael has more than 18 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.