AI Tool Could Allow Contactless Blood Pressure and Diabetes Screening

Researchers in Japan are developing an AI-powered tool that may allow quick, contactless screenings for high blood pressure and diabetes, potentially transforming routine health monitoring. The new system uses a high-speed video camera to capture brief clips of a person’s face and hands, then analyzes subtle changes in blood flow using an AI algorithm - all without needing blood tests, blood pressure cuffs, or expensive wearable devices.

A Breakthrough in Non-Invasive Health Monitoring

Preliminary findings from the University of Tokyo suggest that the tool could detect high blood pressure with up to 94% accuracy and identify diabetes with 75% accuracy, offering a possible alternative to invasive tests. The technology, presented at the American Heart Association’s Scientific Sessions 2024, may enable people to monitor their health from the comfort of their own home.

“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,” said study author Ryoko Uchida, B.Sc. (Pharm.), a project researcher in the department of advanced cardiology at the University of Tokyo.

How the Technology Works

This tool uses a high-speed video camera to capture skin images from the face and hands at 150 frames per second. An AI-powered algorithm then analyzes blood flow features, detecting blood pressure changes and diabetic markers from the data. Researchers hope the tool could eventually be added to everyday devices like smartphones, allowing at-home health monitoring.

Study Highlights

• Accuracy: 94% for detecting stage 1 hypertension and 75% for diabetes.

• Real-World Adaptations: Researchers are working to improve accuracy and make the technology affordable for home use.

• Limitations: Study was conducted in a controlled environment with a predominantly Asian participant group, which may affect generalizability.

Eugene Yang, M.D., a cardiology professor at the University of Washington, commented on the potential impact, stating, “It is really exciting to see more research that identifies ways to diagnose high blood pressure and diabetes non-invasively, two major risk factors for cardiovascular disease.” However, he emphasized the need for further validation of these technologies.

Study Details

The preliminary study included 215 adult participants, with an average age of 64 years; 36% of the participants were female. The majority self-identified as Japanese, while others identified as “other” Asian groups. Of the participants:

• 62 individuals had high blood pressure (130/80 mm Hg or higher).

• 88 individuals had normal blood pressure according to Japanese standards (below 115/75 mm Hg).

• 65 individuals had blood pressure readings that fell between these two ranges.

• 44 individuals either had a diabetes diagnosis or an HbA1c level of 6.5% or higher, which is the standard cut-off for elevated blood sugar levels.

The study took place at the University of Tokyo Hospital, with data collected from August 2022 to May 2024 in cardiology wards and outpatient settings. During the study, participants remained still as high-speed video recordings were taken of 22 regions of the face and 8 sections of the palm, capturing the subtle blood flow changes used for analysis. Read more on the American Heart Association's website.

“It is really exciting to see more research that identifies ways to diagnose high blood pressure and diabetes non-invasively, two major risk factors for cardiovascular disease,” commented Eugene Yang, M.D., M.S., clinical professor of medicine in the division of cardiology at the University of Washington School of Medicine.

What This Means

This research highlights an innovative approach to health monitoring, with the potential to make screenings more accessible and less invasive. If successfully adapted for real-world use, this tool could empower people to monitor their health more easily and encourage early detection and treatment of high blood pressure and diabetes, which can lead to severe health complications if left unmanaged.

Editor’s Note: This article was created by Alicia Shapiro, CMO of AiNews.com, with writing, image, and idea-generation support from ChatGPT, an AI assistant. However, the final perspective and editorial choices are solely Alicia Shapiro’s. Special thanks to ChatGPT for assistance with research and editorial support in crafting this article.