AI-based glaucoma screening could revolutionize eye health

AI-based glaucoma screening could revolutionize eye health

Imagine walking into a supermarket, train station or shopping center and having your eyes shielded within seconds of glaucoma - no appointment required. With the AI-based Glaucoma Screening (AI-GS) network, this vision could soon become a reality.

Glaucoma is the most common cause of irreversible blindness in Japan and worldwide. Early detection is critical because the disease progresses silently and slowly limits peripheral vision. Patients often don't notice this vision loss at first, meaning extensive and irreversible damage can occur before a patient even thinks about booking a doctor's appointment. As a result, many cases remain undiagnosed due to the limited availability of ophthalmologists and the challenges of conducting mass screenings, particularly in resource-limited regions.

"For this reason, we have developed a new, rapid, portable testing method. It analyzes several key indicators of glaucoma, integrates the results and determines the presence of the disease with unprecedented precision," explains Professor Toru Nakazawa (Tohoku University).

The AI-GS was developed by a research team led by Nakazawa and Associate Professor Parmanand Sharma at the Graduate School of Medicine (Tohoku University).

The AI-GS network was back tested on a dataset of 8,000 fundus images of the eye (where glaucomatous damage occurs), achieving an impressive sensitivity of 93.52% at 95% specificity - a level comparable to expert ophthalmologists. Unlike traditional AI models, this system excels at detecting early-stage glaucoma, even in cases where fundus abnormalities are subtle and difficult to detect.

A major challenge in AI-driven healthcare is the lack of interpretability – the so-called “black box” problem, where it is unclear what steps the AI ​​took to reach a conclusion. AI-GS solves this by providing numerical values ​​for each diagnostic feature, allowing ophthalmologists to understand and review their decision-making process. This transparency improves trust and facilitates seamless integration into clinical practice.

Another important aspect that made practical implementation as simple as possible was size. At just 110MB, the AI-GS network is designed for portability and efficiency. It requires minimal computing power and provides diagnostic results in one second.

AI-GS brings expert-level glaucoma screening into your pocket and complements specialty assessments. It can be run on a mobile device and used in all sorts of public places due to its portability. They can perform screenings at train stations or even remote regions that otherwise have limited access to ophthalmologists. “

Parmanand Sharma, Associate Professor, Tohoku University

“This AI technology bridges a critical gap in glaucoma detection by making specialty-level diagnostics accessible to underserved communities,” notes Professor Nakazawa. By enabling early detection at scale, we have the potential to prevent blindness for millions worldwide. “

With its high accuracy, AI explanation and lightweight design, the AI-GS network represents a major breakthrough in AI-driven ophthalmology, bringing glaucoma screening out of hospitals and into everyday life. Large-scale implementation of this system could revolutionize glaucoma care and ensure that no patient goes undiagnosed due to a lack of access to specialists.

Sources: