Artificial Intelligence | News | Insights | AiThority
[bsfp-cryptocurrency style=”widget-18″ align=”marquee” columns=”6″ coins=”selected” coins-count=”6″ coins-selected=”BTC,ETH,XRP,LTC,EOS,ADA,XLM,NEO,LTC,EOS,XEM,DASH,USDT,BNB,QTUM,XVG,ONT,ZEC,STEEM” currency=”USD” title=”Cryptocurrency Widget” show_title=”0″ icon=”” scheme=”light” bs-show-desktop=”1″ bs-show-tablet=”1″ bs-show-phone=”1″ custom-css-class=”” custom-id=”” css=”.vc_custom_1523079266073{margin-bottom: 0px !important;padding-top: 0px !important;padding-bottom: 0px !important;}”]

AEYE Health Announces Best-In-Class Results, Proving AI Software Is Capable of Predicting the Future Development of Diabetic Retinopathy in Patients Before Diagnosable Symptoms Manifest

 AEYE Health, a leading AI company for retinal-based diagnostics, is pleased to announce the recent publication of its paper describing the development of a deep learning algorithm which can accurately predict the future development of diabetic retinopathy in patients without any diagnosable  retinopathy symptoms.

The paper was published in the British Medical Journal (BMJ), a peer-reviewed publication.

Recommended AI: aelf Announces the form of aelf DAO, Enhancing Decentralization of Governance and Ecosystem Growth

The research presents an artificial intelligence (AI) machine learning model which can predict the development of referable DR. The model does so using fundus imagery of otherwise healthy eyes, and boasts high efficacy, featuring an area-under-the-receiver-operating-curve (AUC) of above 0.81.

The significance of this study lies in the fact that not only can AI diagnose existing disease, it can also accurately predict the future development of a disease from subtle clues in the retinal image that human experts cannot discern. No additional input was given to the AI system aside from the retinal images.

Related Posts
1 of 41,068

Beyond the technical achievement for AI technology, disease prediction has significant clinical benefits. With an accurate indication for which patients are at high-risk for developing a disease, screening protocols can be adapted, allowing doctors to more closely monitor high-risk patients. Preventative treatment might also be considered in order to avoid the disease altogether, or mitigate effects. Similarly, very low-risk patients may be advised to undergo screening every 24 months, rather than current guidelines which advise annual screening.

Recommended AI: Himax Partners with Novatek to Unveil Industry Leading Ultralow Power Pre-Roll AI Solution for Battery Surveillance Camera

This publication came two months following AEYE’s FDA clearance for diabetic retinopathy screening. AEYE’s best-in-class technology showed, for the first time, sensitivity and specificity above 90% while using a single-image-per-eye, as well as rarely requiring dilation. Each of these innovations is key to making screening more accessible and practical. The solution is currently being deployed in primary care clinics to help address the care gaps that result from less than 50% of patients currently undergoing the yearly recommended retinal screenings.

Recommended AI: GoodFirms Unlocks the Best Task Management Software with Rich Features

[To share your insights with us, please write to sghosh@martechseries.com]

Comments are closed.