Science

Canada: Overview of partnership between Montreal Hospital Center and DIAGNOS in screening for diabetic retinopathy

One of the complications of diabetes can be diabetic retinopathy, i.e. damage to the retina, the thin membrane necessary for vision that covers the back of the eye, followed by reduced vision or even blindness. In June 2018, DIAGNOS, a company specializing in AI-assisted screening for serious illnesses, launched an automated AI-assisted diabetic retinopathy screening project with the University of Montreal Hospital Center (CHUM). On May 26, both announced the launch of a test phase of autonomous AI solutions dedicated to this screening.

Diabetes mellitus is a chronic disease characterized by excess sugar in the blood. There are 2 different types of diabetes due to different dysfunctions: type 1 diabetes and type 2 diabetes. The latter is the most frequent and rapidly increasing.

According to the Institut Pasteur in Lille, there were 463 million people with diabetes aged 20 to 79 worldwide in 2020, including 5 million in France. In addition, it is estimated that 700,000 people suffer from this metabolic disease in our country and do not know about it. However, there may be many complications affecting the heart and arteries, eyes, kidneys, nerves, legs, the prevention of which is important.

Early detection of diabetic retinopathy is very important because treatment is possible, otherwise blindness can occur at a late stage, which then becomes irreversible.

Launch of a clinical study

The launch of this clinical trial will allow to more accurately determine the level of performance of autonomous algorithms for detecting and classifying the severity of the disease in patients with diabetic retinopathy.

André Larente, President of DIAGNOS, says:

“THIS PHASE STARTS A PARTNERSHIP ON THE AUTOMATED DETECTION OF DIABETIC RETINOPATHY, BEGINNING IN JUNE 2018. THIS STAGE OF TESTING AND PERFORMANCE ANALYSIS HAS BEEN APPROVED BY WHOM, AFTER POSITIVE RESULTS OF EVALUATION OF SEVERUSTO LEVEL MODE CLASSIFICATION ALGORITHMS MEET IN THE LAST MONTHS, AFTER A STRICT INDEPENDENT EVALUATION PROCESS PERFORMED BY CHUM. »

Fundus retinal images of more than 600 diabetic patients from the CHUM Endocrinology Department will be analyzed by the DIAGNOS “NeoRetina” deep learning algorithm in collaboration with the CHUM Department of Ophthalmology. The latter makes it possible to identify lesions caused by diabetic retinopathy and classify the evolution of the disease according to severity. Conducted in a double-blind comparison mode, this test will allow CHUM experts to accurately determine the level of performance and accuracy of NeoRetina’s offline algorithms.

AI will increase the number of examinations, says the head of the department of endocrinology CHUM Andre Boucher:

“DIABETIC RETINOPATHY AFFECTS A LARGE NUMBER OF DIABETES PATIENTS. HOWEVER, BECAUSE IN THE EARLY STAGES OF THE DISEASE, PATIENTS ARE GENERALLY SYMPTOM-FREE, AND SYMPTOMS ARE GENERALLY ONLY PRESENT IN THE MORE ADVANCED STAGES OF THE DISEASE, THIS MODALITY OF AUTONOMOUS SCREENING IS EASILY PERFORMED DURING THE ANNUAL USE. REDUCING COMPLICATIONS THAT CAN CAUSE BLINDNESS. »

Dr. Salim Lahoud, head of CHUM’s ophthalmology department, claims that screening for diabetic retinopathy using AI solutions developed by DIAGNOS will help prioritize and speed up patient care by ophthalmologists in his department. Fast, efficient and accurate, they significantly reduce screening costs.

Since diabetes is the second leading cause of blindness in Canada, integrating these solutions into health care programs for diabetic patients will help them maintain their vision…

Dr. Fabrice Brunet, President and CEO of CHUM, concludes:

“THIS PROJECT IS FULLY IN CHUM’S DESIRE TO IMPROVE PATIENT SERVICE AVAILABILITY THROUGH PARTNERSHIPS THAT ENSURE THE DEVELOPMENT AND INTEGRATION OF INNOVATIVE SOLUTIONS. »

Back to top button

Adblock Detected

Please consider supporting us by disabling your ad blocker.