The CDC recommends that each of the 34.2 million patients with diabetes in the United States is screenedannually for diabetic retinopathy (DR), a major cause of preventable blindness. Less than 50% of diabetespatients actually follow these guidelines due to lack of access to medical care and eye specialists, time andmoney constraints, and lack of symptoms with early-stage disease.To address these problems, our team at AI Optics is developing the world's first artificial intelligence-basedhandheld retinal camera to allow for point-of-care DR screening. This device is designed to be portable, easyto use, and workflow friendly. It performs high-accuracy DR screenings on non-dilated patients, maintainingoptimal security and remaining resilient to connectivity issues. Our goal is that this novel diagnostic device willexpand DR screenings beyond the offices of eye specialists and into primary care, optometry offices, diabetesclinics, and retail health settings. This increased access to screening will increase early-stage diagnosis ratesand avoid preventable vision loss.In this Phase I SBIR project, we will develop a retinal camera that complies with ISO 10940:2009 standards,which will be able to capture high-quality fundus images in a handheld device. To ensure that full-scale imageclassification can be conducted, we will also utilize our proprietary, deep-learning artificial intelligence system.Finally, we will ensure that images captured from our retinal camera can be analyzed by our artificialintelligence for the presence of DR. The successful completion of this project will result in an improved andmore accessible tool for DR screenings that could lead to earlier DR diagnosis, blindness prevention, andsignificant cost savings for millions of people with diabetes.
Public Health Relevance Statement: PROJECT NARRATIVE
Less than 50% of the 34.2 million people with diabetes in the United States follow CDC guidelines to get
annual screenings for diabetic retinopathy (DR), a leading cause of blindness that impacts up to 40% of
diabetic patients. To address this problem, we propose the development of the world's first handheld retinal
camera that uses artificial intelligence for point-of-care DR screenings in primary care, urgent care, and retail
health settings. As it can be operated without an eye specialist or Internet access, this handheld device will be
portable, easy to use, and workflow friendly, enabling more screenings, earlier DR diagnosis, vision-loss
prevention and significant cost savings for millions.
Project Terms: Achievement ; Achievement Attainment ; Artificial Intelligence ; AI system ; Computer Reasoning ; Machine Intelligence ; Blood Glucose ; Blood Sugar ; Centers for Disease Control and Prevention (U.S.) ; CDC ; Centers for Disease Control ; Centers for Disease Control and Prevention ; United States Centers for Disease Control ; United States Centers for Disease Control and Prevention ; Classification ; Systematics ; Diabetes Mellitus ; diabetes ; Non-Insulin-Dependent Diabetes Mellitus ; Adult-Onset Diabetes Mellitus ; Ketosis-Resistant Diabetes Mellitus ; Maturity-Onset Diabetes Mellitus ; NIDDM ; Non-Insulin Dependent Diabetes ; Noninsulin Dependent Diabetes ; Noninsulin Dependent Diabetes Mellitus ; Slow-Onset Diabetes Mellitus ; Stable Diabetes Mellitus ; T2 DM ; T2D ; T2DM ; Type 2 Diabetes Mellitus ; Type 2 diabetes ; Type II Diabetes Mellitus ; Type II diabetes ; adult onset diabetes ; ketosis resistant diabetes ; maturity onset diabetes ; type 2 DM ; type II DM ; type two diabetes ; Diabetic Retinopathy ; Diagnosis ; Disease ; Disorder ; Environment ; Expert Systems ; Intelligent systems ; Eye ; Eyeball ; Goals ; Health ; Hemorrhage ; Bleeding ; blood loss ; Housing ; Human ; Modern Man ; Lead ; Pb element ; heavy metal Pb ; heavy metal lead ; Persons ; Optics ; optical ; Optometry ; Optometries ; Patients ; Physicians ; Primary Health Care ; Primary Care ; Primary Healthcare ; Retina ; retina blood vessel structure ; Retinal Blood Vessels ; Retinal Vessels ; Running ; Testing ; Time ; United States ; Vision ; Sight ; visual function ; Measures ; Cost Savings ; Specialist ; Caring ; Custom ; Guidelines ; base ; improved ; Procedures ; Left ; Phase ; Medical ; Ensure ; Training ; retinal damage ; damage to retina ; Databases ; Data Bases ; data base ; Ophthalmologist ; Internet ; WWW ; web ; world wide web ; Phase II Clinical Trials ; Phase 2 Clinical Trials ; phase II protocol ; Point-of-Care Systems ; tool ; mechanical ; Mechanics ; Clinic ; System ; vision loss ; visual loss ; Blindness ; early detection ; Early Diagnosis ; success ; HIPAA ; Kennedy Kassebaum Act ; PL 104-191 ; PL104-191 ; Public Law 104-191 ; United States Health Insurance Portability and Accountability Act ; Health Insurance Portability and Accountability Act ; Participant ; Prevention ; Devices ; Modeling ; handheld device ; handheld equipment ; portability ; Address ; Symptoms ; Detection ; Resolution ; Security ; Small Business Innovation Research Grant ; SBIR ; Small Business Innovation Research ; Process ; Development ; developmental ; point of care ; Image ; imaging ; cost ; design ; designing ; Outcome ; Population ; Early treatment ; early therapy ; Network-based ; graphical user interface ; Graphical interface ; graphic user interface ; software user interface ; novel diagnostics ; new diagnostics ; next generation diagnostics ; prototype ; commercialization ; lens ; lenses ; diabetic patient ; product development ; Secure ; screening ; urgent care ; Cloud Computing ; Cloud Infrastructure ; cloud computer ; routine screening ; annual screening ; fundus imaging ; retinal imaging ; retina imaging ; deep learning ; convolutional neural network ; ConvNet ; convolutional network ; convolutional neural nets ; screening services ;
