| Title: | Deep learning algorithms based on ocular and health status predict cognitive dysfunction and development of dementia. |
| Lead Institution: | AEYE Health. |
| Principal investigator: | Dr Katerina Kiroshka |
Application 75750
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
About
Worldwide, around 50 million people have dementia. The prevalence of dementia is estimated at 10% of individuals aged 65 and older. Its incidence increases with age, from 5% in ages 65-74 to 30% in ages 85 and older. (WHO) We review two major risk factors for developing dementia. First, visual impairment that affects productivity and significant lifestyle changes in elderly population. Moderate-to-severe visual impairment is a potential predictor and a risk factor for dementia. We study the most prevalent reason for visual impairment among the aging population, and the potential interaction between visual impairment and dementia. Second, cardiovascular risk factors are also suggested risk factors for dementia. Multiple studies conclusively show that the significant risk factors for stroke are also the most common risk factors for cardiovascular and peripheral vascular disease, suggesting that these disorders share a common mechanism of vascular injury. Risk factors for cardiovascular and peripheral vascular disease due to SCORE quiz (age, sex, systolic blood pressure, use of antihypertensives, left ventricular hypertrophy, prevalent cardiovascular disease, smoking status, atrial fibrillation, and diabetes mellitus) Vascular factors commonly lead to a spectrum of asymptomatic brain injury and potential dementia. Our aim is prediction and early detection of dementia which are very important to early and optimal management. We estimate algorithms based on deep learning that can be applied to extract novel information such as dementia from ocular and health status. Deep learning is a class of machine learning techniques that has tremendous global interest in the last few years, recognizing that it is increasingly embraced and utilized. In medicine and healthcare, deep learning (DL) has been primarily applied to medical imaging analysis, in which DL systems have shown robust diagnostic performance in detecting various medical conditions. Major ophthalmic diseases which DL techniques have been used for including diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD). DL has also been applied to estimate refractive error and cardiovascular risk factors (eg, age, blood pressure, smoking status and body mass index).1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 18372 | Non-contact optical blood pressure biometry using AI-based analysis of non-mydriatic fundus imaging | Idan Bressler (+7) | 2026 | BMJ Innovations |
Enabling scientific discoveries that improve human health