DESIGN: Artificial intelligence (neural network) study.
METHODS: We assessed 1400 OCT scans of patients with neovascular AMD. Fifteen physical features for each eligible OCT, as well as patient age, were used as input data and corresponding recorded visual acuity as the target data to train, validate, and test a supervised neural network. We then applied this network to model the impact on acuity of defined OCT changes in subretinal fluid, subretinal hyperreflective material, and loss of external limiting membrane (ELM) integrity.
RESULTS: A total of 1210 eligible OCT scans were analyzed, resulting in 1210 data points, which were each 16-dimensional. A 10-layer feed-forward neural network with 1 hidden layer of 10 neurons was trained to predict acuity and demonstrated a root mean square error of 8.2 letters for predicted compared to actual visual acuity and a mean regression coefficient of 0.85. A virtual model using this network demonstrated the relationship of visual acuity to specific, programmed changes in OCT characteristics. When ELM is intact, there is a shallow decline in acuity with increasing subretinal fluid but a much steeper decline with equivalent increasing subretinal hyperreflective material. When ELM is not intact, all visual acuities are reduced. Increasing subretinal hyperreflective material or subretinal fluid in this circumstance reduces vision further still, but with a smaller gradient than when ELM is intact.
CONCLUSIONS: The supervised machine learning neural network developed is able to generate an estimated visual acuity value from OCT images in a population of patients with AMD. These findings should be of clinical and research interest in macular degeneration, for example in estimating visual prognosis or highlighting the importance of developing treatments targeting more visually destructive pathologies.
METHODS: Utilizing the Malaysian National Cardiovascular Disease Database-Percutaneous Coronary Intervention (NCVD-PCI) registry data from 2007 to 2014, STEMI patients treated with percutaneous coronary intervention (PCI) were stratified into presence (GFR
PATIENTS AND METHODS: Male patients aged 50 years and above (including indigenous people) with angiographically diagnosed significant CAD in the recent one year were screened for AAA. Standard definition of abdominal aortic aneurysm and CAD was used. All new patients were followed up for six months for AAA events (ruptured AAA and AAA-related mortality).
RESULTS: A total of 277 male patients were recruited into this study. The total prevalence of undiagnosed AAA in this study population was 1.1% (95% CI 0.2-3.1). In patients with high-risk CAD, the prevalence of undiagnosed AAA was 1.7% (95% CI 0.3-4.8). The detected aneurysms ranged in size from 35.0mm to 63.8mm. Obesity was a common factor in these patients. There were no AAA-related mortality or morbidity during the follow-up. Although the total prevalence of undiagnosed AAA is low in the studied population, the prevalence of sub-aneurysmal aortic dilatation in patients with significant CAD was high at 6.6% (95% CI 3.9-10.2), in which majority were within the younger age group than 65 years old.
CONCLUSION: This was the first study on the prevalence of undiagnosed AAA in a significant CAD population involving indigenous people in the island of Borneo. Targeted screening of patients with high-risk CAD even though they are younger than 65 years old effectively discover potentially harmful asymptomatic AAA and sub-aneurysmal aortic dilatations.