Predicting Brain Amyloid Accumulation Using RetiSpec: Sharon Cohen, MD, FRCPC

WATCH TIME: 3 minutes

RetiSpec, noninvasive retinal imaging tool, uses hyperspectral technology combined with artificial intelligence to look for distinctive signs of Alzheimer disease (AD), as well as Parkinson disease, vascular dementia, and amyotrophic lateral sclerosis. At the 14th Clinical Trials on Alzheimer’s Disease Conference (CTAD), November 9-12, 2021, investigators presented research that demonstrated RetiSpec’s ability to predict brain amyloid status.¹

In a cross-sectional validation study, 108 patients who were at risk for or who had preclinical AD or mild cognitive impairment (MCI) had amyloid-ß assessment via cerebrospinal fluid and/or PET scan within 12 months of retinal imaging were included. The system captured high resolution hyperspectral images of the retina in the wavelength range of 450 to 1000 nm. In the first analysis, the diagnostic performance of the approach yielded an area under the curve (AUC) of 0.88, which corresponded with 86% sensitivity and 80% specificity. No other data, including age and apolipoprotein status, added to the outcome of the model. Additionally, patients reported an easy and comfortable experience of undergoing the RetiSpec scan and reported high willingness to undergo the scan in the future.

Lead author Sharon Cohen, MD, FRCPC, neurologist and assistant professor, University of Toronto, sat down with NeurologyLive® to detail how she and her colleagues conducted the study, along with the topline findings and the advantages it might bring.

REFERENCE
1. Cohen S, Plante A, Hazan Al, et al. RetiSpec’s hyperspectral imaging system: results of a validation study in preclinical AD and MCI. Presented at CTAD 2021; November 9-12. Poster LP16