IMPORTANCENoninvasive retinal imaging may detect structural changes associated with Parkinson disease (PD) and may represent a novel biomarker for disease detection.OBJECTIVE To characterize alterations in the structure and microvasculature of the retina and choroid in eyes of individuals with PD and compare them with eyes of age-and sex-matched cognitively healthy control individuals using optical coherence tomography (OCT) and OCT angiography (OCTA). DESIGN, SETTING, AND PARTICIPANTSThis cross-sectional study was conducted at the Duke Neurological Disorders Clinic in Durham, North Carolina. Individuals aged 50 years or older with a diagnosis of PD were eligible for inclusion and underwent an evaluation and diagnosis confirmation before enrollment. Control individuals aged 50 years or older and without subjective cognitive dysfunction, a history of tremor, or evidence of motor dysfunction consistent with parkinsonism were solicited from the clinic or the Duke Alzheimer's Disease Prevention Registry. Individuals with diabetes, glaucoma, retinal pathology, other dementias, and corrected Early Treatment Diabetic Retinopathy Study (ETDRS) visual acuity worse than 20/40 Snellen were excluded. Data were analyzed between January 1, 2020, and March 30, 2020.EXPOSURES All participants underwent OCT and OCTA imaging. MAIN OUTCOMES AND MEASURESGeneralized estimating equation analysis was used to characterize the association between imaging parameters and PD diagnosis. Superficial capillary plexus vessel density (VD) and perfusion density (PFD) were assessed within the ETDRS 6 × 6-mm circle, 6 × 6-mm inner ring, and 6 × 6-mm outer ring, as was the foveal avascular zone area. Peripapillary retinal nerve fiber layer thickness, macular ganglion cell-inner plexiform layer thickness, central subfield thickness, subfoveal choroidal thickness, total choroidal area, luminal area, and choroidal vascularity index (CVI) were measured.RESULTS A total of 124 eyes of 69 participants with PD (39 men [56.5%]; mean [SD] age, 71.7 [7.0] years) and 248 eyes of 137 control participants (77 men [56.2%]; mean [SD] age, 70.9 [6.7] years) were analyzed. In the 6 × 6-mm ETDRS circle, VD (β coefficient = 0.37; 95% CI, 0.04-0.71; P = .03) and PFD (β coefficient = 0.009; 95% CI, 0.0003-0.018; P = .04) were lower in eyes of participants with PD. In the inner ring of the 6 × 6-mm ETDRS circle, VD (β coefficient = 0.61; 95% CI, 0.20-1.02; P = .003) and PFD (β coefficient = 0.015; 95% CI, 0.005-0.026; P = .004) were lower in eyes of participants with PD. Total choroidal area (β coefficient = -1.74 units 2 ; 95% CI, −3.12 to −0.37 units 2 ; P = .01) and luminal area (β coefficient = -1.02 units 2 ; 95% CI, −1.86 to −0.18 units 2 ; P = .02) were greater, but CVI was lower (β coefficient = 0.5%; 95% CI, 0.2%-0.8%; P < .001) in eyes of individuals with PD.CONCLUSIONS AND RELEVANCE This study found that individuals with PD had decreased retinal VD and PFD as well as choroidal structural changes compared with age-and sex-matched control participants. Given the ...

Background/AimsTo develop a convolutional neural network (CNN) to detect symptomatic Alzheimer’s disease (AD) using a combination of multimodal retinal images and patient data.MethodsColour maps of ganglion cell-inner plexiform layer (GC-IPL) thickness, superficial capillary plexus (SCP) optical coherence tomography angiography (OCTA) images, and ultra-widefield (UWF) colour and fundus autofluorescence (FAF) scanning laser ophthalmoscopy images were captured in individuals with AD or healthy cognition. A CNN to predict AD diagnosis was developed using multimodal retinal images, OCT and OCTA quantitative data, and patient data.Results284 eyes of 159 subjects (222 eyes from 123 cognitively healthy subjects and 62 eyes from 36 subjects with AD) were used to develop the model. Area under the receiving operating characteristic curve (AUC) values for predicted probability of AD for the independent test set varied by input used: UWF colour AUC 0.450 (95% CI 0.282, 0.592), OCTA SCP 0.582 (95% CI 0.440, 0.724), UWF FAF 0.618 (95% CI 0.462, 0.773), GC-IPL maps 0.809 (95% CI 0.700, 0.919). A model incorporating all images, quantitative data and patient data (AUC 0.836 (CI 0.729, 0.943)) performed similarly to models only incorporating all images (AUC 0.829 (95% CI 0.719, 0.939)). GC-IPL maps, quantitative data and patient data AUC 0.841 (95% CI 0.739, 0.943).ConclusionOur CNN used multimodal retinal images to successfully predict diagnosis of symptomatic AD in an independent test set. GC-IPL maps were the most useful single inputs for prediction. Models including only images performed similarly to models also including quantitative data and patient data.

Introduction: Discovering non-invasive and easily acquired biomarkers that are conducive to the accurate diagnosis of dementia is an urgent area of ongoing clinical research. One promising approach is retinal imaging, as there is homology between retinal and cerebral vasculature. Recently, optical coherence tomography angiography (OCT-A) has emerged as a promising new technology for imaging the microvasculature of the retina. Methods:A systematic review and meta-analysis was conducted to examine the application of OCT-A in dementia.Results: Fourteen studies assessing OCT-A in preclinical Alzheimer's disease (AD), mild cognitive impairment, or AD were included. Exploratory meta-analyses revealed a significant increase in the foveal avascular zone area and a significant decrease in superficial parafoveal and whole vessel density in AD, although there was significant heterogeneity between studies.Discussion: Although certain OCT-A metrics may have the potential to serve as biomarkers for AD, the field requires further standardization to allow conclusions to be reached regarding their clinical utility.

No abstract

No abstract