Introduction Advanced machine learning methods might help to identify dementia risk from neuroimaging, but their accuracy to date is unclear. Methods We systematically reviewed the literature, 2006 to late 2016, for machine learning studies differentiating healthy aging from dementia of various types, assessing study quality, and comparing accuracy at different disease boundaries. Results Of 111 relevant studies, most assessed Alzheimer's disease versus healthy controls, using AD Neuroimaging Initiative data, support vector machines, and only T1-weighted sequences. Accuracy was highest for differentiating Alzheimer's disease from healthy controls and poor for differentiating healthy controls versus mild cognitive impairment versus Alzheimer's disease or mild cognitive impairment converters versus nonconverters. Accuracy increased using combined data types, but not by data source, sample size, or machine learning method. Discussion Machine learning does not differentiate clinically relevant disease categories yet. More diverse data sets, combinations of different types of data, and close clinical integration of machine learning would help to advance the field.

IntroductionThe ease of imaging the retinal vasculature, and the evolving evidence suggesting this microvascular bed might reflect the cerebral microvasculature, presents an opportunity to investigate cerebrovascular disease and the contribution of microvascular disease to dementia with fundus camera imaging.MethodsA systematic review and meta-analysis was carried out to assess the measurement of retinal properties in dementia using fundus imaging.ResultsTen studies assessing retinal properties in dementia were included. Quantitative measurement revealed significant yet inconsistent pathologic changes in vessel caliber, tortuosity, and fractal dimension. Retinopathy was more prevalent in dementia. No association of age-related macular degeneration with dementia was reported.DiscussionInconsistent findings across studies provide tentative support for the application of fundus camera imaging as a means of identifying changes associated with dementia. The potential of fundus image analysis in differentiating between dementia subtypes should be investigated using larger well-characterized samples. Future work should focus on refining and standardizing methods and measurements.

Purpose: To examine whether ultra-widefield (UWF) retinal imaging can identify biomarkers for Alzheimer’s disease (AD) and its progression. Methods: Images were taken using a UWF scanning laser ophthalmoscope (Optos P200C AF) to determine phenotypic variations in 59 patients with AD and 48 healthy controls at baseline (BL). All living participants were invited for a follow-up (FU) after 2 years and imaged again (if still able to participate). All participants had blood taken for genotyping at BL. Images were graded for the prevalence of age-related macular degeneration-like pathologies and retinal vascular parameters. Comparison between AD patients and controls was made using the Student t test and the χ² test. Results: Analysis at BL revealed a significantly higher prevalence of a hard drusen phenotype in the periphery of AD patients (14/55; 25.4%) compared to controls (2/48; 4.2%) [χ² = 9.9, df = 4, p = 0.04]. A markedly increased drusen number was observed at the 2-year FU in patients with AD compared to controls. There was a significant increase in venular width gradient at BL (zone C: 8.425 × 10^–3 ± 2.865 × 10^–3 vs. 6.375 × 10^–3 ± 1.532 × 10^–3, p = 0.008; entire image: 8.235 × 10^–3 ± 2.839 × 10^–3 vs. 6.050 × 10^–3 ± 1.414 × 10^–3, p = 0.004) and a significant decrease in arterial fractal dimension in AD at BL (entire image: 1.250 ± 0.086 vs. 1.304 ± 0.089, p = 0.049) with a trend for both at FU. Conclusions: UWF retinal imaging revealed a significant association between AD and peripheral hard drusen formation and changes to the vasculature beyond the posterior pole, at BL and after clinical progression over 2 years, suggesting that monitoring pathological changes in the peripheral retina might become a valuable tool in AD monitoring.

PurposeSemiautomated software applications derive quantitative retinal vascular parameters from fundus camera images. However, the extent of agreement between measurements from different applications is unclear. We evaluate the agreement between retinal measures from two software applications, the Singapore “I” Vessel Assessment (SIVA) and the Vessel Assessment and Measurement Platform for Images of the Retina (VAMPIRE), and examine respective associations between retinal and systemic outcomes.MethodFundus camera images from 665 Lothian Birth Cohort 1936 participants were analyzed with SIVA and VAMPIRE. Intraclass correlation coefficients (ICC) and Bland-Altman plots assessed agreement between retinal parameters: measurements of vessel width, fractal dimension, and tortuosity. Retinal–systemic variable associations were assessed with Pearson's correlation, and intersoftware correlation magnitude differences were examined with Williams's test.ResultsICC values indicated poor to limited agreement for all retinal parameters (0.159–0.410). Bland-Altman plots revealed proportional bias in the majority, and systematic bias in all measurements. SIVA and VAMPIRE measurements were associated most consistently with systemic variables relating to blood pressure (SIVA r's from −0.122 to −0.183; VAMPIRE r's from −0.078 to −0.177). Williams's tests indicated significant differences in the magnitude of association between retinal and systemic variables for 7 of 77 comparisons (P < 0.05).ConclusionsAgreement between two common software applications was poor. Further studies are required to determine whether associations with systemic variables are software-dependent.Translational RelevanceStandardization of the measurement of retinal vascular parameters is warranted to ensure that they are reliable and application-independent. This would be an important step towards realizing the potential of the retina as a source of imaging-derived biomarkers that are clinically useful.