Introduction
The eye offers potential for the diagnosis of Alzheimer’s disease (AD) with retinal imaging techniques being explored to quantify amyloid accumulation and aspects of neurodegeneration. To assess these changes, this proof-of-concept study combined hyperspectral imaging and optical coherence tomography to build a classification model to differentiate between AD patients and controls.
Methods
In a memory clinic setting, patients with a diagnosis of clinically probable AD (n = 10) or biomarker-proven AD (n = 7) and controls (n = 22) underwent non-invasive retinal imaging with an easy-to-use hyperspectral snapshot camera that collects information from 16 spectral bands (460–620 nm, 10-nm bandwidth) in one capture. The individuals were also imaged using optical coherence tomography for assessing retinal nerve fiber layer thickness (RNFL). Dedicated image preprocessing analysis was followed by machine learning to discriminate between both groups.
Results
Hyperspectral data and retinal nerve fiber layer thickness data were used in a linear discriminant classification model to discriminate between AD patients and controls. Nested leave-one-out cross-validation resulted in a fair accuracy, providing an area under the receiver operating characteristic curve of 0.74 (95% confidence interval [0.60–0.89]). Inner loop results showed that the inclusion of the RNFL features resulted in an improvement of the area under the receiver operating characteristic curve: for the most informative region assessed, the average area under the receiver operating characteristic curve was 0.70 (95% confidence interval [0.55, 0.86]) and 0.79 (95% confidence interval [0.65, 0.93]), respectively. The robust statistics used in this study reduces the risk of overfitting and partly compensates for the limited sample size.
Conclusions
This study in a memory-clinic-based cohort supports the potential of hyperspectral imaging and suggests an added value of combining retinal imaging modalities. Standardization and longitudinal data on fully amyloid-phenotyped cohorts are required to elucidate the relationship between retinal structure and cognitive function and to evaluate the robustness of the classification model.
Low BP (blood pressure) is a recognized risk factor for some patients with NPG (normal pressure glaucoma). We have shown previously that patients with orthostasis have impaired circadian renal handling of sodium, which may contribute to the low BP. Therefore the aim of the present study was to examine the renal handling of sodium, the circadian variations in BP and the neurohormonal response to an orthostatic test in a selected subpopulation of 18 patients with NPG with vasospastic and orthostatic symptoms, and in 24 healthy control subjects. The variations in BP and renal tubular sodium handling were evaluated using 24 h ambulatory BP recordings, 24 h urine collections and determination of endogenous lithium clearance as a marker of proximal sodium reabsorption. The neurohormonal and BP responses to changes in posture were also determined in a 30 min orthostatic test. This selected group of patients with NPG had lower 24 h ambulatory BPs (P<0.001), and a more pronounced fall in BP when assuming an upright position (P<0.001) compared with controls. FE(Li) (fractional excretion of lithium) was higher in patients with NPG than controls during the day (36.6+/-21.8 compared with 20.4+/-8.7% respectively; P<0.01; values are means+/-S.D.) as well as during the night (38.8+/-41.9 compared with 19.7+/-10.8% respectively; P<0.02), suggesting a reduced reabsorption of sodium in the proximal tubule. This was compensated for by an increased distal reabsorption of sodium in patients with NPG (P<0.01). These data demonstrate that patients with vasospastic NPG have a high excretion of lithium, suggesting reduced sodium reabsorption in the proximal tubule, in spite of a low BP. The abnormal renal sodium handling might contribute to the maintenance of arterial hypotension and progression of the optic nerve damage in these patients.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.