Automated machine learning-based classification of proliferative and non-proliferative diabetic retinopathy using optical coherence tomography angiography vascular density maps.

PURPOSE: The study aims to classify the eyes with proliferative diabetic retinopathy (PDR) and non-proliferative diabetic retinopathy (NPDR) based on the optical coherence tomography angiography (OCTA) vascular density maps using a supervised machine learning algorithm. METHODS: OCTA vascular density maps (at superficial capillary plexus (SCP), deep capillary plexus (DCP), and total retina (R) levels) of 148 eyes from 78 patients with diabetic retinopathy (45 PDR and 103 NPDR) was used to classify the images to NPDR and PDR groups based on a supervised machine learning algorithm known as the support vector machine (SVM) classifier optimized by a genetic evolutionary algorithm. RESULTS: The implemented algorithm in three different models reached up to 85% accuracy in classifying PDR and NPDR in all three levels of vascular density maps. The deep retinal layer vascular density map demonstrated the best performance with a 90% accuracy in discriminating between PDR and NPDR. CONCLUSIONS: The current study on a limited number of patients with diabetic retinopathy demonstrated that a supervised machine learning-based method known as SVM can be used to differentiate PDR and NPDR patients using OCTA vascular density maps.

Plasma Neurofilament Light Chain Levels Are Associated With Cortical Hypometabolism in Alzheimer Disease Signature Regions.

Neurofilament light chain (NFL) has been recently introduced as a biomarker of early dementia. 18-Fluorodeoxyglucose positron emission tomography (18F-FDG-PET) is a proxy for regional hypometabolism in Alzheimer disease (AD). Globally normalized 18F-FDG-PET values and levels of NFL and tau were obtained from 149 patients with mild cognitive impairment (MCI) from the baseline cohort of the Alzheimer's Disease Neuroimaging Initiative database. We adopted a stepwise partial correlation model using plasma NFL, plasma tau, CSF NFL, and regional cerebral metabolic rate of glucose (CMRGlc) as main variables, and age, sex, and Alzheimer's Disease Rating Scale (ADAS) as covariates. Significant regions were entered into a stepwise multiple regression analysis to investigate the independent correlation of each biomarker to baseline regional CMRGlc and its progression in patients with MCI. Higher baseline CSF NFL levels correlated with hypometabolism in bilateral precuneal and posterior cingulate cortex. After correction for age, sex, and ADAS score, plasma NFL levels correlated with hypometabolism in bilateral parahippocampal and middle temporal gyri. Cortical hypometabolism in bilateral parahippocampal gyri and right fusiform and middle temporal gyri was independently predicted by higher baseline plasma NFL levels in a multiple regression model. Plasma NFL promises to be an early biomarker of cortical hypometabolism in MCI and for MCI progression to AD.