Development and validation of a deep learning algorithm based on fundus photographs for estimating the CAIDE dementia risk score

Oculomics: Current concepts and evidence

The eye provides novel insights into general health, as well as pathogenesis and development of systemic diseases. In the past decade, growing evidence has demonstrated that the eye's structure and function mirror multiple systemic health conditions, especially in cardiovascular diseases, neurodegenerative disorders, and kidney impairments. This has given rise to the field of oculomics-the application of ophthalmic biomarkers to understand mechanisms, detect and predict disease. The development of this field has been accelerated by three major advances: 1) the availability and widespread clinical adoption of high-resolution and non-invasive ophthalmic imaging ("hardware"); 2) the availability of large studies to interrogate associations ("big data"); 3) the development of novel analytical methods, including artificial intelligence (AI) ("software"). Oculomics offers an opportunity to enhance our understanding of the interplay between the eye and the body, while supporting development of innovative diagnostic, prognostic, and therapeutic tools. These advances have been further accelerated by developments in AI, coupled with large-scale linkage datasets linking ocular imaging data with systemic health data. Oculomics also enables the detection, screening, diagnosis, and monitoring of many systemic health conditions. Furthermore, oculomics with AI allows prediction of the risk of systemic diseases, enabling risk stratification, opening up new avenues for prevention or individualized risk prediction and prevention, facilitating personalized medicine. In this review, we summarise current concepts and evidence in the field of oculomics, highlighting the progress that has been made, remaining challenges, and the opportunities for future research.

Deep learning applications in vascular dementia using neuroimaging

PURPOSE OF REVIEW

Vascular dementia (VaD) is the second common cause of dementia after Alzheimer's disease, and deep learning has emerged as a critical tool in dementia research. The aim of this article is to highlight the current deep learning applications in VaD-related imaging biomarkers and diagnosis.

RECENT FINDINGS

The main deep learning technology applied in VaD using neuroimaging data is convolutional neural networks (CNN). CNN models have been widely used for lesion detection and segmentation, such as white matter hyperintensities (WMH), cerebral microbleeds (CMBs), perivascular spaces (PVS), lacunes, cortical superficial siderosis, and brain atrophy. Applications in VaD subtypes classification also showed excellent results. CNN-based deep learning models have potential for further diagnosis and prognosis of VaD.

SUMMARY

Deep learning neural networks with neuroimaging data in VaD research represent significant promise for advancing early diagnosis and treatment strategies. Ongoing research and collaboration between clinicians, data scientists, and neuroimaging experts are essential to address challenges and unlock the full potential of deep learning in VaD diagnosis and management.

Deep Learning and Machine Learning Algorithms for Retinal Image Analysis in Neurodegenerative Disease: Systematic Review of Datasets and Models

Purpose

Retinal images contain rich biomarker information for neurodegenerative disease. Recently, deep learning models have been used for automated neurodegenerative disease diagnosis and risk prediction using retinal images with good results.

Methods

In this review, we systematically report studies with datasets of retinal images from patients with neurodegenerative diseases, including Alzheimer's disease, Huntington's disease, Parkinson's disease, amyotrophic lateral sclerosis, and others. We also review and characterize the models in the current literature which have been used for classification, regression, or segmentation problems using retinal images in patients with neurodegenerative diseases.

Results

Our review found several existing datasets and models with various imaging modalities primarily in patients with Alzheimer's disease, with most datasets on the order of tens to a few hundred images. We found limited data available for the other neurodegenerative diseases. Although cross-sectional imaging data for Alzheimer's disease is becoming more abundant, datasets with longitudinal imaging of any disease are lacking.

Conclusions

The use of bilateral and multimodal imaging together with metadata seems to improve model performance, thus multimodal bilateral image datasets with patient metadata are needed. We identified several deep learning tools that have been useful in this context including feature extraction algorithms specifically for retinal images, retinal image preprocessing techniques, transfer learning, feature fusion, and attention mapping. Importantly, we also consider the limitations common to these models in real-world clinical applications.

Translational Relevance

This systematic review evaluates the deep learning models and retinal features relevant in the evaluation of retinal images of patients with neurodegenerative disease.

CAIDE Score, Alzheimer's Disease Pathology, and Cognition in Cognitively Normal Adults: The CABLE Study

Background

Cardiovascular Risk Factors, Ageing and Dementia (CAIDE) risk score serves as a credible predictor of an individual's risk of dementia. However, studies on the link of the CAIDE score to Alzheimer's disease (AD) pathology are scarce.

Objective

To explore the links of CAIDE score to cerebrospinal fluid (CSF) biomarkers of AD as well as to cognitive performance.

Methods

In the Chinese Alzheimer's Biomarker and LifestylE (CABLE) study, we recruited 600 cognitively normal participants. Correlations between the CAIDE score and CSF biomarkers of AD as well as cognitive performance were probed through multiple linear regression models. Whether the correlation between CAIDE score and cognitive performance was mediated by AD pathology was researched by means of mediation analyses.

Results

Linear regression analyses illustrated that CAIDE score was positively associated with tau-related biomarkers, including pTau (p < 0.001), tTau (p < 0.001), as well as tTau/Aβ42 (p = 0.008), while it was in negative association with cognitive scores, consisting of MMSE score (p < 0.001) as well as MoCA score (p < 0.001). The correlation from CAIDE score to cognitive scores was in part mediated by tau pathology, with a mediation rate varying from 3.2% to 13.2%.

Conclusions

A higher CAIDE score, as demonstrated in our study, was linked to more severe tau pathology and poorer cognitive performance, and tau pathology mediated the link of CAIDE score to cognitive performance. Increased dementia risk will lead to cognitive decline through aggravating neurodegeneration.

Preventing Dementia-A Cross-Sectional Study of Outpatients in a Tertiary Internal Medicine Department

Dementia is a significant health problem worldwide, being the seventh leading cause of death (2,382,000 deaths worldwide in 2016). Recent data suggest there are several modifiable risk factors that, if addressed, can decrease dementia risk. Several national dementia screening programs exist; however, limited-income countries do not have the means to implement such measures. We performed a prospective cross-sectional study in an outpatient department to identify individuals at risk for dementia. Patients with no known cognitive dysfunction seeking a medical consult were screened for dementia risk by means of the cardiovascular risk factors, ageing, and dementia (CAIDE) and modified CAIDE tests. Additionally, we collected demographic and clinical data and assessed each participant for depression, mental state, and ability to perform daily activities. Of the 169 patients enrolled, 63.3% were identified as being in the intermediate-risk or high-risk group, scoring more than seven points on the mCAIDE test. Over 40% of the elderly individuals in the study were assessed as "somewhat depressed" or "depressed" on the geriatric depression scale. Almost 10% of the study population was diagnosed de novo with cognitive dysfunction. In conclusion, using a simple questionnaire such as the mCAIDE in a predefined high-risk population is easy and does not represent a major financial burden. At-risk individuals can subsequently benefit from personalized interventions that are more likely to be successful. Limited-resource countries can implement such screening tools in outpatient clinics.