Alzheimer's disease detection using data fusion with a deep supervised encoder.

Alzheimer's disease (AD) is affecting a growing number of individuals. As a result, there is a pressing need for accurate and early diagnosis methods. This study aims to achieve this goal by developing an optimal data analysis strategy to enhance computational diagnosis. Although various modalities of AD diagnostic data are collected, past research on computational methods of AD diagnosis has mainly focused on using single-modal inputs. We hypothesize that integrating, or "fusing," various data modalities as inputs to prediction models could enhance diagnostic accuracy by offering a more comprehensive view of an individual's health profile. However, a potential challenge arises as this fusion of multiple modalities may result in significantly higher dimensional data. We hypothesize that employing suitable dimensionality reduction methods across heterogeneous modalities would not only help diagnosis models extract latent information but also enhance accuracy. Therefore, it is imperative to identify optimal strategies for both data fusion and dimensionality reduction. In this paper, we have conducted a comprehensive comparison of over 80 statistical machine learning methods, considering various classifiers, dimensionality reduction techniques, and data fusion strategies to assess our hypotheses. Specifically, we have explored three primary strategies: (1) Simple data fusion, which involves straightforward concatenation (fusion) of datasets before inputting them into a classifier; (2) Early data fusion, in which datasets are concatenated first, and then a dimensionality reduction technique is applied before feeding the resulting data into a classifier; and (3) Intermediate data fusion, in which dimensionality reduction methods are applied individually to each dataset before concatenating them to construct a classifier. For dimensionality reduction, we have explored several commonly-used techniques such as principal component analysis (PCA), autoencoder (AE), and LASSO. Additionally, we have implemented a new dimensionality-reduction method called the supervised encoder (SE), which involves slight modifications to standard deep neural networks. Our results show that SE substantially improves prediction accuracy compared to PCA, AE, and LASSO, especially in combination with intermediate fusion for multiclass diagnosis prediction.

Improving clinical efficiency in screening for cognitive impairment due to Alzheimer's.

INTRODUCTION: To reduce demands on expert time and improve clinical efficiency, we developed a framework to evaluate whether inexpensive, accessible data could accurately classify Alzheimer's disease (AD) clinical diagnosis and predict the likelihood of progression. METHODS: We stratified relevant data into three tiers: obtainable at primary care (low-cost), mostly available at specialty visits (medium-cost), and research-only (high-cost). We trained several machine learning models, including a hierarchical model, an ensemble model, and a clustering model, to distinguish between diagnoses of cognitively unimpaired, mild cognitive impairment, and dementia due to AD. RESULTS: All models showed viable classification, but the hierarchical and ensemble models outperformed the conventional model. Classifier "error" was predictive of progression rates, and cluster membership identified subgroups with high and low risk of progression within 1.5 to 3 years. DISCUSSION: Accessible, inexpensive clinical data can be used to guide AD diagnosis and are predictive of current and future disease states. HIGHLIGHTS: Classification performance using cost-effective features was accurate and robustHierarchical classification outperformed conventional multinomial classificationClassification labels indicated significant changes in conversion risk at follow-upA clustering-classification method identified subgroups at high risk of decline.

Regional Cortical Thickness Predicts Top Cognitive Performance in the Elderly.

While aging is typically associated with cognitive decline, some individuals are able to diverge from the characteristic downward slope and maintain very high levels of cognitive performance. Prior studies have found that cortical thickness in the cingulate cortex, a region involved in information processing, memory, and attention, distinguish those with exceptional cognitive abilities when compared to their cognitively more typical elderly peers. Others major areas outside of the cingulate, such as the prefrontal cortex and insula, are also key in successful aging well into late age, suggesting that structural properties across a wide range of areas may better explain differences in cognitive abilities. Here, we aim to assess the role of regional cortical thickness, both in the cingulate and the whole brain, in modeling Top Cognitive Performance (TCP), measured by performance in the top 50th percentile of memory and executive function. Using data from National Alzheimer's Coordinating Center and The 90 + Study, we examined healthy subjects aged 70-100 years old. We found that, while thickness in cingulate regions can model TCP status with some degree of accuracy, a whole-brain, network-level approach out-performed the localist, cingulate models. These findings suggests a need for more network-style approaches and furthers our understanding of neurobiological factors contributing to preserved cognition.