Cluster Analysis of Cortical Amyloid Burden for Identifying Imaging-driven Subtypes in Mild Cognitive Impairment.

Over the past decade, Alzheimer's disease (AD) has become increasingly severe and gained greater attention. Mild Cognitive Impairment (MCI) serves as an important prodromal stage of AD, highlighting the urgency of early diagnosis for timely treatment and control of the condition. Identifying the subtypes of MCI patients exhibits importance for dissecting the heterogeneity of this complex disorder and facilitating more effective target discovery and therapeutic development. Conventional method uses clinical measurements such as cognitive score and neurophysical assessment to stratify MCI patients into two groups with early MCI (EMCI) and late MCI (LMCI), which shows their progressive stages. However, such clinical method is not designed to de-convolute the heterogeneity of the disorder. This study uses a data-driven approach to divide MCI patients into a novel grouping of two subtypes based on an amyloid dataset of 68 cortical features from positron emission tomography (PET), where each subtype has a homogeneous cortical amyloid burden pattern. Experimental evaluation including visual two-dimensional cluster distribution, Kaplan-Meier plot, genetic association studies, and biomarker distribution analysis demonstrates that the identified subtypes performs better across all metrics than the conventional EMCI and LMCI grouping.

PFERM: A Fair Empirical Risk Minimization Approach with Prior Knowledge.

Fairness is crucial in machine learning to prevent bias based on sensitive attributes in classifier predictions. However, the pursuit of strict fairness often sacrifices accuracy, particularly when significant prevalence disparities exist among groups, making classifiers less practical. For example, Alzheimer's disease (AD) is more prevalent in women than men, making equal treatment inequitable for females. Accounting for prevalence ratios among groups is essential for fair decision-making. In this paper, we introduce prior knowledge for fairness, which incorporates prevalence ratio information into the fairness constraint within the Empirical Risk Minimization (ERM) framework. We develop the Prior-knowledge-guided Fair ERM (PFERM) framework, aiming to minimize expected risk within a specified function class while adhering to a prior-knowledge-guided fairness constraint. This approach strikes a flexible balance between accuracy and fairness. Empirical results confirm its effectiveness in preserving fairness without compromising accuracy.

Comparing Amyloid Imaging Normalization Strategies for Alzheimer's Disease Classification using an Automated Machine Learning Pipeline.

Amyloid imaging has been widely used in Alzheimer's disease (AD) diagnosis and biomarker discovery through detecting the regional amyloid plaque density. It is essential to be normalized by a reference region to reduce noise and artifacts. To explore an optimal normalization strategy, we employ an automated machine learning (AutoML) pipeline, STREAMLINE, to conduct the AD diagnosis binary classification and perform permutation-based feature importance analysis with thirteen machine learning models. In this work, we perform a comparative study to evaluate the prediction performance and biomarker discovery capability of three amyloid imaging measures, including one original measure and two normalized measures using two reference regions (i.e., the whole cerebellum and the composite reference region). Our AutoML results indicate that the composite reference region normalization dataset yields a higher balanced accuracy, and identifies more AD-related regions based on the fractioned feature importance ranking.

Exploring Automated Machine Learning for Cognitive Outcome Prediction from Multimodal Brain Imaging using STREAMLINE.

STREAMLINE is a simple, transparent, end-to-end automated machine learning (AutoML) pipeline for easily conducting rigorous machine learning (ML) modeling and analysis. The initial version is limited to binary classification. In this work, we extend STREAMLINE through implementing multiple regression-based ML models, including linear regression, elastic net, group lasso, and L21 norm. We demonstrate the effectiveness of the regression version of STREAMLINE by applying it to the prediction of Alzheimer's disease (AD) cognitive outcomes using multimodal brain imaging data. Our empirical results demonstrate the feasibility and effectiveness of the newly expanded STREAMLINE as an AutoML pipeline for evaluating AD regression models, and for discovering multimodal imaging biomarkers.

Mining Regional Imaging Genetic Associations via Voxel-wise Enrichment Analysis.

Brain imaging genetics aims to reveal genetic effects on brain phenotypes, where most studies examine phenotypes defined on anatomical or functional regions of interest (ROIs) given their biologically meaningful annotation and modest dimensionality compared with voxel-wise approaches. Typical ROI-level measures used in these studies are summary statistics from voxel-wise measures in the region, without making full use of individual voxel signals. In this paper, we propose a flexible and powerful framework for mining regional imaging genetic associations via voxel-wise enrichment analysis, which embraces the collective effect of weak voxel-level signals within an ROI. We demonstrate our method on an imaging genetic analysis using data from the Alzheimers Disease Neuroimaging Initiative, where we assess the collective regional genetic effects of voxel-wise FDGPET measures between 116 ROIs and 19 AD candidate SNPs. Compared with traditional ROI-wise and voxel-wise approaches, our method identified 102 additional significant associations, some of which were further supported by evidences in brain tissue-specific expression analysis. This demonstrates the promise of the proposed method as a flexible and powerful framework for exploring imaging genetic effects on the brain.

Cognitive impairment in older patients with breast cancer before systemic therapy: is there an interaction between cancer and comorbidity?

PURPOSE: To determine if older patients with breast cancer have cognitive impairment before systemic therapy. PATIENTS AND METHODS: Participants were patients with newly diagnosed nonmetastatic breast cancer and matched friend or community controls age > 60 years without prior systemic treatment, dementia, or neurologic disease. Participants completed surveys and a 55-minute battery of 17 neuropsychological tests. Biospecimens were obtained for APOE genotyping, and clinical data were abstracted. Neuropsychological test scores were standardized using control means and standard deviations (SDs) and grouped into five domain z scores. Cognitive impairment was defined as any domain z score two SDs below or ≥ two z scores 1.5 SDs below the control mean. Multivariable analyses evaluated pretreatment differences considering age, race, education, and site; comparisons between patient cases also controlled for surgery. RESULTS: The 164 patient cases and 182 controls had similar neuropsychological domain scores. However, among patient cases, those with stage II to III cancers had lower executive function compared with those with stage 0 to I disease, after adjustment (P = .05). The odds of impairment were significantly higher among older, nonwhite, less educated women and those with greater comorbidity, after adjustment. Patient case or control status, anxiety, depression, fatigue, and surgery were not associated with impairment. However, there was an interaction between comorbidity and patient case or control status; comorbidity was strongly associated with impairment among patient cases (adjusted odds ratio, 8.77; 95% CI, 2.06 to 37.4; P = .003) but not among controls (P = .97). Only diabetes and cardiovascular disease were associated with impairment among patient cases. CONCLUSION: There were no overall differences between patients with breast cancer and controls before systemic treatment, but there may be pretreatment cognitive impairment within subgroups of patient cases with greater tumor or comorbidity burden.