Robust Discovery of Mild Cognitive Impairment Subtypes and Their Risk of Alzheimer's Disease Conversion Using Unsupervised Machine Learning and Gaussian Mixture Modeling

Identification of disease-specific bio-markers through network-based analysis of gene co-expression: A case study on Alzheimer's disease

Finding biomarker genes for complex diseases attracts persistent attention due to its application in clinics. In this paper, we propose a network-based method to obtain a set of biomarker genes. The key idea is to construct a gene co-expression network among sensitive genes and cluster the genes into different modules. For each module, we can identify its representative, i.e., the gene with the largest connectivity and the smallest average shortest path length to other genes within the module. We believe these representative genes could serve as a new set of potential biomarkers for diseases. As a typical example, we investigated Alzheimer's disease, obtaining a total of 16 potential representative genes, three of which belong to the non-transcriptome. A total of 11 out of these genes are found in literature from different perspectives and methods. The incipient groups were classified into two different subtypes using machine learning algorithms. We subjected the two subtypes to Gene Ontology analysis and Kyoto Encyclopedia of Genes and Genomes analysis with healthy groups and moderate groups, respectively. The two sub-type groups were involved in two different biological processes, demonstrating the validity of this approach. This method is disease-specific and independent; hence, it can be extended to classify other kinds of complex diseases.

Robustly uncovering the heterogeneity of neurodegenerative disease by using data-driven subtyping in neuroimaging: A review

Neurodegenerative diseases are associated with heterogeneity in genetics, pathology, and clinical manifestation. Understanding this heterogeneity is particularly relevant for clinical prognosis and stratifying patients for disease modifying treatments. Recently, data-driven methods based on neuroimaging have been applied to investigate the subtyping of neurodegenerative disease, helping to disentangle this heterogeneity. We reviewed brain-based subtyping studies in aging and representative neurodegenerative diseases, including Alzheimer's disease, mild cognitive impairment, frontotemporal dementia, and Lewy body dementia, from January 2000 to November 2022. We summarized clustering methods, validation, robustness, reproducibility, and clinical relevance of 71 eligible studies in the present study. We found vast variations in approaches between studies, including ten neuroimaging modalities, 24 cluster algorithms, and 41 methods of cluster number determination. The clinical relevance of subtyping studies was evaluated by summarizing the analysis method of clinical measurements, showing a relatively low clinical utility in the current studies. Finally, we conclude that future studies of heterogeneity in neurodegenerative disease should focus on validation, comparison between subtyping approaches, and prioritise clinical utility.

Artificial intelligence for dementia prevention

INTRODUCTION

A wide range of modifiable risk factors for dementia have been identified. Considerable debate remains about these risk factors, possible interactions between them or with genetic risk, and causality, and how they can help in clinical trial recruitment and drug development. Artificial intelligence (AI) and machine learning (ML) may refine understanding.

METHODS

ML approaches are being developed in dementia prevention. We discuss exemplar uses and evaluate the current applications and limitations in the dementia prevention field.

RESULTS

Risk-profiling tools may help identify high-risk populations for clinical trials; however, their performance needs improvement. New risk-profiling and trial-recruitment tools underpinned by ML models may be effective in reducing costs and improving future trials. ML can inform drug-repurposing efforts and prioritization of disease-modifying therapeutics.

DISCUSSION

ML is not yet widely used but has considerable potential to enhance precision in dementia prevention.

HIGHLIGHTS

Artificial intelligence (AI) is not widely used in the dementia prevention field. Risk-profiling tools are not used in clinical practice. Causal insights are needed to understand risk factors over the lifespan. AI will help personalize risk-management tools for dementia prevention. AI could target specific patient groups that will benefit most for clinical trials.

A graph theoretic approach to neurodegeneration: five data-driven neuropsychological subtypes in mild cognitive impairment

Mild cognitive Impairment (MCI) is notoriously heterogenous in terms of clinical presentation, neuroimaging correlates, and subsequent progression. Predicting who will progress to dementia, which type of dementia, and over what timeframe is challenging. Previous work has attempted to identify MCI subtypes using neuropsychological measures in an effort to address this challenge; however, there is no consensus on approach, which may account for some of the variability. Using a hierarchical community detection approach, we examined cognitive subtypes within an MCI sample (from the Alzheimer's Disease Neuroimaging Initiative [ADNI] study). We then examined whether these subtypes were related to biomarkers (e.g., cortical volumes, fluorodeoxyglucose (FDG)-positron emission tomography (PET) hypometabolism) or clinical progression. We identified five communities (i.e., cognitive subtypes) within the MCI sample: 1) predominantly memory impairment, 2) predominantly language impairment, 3) cognitively normal, 4) multidomain, with notable executive dysfunction, 5) multidomain, with notable processing speed impairment. Community membership was significantly associated with 1) cortical volume in the hippocampus, entorhinal cortex, and fusiform cortex; 2) FDG PET hypometabolism in the posterior cingulate, angular gyrus, and inferior/middle temporal gyrus; and 3) conversion to dementia at follow up. Overall, community detection as an approach appears a viable method for identifying unique cognitive subtypes in a neurodegenerative sample that were linked to several meaningful biomarkers and modestly with progression at one year follow up.

Comorbidity-driven multi-modal subtype analysis in mild cognitive impairment of Alzheimer's disease

BACKGROUND

Mild cognitive impairment (MCI) is a heterogeneous condition with high individual variabilities in clinical outcomes driven by patient demographics, genetics, brain structure features, blood biomarkers, and comorbidities. Multi-modality data-driven approaches have been used to discover MCI subtypes; however, disease comorbidities have not been included as a modality though multiple diseases including hypertension are well-known risk factors for Alzheimer's disease (AD). The aim of this study was to examine MCI heterogeneity in the context of AD-related comorbidities along with other AD-relevant features and biomarkers.

METHODS

A total of 325 MCI subjects with 32 AD-relevant comorbidities and features were considered. Mixed-data clustering is applied to discover and compare MCI subtypes with and without including AD-related comorbidities. Finally, the relevance of each comorbidity-driven subtype was determined by examining their MCI to AD disease prognosis, descriptive statistics, and conversion rates.

RESULTS

We identified four (five) MCI subtypes: poor-, average-, good-, and best-AD prognosis by including comorbidities (without including comorbidities). We demonstrated that comorbidity-driven MCI subtypes differed from those identified without comorbidity information. We further demonstrated the clinical relevance of comorbidity-driven MCI subtypes. Among the four comorbidity-driven MCI subtypes there were substantial differences in the proportions of participants who reverted to normal function, remained stable, or converted to AD. The groups showed different behaviors, having significantly different MCI to AD prognosis, significantly different means for cognitive test-related and plasma features, and by the proportion of comorbidities.

CONCLUSIONS

Our study indicates that AD comorbidities should be considered along with other diverse AD-relevant characteristics to better understand MCI heterogeneity.

Uncovering heterogeneous cognitive trajectories in mild cognitive impairment: a data-driven approach

BACKGROUND

Given the complex and progressive nature of mild cognitive impairment (MCI), the ability to delineate and understand the heterogeneous cognitive trajectories is crucial for developing personalized medicine and informing trial design. The primary goals of this study were to examine whether different cognitive trajectories can be identified within subjects with MCI and, if present, to characterize each trajectory in relation to changes in all major Alzheimer's disease (AD) biomarkers over time.

METHODS

Individuals with a diagnosis of MCI at the first visit and ≥ 1 follow-up cognitive assessment were selected from the Alzheimer's Disease Neuroimaging Initiative database (n = 936; age 73 ± 8; 40% female; 16 ± 3 years of education; 50% APOE4 carriers). Based on the Alzheimer's Disease Assessment Scale-Cognitive Subscale-13 (ADAS-Cog-13) total scores from baseline up to 5 years follow-up, a non-parametric k-means longitudinal clustering method was performed to obtain clusters of individuals with similar patterns of cognitive decline. We further conducted a series of linear mixed-effects models to study the associations of cluster membership with longitudinal changes in other cognitive measures, neurodegeneration, and in vivo AD pathologies.

RESULTS

Four distinct cognitive trajectories emerged. Cluster 1 consisted of 255 individuals (27%) with a nearly non-existent rate of change in the ADAS-Cog-13 over 5 years of follow-up and a healthy-looking biomarker profile. Individuals in the cluster 2 (n = 336, 35%) and 3 (n = 240, 26%) groups showed relatively mild and moderate cognitive decline trajectories, respectively. Cluster 4, comprising about 11% of our study sample (n = 105), exhibited an aggressive cognitive decline trajectory and was characterized by a pronouncedly abnormal biomarker profile.

CONCLUSIONS

Individuals with MCI show substantial heterogeneity in cognitive decline. Our findings may potentially contribute to improved trial design and patient stratification.