Unsupervised Machine Learning to Identify Separable Clinical Alzheimer’s Disease Sub-Populations

Abstract

Heterogeneity among Alzheimer’s disease (AD) patients confounds clinical trial patient selection and therapeutic efficacy evaluation. This work defines separable AD clinical sub-populations using unsupervised machine learning. Clustering (t-SNE followed by k-means) of patient features and association rule mining (ARM) was performed on the ADNIMERGE dataset from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Patient sociodemographics, brain imaging, biomarkers, cognitive tests, and medication usage were included for analysis. Four AD clinical sub-populations were identified using between-cluster mean fold changes [cognitive performance, brain volume]: cluster-1 represented least severe disease [+17.3, +13.3]; cluster-0 [−4.6, +3.8] and cluster-3 [+10.8, −4.9] represented mid-severity sub-populations; cluster-2 represented most severe disease [−18.4, −8.4]. ARM assessed frequently occurring pharmacologic substances within the 4 sub-populations. No drug class was associated with the least severe AD (cluster-1), likely due to lesser antecedent disease. Anti-hyperlipidemia drugs associated with cluster-0 (mid-severity, higher volume). Interestingly, antioxidants vitamin C and E associated with cluster-3 (mid-severity, higher cognition). Anti-depressants like Zoloft associated with most severe disease (cluster-2). Vitamin D is protective for AD, but ARM identified significant underutilization across all AD sub-populations. Identification and feature characterization of four distinct AD sub-population “clusters” using standard clinical features enhances future clinical trial selection criteria and cross-study comparative analysis.

Alzheimer’s Disease Classification Using Cluster-based Labelling for Graph Neural Network on Heterogeneous Data

“…It is interesting to speculate that the Young-FH could be due to relatively younger participants who were concerned about their own health given that their parents had a history of AD. The 2 gender specific clusters identified seemed to be in line with previous studies (Gamberger et al, 2016; Prakash et al, 2021, Alexander et al, 2020; Alexander et al, 2021). Cluster AD membership was associated with having 2 copies of APoE ε4 allele or had high tau level in the left fusiform cortex, consistent with genetic risk factor (e.g.…”

“…amyloid PET, and the recent approval of its use by the U.S. FDA (Jie et al, 2021). Importantly, these studies, together with the literature on unsupervised learning approaches applied to AD (Gamberger et al, 2016; Gamberger et al, 2017; Martí-Juan et al, 2019; Ferreira et al, 2019; Alashwal et al, 2019; Wang et al, 2021; Katabathula et al, 2021; Prakash et al, 2021, Alexander et al, 2020; Alexander et al, 2021; Prakash et al, 2021), have not used cluster-based class re-labelling for GNN’s classification of AD. Here, we have made use of the robust auto-metric GNN model by Song et al (2021).…”

“…Alashwal et al, 2019; Wang et al, 2021; Katabathula et al, 2021). In particular, some studies using clustering methods had identified sub-populations that were relatively homogeneous based on clinical and biological features (Gamberger et al, 2016; Martí-Juan et al, 2019; Ferreira et al, 2019; Prakash et al, 2021, Alexander et al, 2020; Alexander et al, 2021), differing rates of cognitive decline of sub-groups of prodromal AD patients (Gamberger et al, 2017; Alexander et al, 2020; Alexander et al, 2021), and for stratifying treatments (Prakash et al, 2021).…”

Optimizations for Computing Relatedness in Biomedical Heterogeneous Information Networks: SemNet 2.0

“…As researchers delved deeper into the disease, the breadth of risk factors across various domains, such as pharmaceuticals, antecedent disease, psychological profile, and lifestyle, has further increased overall complexity of AD investigation [ 27 , 29 , 30 ]. This complexity is exacerbated by the difficulty of defining AD sub-populations, a problem that impacts clinical trial patient selection and therapeutic evaluation [ 31 ]. Given AD’s heterogeneous nature, traditional bioinformatics solutions struggle where the SemNet framework thrives.…”

“…Amyloid was chosen as a known “control”, where the relationship between amyloid and Alzheimer’s disease is well known and validated; therefore, amyloid has many paths and metapaths connecting it to AD [ 32 ]. Insulin and hypothyroidism were chosen to assess a newer hypothesis that metabolic syndromes may play a significant role in the onset risk or outcome of AD [ 31 , 33 ]. The nodes of insulin and hypothyroidism have sufficient connections to AD to be considered relevant but are distant enough, domain wise, to showcase SemNet’s flexibility in exploring more nuanced, and lesser cited multi-factorial disease etiology [ 34 , 35 ].…”