Clusters of anatomical disease-burden patterns in ALS: a data-driven approach confirms radiological subtypes

Abstract

Amyotrophic lateral sclerosis (ALS) is associated with considerable clinical heterogeneity spanning from diverse disability profiles, differences in UMN/LMN involvement, divergent progression rates, to variability in frontotemporal dysfunction. A multitude of classification frameworks and staging systems have been proposed based on clinical and neuropsychological characteristics, but disease subtypes are seldom defined based on anatomical patterns of disease burden without a prior clinical stratification. A prospective research study was conducted with a uniform imaging protocol to ascertain disease subtypes based on preferential cerebral involvement. Fifteen brain regions were systematically evaluated in each participant based on a comprehensive panel of cortical, subcortical and white matter integrity metrics. Using min–max scaled composite regional integrity scores, a two-step cluster analysis was conducted. Two radiological clusters were identified; 35.5% of patients belonging to ‘Cluster 1’ and 64.5% of patients segregating to ‘Cluster 2’. Subjects in Cluster 1 exhibited marked frontotemporal change. Predictor ranking revealed the following hierarchy of anatomical regions in decreasing importance: superior lateral temporal, inferior frontal, superior frontal, parietal, limbic, mesial inferior temporal, peri-Sylvian, subcortical, long association fibres, commissural, occipital, ‘sensory’, ‘motor’, cerebellum, and brainstem. While the majority of imaging studies first stratify patients based on clinical criteria or genetic profiles to describe phenotype- and genotype-associated imaging signatures, a data-driven approach may identify distinct disease subtypes without a priori patient categorisation. Our study illustrates that large radiology datasets may be potentially utilised to uncover disease subtypes associated with unique genetic, clinical or prognostic profiles.

Hippocampal Metabolic Alterations in Amyotrophic Lateral Sclerosis: A Magnetic Resonance Spectroscopy Study

“…Another trend of “big data” interrogation in ALS is the implementation of various clustering approaches to unravel inherent, naturally occurring sub-groups or patient cohorts with distinctive characteristics. A number of recent imaging studies have confirmed the existence of radiological sub-phenotypes using cluster analyses of connectomics [ 108 ], functional [ 109 ], or structural [ 110 ] raw datasets. The inclusion of MRS data into similar clustering pipelines may further help to untangle the heterogeneity of ALS and identify subcohorts with distinctive radiological characteristics.…”

Thalamic pathology in frontotemporal dementia: Predilection for specific nuclei, phenotype‐specific signatures, clinical correlates, and practical relevance

“…Clustering strategies on large admixed imaging datasets have revealed clinically and radiologically distinct subgroups. For example, various clustering approaches have consistently captured a subcohort of patients with marked frontotemporal change among unselected ALS patients (Bede et al., 2022 ; Dukic et al., 2022 ; Tan et al., 2022 ). Clustering initiatives without a priori hypotheses may successfully uncover pathologically homogenous subgroups that may have distinctive genetic or clinical correlates (Tan et al., 2022 ).…”

The involvement of language‐associated networks, tracts, and cortical regions in frontotemporal dementia and amyotrophic lateral sclerosis: Structural and functional alterations

“…With the emergence of antisense oligonucleotide therapies, genotype‐associated changes are of particular interest in both ALS and FTD (Li Hi Shing, McKenna, et al., 2021 ; McKenna et al., 2022 ; Nigri et al., 2023 ). Cluster analyses of unselected patient cohorts often revealed subpopulations of patients with particularly severe frontotemporal or cerebellar change (Bede et al., 2022 ; Dukic et al., 2022 ; Tan et al., 2022 ). While C9orf72 hexanucleotide repeats in ALS are classically associated with marked frontotemporal dysfunction, a series of studies have highlighted that extra‐motor involvement is not unique to the C9orf72 genotype (Westeneng et al., 2016 ).…”