Multimodal in vivo staging in amyotrophic lateral sclerosis using artificial intelligence

Abstract

Background The underlying neuropathological process of amyotrophic lateral sclerosis (ALS) can be classified in a four‐stage sequential pTDP‐43 cerebral propagation scheme. Using diffusion tensor imaging (DTI), in vivo imaging of these stages has already been shown to be feasible for the specific corticoefferent tract systems. Because both cognitive and oculomotor dysfunctions are associated with microstructural changes at the brain level in ALS, a cognitive and an oculomotor staging classification were developed, respectively. The association of these different in vivo staging schemes has not been attempted to date. Methods A total of 245 patients with ALS underwent DTI, video‐oculography, and cognitive testing using Edinburgh Cognitive and Behavioral ALS Screen (ECAS). A set of tract‐related diffusion metrics, cognitive, and oculomotor parameters was selected for further analysis. Hierarchical and k‐means clustering algorithms were used to obtain an optimal cluster solution. Results According to cluster analysis, differentiation of patients with ALS into four clusters resulted: Cluster A showed the highest fractional anisotropy (FA) values and thereby the best performances in executive oculomotor tasks and cognitive tests, whereas cluster D showed the lowest FA values, the lowest ECAS scores, and the worst executive oculomotor performance across all clusters. Clusters B and C showed intermediate results regarding parameter values. Discussion In a multimodal dataset of technical assessments of brain structure and function in ALS, an artificial intelligence‐based cluster analysis showed high congruence of DTI, executive oculomotor function, and neuropsychological performance for mapping in vivo correlates of neuropathological spreading.

Presymptomatic grey matter alterations in ALS kindreds: a computational neuroimaging study of asymptomatic C9orf72 and SOD1 mutation carriers

“…The utility of machine learning (ML) has already been demonstrated in a variety of prognostic and diagnostic applications in ALS [ 85 – 87 ]. Imaging-based ML models in ALS increasingly include subcortical measures [ 88 – 91 ] in addition to cortical grey matter and cerebral white matter metrics [ 92 – 95 ]. Feature importance analyses and cluster analyses consistently confirmed the discriminatory potential of subcortical indices and integrity metrics of networks relayed through subcortical nuclei [ 96 , 97 ].…”

Editorial: The gap between academic advances and therapy development in motor neuron disease

“…Where academic studies describe 'typical' disease burden patterns and 'representative' longitudinal trajectories inferred from hundreds of patients, the quest of a clinician is accurately classifying a single patient into relevant diagnostic, phenotypic and prognostic categories. Accordingly, numerous machine-learning initiatives have been published recently using a variety of models to categorize patients into clinically relevant subgroups [35][36][37][38][39]. Although these have shown promise to discriminate patients from controls, the distinction of patients from 'disease controls' proved more challenging [40], and the search for reliable prognostic indicators also continues [41][42][43].…”