Survival prediction models in motor neuron disease

Abstract

Background and purpose This study aimed to assess the predictive value of multimodal brain magnetic resonance imaging (MRI) on survival in a large cohort of patients with motor neuron disease (MND), in combination with clinical and cognitive features. Methods Two hundred MND patients were followed up prospectively for a median of 4.13 years. At baseline, subjects underwent neurological examination, cognitive assessment and brain MRI. Grey matter volumes of cortical and subcortical structures and diffusion tensor MRI metrics of white matter tracts were obtained. A multivariable Royston–Parmar survival model was created using clinical and cognitive variables. The increase of survival prediction accuracy provided by MRI variables was assessed. Results The multivariable clinical model included predominant upper or lower motor neuron presentations and diagnostic delay as significant prognostic predictors, reaching an area under the receiver operating characteristic curve (AUC) of a 4‐year survival prediction of 0.79. The combined clinical and MRI model including selected grey matter fronto‐temporal volumes and diffusion tensor MRI metrics of the corticospinal and extra‐motor tracts reached an AUC of 0.89. Considering amyotrophic lateral sclerosis patients only, the clinical model including diagnostic delay and semantic fluency scores provided an AUC of 0.62, whereas the combined clinical and MRI model reached an AUC of 0.77. Conclusion Our study demonstrated that brain MRI measures of motor and extra‐motor structural damage, when combined with clinical and cognitive features, are useful predictors of survival in patients with MND, particularly when a diagnosis of amyotrophic lateral sclerosis is made.

Language impairment in motor neuron disease phenotypes different from classical amyotrophic lateral sclerosis: a review

“…(2013), Spinelli et al .’s (2016) investigation took into account highly heterogeneous patients as far as etiology is concerned. In the study by Agosta et al . (2019) [see above, 3.2.2.…”

“…Since N =4 UMND patients were classified as NECI, whereas N =7 as NCCI, it cannot be ruled out that some of them presented with language impairment. In a third study, the Authors [Agosta et al . 2019] administered BADA object- and action-naming sub-tests to a large cohort of MND patients including classical ALS, prUMND and prLMND patients [Chiò et al ., 2011].…”

“…Furthermore, it must be taken into consideration that, in some of the studies included [ e . g ., Gallassi et al ., 1985; Consonni et al ., 2013; Spinelli et al ., 2016; 2019], a considerable within-cohort heterogeneity could be detected – e . g ., patients falling under the same classification ( e .…”

Development and validation of a 1-year survival prognosis estimation model for Amyotrophic Lateral Sclerosis using manifold learning algorithm UMAP

“…Additional clinical features, such as upper or lower limb onset, upper or lower motor neuron predominance, may be potential predictors to improve our model further. The inclusion of biological, genetic 33 , and imaging features 14 , 34 are likely to have improved current prognosis modelling 35 . In our study, overall survival was only regarded as a secondary outcome as global survival was not available in most cases.…”

Identification of Amyotrophic Lateral Sclerosis Based on Diffusion Tensor Imaging and Support Vector Machine

“…Furthermore, DTI measurement may have an improved potential role in the correct discrimination of ALS when combined with other neuroimaging biomarkers (such as cortical thickness and functional measurement) (10,12). In addition, adopting diffusion measuring and high-resolution volumetric/surface imaging simultaneously, researchers have demonstrated the feasibility of multi-model neuroimaging for predicting survival of ALS patients (13,14).…”