Survival prediction models in motor neuron disease

From use of omics to systems biology: Identifying therapeutic targets for amyotrophic lateral sclerosis

Amyotrophic lateral sclerosis (ALS) is a heterogeneous progressive neurodegenerative disorder with available treatments such as riluzole and edaravone extending survival by an average of 3-6 months. The lack of highly effective, widely available therapies reflects the complexity of ALS. Omics technologies, including genomics, transcriptomic and proteomics have contributed to the identification of biological pathways dysregulated and targeted by therapeutic strategies in preclinical and clinical trials. Integrating clinical, environmental and neuroimaging information with omics data and applying a systems biology approach can further improve our understanding of the disease with the potential to stratify patients and provide more personalised medicine. This chapter will review the omics technologies that contribute to a systems biology approach and how these components have assisted in identifying therapeutic targets. Current strategies, including the use of genetic screening and biosampling in clinical trials, as well as the future application of additional technological advances, will also be discussed.

Toward diffusion tensor imaging as a biomarker in neurodegenerative diseases: technical considerations to optimize recordings and data processing

Neuroimaging biomarkers have shown high potential to map the disease processes in the application to neurodegenerative diseases (NDD), e.g., diffusion tensor imaging (DTI). For DTI, the implementation of a standardized scanning and analysis cascade in clinical trials has potential to be further optimized. Over the last few years, various approaches to improve DTI applications to NDD have been developed. The core issue of this review was to address considerations and limitations of DTI in NDD: we discuss suggestions for improvements of DTI applications to NDD. Based on this technical approach, a set of recommendations was proposed for a standardized DTI scan protocol and an analysis cascade of DTI data pre-and postprocessing and statistical analysis. In summary, considering advantages and limitations of the DTI in NDD we suggest improvements for a standardized framework for a DTI-based protocol to be applied to future imaging studies in NDD, towards the goal to proceed to establish DTI as a biomarker in clinical trials in neurodegeneration.

Artificial intelligence and statistical methods for stratification and prediction of progression in amyotrophic lateral sclerosis: A systematic review

BACKGROUND

Amyotrophic Lateral Sclerosis (ALS) is a fatal neurodegenerative disorder characterised by the progressive loss of motor neurons in the brain and spinal cord. The fact that ALS's disease course is highly heterogeneous, and its determinants not fully known, combined with ALS's relatively low prevalence, renders the successful application of artificial intelligence (AI) techniques particularly arduous.

OBJECTIVE

This systematic review aims at identifying areas of agreement and unanswered questions regarding two notable applications of AI in ALS, namely the automatic, data-driven stratification of patients according to their phenotype, and the prediction of ALS progression. Differently from previous works, this review is focused on the methodological landscape of AI in ALS.

METHODS

We conducted a systematic search of the Scopus and PubMed databases, looking for studies on data-driven stratification methods based on unsupervised techniques resulting in (A) automatic group discovery or (B) a transformation of the feature space allowing patient subgroups to be identified; and for studies on internally or externally validated methods for the prediction of ALS progression. We described the selected studies according to the following characteristics, when applicable: variables used, methodology, splitting criteria and number of groups, prediction outcomes, validation schemes, and metrics.

RESULTS

Of the starting 1604 unique reports (2837 combined hits between Scopus and PubMed), 239 were selected for thorough screening, leading to the inclusion of 15 studies on patient stratification, 28 on prediction of ALS progression, and 6 on both stratification and prediction. In terms of variables used, most stratification and prediction studies included demographics and features derived from the ALSFRS or ALSFRS-R scores, which were also the main prediction targets. The most represented stratification methods were K-means, and hierarchical and expectation-maximisation clustering; while random forests, logistic regression, the Cox proportional hazard model, and various flavours of deep learning were the most widely used prediction methods. Predictive model validation was, albeit unexpectedly, quite rarely performed in absolute terms (leading to the exclusion of 78 eligible studies), with the overwhelming majority of included studies resorting to internal validation only.

CONCLUSION

This systematic review highlighted a general agreement in terms of input variable selection for both stratification and prediction of ALS progression, and in terms of prediction targets. A striking lack of validated models emerged, as well as a general difficulty in reproducing many published studies, mainly due to the absence of the corresponding parameter lists. While deep learning seems promising for prediction applications, its superiority with respect to traditional methods has not been established; there is, instead, ample room for its application in the subfield of patient stratification. Finally, an open question remains on the role of new environmental and behavioural variables collected via novel, real-time sensors.

Italian reference values and brain correlates of verbal fluency index - vs standard verbal fluency test - to assess executive dysfunction in ALS

Objectives: In amyotrophic lateral sclerosis (ALS), verbal fluency index (Vfi) is used to investigate fluency accounting for motor impairment. This study has three aims: (1) to provide Vfi reference values from a cohort of Italian healthy subjects; (2) to assess the ability of Vfi reference values (vs standard verbal fluency test [VFT]) in distinguishing ALS patients with and without executive dysfunction; and (3) to investigate the association between Vfi and brain structural features of ALS patients. Methods: We included 180 healthy subjects and 157 ALS patients who underwent neuropsychological assessment, including VFT and Vfi, and brain MRI. Healthy subjects were split into four subgroups according to sex and education. For each subgroup, we defined the 95th percentile of Vfi as the cutoff. In ALS, the distributions of "abnormal" cases based on Vfi and standard VFT cutoffs were compared using Fisher's exact test. Using quantile regressions in patients, we assessed the association between Vfi and VFT scores, separately, with gray matter volumes and white matter (WM) tract integrity. Results: Applying Vfi and VFT cutoffs, 9 and 13% of ALS cases, respectively, had abnormal scores (p < 0.001). In ALS, while higher Vfi scores were associated with WM changes of callosal fibers linking supplementary motor area, lower VFT performances related to corticospinal tract alterations. Discussion: We provided Italian reference values for the spoken Vfi. Compared to VFT, Vfis are critical to disentangle motor and cognitive deficits in ALS. In patients, abnormal Vfis were associated with damage to WM tracts specifically involved in ideational information processing.

Neuroimaging findings in preclinical amyotrophic lateral sclerosis models-How well do they mimic the clinical phenotype? A systematic review

Background and objectives

Animal models for motor neuron diseases (MND) such as amyotrophic lateral sclerosis (ALS) are commonly used in preclinical research. However, it is insufficiently understood how much findings from these model systems can be translated to humans. Thus, we aimed at systematically assessing the translational value of MND animal models to probe their external validity with regards to magnetic resonance imaging (MRI) features.

Methods

In a comprehensive literature search in PubMed and Embase, we retrieved 201 unique publications of which 34 were deemed eligible for qualitative synthesis including risk of bias assessment.

Results

ALS animal models can indeed present with human ALS neuroimaging features: Similar to the human paradigm, (regional) brain and spinal cord atrophy as well as signal changes in motor systems are commonly observed in ALS animal models. Blood-brain barrier breakdown seems to be more specific to ALS models, at least in the imaging domain. It is noteworthy that the G93A-SOD1 model, mimicking a rare clinical genotype, was the most frequently used ALS proxy.

Conclusions

Our systematic review provides high-grade evidence that preclinical ALS models indeed show imaging features highly reminiscent of human ALS assigning them a high external validity in this domain. This opposes the high attrition of drugs during bench-to-bedside translation and thus raises concerns that phenotypic reproducibility does not necessarily render an animal model appropriate for drug development. These findings emphasize a careful application of these model systems for ALS therapy development thereby benefiting refinement of animal experiments.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO/, identifier: CRD42022373146.

Role of brain 2-[18F]fluoro-2-deoxy-D-glucose-positron-emission tomography as survival predictor in amyotrophic lateral sclerosis

PURPOSE

The identification of prognostic tools in amyotrophic lateral sclerosis (ALS) would improve the design of clinical trials, the management of patients, and life planning. We aimed to evaluate the accuracy of brain 2-[¹⁸F]fluoro-2-deoxy-D-glucose-positron-emission tomography (2-[¹⁸F]FDG-PET) as an independent predictor of survival in ALS.

METHODS

A prospective cohort study enrolled 418 ALS patients, who underwent brain 2-[¹⁸F]FDG-PET at diagnosis and whose survival time was available. We discretized the survival time in a finite number of classes in a data-driven fashion by employing a k-means-like strategy. We identified "hot brain regions" with maximal power in discriminating survival classes, by evaluating the Laplacian scores in a class-aware fashion. We retained the top-m features for each class to train the classification systems (i.e., a support vector machine, SVM), using 10% of the ALS cohort as test set.

RESULTS

Data were discretized in three survival profiles: 0-2 years, 2-5 years, and > 5 years. SVM resulted in an error rate < 20% for two out of three classes separately. As for class one, the discriminant clusters included left caudate body and anterior cingulate cortex. The most discriminant regions were bilateral cerebellar pyramid in class two, and right cerebellar dentate nucleus, and left cerebellar nodule in class three.

CONCLUSION

Brain 2-[¹⁸F]FDG-PET along with artificial intelligence was able to predict with high accuracy the survival time range in our ALS cohort. Healthcare professionals can benefit from this prognostic tool for planning patients' management and follow-up. 2-[¹⁸F]FDG-PET represents a promising biomarker for individual patients' stratification in clinical trials. The lack of a multicentre external validation of the model warrants further studies to evaluate its generalization capability.

Structural magnetic resonance imaging findings and histopathological correlations in motor neuron diseases—A systematic review and meta-analysis

Objectives

The lack of systematic evidence on neuroimaging findings in motor neuron diseases (MND) hampers the diagnostic utility of magnetic resonance imaging (MRI). Thus, we aimed at performing a systematic review and meta-analysis of MRI features in MND including their histopathological correlation.

Methods

In a comprehensive literature search, out of 5941 unique publications, 223 records assessing brain and spinal cord MRI findings in MND were eligible for a qualitative synthesis. 21 records were included in a random effect model meta-analysis.

Results

Our meta-analysis shows that both T2-hyperintensities along the corticospinal tracts (CST) and motor cortex T2*-hypointensitites, also called “motor band sign”, are more prevalent in ALS patients compared to controls [OR 2.21 (95%-CI: 1.40–3.49) and 10.85 (95%-CI: 3.74–31.44), respectively]. These two imaging findings correlate to focal axonal degeneration/myelin pallor or glial iron deposition on histopathology, respectively. Additionally, certain clinical MND phenotypes such as amyotrophic lateral sclerosis (ALS) seem to present with distinct CNS atrophy patterns.

Conclusions

Although CST T2-hyperintensities and the “motor band sign” are non-specific imaging features, they can be leveraged for diagnostic workup of suspected MND cases, together with certain brain atrophy patterns. Collectively, this study provides high-grade evidence for the usefulness of MRI in the diagnostic workup of suspected MND cases.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO/, identifier: CRD42020182682.

Recent advances in the diagnosis and prognosis of amyotrophic lateral sclerosis

The diagnosis of amyotrophic lateral sclerosis can be challenging due to its heterogeneity in clinical presentation and overlap with other neurological disorders. Diagnosis early in the disease course can improve outcomes as timely interventions can slow disease progression. An evolving awareness of disease genotypes and phenotypes and new diagnostic criteria, such as the recent Gold Coast criteria, could expedite diagnosis. Improved prognosis, such as that achieved with the survival model from the European Network for the Cure of ALS, could inform the patient and their family about disease course and improve end-of-life planning. Novel staging and scoring systems can help monitor disease progression and might potentially serve as clinical trial outcomes. Lastly, new tools, such as fluid biomarkers, imaging modalities, and neuromuscular electrophysiological measurements, might increase diagnostic and prognostic accuracy.

Resting state functional brain networks associated with emotion processing in frontotemporal lobar degeneration

This study investigated the relationship between emotion processing and resting-state functional connectivity (rs-FC) of the brain networks in frontotemporal lobar degeneration (FTLD). Eighty FTLD patients (including cases with behavioral variant of frontotemporal dementia, primary progressive aphasia, progressive supranuclear palsy syndrome, motor neuron disease) and 65 healthy controls underwent rs-functional MRI. Emotion processing was tested using the Comprehensive Affect Testing System (CATS). In patients and controls, correlations were investigated between each emotion construct and rs-FC changes within critical networks. Mean rs-FC of the clusters significantly associated with CATS scoring were compared among FTLD groups. FTLD patients had pathological CATS scores compared with controls. In controls, increased rs-FC of the cerebellar and visuo-associative networks correlated with better scores in emotion-matching and discrimination tasks, respectively; while decreased rs-FC of the visuo-spatial network was related with better performance in the affect-matching and naming. In FTLD, the associations between rs-FC and CATS scores involved more brain regions, such as orbitofrontal and middle frontal gyri within anterior networks (i.e., salience and default-mode), parietal and somatosensory regions within visuo-spatial and sensorimotor networks, caudate and thalamus within basal-ganglia network. Rs-FC changes associated with CATS were similar among all FTLD groups. In FTLD compared to controls, the pattern of rs-FC associated with emotional processing involves a larger number of brain regions, likely due to functional specificity loss and compensatory attempts. These associations were similar across all FTLD groups, suggesting a common physiopathological mechanism of emotion processing breakdown, regardless the clinical presentation and pattern of atrophy.

Prognostic models for amyotrophic lateral sclerosis: a systematic review

BACKGROUND

Increasing prognostic models for amyotrophic lateral sclerosis (ALS) have been developed. However, no comprehensive evaluation of these models has been done. The purpose of this study was to map the prognostic models for ALS to assess their potential contribution and suggest future improvements on modeling strategy.

METHODS

Databases including Medline, Embase, Web of Science, and Cochrane library were searched from inception to 20 February 2021. All studies developing and/or validating prognostic models for ALS were selected. Information regarding modelling method and methodological quality was extracted.

RESULTS

A total of 28 studies describing the development of 34 models and the external validation of 19 models were included. The outcomes concerned were ALS progression (n = 12; 35%), change in weight (n = 1; 3%), respiratory insufficiency (n = 2; 6%), and survival (n = 19; 56%). Among the models predicting ALS progression or survival, the most frequently used predictors were age, ALS Functional Rating Scale/ALS Functional Rating Scale-Revised, site of onset, and disease duration. The modelling method adopted most was machine learning (n = 16; 47%). Most of the models (n = 25; 74%) were not presented. Discrimination and calibration were assessed in 12 (35%) and 2 (6%) models, respectively. Only one model by Westeneng et al. (Lancet Neurol 17:423-433, 2018) was assessed with overall low risk of bias and it performed well in both discrimination and calibration, suggesting a relatively reliable model for practice.

CONCLUSIONS

This study systematically reviewed the prognostic models for ALS. Their usefulness is questionable due to several methodological pitfalls and the lack of external validation done by fully independent researchers. Future research should pay more attention to the addition of novel promising predictors, external validation, and head-to-head comparisons of existing models.

Progression of brain functional connectivity and frontal cognitive dysfunction in ALS

OBJECTIVE

To investigate the progression of resting-state functional connectivity (rs-FC) changes in patients with amyotrophic lateral sclerosis (ALS) and their relationship with frontal cognitive alterations.

METHODS

This is a multicentre, observational and longitudinal study. At baseline and after six months, 25 ALS patients underwent 3D T1-weighted MRI, resting-state functional MRI (rs-fMRI), and the computerized Test of Attentional Performance (TAP). Using independent component analysis, rs-FC changes of brain networks involving connections to frontal lobes and their relationship with baseline cognitive scores and cognitive changes over time were assessed. With a seed-based approach, rs-FC longitudinal changes of the middle frontal gyrus (MFG) were also explored.

RESULTS

After six months, ALS patients showed an increased rs-FC of the left anterior cingulate, left middle frontal gyrus (MFG) and left superior frontal gyrus within the frontostriatal network, and of the left MFG, left supramarginal gyrus and right angular gyrus within the left frontoparietal network. Within the frontostriatal network, a worse baseline performance at TAP divided attention task was associated with an increased rs-FC over time in the left MFG and a worse baseline performance at the category fluency index was related with increased rs-FC over time in the left frontal superior gyrus. After six months, the seed-based rs-FC analysis of the MFG with the whole brain showed decreased rs-FC of the right MFG with frontoparietal regions in patients compared to controls.

CONCLUSIONS

Rs-FC changes in ALS patients progressed over time within the frontostriatal and the frontoparietal networks and are related to frontal-executive dysfunction. The MFG seems a potential core region in the framework of a frontoparietal functional breakdown, which is typical of frontotemporal lobar degeneration. These findings offer new potential markers for monitoring extra-motor progression in ALS.

Resting state functional MRI brain signatures of fast disease progression in amyotrophic lateral sclerosis: a retrospective study

OBJECTIVE

Advanced neuroimaging techniques may offer the potential to monitor disease spreading in amyotrophic lateral sclerosis (ALS). We aim to investigate brain functional and structural magnetic resonance imaging (MRI) changes in a cohort of ALS patients, examined at diagnosis and clinically monitored over 18 months, in order to early discriminate fast progressors (FPs) from slow progressors (SPs). Methods: Resting state functional MRI (RS-fMRI), diffusion tensor imaging (DTI) and voxel-based morphometry (VBM) analyses were performed at baseline in 54 patients with ALS and 22 HCs. ALS patients were classified a posteriori into FPs (n = 25) and SPs (n = 29) based on changes in Amyotrophic Lateral Sclerosis Functional Rating Scale-Revised score from baseline to the 18-month assessment (ΔALSFRS-R), applying a k-means clustering algorithm. Results: At diagnosis, when compared to HCs, ALS patients showed reduced functional connectivity in both motor and extra-motor networks. When compared to SPs, at baseline, FPs showed decreased function connectivity in paracentral lobule (sensorimotor network), precuneus (in the default mode network), middle frontal gyri (frontoparietal networks) and increased functional connectivity in insular cortices (salience network). Structural analyses did not reveal significant differences in gray and white matter damage by comparing FPs to SPs. Receiver operating characteristic (ROC) curve analysis showed that functional connectivity increase in the left insula at baseline best discriminated FPs and SPs (area under the curve 78%). Conclusions: Impairment of extra-motor networks may appear early in ALS patients with faster disease progression, suggesting that a more widespread functional connectivity damage may be an indicator of poorer prognosis.

Manifold learning for amyotrophic lateral sclerosis functional loss assessment : Development and validation of a prognosis model

Amyotrophic lateral sclerosis (ALS) is an inexorably progressive neurodegenerative condition with no effective disease-modifying therapy at present. Given the striking clinical heterogeneity of the condition, the development and validation of reliable prognostic models is a recognised research priority. We present a prognostic model for functional decline in ALS where outcome uncertainty is taken into account. Patient data were reduced and projected onto a 2D space using Uniform Manifold Approximation and Projection (UMAP), a novel non-linear dimension reduction technique. Information from 3756 patients was included. Development data were sourced from past clinical trials. Real-world population data were used as validation data. Predictors included age, gender, region of onset, symptom duration, weight at baseline, functional impairment, and estimated rate of functional loss. UMAP projection of patients showed an informative 2D data distribution. As limited data availability precluded complex model designs, the projection was divided into three zones defined by a functional impairment range probability. Zone membership allowed individual patient prediction. Patients belonging to the first zone had a probability of [Formula: see text] (± [Formula: see text]) to have an ALSFRS score over 20 at 1-year follow-up. Patients within the second zone had a probability of [Formula: see text] (± [Formula: see text]) to have an ALSFRS score between 10 and 30 at 1 year follow-up. Finally, patients within the third zone had a probability of [Formula: see text] (± [Formula: see text]) to have an ALSFRS score lower than 20 at 1 year follow-up. This approach requires a limited set of features, is easily updated, improves with additional patient data, and accounts for results uncertainty. This method could therefore be used in a clinical setting for patient stratification and outcome projection.

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

Amyotrophic Lateral Sclerosis (ALS) is an inexorably progressive neurodegenerative condition with no effective disease modifying therapies. The development and validation of reliable prognostic models is a recognised research priority. We present a prognostic model for survival in ALS where result uncertainty is taken into account. Patient data were reduced and projected onto a 2D space using Uniform Manifold Approximation and Projection (UMAP), a novel non-linear dimension reduction technique. Information from 5,220 patients was included as development data originating from past clinical trials, and real-world population data as validation data. Predictors included age, gender, region of onset, symptom duration, weight at baseline, functional impairment, and estimated rate of functional loss. UMAP projection of patients shows an informative 2D data distribution. As limited data availability precluded complex model designs, the projection was divided into three zones with relevant survival rates. These rates were defined using confidence bounds: high, intermediate, and low 1-year survival rates at respectively [Formula: see text] ([Formula: see text]), [Formula: see text] ([Formula: see text]) and [Formula: see text] ([Formula: see text]). Predicted 1-year survival was estimated using zone membership. This approach requires a limited set of features, is easily updated, improves with additional patient data, and accounts for results uncertainty.

What do we know about the variability in survival of patients with amyotrophic lateral sclerosis?

INTRODUCTION

ALS is a fatal neurodegenerative disease. However, patients show variability in the length of survival after symptom onset. Understanding the mechanisms of long survival could lead to possible avenues for therapy.

AREAS COVERED

This review surveys the reported length of survival in ALS, the clinical features that predict survival in individual patients, and possible factors, particularly genetic factors, that could cause short or long survival. The authors also speculate on possible mechanisms.

EXPERT OPINION

a small number of known factors can explain some variability in ALS survival. However, other disease-modifying factors likely exist. Factors that alter motor neurone vulnerability and immune, metabolic, and muscle function could affect survival by modulating the disease process. Knowing these factors could lead to interventions to change the course of the disease. The authors suggest a broad approach is needed to quantify the proportion of variation survival attributable to genetic and non-genetic factors and to identify and estimate the effect size of specific factors. Studies of this nature could not only identify novel avenues for therapeutic research but also play an important role in clinical trial design and personalized medicine.

Structural MRI outcomes and predictors of disease progression in amyotrophic lateral sclerosis

•

Serial diffusion tensor (DT) MRI showed progression of white matter pathology in ALS.

•

Early involvement of motor fibers and later spread to extra-motor regions was found.

•

DT MRI measures of damage to the motor networks showed consistent worsening.

•

These correlated with clinical progression and long-term functional prognosis.

•

No significant cortical thinning was detected either at baseline or over time.

Background and aims

Considering the great heterogeneity of amyotrophic lateral sclerosis (ALS), the identification of accurate prognostic predictors is fundamental for both the clinical practice and the design of treatment trials. This study aimed to explore the progression of clinical and structural brain changes in patients with ALS, and to assess magnetic resonance imaging (MRI) measures of brain damage as predictors of subsequent functional decline.

Methods

50 ALS patients underwent clinical evaluations and 3 T MRI scans at regular intervals for a maximum of 2 years (total MRI scans = 164). MRI measures of cortical thickness, as well as diffusion tensor (DT) metrics of microstructural damage along white matter (WM) tracts were obtained. Voxel-wise regression models and longitudinal mixed-effects models were used to test the relationship between clinical decline and baseline and longitudinal MRI features.

Results

The rate of decline of the ALS Functional Rating Scale revised (ALSFRS-r) was significantly associated with the rate of fractional anisotropy (FA) decrease in the body of the corpus callosum (CC). Corticospinal tract (CST) and CC-body alterations had a faster progression in patients with higher baseline ALSFRS-r scores and greater CC-body disruption at baseline. Lower FA of the cerebral peduncle was associated with faster subsequent clinical progression.

Conclusions

In this longitudinal study, we identified a significant association between measures of WM damage of the motor tracts and functional decline in ALS patients. Our data suggest that a multiparametric approach including DT MRI measures of brain damage would provide an optimal method for an accurate stratification of ALS patients into prognostic classes.

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

Objectives: White matter (WM) impairments involving both motor and extra-motor areas have been well-documented in amyotrophic lateral sclerosis (ALS). This study tested the potential of diffusion measurements in WM for identifying ALS based on support vector machine (SVM). Methods: Voxel-wise fractional anisotropy (FA) values of diffusion tensor images (DTI) were extracted from 22 ALS patients and 26 healthy controls and served as discrimination features. The revised ALS Functional Rating Scale (ALSFRS-R) was employed to assess ALS severity. Feature ranking and selection were based on Fisher scores. A linear kernel SVM algorithm was applied to build the classification model, from which the classification performance was evaluated. To promote classifier generalization ability, a leave-one-out cross-validation (LOOCV) method was adopted. Results: By using the 2,400~3,400 ranked features as optimal features, the highest classification accuracy of 83.33% (sensitivity = 77.27% and specificity = 88.46%, P = 0.0001) was achieved, with an area under receiver operating characteristic curve of 0.862. The predicted function value was positively correlated with patient ALSFRS-R scores (r = 0.493, P = 0.020). In the optimized SVM model, FA values from several regions mostly contributed to classification, primarily involving the corticospinal tract pathway, postcentral gyrus, and frontal and parietal areas. Conclusions: Our results suggest the feasibility of ALS diagnosis based on SVM analysis and diffusion measurements of WM. Additional investigations using a larger cohort is recommended in order to validate the results of this study.