Amyotrophic Lateral Sclerosis (ALS) is a relentlessly progressive neurodegenerative condition with limited therapeutic options at present. Survival from symptom onset ranges from 3 to 5 years ...depending on genetic, demographic, and phenotypic factors. Despite tireless research efforts, the core etiology of the disease remains elusive and drug development efforts are confounded by the lack of accurate monitoring markers. Disease heterogeneity, late-stage recruitment into pharmaceutical trials, and inclusion of phenotypically admixed patient cohorts are some of the key barriers to successful clinical trials. Machine Learning (ML) models and large international data sets offer unprecedented opportunities to appraise candidate diagnostic, monitoring, and prognostic markers. Accurate patient stratification into well-defined prognostic categories is another aspiration of emerging classification and staging systems.
The objective of this paper is the comprehensive, systematic, and critical review of ML initiatives in ALS to date and their potential in research, clinical, and pharmacological applications. The focus of this review is to provide a dual, clinical-mathematical perspective on recent advances and future directions of the field. Another objective of the paper is the frank discussion of the pitfalls and drawbacks of specific models, highlighting the shortcomings of existing studies and to provide methodological recommendations for future study designs.
Despite considerable sample size limitations, ML techniques have already been successfully applied to ALS data sets and a number of promising diagnosis models have been proposed. Prognostic models have been tested using core clinical variables, biological, and neuroimaging data. These models also offer patient stratification opportunities for future clinical trials. Despite the enormous potential of ML in ALS research, statistical assumptions are often violated, the choice of specific statistical models is seldom justified, and the constraints of ML models are rarely enunciated.
From a mathematical perspective, the main barrier to the development of validated diagnostic, prognostic, and monitoring indicators stem from limited sample sizes. The combination of multiple clinical, biofluid, and imaging biomarkers is likely to increase the accuracy of mathematical modeling and contribute to optimized clinical trial designs.
Amyotrophic lateral sclerosis (ALS) is the most common adult onset motor neuron disease with no effective disease modifying therapies at present. Spinal cord degeneration is a hallmark feature of ...ALS, highlighted in the earliest descriptions of the disease by Lockhart Clarke and Jean-Martin Charcot. The anterior horns and corticospinal tracts are invariably affected in ALS, but up to recently it has been notoriously challenging to detect and characterize spinal pathology
. With recent technological advances, spinal imaging now offers unique opportunities to appraise lower motor neuron degeneration, sensory involvement, metabolic alterations, and interneuron pathology in ALS. Quantitative spinal imaging in ALS has now been used in cross-sectional and longitudinal study designs, applied to presymptomatic mutation carriers, and utilized in machine learning applications. Despite its enormous clinical and academic potential, a number of physiological, technological, and methodological challenges limit the routine use of computational spinal imaging in ALS. In this review, we provide a comprehensive overview of emerging spinal cord imaging methods and discuss their advantages, drawbacks, and biomarker potential in clinical applications, clinical trial settings, monitoring, and prognostic roles.
Background
Gait impairment is poorly characterized in amyotrophic lateral sclerosis (ALS), despite increasing evidence of extrapyramidal and cerebellar dysfunction. Gait impairment adds to the ...considerable motor disability of ALS patients and requires targeted multidisciplinary interventions.
Purpose
To assess gait imagery‐specific networks and functional adaptation in ALS.
Study Type
Prospective.
Population
Seventeen ALS patients with lower motor neuron predominant (LMNp) disability, 14 patients with upper motor neurons predominant (UMNp) disease, and 14 healthy controls were included.
Field Strength/Sequences
3T / gradient echo echo planar (GE‐EPI).
Assessment
Subjects performed a dual motor imagery task: normal and precision gait. The Movement Imagery Questionnaire – Revised Second Version (MIQ‐rs) was used to appraise movement imagery in each participant. Study group‐specific activation patterns were evaluated during motor imagery of gait. Additional generalized psychophysiological interaction analyses were carried out using the supplementary motor area, caudate, cerebellum, and superior parietal lobule as seed regions.
Statistical Tests
Repeated‐measures analysis of variance (ANOVA) was used to compare time imagery and MIQ‐rs scores between groups. Size effects were also reported as partial eta squared (η2). One‐way ANOVA was performed to explore differences in terms of connexions during motor imagery tasks.
Results
A significant increase in imagery time in UMNp patients compared to controls (P < 0.05) and LMNp (P < 0.05) during imagined gait was demonstrated. UMNp patients exhibited altered supplementary motor area, precentral gyrus, superior parietal lobule, and dorsolateral prefrontal cortex activation and increased orbitofrontal (pFDR(False Discovery Rate) < 0.05), posterior parietal (pFDR < 0.05) caudate (pFDR < 0.05), and cerebellar (pFDR < 0.05) signal during imagined locomotion. Increased effective connectivity of the striato‐cerebellar and parieto‐cerebellar circuits was also demonstrated. Additional activation was detected in the insula and cingulate cortex.
Data Conclusion
Enhanced striato‐ and parieto‐cerebellar networks in UMNp ALS patients are likely to represent a compensatory response to impaired postural control.
Level of Evidence
2
Technical Efficacy Stage
5
Objective
C9orf72 hexanucleotide repeats expansions account for almost half of familial amyotrophic lateral sclerosis (ALS) and frontotemporal dementia (FTD) cases. Recent imaging studies in ...asymptomatic C9orf72 carriers have demonstrated cerebral white (WM) and gray matter (GM) degeneration before the age of 40 years. The objective of this study was to characterize cervical spinal cord (SC) changes in asymptomatic C9orf72 hexanucleotide carriers.
Methods
Seventy‐two asymptomatic individuals were enrolled in a prospective study of first‐degree relatives of ALS and FTD patients carrying the c9orf72 hexanucleotide expansion. Forty of them carried the pathogenic mutation (C9+). Each subject underwent quantitative cervical cord imaging. Structural GM and WM metrics and diffusivity parameters were evaluated at baseline and 18 months later. Data were analyzed in C9+ and C9− subgroups, and C9+ subjects were further stratified by age.
Results
At baseline, significant WM atrophy was detected at each cervical vertebral level in C9+ subjects older than 40 years without associated changes in GM and diffusion tensor imaging parameters. At 18‐month follow‐up, WM atrophy was accompanied by significant corticospinal tract (CST) fractional anisotropy (FA) reductions. Intriguingly, asymptomatic C9+ subjects older than 40 years with family history of ALS (as opposed to FTD) also exhibited significant CST FA reduction at baseline.
Interpretation
Cervical SC imaging detects WM atrophy exclusively in C9+ subjects older than 40 years, and progressive CST FA reductions can be identified on 18‐month follow‐up. Cervical SC magnetic resonance imaging readily captures presymptomatic pathological changes and disease propagation in c9orf72‐associated conditions. ANN NEUROL 2019;86:158–167
Abstract
Serum creatinine has been indicated as a potential marker of motor function in SBMA and results form previous longitudinal studies pointed to its decline over time. This is a longitudinal ...retrospective study investigating creatinine changes over a 36-month-period in 73 patients with SBMA. Severity and progression of the disease was assessed according to serum creatine kinase (CK) values, manual muscle testing (MMT), SBMA functional rating scale (SBMAFRS) score
,
6-min-walk test (6MWT) value, and spirometry (forced vital capacity, fVC%) obtained at the baseline and at each of the annual follow-up visits. Baseline serum creatinine concentrations positively correlated with 6MWT, the MMT megascore score of both the upper (ULM) and lower (LLM) limbs and SBMAFRS. No correlation was found with CK or fVC% values. Similar correlation results were achieved at all the subsequent time points. Longitudinal assessments conducted by the generalized estimating equations (GEE) method returned significant changes for SBMAFRS (− 1.41 points per year,
p
< 0.001), ULM and LLM (− 0.69,
p
= 0.01; and − 1.07,
p
< 0.001, respectively), 6MWT (− 47 m,
p
< 0.001) but not for creatinine (− 0.82,
p
> 0.05). We also observed that creatinine levels at baseline did not correlate with changes in the other measures from baseline at each annual visit. Our data do not support a role for serum creatinine as sensitive biomarker of disease progression, and possibily prognosis, in SBMA.
Spinal muscular atrophy (SMA) is a lower motor neuron disease due to biallelic mutations in the
SMN1
gene on chromosome 5. It is characterized by progressive muscle weakness of limbs, bulbar and ...respiratory muscles. The disease is usually classified in four different phenotypes (1–4) according to age at symptoms onset and maximal motor milestones achieved. Recently, three disease modifying treatments have received approval from the Food and Drug Administration (FDA) and the European Medicines Agency (EMA), while several other innovative drugs are under study. New therapies have been game changing, improving survival and life quality for SMA patients. However, they have also intensified the need for accurate biomarkers to monitor disease progression and treatment efficacy. While clinical and neurophysiological biomarkers are well established and helpful in describing disease progression, there is a great need to develop more robust and sensitive circulating biomarkers, such as proteins, nucleic acids, and other small molecules. Used alone or in combination with clinical biomarkers, they will play a critical role in enhancing patients’ stratification for clinical trials and access to approved treatments, as well as in tracking response to therapy, paving the way to the development of individualized therapeutic approaches. In this comprehensive review, we describe the foremost circulating biomarkers of current significance, analyzing existing literature on non-treated and treated patients with a special focus on neurofilaments and circulating miRNA, aiming to identify and examine their role in the follow-up of patients treated with innovative treatments, including gene therapy.
Spinal muscular atrophy (SMA) is currently classified into five different subtypes, from the most severe (type 0) to the mildest (type 4) depending on age at onset, best motor function achieved, and ...copy number of the SMN2 gene. The two recent approved treatments for SMA patients revolutionized their life quality and perspectives. However, upon treatment with Nusinersen, the most widely administered therapy up to date, a high degree of variability in therapeutic response was observed in adult SMA patients. These data, together with the lack of natural history information and the wide spectrum of disease phenotypes, suggest that further efforts are needed to develop precision medicine approaches for all SMA patients. Here, we compile the current methods for functional evaluation of adult SMA patients treated with Nusinersen. We also present an overview of the known molecular changes underpinning disease heterogeneity. We finally highlight the need for novel techniques, i.e., -omics approaches, to capture phenotypic differences and to understand the biological signature in order to revise the disease classification and device personalized treatments.
The aim of this multicenter, retrospective study is to investigate the role of clinical characteristics and therapeutic intervention on ALS prognosis. The study included patients diagnosed from ...January 1, 2009 to December 31, 2013 in 13 Italian referral centers for ALS located in 10 Italian regions. Caring neurologists collected a detailed phenotypic profile and follow-up data until death into an electronic database. One center collected also data from a population-based registry for ALS. 2648 incident cases were collected. The median survival time from onset to death/tracheostomy was 44 months (SE 1.18, CI 42–46). According to univariate analysis, factors related to survival from onset to death/tracheostomy were: age at onset, diagnostic delay, site of onset, phenotype, degree of certainty at diagnosis according to revised El Escorial criteria (R-EEC), presence/absence of dementia, BMI at diagnosis, patients’ provenance. In the multivariate analysis, age at onset, diagnostic delay, phenotypes but not site of onset, presence/absence of dementia, BMI, riluzole use, R-EEC criteria were independent prognostic factors of survival in ALS. We compared patients from an ALS Registry with patients from tertiary centers; the latter ones were younger, less frequently bulbar, but more frequently familial and definite at diagnosis. Our large, multicenter study demonstrated the role of some clinical and demographic factors on ALS survival, and showed some interesting differences between referral centers’ patients and the general ALS population. These results can be helpful for clinical practice, in clinical trial design and to validate new tools to predict disease progression.
Introduction
Extrapyramidal deficits are poorly characterised in amyotrophic lateral sclerosis (ALS) despite their contribution to functional disability, increased fall risk and their quality-of-life ...implications. Given the concomitant pyramidal and cerebellar degeneration in ALS, the clinical assessment of extrapyramidal features is particularly challenging.
Objective
The comprehensive characterisation of postural instability in ALS using standardised clinical assessments, gait analyses and computational neuroimaging tools in a prospective study design.
Methods
Parameters of gait initiation in the anticipatory postural adjustment phase (APA) and execution phase (EP) were evaluated in ALS patients with and without postural instability and healthy controls. Clinical and gait analysis parameters were interpreted in the context of brain imaging findings.
Results
ALS patients with postural instability exhibit impaired gait initiation with an altered APA phase, poor dynamic postural control and significantly decreased braking index. Consistent with their clinical profile, “unsteady” ALS patients have reduced caudate and brain stem volumes compared to “steady” ALS patients.
Interpretation
Our findings highlight that the ALS functional rating scale (ALSFRS-r) does not account for extrapyramidal deficits, which are major contributors to gait impairment in a subset of ALS patients. Basal ganglia degeneration in ALS does not only contribute to cognitive and behavioural deficits, but also adds to the heterogeneity of motor disability.
Kennedy's disease (KD), also known as spinal and bulbar muscular atrophy (SBMA), is a rare, adult-onset, X-linked recessive neuromuscular disease caused by CAG expansions in exon 1 of the androgen ...receptor gene (AR). The objective of the French national diagnostic and management protocol is to provide evidence-based best practice recommendations and outline an optimised care pathway for patients with KD, based on a systematic literature review and consensus multidisciplinary observations.
The initial evaluation, confirmation of the diagnosis, and management should ideally take place in a tertiary referral centre for motor neuron diseases, and involve an experienced multidisciplinary team of neurologists, endocrinologists, cardiologists and allied healthcare professionals. The diagnosis should be suspected in an adult male presenting with slowly progressive lower motor neuron symptoms, typically affecting the lower limbs at onset. Bulbar involvement (dysarthria and dysphagia) is often a later manifestation of the disease. Gynecomastia is not a constant feature, but is suggestive of a suspected diagnosis, which is further supported by electromyography showing diffuse motor neuron involvement often with asymptomatic sensory changes. A suspected diagnosis is confirmed by genetic testing. The multidisciplinary assessment should ascertain extra-neurological involvement such as cardiac repolarisation abnormalities (Brugada syndrome), signs of androgen resistance, genitourinary abnormalities, endocrine and metabolic changes (glucose intolerance, hyperlipidemia). In the absence of effective disease modifying therapies, the mainstay of management is symptomatic support using rehabilitation strategies (physiotherapy and speech therapy). Nutritional evaluation by an expert dietician is essential, and enteral nutrition (gastrostomy) may be required. Respiratory management centres on the detection and treatment of bronchial obstructions, as well as screening for aspiration pneumonia (chest physiotherapy, drainage, positioning, breath stacking, mechanical insufflation-exsufflation, cough assist machnie, antibiotics). Non-invasive mechanical ventilation is seldom needed. Symptomatic pharmaceutical therapy includes pain management, endocrine and metabolic interventions. There is no evidence for androgen substitution therapy.
The French national Kennedy's disease protocol provides management recommendations for patients with KD. In a low-incidence condition, sharing and integrating regional expertise, multidisciplinary experience and defining consensus best-practice recommendations is particularly important. Well-coordinated collaborative efforts will ultimately pave the way to the development of evidence-based international guidelines.
PDF
