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

Progressive Cerebrocerebellar Uncoupling in Sporadic and Genetic Forms of Amyotrophic Lateral Sclerosis

BACKGROUND AND OBJECTIVES

Amyotrophic lateral sclerosis (ALS) is predominantly associated with motor cortex, corticospinal tract (CST), brainstem, and spinal cord degeneration, and cerebellar involvement is much less well characterized. However, some of the cardinal clinical features of ALS, such as dysarthria, dysphagia, gait impairment, falls, and impaired dexterity, are believed to be exacerbated by coexisting cerebellar pathology. Cerebellar pathology may also contribute to cognitive, behavioral, and pseudobulbar manifestations. Our objective was to systematically assess both intracerebellar pathology and cerebrocerebellar connectivity alterations in a genetically stratified cohort of ALS.

METHODS

A prospective, multimodal neuroimaging study was conducted to evaluate the longitudinal evolution of intracerebellar pathology and cerebrocerebellar connectivity, using structural and functional measures.

RESULTS

A total of 113 healthy controls and 212 genetically stratified individuals with ALS were included: (1) C9orf72 hexanucleotide carriers ("C9POS"), (2) sporadic patients who tested negative for ALS-associated genetic variants, and (3) intermediate-length CAG trinucleotide carriers in ATXN2 ("ATXN2"). Flocculonodular lobule (padj = 0.014, 95% CI -5.06e-5 to -3.98e-6) and crura (padj = 0.031, 95% CI -1.63e-3 to -5.55e-5) volume reductions were detected at baseline in sporadic patients. Cerebellofrontal and cerebelloparietal structural connectivity impairment was observed in both C9POS and sporadic patients at baseline, and both projections deteriorated further over time in sporadic patients (padj = 0.003, t(249) = 3.04 and padj = 0.05, t(249) = 1.93). Functional cerebelloparietal uncoupling was evident in sporadic patients at baseline (padj = 0.004, 95% CI -0.19 to -0.03). ATXN2 patients exhibited decreased cerebello-occipital functional connectivity at baseline (padj = 0.004, 95% CI -0.63 to -0.06), progressive cerebellotemporal functional disconnection (padj = 0.025, t(199) = -2.26), and progressive flocculonodular lobule degeneration (padj = 0.017, t(249) = -2.24). C9POS patients showed progressive ventral dentate atrophy (padj = 0.007, t(249) = -2.75). The CSTs (padj < 0.001, 95% CI 4.89e-5 to 1.14e-4) and transcallosal interhemispheric fibers (padj < 0.001, 95% CI 5.21e-5 to 1.31e-4) were affected at baseline in C9POS and exhibited rapid degeneration over the 4 time points. The rate of decline in CST and corpus callosum integrity was faster than the rate of cerebrocerebellar disconnection (padj = 0.001, t(190) = 6.93).

DISCUSSION

ALS is associated with accruing intracerebellar disease burden as well as progressive corticocerebellar uncoupling. Contrary to previous suggestions, we have not detected evidence of compensatory structural or functional changes in response to supratentorial degeneration. The contribution of cerebellar disease burden to dysarthria, dysphagia, gait impairment, pseudobulbar affect, and cognitive deficits should be carefully considered in clinical assessments, monitoring, and multidisciplinary interventions.

Dietary patterns associated with the incidence of hypertension among adult Japanese males: application of machine learning to a cohort study

PURPOSE

The previous studies that examined the effectiveness of unsupervised machine learning methods versus traditional methods in assessing dietary patterns and their association with incident hypertension showed contradictory results. Consequently, our aim is to explore the correlation between the incidence of hypertension and overall dietary patterns that were extracted using unsupervised machine learning techniques.

METHODS

Data were obtained from Japanese male participants enrolled in a prospective cohort study between August 2008 and August 2010. A final dataset of 447 male participants was used for analysis. Dimension reduction using uniform manifold approximation and projection (UMAP) and subsequent K-means clustering was used to derive dietary patterns. In addition, multivariable logistic regression was used to evaluate the association between dietary patterns and the incidence of hypertension.

RESULTS

We identified four dietary patterns: 'Low-protein/fiber High-sugar,' 'Dairy/vegetable-based,' 'Meat-based,' and 'Seafood and Alcohol.' Compared with 'Seafood and Alcohol' as a reference, the protective dietary patterns for hypertension were 'Dairy/vegetable-based' (OR 0.39, 95% CI 0.19-0.80, P = 0.013) and the 'Meat-based' (OR 0.37, 95% CI 0.16-0.86, P = 0.022) after adjusting for potential confounding factors, including age, body mass index, smoking, education, physical activity, dyslipidemia, and diabetes. An age-matched sensitivity analysis confirmed this finding.

CONCLUSION

This study finds that relative to the 'Seafood and Alcohol' pattern, the 'Dairy/vegetable-based' and 'Meat-based' dietary patterns are associated with a lower risk of hypertension among men.

Ensemble-imbalance-based classification for amyotrophic lateral sclerosis prognostic prediction: identifying short-survival patients at diagnosis

Prognosticating Amyotrophic Lateral Sclerosis (ALS) presents a formidable challenge due to patients exhibiting different onset sites, progression rates, and survival times. In this study, we have developed and evaluated Machine Learning (ML) algorithms that integrate Ensemble and Imbalance Learning techniques to classify patients into Short and Non-Short survival groups based on data collected during diagnosis. We aimed to identify individuals at high risk of mortality within 24 months of symptom onset through analysis of patient data commonly encountered in daily clinical practice. Our Ensemble-Imbalance approach underwent evaluation employing six ML algorithms as base classifiers. Remarkably, our results outperformed those of individual algorithms, achieving a Balanced Accuracy of 88% and a Sensitivity of 96%. Additionally, we used the Shapley Additive Explanations framework to elucidate the decision-making process of the top-performing model, pinpointing the most important features and their correlations with the target prediction. Furthermore, we presented helpful tools to visualize and compare patient similarities, offering valuable insights. Confirming the obtained results, our approach could aid physicians in devising personalized treatment plans at the time of diagnosis or serve as an inclusion/exclusion criterion in clinical trials.

Language deficits in primary lateral sclerosis: cortical atrophy, white matter degeneration and functional disconnection between cerebral regions

BACKGROUND

Primary lateral sclerosis (PLS) is traditionally regarded as a pure upper motor neuron disorder, but recent cases series have highlighted cognitive deficits in executive and language domains.

METHODS

A single-centre, prospective neuroimaging study was conducted with comprehensive clinical and genetic profiling. The structural and functional integrity of language-associated brain regions and networks were systematically evaluated in 40 patients with PLS in comparison to 111 healthy controls. The structural integrity of the arcuate fascicle, frontal aslant tract, inferior occipito-frontal fascicle, inferior longitudinal fascicle, superior longitudinal fascicle and uncinate fascicle was evaluated. Functional connectivity between the supplementary motor region and the inferior frontal gyrus and connectivity between Wernicke's and Broca's areas was also assessed.

RESULTS

Cortical thickness reductions were observed in both Wernicke's and Broca's areas. Fractional anisotropy reduction was noted in the aslant tract and increased radical diffusivity (RD) identified in the aslant tract, arcuate fascicle and superior longitudinal fascicle in the left hemisphere. Functional connectivity was reduced along the aslant track, i.e. between the supplementary motor region and the inferior frontal gyrus, but unaffected between Wernicke's and Broca's areas. Cortical thickness alterations, structural and functional connectivity changes were also noted in the right hemisphere.

CONCLUSIONS

Disease-burden in PLS is not confined to motor regions, but there is also a marked involvement of language-associated tracts, networks and cortical regions. Given the considerably longer survival in PLS compared to ALS, the impact of language impairment on the management of PLS needs to be carefully considered.

Accurate personalized survival prediction for amyotrophic lateral sclerosis patients

Amyotrophic Lateral Sclerosis (ALS) is a rapidly progressive neurodegenerative disease. Accurately predicting the survival time for ALS patients can help patients and clinicians to plan for future treatment and care. We describe the application of a machine-learned tool that incorporates clinical features and cortical thickness from brain magnetic resonance (MR) images to estimate the time until a composite respiratory failure event for ALS patients, and presents the prediction as individual survival distributions (ISDs). These ISDs provide the probability of survival (none of the respiratory failures) at multiple future time points, for each individual patient. Our learner considers several survival prediction models, and selects the best model to provide predictions. We evaluate our learned model using the mean absolute error margin (MAE-margin), a modified version of mean absolute error that handles data with censored outcomes. We show that our tool can provide helpful information for patients and clinicians in planning future treatment.

Digital Alternative Communication for Individuals with Amyotrophic Lateral Sclerosis: What We Have

Amyotrophic Lateral Sclerosis is a disease that compromises the motor system and the functional abilities of the person in an irreversible way, causing the progressive loss of the ability to communicate. Tools based on Augmentative and Alternative Communication are essential for promoting autonomy and improving communication, life quality, and survival. This Systematic Literature Review aimed to provide evidence on eye-image-based Human-Computer Interaction approaches for the Augmentative and Alternative Communication of people with Amyotrophic Lateral Sclerosis. The Systematic Literature Review was conducted and guided following a protocol consisting of search questions, inclusion and exclusion criteria, and quality assessment, to select primary studies published between 2010 and 2021 in six repositories: Science Direct, Web of Science, Springer, IEEE Xplore, ACM Digital Library, and PubMed. After the screening, 25 primary studies were evaluated. These studies showcased four low-cost, non-invasive Human-Computer Interaction strategies employed for Augmentative and Alternative Communication in people with Amyotrophic Lateral Sclerosis. The strategies included Eye-Gaze, which featured in 36% of the studies; Eye-Blink and Eye-Tracking, each accounting for 28% of the approaches; and the Hybrid strategy, employed in 8% of the studies. For these approaches, several computational techniques were identified. For a better understanding, a workflow containing the development phases and the respective methods used by each strategy was generated. The results indicate the possibility and feasibility of developing Human-Computer Interaction resources based on eye images for Augmentative and Alternative Communication in a control group. The absence of experimental testing in people with Amyotrophic Lateral Sclerosis reiterates the challenges related to the scalability, efficiency, and usability of these technologies for people with the disease. Although challenges still exist, the findings represent important advances in the fields of health sciences and technology, promoting a promising future with possibilities for better life quality.

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.

Brainstem-cortex disconnection in amyotrophic lateral sclerosis: bulbar impairment, genotype associations, asymptomatic changes and biomarker opportunities

BACKGROUND

Bulbar dysfunction is a cardinal feature of ALS with important quality of life and management implications. The objective of this study is the longitudinal evaluation of a large panel imaging metrics pertaining to bulbar dysfunction, encompassing cortical measures, structural and functional cortico-medullary connectivity indices and brainstem metrics.

METHODS

A standardised, multimodal imaging protocol was implemented with clinical and genetic profiling to systematically appraise the biomarker potential of specific metrics. A total of 198 patients with ALS and 108 healthy controls were included.

RESULTS

Longitudinal analyses revealed progressive structural and functional disconnection between the motor cortex and the brainstem over time. Cortical thickness reduction was an early feature on cross-sectional analyses with limited further progression on longitudinal follow-up. Receiver operating characteristic analyses of the panel of MR metrics confirmed the discriminatory potential of bulbar imaging measures between patients and controls and area-under-the-curve values increased significantly on longitudinal follow-up. C9orf72 carriers exhibited lower brainstem volumes, lower cortico-medullary structural connectivity and faster cortical thinning. Sporadic patients without bulbar symptoms, already exhibit significant brainstem and cortico-medullary connectivity alterations.

DISCUSSION

Our results indicate that ALS is associated with multi-level integrity change from cortex to brainstem. The demonstration of significant corticobulbar alterations in patients without bulbar symptoms confirms considerable presymptomatic disease burden in sporadic ALS. The systematic assessment of radiological measures in a single-centre academic study helps to appraise the diagnostic and monitoring utility of specific measures for future clinical and clinical trial applications.

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

BACKGROUND

Magnetic resonance spectroscopy (MRS) in amyotrophic lateral sclerosis (ALS) has been overwhelmingly applied to motor regions to date and our understanding of frontotemporal metabolic signatures is relatively limited. The association between metabolic alterations and cognitive performance in also poorly characterised.

MATERIAL AND METHODS

In a multimodal, prospective pilot study, the structural, metabolic, and diffusivity profile of the hippocampus was systematically evaluated in patients with ALS. Patients underwent careful clinical and neurocognitive assessments. All patients were non-demented and exhibited normal memory performance. 1H-MRS spectra of the right and left hippocampi were acquired at 3.0T to determine the concentration of a panel of metabolites. The imaging protocol also included high-resolution T1-weighted structural imaging for subsequent hippocampal grey matter (GM) analyses and diffusion tensor imaging (DTI) for the tractographic evaluation of the integrity of the hippocampal perforant pathway zone (PPZ).

RESULTS

ALS patients exhibited higher hippocampal tNAA, tNAA/tCr and tCho bilaterally, despite the absence of volumetric and PPZ diffusivity differences between the two groups. Furthermore, superior memory performance was associated with higher hippocampal tNAA/tCr bilaterally. Both longer symptom duration and greater functional disability correlated with higher tCho levels.

CONCLUSION

Hippocampal 1H-MRS may not only contribute to a better academic understanding of extra-motor disease burden in ALS, but given its sensitive correlations with validated clinical metrics, it may serve as practical biomarker for future clinical and clinical trial applications. Neuroimaging protocols in ALS should incorporate MRS in addition to standard structural, functional, and diffusion sequences.

Algorithm-Based Risk Identification in Patients with Breast Cancer-Related Lymphedema: A Cross-Sectional Study

Background: Breast cancer-related lymphedema (BCRL) could be one consequence of breast cancer (BC). Although several risk factors have been identified, a predictive algorithm still needs to be made available to determine the patient's risk from an ensemble of clinical variables. Therefore, this study aimed to characterize the risk of BCRL by investigating the characteristics of autogenerated clusters of patients. Methods: The dataset under analysis was a multi-centric data collection of twenty-three clinical features from patients undergoing axillary dissection for BC and presenting BCRL or not. The patients' variables were initially analyzed separately in two low-dimensional embeddings. Afterward, the two models were merged in a bi-dimensional prognostic map, with patients categorized into three clusters using a Gaussian mixture model. Results: The prognostic map represented the medical records of 294 women (mean age: 59.823±12.879 years) grouped into three clusters with a different proportion of subjects affected by BCRL (probability that a patient with BCRL belonged to Cluster A: 5.71%; Cluster B: 71.42%; Cluster C: 22.86%). The investigation evaluated intra- and inter-cluster factors and identified a subset of clinical variables meaningful in determining cluster membership and significantly associated with BCRL biological hazard. Conclusions: The results of this study provide potential insight for precise risk assessment of patients affected by BCRL, with implications in prevention strategies, for instance, focusing the resources on identifying patients at higher risk.

Neuroimaging in hereditary spastic paraplegias: from qualitative cues to precision biomarkers

INTRODUCTION

: Hereditary spastic paraplegias (HSP) include a clinically and genetically heterogeneous group of conditions. Novel imaging modalities have been increasingly applied to HSP cohorts which helps to quantitatively evaluate the integrity of specific anatomical structures and develop monitoring markers for both clinical care and future clinical trials.

AREAS COVERED

: Advances in HSP imaging are systematically reviewed with a focus on cohort sizes, imaging modalities, study design, clinical correlates, methodological approaches, and key findings.

EXPERT OPINION

: A wide range of imaging techniques have been recently applied to HSP cohorts. Common shortcomings of existing studies include the evaluation of genetically unconfirmed or admixed cohorts, limited sample sizes, unimodal imaging approaches, lack of postmortem validation, and a limited clinical battery, often exclusively focusing on motor aspects of the condition. A number of innovative methodological approaches have also be identified, such as robust longitudinal study designs, the implementation of multimodal imaging protocols, complementary cognitive assessments, and the comparison of HSP cohorts to MND cohorts. Collaborative multicentre initiatives may overcome sample limitations, and comprehensive clinical profiling with motor, extrapyramidal, cerebellar, and neuropsychological assessments would permit systematic clinico-radiological correlations. Academic achievements in HSP imaging have the potential to be developed into viable clinical applications to expedite the diagnosis and monitor disease progression.

Cost function for low-dimensional manifold topology assessment

In reduced-order modeling, complex systems that exhibit high state-space dimensionality are described and evolved using a small number of parameters. These parameters can be obtained in a data-driven way, where a high-dimensional dataset is projected onto a lower-dimensional basis. A complex system is then restricted to states on a low-dimensional manifold where it can be efficiently modeled. While this approach brings computational benefits, obtaining a good quality of the manifold topology becomes a crucial aspect when models, such as nonlinear regression, are built on top of the manifold. Here, we present a quantitative metric for characterizing manifold topologies. Our metric pays attention to non-uniqueness and spatial gradients in physical quantities of interest, and can be applied to manifolds of arbitrary dimensionality. Using the metric as a cost function in optimization algorithms, we show that optimized low-dimensional projections can be found. We delineate a few applications of the cost function to datasets representing argon plasma, reacting flows and atmospheric pollutant dispersion. We demonstrate how the cost function can assess various dimensionality reduction and manifold learning techniques as well as data preprocessing strategies in their capacity to yield quality low-dimensional projections. We show that improved manifold topologies can facilitate building nonlinear regression models.

Machine learning of COVID-19 clinical data identifies population structures with therapeutic potential

Clinical outcomes for patients with COVID-19 are heterogeneous and there is interest in defining subgroups for prognostic modeling and development of treatment algorithms. We obtained 28 demographic and laboratory variables in patients admitted to hospital with COVID-19. These comprised a training cohort (n = 6099) and two validation cohorts during the first and second waves of the pandemic (n = 996; n = 1011). Uniform manifold approximation and projection (UMAP) dimension reduction and Gaussian mixture model (GMM) analysis was used to define patient clusters. 29 clusters were defined in the training cohort and associated with markedly different mortality rates, which were predictive within confirmation datasets. Deconvolution of clinical features within clusters identified unexpected relationships between variables. Integration of large datasets using UMAP-assisted clustering can therefore identify patient subgroups with prognostic information and uncovers unexpected interactions between clinical variables. This application of machine learning represents a powerful approach for delineating disease pathogenesis and potential therapeutic interventions.

Mapping cortical disease-burden at individual-level in frontotemporal dementia: implications for clinical care and pharmacological trials

Imaging studies of FTD typically present group-level statistics between large cohorts of genetically, molecularly or clinically stratified patients. Group-level statistics are indispensable to appraise unifying radiological traits and describe genotype-associated signatures in academic studies. However, in a clinical setting, the primary objective is the meaningful interpretation of imaging data from individual patients to assist diagnostic classification, inform prognosis, and enable the assessment of progressive changes compared to baseline scans. In an attempt to address the pragmatic demands of clinical imaging, a prospective computational neuroimaging study was undertaken in a cohort of patients across the spectrum of FTD phenotypes. Cortical changes were evaluated in a dual pipeline, using standard cortical thickness analyses and an individualised, z-score based approach to characterise subject-level disease burden. Phenotype-specific patterns of cortical atrophy were readily detected with both methodological approaches. Consistent with their clinical profiles, patients with bvFTD exhibited orbitofrontal, cingulate and dorsolateral prefrontal atrophy. Patients with ALS-FTD displayed precentral gyrus involvement, nfvPPA patients showed widespread cortical degeneration including insular and opercular regions and patients with svPPA exhibited relatively focal anterior temporal lobe atrophy. Cortical atrophy patterns were reliably detected in single individuals, and these maps were consistent with the clinical categorisation. Our preliminary data indicate that standard T1-weighted structural data from single patients may be utilised to generate maps of cortical atrophy. While the computational interpretation of single scans is challenging, it offers unrivalled insights compared to visual inspection. The quantitative evaluation of individual MRI data may aid diagnostic classification, clinical decision making, and assessing longitudinal changes.

Identifying and predicting amyotrophic lateral sclerosis clinical subgroups: a population-based machine-learning study

BACKGROUND

Amyotrophic lateral sclerosis (ALS) is known to represent a collection of overlapping syndromes. Various classification systems based on empirical observations have been proposed, but it is unclear to what extent they reflect ALS population substructures. We aimed to use machine-learning techniques to identify the number and nature of ALS subtypes to obtain a better understanding of this heterogeneity, enhance our understanding of the disease, and improve clinical care.

METHODS

In this retrospective study, we applied unsupervised Uniform Manifold Approximation and Projection [UMAP]) modelling, semi-supervised (neural network UMAP) modelling, and supervised (ensemble learning based on LightGBM) modelling to a population-based discovery cohort of patients who were diagnosed with ALS while living in the Piedmont and Valle d'Aosta regions of Italy, for whom detailed clinical data, such as age at symptom onset, were available. We excluded patients with missing Revised ALS Functional Rating Scale (ALSFRS-R) feature values from the unsupervised and semi-supervised steps. We replicated our findings in an independent population-based cohort of patients who were diagnosed with ALS while living in the Emilia Romagna region of Italy.

FINDINGS

Between Jan 1, 1995, and Dec 31, 2015, 2858 patients were entered in the discovery cohort. After excluding 497 (17%) patients with missing ALSFRS-R feature values, data for 42 clinical features across 2361 (83%) patients were available for the unsupervised and semi-supervised analysis. We found that semi-supervised machine learning produced the optimum clustering of the patients with ALS. These clusters roughly corresponded to the six clinical subtypes defined by the Chiò classification system (ie, bulbar, respiratory, flail arm, classical, pyramidal, and flail leg ALS). Between Jan 1, 2009, and March 1, 2018, 1097 patients were entered in the replication cohort. After excluding 108 (10%) patients with missing ALSFRS-R feature values, data for 42 clinical features across 989 patients were available for the unsupervised and semi-supervised analysis. All 1097 patients were included in the supervised analysis. The same clusters were identified in the replication cohort. By contrast, other ALS classification schemes, such as the El Escorial categories, Milano-Torino clinical staging, and King's clinical stages, did not adequately label the clusters. Supervised learning identified 11 clinical parameters that predicted ALS clinical subtypes with high accuracy (area under the curve 0·982 [95% CI 0·980-0·983]).

INTERPRETATION

Our data-driven study provides insight into the ALS population substructure and confirms that the Chiò classification system successfully identifies ALS subtypes. Additional validation is required to determine the accuracy and clinical use of these algorithms in assigning clinical subtypes. Nevertheless, our algorithms offer a broad insight into the clinical heterogeneity of ALS and help to determine the actual subtypes of disease that exist within this fatal neurodegenerative syndrome. The systematic identification of ALS subtypes will improve clinical care and clinical trial design.

FUNDING

US National Institute on Aging, US National Institutes of Health, Italian Ministry of Health, European Commission, University of Torino Rita Levi Montalcini Department of Neurosciences, Emilia Romagna Regional Health Authority, and Italian Ministry of Education, University, and Research.

TRANSLATIONS

For the Italian and German translations of the abstract see Supplementary Materials section.

Machine Learning Solutions Applied to Amyotrophic Lateral Sclerosis Prognosis: A Review

The prognosis of Amyotrophic Lateral Sclerosis (ALS), a complex and rare disease, represents a challenging and essential task to better comprehend its progression and improve patients' quality of life. The use of Machine Learning (ML) techniques in healthcare has produced valuable contributions to the prognosis field. This article presents a systematic and critical review of primary studies that used ML applied to the ALS prognosis, searching for databases, relevant predictor biomarkers, the ML algorithms and techniques, and their outcomes. We focused on studies that analyzed biomarkers commonly present in the ALS disease clinical practice, such as demographic, clinical, laboratory, and imaging data. Hence, we investigate studies to provide an overview of solutions that can be applied to develop decision support systems and be used by a higher number of ALS clinical settings. The studies were retrieved from PubMed, Science Direct, IEEEXplore, and Web of Science databases. After completing the searching and screening process, 10 articles were selected to be analyzed and summarized. The studies evaluated and used different ML algorithms, techniques, datasets, sample sizes, biomarkers, and performance metrics. Based on the results, three distinct types of prediction were identified: Disease Progression, Survival Time, and Need for Support. The biomarkers identified as relevant in more than one study were the ALSFRS/ALSFRS-R, disease duration, Forced Vital Capacity, Body Mass Index, age at onset, and Creatinine. In general, the studies presented promissory results that can be applied in developing decision support systems. Besides, we discussed the open challenges, the limitations identified, and future research opportunities.

The changing landscape of neuroimaging in frontotemporal lobar degeneration: from group-level observations to single-subject data interpretation

INTRODUCTION

While the imaging signatures of frontotemporal lobar degeneration (FTLD) phenotypes and genotypes are well-characterised based on group-level descriptive analyses, the meaningful interpretation of single MRI scans remains challenging. Single-subject MRI classification frameworks rely on complex computational models and large training datasets to categorise individual patients into diagnostic subgroups based on distinguishing imaging features. Reliable individual subject data interpretation is hugely important in the clinical setting to expedite the diagnosis and classify individuals into relevant prognostic categories.

AREAS COVERED

This article reviews (1) the neuroimaging studies that propose single-subject MRI classification strategies in symptomatic and pre-symptomatic FTLD, (2) potential practical implications and (3) the limitations of current single-subject data interpretation models.

EXPERT OPINION

Classification studies in FTLD have demonstrated the feasibility of categorising individual subjects into diagnostic groups based on multiparametric imaging data. Preliminary data indicate that pre-symptomatic FTLD mutation carriers may also be reliably distinguished from controls. Despite momentous advances in the field, significant further improvements are needed before these models can be developed into viable clinical applications.

White matter microstructure alterations in frontotemporal dementia: Phenotype-associated signatures and single-subject interpretation

BACKGROUND

Frontotemporal dementias (FTD) include a genetically heterogeneous group of conditions with distinctive molecular, radiological and clinical features. The majority of radiology studies in FTD compare FTD subgroups to healthy controls to describe phenotype- or genotype-associated imaging signatures. While the characterization of group-specific imaging traits is academically important, the priority of clinical imaging is the meaningful interpretation of individual datasets.

METHODS

To demonstrate the feasibility of single-subject magnetic resonance imaging (MRI) interpretation, we have evaluated the white matter profile of 60 patients across the clinical spectrum of FTD. A z-score-based approach was implemented, where the diffusivity metrics of individual patients were appraised with reference to demographically matched healthy controls. Fifty white matter tracts were systematically evaluated in each subject with reference to normative data.

RESULTS

The z-score-based approach successfully detected white matter pathology in single subjects, and group-level inferences were analogous to the outputs of standard track-based spatial statistics.

CONCLUSIONS

Our findings suggest that it is possible to meaningfully evaluate the diffusion profile of single FTD patients if large normative datasets are available. In contrast to the visual review of FLAIR and T2-weighted images, computational imaging offers objective, quantitative insights into white matter integrity changes even at single-subject level.

Phenotypic categorisation of individual subjects with motor neuron disease based on radiological disease burden patterns: A machine-learning approach

Motor neuron disease is an umbrella term encompassing a multitude of clinically heterogeneous phenotypes. The early and accurate categorisation of patients is hugely important, as MND phenotypes are associated with markedly different prognoses, progression rates, care needs and benefit from divergent management strategies. The categorisation of patients shortly after symptom onset is challenging, and often lengthy clinical monitoring is needed to assign patients to the appropriate phenotypic subgroup. In this study, a multi-class machine-learning strategy was implemented to classify 300 patients based on their radiological profile into diagnostic labels along the UMN-LMN spectrum. A comprehensive panel of cortical thickness measures, subcortical grey matter variables, and white matter integrity metrics were evaluated in a multilayer perceptron (MLP) model. Additional exploratory analyses were also carried out using discriminant function analyses (DFA). Excellent classification accuracy was achieved for amyotrophic lateral sclerosis in the testing cohort (93.7%) using the MLP model, but poor diagnostic accuracy was detected for primary lateral sclerosis (43.8%) and poliomyelitis survivors (60%). Feature importance analyses highlighted the relevance of white matter diffusivity metrics and the evaluation of cerebellar indices, cingulate measures and thalamic radiation variables to discriminate MND phenotypes. Our data suggest that radiological data from single patients may be meaningfully interpreted if large training data sets are available and the provision of diagnostic probability outcomes may be clinically useful in patients with short symptom duration. The computational interpretation of multimodal radiology datasets herald viable diagnostic, prognostic and clinical trial applications.

Cerebellar degeneration in primary lateral sclerosis: an under-recognized facet of PLS

While primary lateral sclerosis (PLS) has traditionally been regarded as a pure upper motor neuron disorder, recent clinical, neuroimaging and postmortem studies have confirmed significant extra-motor involvement. Sporadic reports have indicated that in addition to the motor cortex and corticospinal tracts, the cerebellum may also be affected in PLS. Cerebellar manifestations are difficult to ascertain in PLS as the clinical picture is dominated by widespread upper motor neuron signs. The likely contribution of cerebellar dysfunction to gait disturbance, falls, pseudobulbar affect and dysarthria may be overlooked in the context of progressive spasticity. The objective of this study is the comprehensive characterization of cerebellar gray and white matter degeneration in PLS using multiparametric quantitative neuroimaging methods to systematically evaluate each cerebellar lobule and peduncle. Forty-two patients with PLS and 117 demographically-matched healthy controls were enrolled in a prospective MRI study. Complementary volumetric and voxelwise analyses revealed focal cerebellar alterations instead of global cerebellar atrophy. Bilateral gray matter volume reductions were observed in lobules III, IV and VIIb. Significant diffusivity alterations within the superior cerebellar peduncle indicate disruption of the main cerebellar outflow tracts. These findings suggest that the considerable intra-cerebellar disease-burden is coupled with concomitant cerebro-cerebellar connectivity disruptions. While cerebellar dysfunction is challenging to demonstrate clinically, cerebellar pathology is likely to be a significant contributor to disability in PLS.

Predictors of survival in patients with amyotrophic lateral sclerosis: A large meta-analysis

Background

The survival time of amyotrophic lateral sclerosis (ALS) is greatly variable and protective or risk effects of the potential survival predictors are controversial. Thus, we aim to undertake a comprehensive meta-analysis of studies investigating non-genetic prognostic and survival factors in patients with ALS.

Methods

A search of relevant literature from PubMed, Embase, Cochrane library and other citations from 1^st January 1966 to 1^st December 020 was conducted. Random-effects models were conducted to pool the multivariable or adjusted hazard ratios (HR) by Stata MP 16.0. PROSPERO registration number: CRD42021256923.

Findings

A total of 5717 reports were identified, with 115 studies meeting pre-designed inclusion criteria involving 55,169 ALS patients. Five dimensions, including demographic, environmental or lifestyle, clinical manifestations, biochemical index, therapeutic factors or comorbidities were investigated. Twenty-five prediction factors, including twenty non-intervenable and five intervenable factors, were associated with ALS survival. Among them, NFL (HR:3.70, 6.80, in serum and CSF, respectively), FTD (HR:2.98), ALSFRS-R change (HR:2.37), respiratory subtype (HR:2.20), executive dysfunction (HR:2.10) and age of onset (HR:1.03) were superior predictors for poor prognosis, but pLMN or pUMN (HR:0.32), baseline ALSFRS-R score (HR:0.95), duration (HR:0.96), diagnostic delay (HR:0.97) were superior predictors for a good prognosis. Our results did not support the involvement of gender, education level, diabetes, hypertension, NIV, gastrostomy, and statins in ALS survival.

Interpretation

Our study provided a comprehensive and quantitative index for assessing the prognosis for ALS patients, and the identified non-intervenable or intervenable factors will facilitate the development of treatment strategies for ALS.

Funding

This study was supported by the National Natural Science Fund of China (Grant No. 81971188), the 1.3.5 project for disciplines of excellence, West China Hospital, Sichuan University (Grant No. 2019HXFH046), and the Science and Technology Bureau Fund of Sichuan Province (No. 2019YFS0216).

Propagation patterns in motor neuron diseases: Individual and phenotype-associated disease-burden trajectories across the UMN-LMN spectrum of MNDs

Motor neuron diseases encompass a divergent group of conditions with considerable differences in clinical manifestations, survival, and genetic vulnerability. One of the key aspects of clinical heterogeneity is the preferential involvement of upper (UMN) and lower motor neurons (LMN). While longitudinal imaging patters are relatively well characterized in ALS, progressive cortical changes in UMN,- and LMN-predominant conditions are seldom evaluated. Accordingly, the objective of this study is the juxtaposition of longitudinal trajectories in 3 motor neuron phenotypes; a UMN-predominant syndrome (PLS), a mixed UMN-LMN condition (ALS), and a lower motor neuron condition (poliomyelitis survivors). A standardized imaging protocol was implemented in a prospective, multi-timepoint longitudinal study with a uniform follow-up interval of 4 months. Forty-five poliomyelitis survivors, 61 patients with amyotrophic lateral sclerosis (ALS), and 23 patients with primary lateral sclerosis (PLS) were included. Cortical thickness alterations were evaluated in a dual analysis pipeline, using standard cortical thickness analyses, and a z-score-based individualized approach. Our results indicate that PLS patients exhibit rapidly progressive cortical thinning primarily in motor regions; ALS patients show cortical atrophy in both motor and extra-motor regions, while poliomyelitis survivors exhibit cortical thickness gains in a number of cerebral regions. Our findings suggest that dynamic cortical changes in motor neuron diseases may depend on relative UMN and/or LMN involvement, and increased cortical thickness in LMN-predominant conditions may represent compensatory, adaptive processes.

Pathological neural networks and artificial neural networks in ALS: diagnostic classification based on pathognomonic neuroimaging features

The description of group-level, genotype- and phenotype-associated imaging traits is academically important, but the practical demands of clinical neurology centre on the accurate classification of individual patients into clinically relevant diagnostic, prognostic and phenotypic categories. Similarly, pharmaceutical trials require the precision stratification of participants based on quantitative measures. A single-centre study was conducted with a uniform imaging protocol to test the accuracy of an artificial neural network classification scheme on a cohort of 378 participants composed of patients with ALS, healthy subjects and disease controls. A comprehensive panel of cerebral volumetric measures, cortical indices and white matter integrity values were systematically retrieved from each participant and fed into a multilayer perceptron model. Data were partitioned into training and testing and receiver-operating characteristic curves were generated for the three study-groups. Area under the curve values were 0.930 for patients with ALS, 0.958 for disease controls, and 0.931 for healthy controls relying on all input imaging variables. The ranking of variables by classification importance revealed that white matter metrics were far more relevant than grey matter indices to classify single subjects. The model was further tested in a subset of patients scanned within 6 weeks of their diagnosis and an AUC of 0.915 was achieved. Our study indicates that individual subjects may be accurately categorised into diagnostic groups in an observer-independent classification framework based on multiparametric, spatially registered radiology data. The development and validation of viable computational models to interpret single imaging datasets are urgently required for a variety of clinical and clinical trial applications.

Frontotemporal Pathology in Motor Neuron Disease Phenotypes: Insights From Neuroimaging

Frontotemporal involvement has been extensively investigated in amyotrophic lateral sclerosis (ALS) but remains relatively poorly characterized in other motor neuron disease (MND) phenotypes such as primary lateral sclerosis (PLS), progressive muscular atrophy (PMA), spinal muscular atrophy (SMA), spinal bulbar muscular atrophy (SBMA), post poliomyelitis syndrome (PPS), and hereditary spastic paraplegia (HSP). This review focuses on insights from structural, metabolic, and functional neuroimaging studies that have advanced our understanding of extra-motor disease burden in these phenotypes. The imaging literature is limited in the majority of these conditions and frontotemporal involvement has been primarily evaluated by neuropsychology and post mortem studies. Existing imaging studies reveal that frontotemporal degeneration can be readily detected in ALS and PLS, varying degree of frontotemporal pathology may be captured in PMA, SBMA, and HSP, SMA exhibits cerebral involvement without regional predilection, and there is limited evidence for cerebral changes in PPS. Our review confirms the heterogeneity extra-motor pathology across the spectrum of MNDs and highlights the role of neuroimaging in characterizing anatomical patterns of disease burden in vivo. Despite the contribution of neuroimaging to MND research, sample size limitations, inclusion bias, attrition rates in longitudinal studies, and methodological constraints need to be carefully considered. Frontotemporal involvement is a quintessential clinical facet of MND which has important implications for screening practices, individualized management strategies, participation in clinical trials, caregiver burden, and resource allocation. The academic relevance of imaging frontotemporal pathology in MND spans from the identification of genetic variants, through the ascertainment of presymptomatic changes to the design of future epidemiology studies.

Prediction of survival in amyotrophic lateral sclerosis: a nationwide, Danish cohort study

Introduction

Amyotrophic lateral sclerosis (ALS) is a progressive motor neuron disease with great heterogeneity. Biological prognostic markers are needed for the patients to plan future supportive treatment, palliative treatment, and end-of-life decisions. In addition, prognostic markers are greatly needed for the randomization in clinical trials.

Objective

This study aimed to test the ALS Functional Rating Scale-Revised (ALSFRS-R) progression rate (ΔFS) as a prognostic marker of survival in a Danish ALS cohort.

Methods

The ALSFRS-R score at test date in association with duration of symptoms, from the onset of symptoms until test date, (defined as ΔFS’) was calculated for 90 Danish patients diagnosed with either probable or definite sporadic ALS. Median survival time was then estimated from the onset of symptoms until primary endpoint (either death or tracheostomy). ΔFS’ was subjected to survival analysis using Cox proportional hazards modelling, log-rank test, and Kaplan-Meier survival analysis.

Results and conclusions

Both ΔFS’ and age was found to be strong predictors of survival of the Danish ALS cohort. Both variables are easily obtained at the time of diagnosis and could be used by clinicians and ALS patients to plan future supportive and palliative treatment. Furthermore, ΔFS’, is a simple, prognostic marker that predicts survival in the early phase of disease as well as at later stages of the disease.

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.

Cortical progression patterns in individual ALS patients across multiple timepoints: a mosaic-based approach for clinical use

INTRODUCTION

The majority of imaging studies in ALS infer group-level imaging signatures from group comparisons, as opposed to estimating disease burden in individual patients. In a condition with considerable clinical heterogeneity, the characterisation of individual patterns of pathology is hugely relevant. In this study, we evaluate a strategy to track progressive cortical involvement in single patients by using subject-specific reference cohorts.

METHODS

We have interrogated a multi-timepoint longitudinal dataset of 61 ALS patients to demonstrate the utility of estimating cortical disease burden and the expansion of cerebral atrophy over time. We contrast our strategy to the gold-standard approach to gauge the advantages and drawbacks of our method. We modelled the evolution of cortical integrity in a conditional growth model, in which we accounted for age, gender, disability, symptom duration, education and handedness. We hypothesised that the variance associated with demographic variables will be successfully eliminated in our approach.

RESULTS

In our model, the only covariate which modulated the expansion of atrophy was motor disability as measured by the ALSFRS-r (t(153) = - 2.533, p = 0.0123). Using the standard approach, age also significantly influenced progression of CT change (t(153) = - 2.151, p = 0.033) demonstrating the validity and potential clinical utility of our approach.

CONCLUSION

Our strategy of estimating the extent of cortical atrophy in individual patients with ALS successfully corrects for demographic factors and captures relevant cortical changes associated with clinical disability. Our approach provides a framework to interpret single T1-weighted images in ALS and offers an opportunity to track cortical propagation patterns both at individual subject level and at cohort level.

The imaging signature of C9orf72 hexanucleotide repeat expansions: implications for clinical trials and therapy development

While C9orf72-specific imaging signatures have been proposed by both ALS and FTD research groups and considerable presymptomatic alterations have also been confirmed in young mutation carriers, considerable inconsistencies exist in the literature. Accordingly, a systematic review of C9orf72-imaging studies has been performed to identify consensus findings, stereotyped shortcomings, and unique contributions to outline future directions. A formal literature review was conducted according to the STROBE guidelines. All identified papers were individually reviewed for sample size, choice of controls, study design, imaging modalities, statistical models, clinical profiling, and identified genotype-associated pathological patterns. A total of 74 imaging papers were systematically reviewed. ALS patients with GGGGCC repeat expansions exhibit relatively limited motor cortex involvement and widespread extra-motor pathology. C9orf72 positive FTD patients often show preferential posterior involvement. Reports of thalamic involvement are relatively consistent across the various phenotypes. Asymptomatic hexanucleotide repeat carriers often exhibit structural and functional changes decades prior to symptom onset. Common shortcomings included sample size limitations, lack of disease-controls, limited clinical profiling, lack of genetic testing in healthy controls, and absence of post mortem validation. There is a striking paucity of longitudinal studies and existing presymptomatic studies have not evaluated the predictive value of radiological changes with regard to age of onset and phenoconversion. With the advent of antisense oligonucleotide therapies, the meticulous characterisation of C9orf72-associated changes has gained practical relevance. Neuroimaging offers non-invasive biomarkers for future clinical trials, presymptomatic ascertainment, diagnostic and prognostic applications.

The presymptomatic phase of amyotrophic lateral sclerosis: are we merely scratching the surface?

Presymptomatic studies in ALS have consistently captured considerable disease burden long before symptom manifestation and contributed important academic insights. With the emergence of genotype-specific therapies, however, there is a pressing need to address practical objectives such as the estimation of age of symptom onset, phenotypic prediction, informing the optimal timing of pharmacological intervention, and identifying a core panel of biomarkers which may detect response to therapy. Existing presymptomatic studies in ALS have adopted striking different study designs, relied on a variety of control groups, used divergent imaging and electrophysiology methods, and focused on different genotypes and demographic groups. We have performed a systematic review of existing presymptomatic studies in ALS to identify common themes, stereotyped shortcomings, and key learning points for future studies. Existing presymptomatic studies in ALS often suffer from sample size limitations, lack of disease controls and rarely follow their cohort until symptom manifestation. As the characterisation of presymptomatic processes in ALS serves a multitude of academic and clinical purposes, the careful review of existing studies offers important lessons for future initiatives.