Machine Learning in Amyotrophic Lateral Sclerosis: Achievements, Pitfalls, and Future Directions

Metabolite alterations in the left dorsolateral prefrontal cortex and its association with cognitive assessments in amyotrophic lateral sclerosis: A longitudinal magnetic resonance spectroscopy study

OBJECTIVE

To characterize the longitudinal metabolite profile of the left dorsolateral prefrontal cortex (DLPFC) in amyotrophic lateral sclerosis (ALS) using magnetic resonance spectroscopy (MRS) and to examine its correlation with cognitive assessments.

METHODS

Thirteen patients at baseline and ten at follow-up, along with 14 age-, sex-, and handedness-matched healthy controls (HCs), were recruited. Three Tesla with a 64-channel coil, Point-RESolved Spectroscopy (PRESS) sequence (TR=1500 ms and TE=140 ms) was used. Metabolites in the left DLPFC were quantified using LCModel. Cognitive performance and functional impairment were assessed using the Edinburgh Cognitive and Behavioral ALS Screen (ECAS) and Revised ALS Functional Rating Scale (ALSFRS-R), respectively. Group comparisons were adjusted for multiple comparisons (p < 0.05, Bonferroni correction). The links between the brain metabolites and cognitive function were investigated using relevant correlation tests (Pearson's or Spearman's).

RESULTS

Our analysis revealed a significant difference in the choline-to-creatine ratio (tCho/tCr) among the three groups. Baseline ALS patients showed a higher tCho/tCr ratio than HCs (p = 0.033, Bonferroni-corrected). Interestingly, the total N-acetyl aspartate (tNAA)/tCr ratio, a marker of neuronal health, was strongly positively correlated with visuospatial cognitive scores at baseline and follow-up. Furthermore, at follow-up, tNAA/tCr was positively correlated with the total scores and specific sub-scores on the ECAS, encompassing both ALS-specific and non-specific cognitive domains. At follow-up, positive correlations emerged between tNAA/tCr and the total language and executive function scores.

CONCLUSIONS

Metabolite alterations and correlations with cognition were observed in the left DLPFC of ALS patients, supporting extra-motor involvement and its association with cognitive decline.

Improving prediction models of amyotrophic lateral sclerosis (ALS) using polygenic, pre-existing conditions, and survey-based risk scores in the UK Biobank

BACKGROUND AND OBJECTIVES

Amyotrophic lateral sclerosis (ALS) causes profound impairments in neurological function, and a cure for this devastating disease remains elusive. This study aimed to identify pre-disposing genetic, phenotypic, and exposure-related factors for amyotrophic lateral sclerosis using multi-modal data and assess their joint predictive potential.

METHODS

Utilizing data from the UK (United Kingdom) Biobank, we analyzed an unrelated set of 292 ALS cases and 408,831 controls of European descent. Two polygenic risk scores (PRS) are constructed: "GWAS Hits PRS" and "PRS-CS," reflecting oligogenic and polygenic ALS risk profiles, respectively. Time-restricted phenome-wide association studies (PheWAS) were performed to identify pre-existing conditions increasing ALS risk, integrated into phenotypic risk scores (PheRS). A poly-exposure score ("PXS") captures the influence of environmental exposures measured through survey questionnaires. We evaluate the performance of these scores for predicting ALS incidence and stratifying risk, adjusting for baseline demographic covariates.

RESULTS

Both PRSs modestly predicted ALS diagnosis but with increased predictive power when combined (covariate-adjusted receiver operating characteristic [AAUC] = 0.584 [0.525, 0.639]). PheRS incorporated diagnoses 1 year before ALS onset (PheRS1) modestly discriminated cases from controls (AAUC = 0.515 [0.472, 0.564]). The "PXS" did not significantly predict ALS. However, a model incorporating PRSs and PheRS1 improved the prediction of ALS (AAUC = 0.604 [0.547, 0.667]), outperforming a model combining all risk scores. This combined risk score identified the top 10% of risk score distribution with a fourfold higher ALS risk (95% CI [2.04, 7.73]) versus those in the 40%-60% range.

DISCUSSION

By leveraging UK Biobank data, our study uncovers pre-disposing ALS factors, highlighting the improved effectiveness of multi-factorial prediction models to identify individuals at highest risk for ALS.

Artificial intelligence for screening and diagnosis of amyotrophic lateral sclerosis: a systematic review and meta-analysis

INTRODUCTION

Amyotrophic lateral sclerosis (ALS) is a rare and fatal neurological disease that leads to progressive motor function degeneration. Diagnosing ALS is challenging due to the absence of a specific detection test. The use of artificial intelligence (AI) can assist in the investigation and treatment of ALS.

METHODS

We searched seven databases for literature on the application of AI in the early diagnosis and screening of ALS in humans. The findings were summarized using random-effects summary receiver operating characteristic curve. The risk of bias (RoB) analysis was carried out using QUADAS-2 or QUADAS-C tools.

RESULTS

In the 34 analyzed studies, a meta-prevalence of 47% for ALS was noted. For ALS detection, the pooled sensitivity of AI models was 94.3% (95% CI - 63.2% to 99.4%) with a pooled specificity of 98.9% (95% CI - 92.4% to 99.9%). For ALS classification, the pooled sensitivity of AI models was 90.9% (95% CI - 86.5% to 93.9%) with a pooled specificity of 92.3% (95% CI - 84.8% to 96.3%). Based on type of input for classification, the pooled sensitivity of AI models for gait, electromyography, and magnetic resonance signals was 91.2%, 92.6%, and 82.2%, respectively. The pooled specificity for gait, electromyography, and magnetic resonance signals was 94.1%, 96.5%, and 77.3%, respectively.

CONCLUSIONS

Although AI can play a significant role in the screening and diagnosis of ALS due to its high sensitivities and specificities, concerns remain regarding quality of evidence reported in the literature.

Connected Speech Fluency in Poststroke and Progressive Aphasia: A Scoping Review of Quantitative Approaches and Features

PURPOSE

Speech fluency has important diagnostic implications for individuals with poststroke aphasia (PSA) as well as primary progressive aphasia (PPA), and quantitative assessment of connected speech has emerged as a widely used approach across both etiologies. The purpose of this review was to provide a clearer picture on the range, nature, and utility of individual quantitative speech/language measures and methods used to assess connected speech fluency in PSA and PPA, and to compare approaches across etiologies.

METHOD

We conducted a scoping review of literature published between 2012 and 2022 following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews guidelines. Forty-five studies were included in the review. Literature was charted and summarized by etiology and characteristics of included patient populations and method(s) used for derivation and analysis of speech/language features. For a subset of included articles, we also charted the individual quantitative speech/language features reported and the level of significance of reported results.

RESULTS

Results showed that similar methodological approaches have been used to quantify connected speech fluency in both PSA and PPA. Two hundred nine individual speech-language features were analyzed in total, with low levels of convergence across etiology on specific features but greater agreement on the most salient features. The most useful features for differentiating fluent from nonfluent aphasia in both PSA and PPA were features related to overall speech quantity, speech rate, or grammatical competence.

CONCLUSIONS

Data from this review demonstrate the feasibility and utility of quantitative approaches to index connected speech fluency in PSA and PPA. We identified emergent trends toward automated analysis methods and data-driven approaches, which offer promising avenues for clinical translation of quantitative approaches. There is a further need for improved consensus on which subset of individual features might be most clinically useful for assessment and monitoring of fluency.

SUPPLEMENTAL MATERIAL

https://doi.org/10.23641/asha.25537237.

Improving prediction models of amyotrophic lateral sclerosis (ALS) using polygenic, pre-existing conditions, and survey-based risk scores in the UK Biobank

Background and Objectives

Amyotrophic lateral sclerosis (ALS) causes profound impairments in neurological function and a cure for this devastating disease remains elusive. Early detection and risk stratification are crucial for timely intervention and improving patient outcomes. This study aimed to identify predisposing genetic, phenotypic, and exposure-related factors for Amyotrophic lateral sclerosis using multi-modal data and assess their joint predictive potential.

Methods

Utilizing data from the UK Biobank, we analyzed an unrelated set of 292 ALS cases and 408,831 controls of European descent. Two polygenic risk scores (PRS) are constructed: "GWAS Hits PRS" and "PRS-CS," reflecting oligogenic and polygenic ALS risk profiles, respectively. Time-restricted phenome-wide association studies (PheWAS) were performed to identify pre-existing conditions increasing ALS risk, integrated into phenotypic risk scores (PheRS). A poly-exposure score ("PXS") captures the influence of environmental exposures measured through survey questionnaires. We evaluate the performance of these scores for predicting ALS incidence and stratifying risk, adjusting for baseline demographic covariates.

Results

Both PRSs modestly predicted ALS diagnosis, but with increased predictive power when combined (covariate-adjusted receiver operating characteristic [AAUC] = 0.584 [0.525, 0.639]). PheRS incorporated diagnoses 1 year before ALS onset (PheRS1) modestly discriminated cases from controls (AAUC = 0.515 [0.472, 0.564]). The "PXS" did not significantly predict ALS. However, a model incorporating PRSs and PheRS1 improved prediction of ALS (AAUC = 0.604 [0.547, 0.667]), outperforming a model combining all risk scores. This combined risk score identified the top 10% of risk score distribution with a 4-fold higher ALS risk (95% CI: [2.04, 7.73]) versus those in the 40%-60% range.

Discussions

By leveraging UK Biobank data, our study uncovers predisposing ALS factors, highlighting the improved effectiveness of multi-factorial prediction models to identify individuals at highest risk for ALS.

The role of artificial intelligence in electrodiagnostic and neuromuscular medicine: Current state and future directions

The rapid advancements in artificial intelligence (AI), including machine learning (ML), and deep learning (DL) have ushered in a new era of technological breakthroughs in healthcare. These technologies are revolutionizing the way we utilize medical data, enabling improved disease classification, more precise diagnoses, better treatment selection, therapeutic monitoring, and highly accurate prognostication. Different ML and DL models have been used to distinguish between electromyography signals in normal individuals and those with amyotrophic lateral sclerosis and myopathy, with accuracy ranging from 67% to 99.5%. DL models have also been successfully applied in neuromuscular ultrasound, with the use of segmentation techniques achieving diagnostic accuracy of at least 90% for nerve entrapment disorders, and 87% for inflammatory myopathies. Other successful AI applications include prediction of treatment response, and prognostication including prediction of intensive care unit admissions for patients with myasthenia gravis. Despite these remarkable strides, significant knowledge, attitude, and practice gaps persist, including within the field of electrodiagnostic and neuromuscular medicine. In this narrative review, we highlight the fundamental principles of AI and draw parallels with the intricacies of human brain networks. Specifically, we explore the immense potential that AI holds for applications in electrodiagnostic studies, neuromuscular ultrasound, and other aspects of neuromuscular medicine. While there are exciting possibilities for the future, it is essential to acknowledge and understand the limitations of AI and take proactive steps to mitigate these challenges. This collective endeavor holds immense potential for the advancement of healthcare through the strategic and responsible integration of AI technologies.

Emerging perspectives of synaptic biomarkers in ALS and FTD

Amyotrophic Lateral Sclerosis (ALS) and Frontotemporal Dementia (FTD) are debilitating neurodegenerative diseases with shared pathological features like transactive response DNA-binding protein of 43 kDa (TDP-43) inclusions and genetic mutations. Both diseases involve synaptic dysfunction, contributing to their clinical features. Synaptic biomarkers, representing proteins associated with synaptic function or structure, offer insights into disease mechanisms, progression, and treatment responses. These biomarkers can detect disease early, track its progression, and evaluate therapeutic efficacy. ALS is characterized by elevated neurofilament light chain (NfL) levels in cerebrospinal fluid (CSF) and blood, correlating with disease progression. TDP-43 is another key ALS biomarker, its mislocalization linked to synaptic dysfunction. In FTD, TDP-43 and tau proteins are studied as biomarkers. Synaptic biomarkers like neuronal pentraxins (NPs), including neuronal pentraxin 2 (NPTX2), and neuronal pentraxin receptor (NPTXR), offer insights into FTD pathology and cognitive decline. Advanced technologies, like machine learning (ML) and artificial intelligence (AI), aid biomarker discovery and drug development. Challenges in this research include technological limitations in detection, variability across patients, and translating findings from animal models. ML/AI can accelerate discovery by analyzing complex data and predicting disease outcomes. Synaptic biomarkers offer early disease detection, personalized treatment strategies, and insights into disease mechanisms. While challenges persist, technological advancements and interdisciplinary efforts promise to revolutionize the understanding and management of ALS and FTD. This review will explore the present comprehension of synaptic biomarkers in ALS and FTD and discuss their significance and emphasize the prospects and obstacles.

Machine learning hypothesis-generation for patient stratification and target discovery in rare disease: our experience with Open Science in ALS

Introduction

Advances in machine learning (ML) methodologies, combined with multidisciplinary collaborations across biological and physical sciences, has the potential to propel drug discovery and development. Open Science fosters this collaboration by releasing datasets and methods into the public space; however, further education and widespread acceptance and adoption of Open Science approaches are necessary to tackle the plethora of known disease states.

Motivation

In addition to providing much needed insights into potential therapeutic protein targets, we also aim to demonstrate that small patient datasets have the potential to provide insights that usually require many samples (>5,000). There are many such datasets available and novel advancements in ML can provide valuable insights from these patient datasets.

Problem statement

Using a public dataset made available by patient advocacy group AnswerALS and a multidisciplinary Open Science approach with a systems biology augmented ML technology, we aim to validate previously reported drug targets in ALS and provide novel insights about ALS subpopulations and potential drug targets using a unique combination of ML methods and graph theory.

Methodology

We use NetraAI to generate hypotheses about specific patient subpopulations, which were then refined and validated through a combination of ML techniques, systems biology methods, and expert input.

Results

We extracted 8 target classes, each comprising of several genes that shed light into ALS pathophysiology and represent new avenues for treatment. These target classes are broadly categorized as inflammation, epigenetic, heat shock, neuromuscular junction, autophagy, apoptosis, axonal transport, and excitotoxicity. These findings are not mutually exclusive, and instead represent a systematic view of ALS pathophysiology. Based on these findings, we suggest that simultaneous targeting of ALS has the potential to mitigate ALS progression, with the plausibility of maintaining and sustaining an improved quality of life (QoL) for ALS patients. Even further, we identified subpopulations based on disease onset.

Conclusion

In the spirit of Open Science, this work aims to bridge the knowledge gap in ALS pathophysiology to aid in diagnostic, prognostic, and therapeutic strategies and pave the way for the development of personalized treatments tailored to the individual's needs.

Exploring the cuproptosis-related molecular clusters in the peripheral blood of patients with amyotrophic lateral sclerosis

BACKGROUND

Amyotrophic lateral sclerosis (ALS) is a progressive and lethal neurodegenerative disease. Several studies have suggested the involvement of cuproptosis in its pathogenesis. In this research, we intend to explore the cuproptosis-related molecular clusters in ALS and develop a novel cuproptosis-related genes prediction model.

METHODS

The peripheral blood gene expression data was downloaded from the Gene Expression Omnibus (GEO) online database. Based on the GSE112681 dataset, we investigated the critical cuproptosis-related genes (CuRGs) and pathological clustering of ALS. The immune microenvironment features of the peripheral blood in ALS patients were also examined using the CIBERSORT algorithm. Cluster-specific hub genes were determined by the WGCNA. The most accurate prediction model was selected by comparing the performance of four machine learning techniques. ROC curves and two independent datasets were applied to validate the prediction accuracy. The available compounds targeting these hub genes were filtered to investigate their efficacy in treating ALS.

RESULTS

We successfully determined four critical cuproptosis-related genes and two pathological clusters with various immune profiles and biological characteristics in ALS. Functional analysis showed that genes in Cluster1 were primarily enriched in pathways closely associated with immunity. The Support Vector Machine (SVM) model exhibited the best discrimination properties with a large area under the curve (AUC = 0.862). Five hub prediction genes (BAP1, SMG1, BCLAF1, DHX15, EIF4G2) were selected to establish a nomogram model, suggesting significant risk prediction potential for ALS. The accuracy of this model in predicting ALS incidence was also demonstrated through calibration curves, nomograms, and decision curve analysis. Finally, three drugs targeting BAP1 were determined through drug-gene interactions.

CONCLUSION

This study elucidated the complex associations between cuproptosis and ALS and constructed a satisfactory predictive model to explore the pathological characteristics of different clusters in ALS patients.

Biomarkers in amyotrophic lateral sclerosis: current status and future prospects

Disease heterogeneity in amyotrophic lateral sclerosis poses a substantial challenge in drug development. Categorization based on clinical features alone can help us predict the disease course and survival, but quantitative measures are also needed that can enhance the sensitivity of the clinical categorization. In this Review, we describe the emerging landscape of diagnostic, categorical and pharmacodynamic biomarkers in amyotrophic lateral sclerosis and their place in the rapidly evolving landscape of new therapeutics. Fluid-based markers from cerebrospinal fluid, blood and urine are emerging as useful diagnostic, pharmacodynamic and predictive biomarkers. Combinations of imaging measures have the potential to provide important diagnostic and prognostic information, and neurophysiological methods, including various electromyography-based measures and quantitative EEG-magnetoencephalography-evoked responses and corticomuscular coherence, are generating useful diagnostic, categorical and prognostic markers. Although none of these biomarker technologies has been fully incorporated into clinical practice or clinical trials as a primary outcome measure, strong evidence is accumulating to support their clinical utility.

The involvement of language-associated networks, tracts, and cortical regions in frontotemporal dementia and amyotrophic lateral sclerosis: Structural and functional alterations

BACKGROUND

Language deficits are cardinal manifestations of some frontotemporal dementia (FTD) phenotypes and also increasingly recognized in sporadic and familial amyotrophic lateral sclerosis (ALS). They have considerable social and quality-of-life implications, and adaptive strategies are challenging to implement. While the neuropsychological profiles of ALS-FTD phenotypes are well characterized, the neuronal underpinnings of language deficits are less well studied.

METHODS

A multiparametric, quantitative neuroimaging study was conducted to characterize the involvement of language-associated networks, tracts, and cortical regions with a panel of structural, diffusivity, and functional magnetic resonance imaging (MRI) metrics. Seven study groups were evaluated along the ALS-FTD spectrum: healthy controls (HC), individuals with ALS without cognitive impairment (ALSnci), C9orf72-negative ALS-FTD, C9orf72-positive ALS-FTD, behavioral-variant FTD (bvFTD), nonfluent variant primary progressive aphasia (nfvPPA), and semantic variant PPA (svPPA). The integrity of the Broca's area, Wernicke's area, frontal aslant tract (FAT), arcuate fascicle (AF), inferior occipitofrontal fascicle (IFO), inferior longitudinal fascicle (ILF), superior longitudinal fascicle (SLF), and uncinate fascicle (UF) was quantitatively evaluated. The functional connectivity (FC) between Broca's and Wernicke' areas and FC along the FAT was also specifically assessed.

RESULTS

Patients with nfvPPA and svPPA exhibit distinctive patterns of gray and white matter degeneration in language-associated brain regions. Individuals with bvFTD exhibit Broca's area, right FAT, right IFO, and UF degeneration. The ALSnci group exhibits Broca's area atrophy and decreased FC along the FAT. Both ALS-FTD cohorts, irrespective of C9orf72 status, show bilateral FAT, AF, and IFO pathology. Interestingly, only C9orf72-negative ALS-FTD patients exhibit bilateral uncinate and right ILF involvement, while C9orf72-positive ALS-FTD patients do not.

CONCLUSIONS

Language-associated tracts and networks are not only affected in language-variant FTD phenotypes but also in ALS and bvFTD. Language domains should be routinely assessed in ALS irrespective of the genotype.

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

BACKGROUND

The characterisation of presymptomatic disease-burden patterns in asymptomatic mutation carriers has a dual academic and clinical relevance. The understanding of disease propagation mechanisms is of considerable conceptual interests, and defining the optimal time of pharmacological intervention is essential for improved clinical trial outcomes.

METHODS

In a prospective, multimodal neuroimaging study, 22 asymptomatic C9orf72 GGGGCC hexanucleotide repeat carriers, 13 asymptomatic subjects with SOD1, and 54 "gene-negative" ALS kindreds were enrolled. Cortical and subcortical grey matter alterations were systematically appraised using volumetric, morphometric, vertex, and cortical thickness analyses. Using a Bayesian approach, the thalamus and amygdala were further parcellated into specific nuclei and the hippocampus was segmented into anatomically defined subfields.

RESULTS

Asymptomatic GGGGCC hexanucleotide repeat carriers in C9orf72 exhibited early subcortical changes with the preferential involvement of the pulvinar and mediodorsal regions of the thalamus, as well as the lateral aspect of the hippocampus. Volumetric approaches, morphometric methods, and vertex analyses were anatomically consistent in capturing focal subcortical changes in asymptomatic C9orf72 hexanucleotide repeat expansion carriers. SOD1 mutation carriers did not exhibit significant subcortical grey matter alterations. In our study, none of the two asymptomatic cohorts exhibited cortical grey matter alterations on either cortical thickness or morphometric analyses.

DISCUSSION

The presymptomatic radiological signature of C9orf72 is associated with selective thalamic and focal hippocampal degeneration which may be readily detectable before cortical grey matter changes ensue. Our findings confirm selective subcortical grey matter involvement early in the course of C9orf72-associated neurodegeneration.

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.

Sympathetic neuropathology is revealed in muscles affected by amyotrophic lateral sclerosis

Rationale: The anatomical substrate of skeletal muscle autonomic innervation has remained underappreciated since it was described many decades ago. As such, the structural and functional features of muscle sympathetic innervation are largely undetermined in both physiology and pathology, mainly due to methodological limitations in the histopathological analysis of small neuronal fibers in tissue samples. Amyotrophic lateral sclerosis (ALS) is a fatal neuromuscular disease which mainly targets motor neurons, and despite autonomic symptoms occurring in a significant fraction of patients, peripheral sympathetic neurons (SNs) are generally considered unaffected and, as such, poorly studied. Purpose: In this research, we compared sympathetic innervation of normal and ALS muscles, through structural analysis of the sympathetic network in human and murine tissue samples. Methods and Results: We first refined tissue processing to circumvent methodological limitations interfering with the detection of muscle sympathetic innervation. The optimized "Neuro Detection Protocol" (NDP) was validated in human muscle biopsies, demonstrating that SNs innervate, at high density, both blood vessels and skeletal myofibers, independent of the fiber metabolic type. Subsequently, NDP was exploited to analyze sympathetic innervation in muscles of SOD1^G93A mice, a preclinical ALS model. Our data show that ALS murine muscles display SN denervation, which has already initiated at the early disease stage and worsened during aging. SN degeneration was also observed in muscles of MLC/SOD1^G93A mice, with muscle specific expression of the SOD1^G93A mutant gene. Notably, similar alterations in SNs were observed in muscle biopsies from an ALS patient, carrying the SOD1^G93A mutation. Conclusion: We set up a protocol for the analysis of murine and, more importantly, human muscle sympathetic innervation. Our results indicate that SNs are additional cell types compromised in ALS and suggest that dysfunctional SOD1^G93A muscles affect their sympathetic innervation.

Quantitative Brain MRI Metrics Distinguish Four Different ALS Phenotypes: A Machine Learning Based Study

Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease whose diagnosis depends on the presence of combined lower motor neuron (LMN) and upper motor neuron (UMN) degeneration. LMN degeneration assessment is aided by electromyography, whereas no equivalent exists to assess UMN dysfunction. Magnetic resonance imaging (MRI) is primarily used to exclude conditions that mimic ALS. We have identified four different clinical/radiological phenotypes of ALS patients. We hypothesize that these ALS phenotypes arise from distinct pathologic processes that result in unique MRI signatures. To our knowledge, no machine learning (ML)-based data analyses have been performed to stratify different ALS phenotypes using MRI measures. During routine clinical evaluation, we obtained T1-, T2-, PD-weighted, diffusion tensor (DT) brain MRI of 15 neurological controls and 91 ALS patients (UMN-predominant ALS with corticospinal tract CST) hyperintensity, n = 21; UMN-predominant ALS without CST hyperintensity, n = 26; classic ALS, n = 23; and ALS patients with frontotemporal dementia, n = 21). From these images, we obtained 101 white matter (WM) attributes (including DT measures, graph theory measures from DT and fractal dimension (FD) measures using T1-weighted), 10 grey matter (GM) attributes (including FD based measures from T1-weighted), and 10 non-imaging attributes (2 demographic and 8 clinical measures of ALS). We employed classification and regression tree, Random Forest (RF) and also artificial neural network for the classifications. RF algorithm provided the best accuracy (70-94%) in classifying four different phenotypes of ALS patients. WM metrics played a dominant role in classifying different phenotypes when compared to GM or clinical measures. Although WM measures from both right and left hemispheres need to be considered to identify ALS phenotypes, they appear to be differentially affected by the degenerative process. Longitudinal studies can confirm and extend our findings.

Triclustering-based classification of longitudinal data for prognostic prediction: targeting relevant clinical endpoints in amyotrophic lateral sclerosis

This work proposes a new class of explainable prognostic models for longitudinal data classification using triclusters. A new temporally constrained triclustering algorithm, termed TCtriCluster, is proposed to comprehensively find informative temporal patterns common to a subset of patients in a subset of features (triclusters), and use them as discriminative features within a state-of-the-art classifier with guarantees of interpretability. The proposed approach further enhances prediction with the potentialities of model explainability by revealing clinically relevant disease progression patterns underlying prognostics, describing features used for classification. The proposed methodology is used in the Amyotrophic Lateral Sclerosis (ALS) Portuguese cohort (N = 1321), providing the first comprehensive assessment of the prognostic limits of five notable clinical endpoints: need for non-invasive ventilation (NIV); need for an auxiliary communication device; need for percutaneous endoscopic gastrostomy (PEG); need for a caregiver; and need for a wheelchair. Triclustering-based predictors outperform state-of-the-art alternatives, being able to predict the need for auxiliary communication device (within 180 days) and the need for PEG (within 90 days) with an AUC above 90%. The approach was validated in clinical practice, supporting healthcare professionals in understanding the link between the highly heterogeneous patterns of ALS disease progression and the prognosis.

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.

Thalamic pathology in frontotemporal dementia: Predilection for specific nuclei, phenotype-specific signatures, clinical correlates, and practical relevance

BACKGROUND

Frontotemporal dementia (FTD) phenotypes are classically associated with distinctive cortical atrophy patterns and regional hypometabolism. However, the spectrum of cognitive and behavioral manifestations in FTD arises from multisynaptic network dysfunction. The thalamus is a key hub of several corticobasal and corticocortical circuits. The main circuits relayed via the thalamic nuclei include the dorsolateral prefrontal circuit, the anterior cingulate circuit, and the orbitofrontal circuit.

METHODS

In this paper, we have reviewed evidence for thalamic pathology in FTD based on radiological and postmortem studies. Original research papers were systematically reviewed for preferential involvement of specific thalamic regions, for phenotype-associated thalamic disease burden patterns, characteristic longitudinal changes, and genotype-associated thalamic signatures. Moreover, evidence for presymptomatic thalamic pathology was also reviewed. Identified papers were systematically scrutinized for imaging methods, cohort sizes, clinical profiles, clinicoradiological associations, and main anatomical findings. The findings of individual research papers were amalgamated for consensus observations and their study designs further evaluated for stereotyped shortcomings. Based on the limitations of existing studies and conflicting reports in low-incidence FTD variants, we sought to outline future research directions and pressing research priorities.

RESULTS

FTD is associated with focal thalamic degeneration. Phenotype-specific thalamic traits mirror established cortical vulnerability patterns. Thalamic nuclei mediating behavioral and language functions are preferentially involved. Given the compelling evidence for considerable thalamic disease burden early in the course of most FTD subtypes, we also reflect on the practical relevance, diagnostic role, prognostic significance, and monitoring potential of thalamic metrics in FTD.

CONCLUSIONS

Cardinal manifestations of FTD phenotypes are likely to stem from thalamocortical circuitry dysfunction and are not exclusively driven by focal cortical changes.

Diffusion Tensor Imaging in Amyotrophic Lateral Sclerosis: Machine Learning for Biomarker Development

Diffusion tensor imaging (DTI) allows the in vivo imaging of pathological white matter alterations, either with unbiased voxel-wise or hypothesis-guided tract-based analysis. Alterations of diffusion metrics are indicative of the cerebral status of patients with amyotrophic lateral sclerosis (ALS) at the individual level. Using machine learning (ML) models to analyze complex and high-dimensional neuroimaging data sets, new opportunities for DTI-based biomarkers in ALS arise. This review aims to summarize how different ML models based on DTI parameters can be used for supervised diagnostic classifications and to provide individualized patient stratification with unsupervised approaches in ALS. To capture the whole spectrum of neuropathological signatures, DTI might be combined with additional modalities, such as structural T1w 3-D MRI in ML models. To further improve the power of ML in ALS and enable the application of deep learning models, standardized DTI protocols and multi-center collaborations are needed to validate multimodal DTI biomarkers. The application of ML models to multiparametric MRI/multimodal DTI-based data sets will enable a detailed assessment of neuropathological signatures in patients with ALS and the development of novel neuroimaging biomarkers that could be used in the clinical workup.

Symptoms timeline and outcomes in amyotrophic lateral sclerosis using artificial intelligence

Amyotrophic lateral sclerosis (ALS) is a fatal, neurodegenerative motor neuron disease. Although an early diagnosis is crucial to provide adequate care and improve survival, patients with ALS experience a significant diagnostic delay. This study aimed to use real-world data to describe the clinical profile and timing between symptom onset, diagnosis, and relevant outcomes in ALS. Retrospective and multicenter study in 5 representative hospitals and Primary Care services in the SESCAM Healthcare Network (Castilla-La Mancha, Spain). Using Natural Language Processing (NLP), the clinical information in electronic health records of all patients with ALS was extracted between January 2014 and December 2018. From a source population of all individuals attended in the participating hospitals, 250 ALS patients were identified (61.6% male, mean age 64.7 years). Of these, 64% had spinal and 36% bulbar ALS. For most defining symptoms, including dyspnea, dysarthria, dysphagia and fasciculations, the overall diagnostic delay from symptom onset was 11 (6-18) months. Prior to diagnosis, only 38.8% of patients had visited the neurologist. In a median post-diagnosis follow-up of 25 months, 52% underwent gastrostomy, 64% non-invasive ventilation, 16.4% tracheostomy, and 87.6% riluzole treatment; these were more commonly reported (all Ps < 0.05) and showed greater probability of occurrence (all Ps < 0.03) in bulbar ALS. Our results highlight the diagnostic delay in ALS and revealed differences in the clinical characteristics and occurrence of major disease-specific events across ALS subtypes. NLP holds great promise for its application in the wider context of rare neurological diseases.

MRI Clustering Reveals Three ALS Subtypes With Unique Neurodegeneration Patterns

OBJECTIVE

The purpose of this study was to identify subtypes of amyotrophic lateral sclerosis (ALS) by comparing patterns of neurodegeneration using brain magnetic resonance imaging (MRI) and explore their phenotypes.

METHODS

We performed T1-weighted and diffusion tensor imaging in 488 clinically well-characterized patients with ALS and 338 control subjects. Measurements of whole-brain cortical thickness and white matter connectome fractional anisotropy were adjusted for disease-unrelated variation. A probabilistic network-based clustering algorithm was used to divide patients into subgroups of similar neurodegeneration patterns. Clinical characteristics and cognitive profiles were assessed for each subgroup. In total, 512 follow-up scans were used to validate clustering results longitudinally.

RESULTS

The clustering algorithm divided patients with ALS into 3 subgroups of 187, 163, and 138 patients. All subgroups displayed involvement of the precentral gyrus and are characterized, respectively, by (1) pure motor involvement (pure motor cluster [PM]), (2) orbitofrontal and temporal involvement (frontotemporal cluster [FT]), and (3) involvement of the posterior cingulate cortex, parietal white matter, temporal operculum, and cerebellum (cingulate-parietal-temporal cluster [CPT]). These subgroups had significantly distinct clinical profiles regarding male-to-female ratio, age at symptom onset, and frequency of bulbar symptom onset. FT and CPT revealed higher rates of cognitive impairment on the Edinburgh cognitive and behavioral ALS screen (ECAS). Longitudinally, clustering remained stable: at 90.4% of their follow-up visits, patients clustered in the same subgroup as their baseline visit.

INTERPRETATION

ALS can manifest itself in 3 main patterns of cerebral neurodegeneration, each associated with distinct clinical characteristics and cognitive profiles. Besides the pure motor and frontotemporal dementia (FTD)-like variants of ALS, a new neuroimaging phenotype has emerged, characterized by posterior cingulate, parietal, temporal, and cerebellar involvement. ANN NEUROL 2022;92:1030-1045.

Cerebellar pathology in motor neuron disease: neuroplasticity and neurodegeneration

Amyotrophic lateral sclerosis is a relentlessly progressive multi-system condition. The clinical picture is dominated by upper and lower motor neuron degeneration, but extra-motor pathology is increasingly recognized, including cerebellar pathology. Post-mortem and neuroimaging studies primarily focus on the characterization of supratentorial disease, despite emerging evidence of cerebellar degeneration in amyotrophic lateral sclerosis. Cardinal clinical features of amyotrophic lateral sclerosis, such as dysarthria, dysphagia, cognitive and behavioral deficits, saccade abnormalities, gait impairment, respiratory weakness and pseudobulbar affect are likely to be exacerbated by co-existing cerebellar pathology. This review summarizes in vivo and post mortem evidence for cerebellar degeneration in amyotrophic lateral sclerosis. Structural imaging studies consistently capture cerebellar grey matter volume reductions, diffusivity studies readily detect both intra-cerebellar and cerebellar peduncle white matter alterations and functional imaging studies commonly report increased functional connectivity with supratentorial regions. Increased functional connectivity is commonly interpreted as evidence of neuroplasticity representing compensatory processes despite the lack of post-mortem validation. There is a scarcity of post-mortem studies focusing on cerebellar alterations, but these detect pTDP-43 in cerebellar nuclei. Cerebellar pathology is an overlooked facet of neurodegeneration in amyotrophic lateral sclerosis despite its contribution to a multitude of clinical symptoms, widespread connectivity to spinal and supratentorial regions and putative role in compensating for the degeneration of primary motor regions.

Learning Prognostic Models Using Disease Progression Patterns: Predicting the Need for Non-Invasive Ventilation in Amyotrophic Lateral Sclerosis

Amyotrophic Lateral Sclerosis is a devastating neurodegenerative disease causing rapid degeneration of motor neurons and usually leading to death by respiratory failure. Since there is no cure, treatment's goal is to improve symptoms and prolong survival. Non-invasive Ventilation (NIV) is an effective treatment, leading to extended life expectancy and improved quality of life. In this scenario, it is paramount to predict its need in order to allow preventive or timely administration. In this work, we propose to use itemset mining together with sequential pattern mining to unravel disease presentation patterns together with disease progression patterns by analysing, respectively, static data collected at diagnosis and longitudinal data from patient follow-up. The goal is to use these static and temporal patterns as features in prognostic models, enabling to take disease progression into account in predictions and promoting model interpretability. As case study, we predict the need for NIV within 90, 180 and 365 days (short, mid and long-term predictions). The learnt prognostic models are promising. Pattern evaluation through growth rate suggests bulbar function and phrenic nerve response amplitude, additionally to respiratory function, are significant features towards determining patient evolution. This confirms clinical knowledge regarding relevant biomarkers of disease progression towards respiratory insufficiency.

Learning prognostic models using a mixture of biclustering and triclustering: Predicting the need for non-invasive ventilation in Amyotrophic Lateral Sclerosis

Longitudinal cohort studies to study disease progression generally combine temporal features produced under periodic assessments (clinical follow-up) with static features associated with single-time assessments, genetic, psychophysiological, and demographic profiles. Subspace clustering, including biclustering and triclustering stances, enables the discovery of local and discriminative patterns from such multidimensional cohort data. These patterns, highly interpretable, are relevant to identifying groups of patients with similar traits or progression patterns. Despite their potential, their use for improving predictive tasks in clinical domains remains unexplored. In this work, we propose to learn predictive models from static and temporal data using discriminative patterns, obtained via biclustering and triclustering, as features within a state-of-the-art classifier, thus enhancing model interpretation. triCluster is extended to find time-contiguous triclusters in temporal data (temporal patterns) and a biclustering algorithm to discover coherent patterns in static data. The transformed data space, composed of bicluster and tricluster features, capture local and cross-variable associations with discriminative power, yielding unique statistical properties of interest. As a case study, we applied our methodology to follow-up data from Portuguese patients with Amyotrophic Lateral Sclerosis (ALS) to predict the need for non-invasive ventilation (NIV) since the last appointment. The results showed that, in general, our methodology outperformed baseline results using the original features. Furthermore, the bicluster/tricluster-based patterns used by the classifier can be used by clinicians to understand the models by highlighting relevant prognostic patterns.

Simultaneous PET/MRI: The future gold standard for characterizing motor neuron disease-A clinico-radiological and neuroscientific perspective

Neuroimaging assessment of motor neuron disease has turned into a cornerstone of its clinical workup. Amyotrophic lateral sclerosis (ALS), as a paradigmatic motor neuron disease, has been extensively studied by advanced neuroimaging methods, including molecular imaging by MRI and PET, furthering finer and more specific details of the cascade of ALS neurodegeneration and symptoms, facilitated by multicentric studies implementing novel methodologies. With an increase in multimodal neuroimaging data on ALS and an exponential improvement in neuroimaging technology, the need for harmonization of protocols and integration of their respective findings into a consistent model becomes mandatory. Integration of multimodal data into a model of a continuing cascade of functional loss also calls for the best attempt to correlate the different molecular imaging measurements as performed at the shortest inter-modality time intervals possible. As outlined in this perspective article, simultaneous PET/MRI, nowadays available at many neuroimaging research sites, offers the perspective of a one-stop shop for reproducible imaging biomarkers on neuronal damage and has the potential to become the new gold standard for characterizing motor neuron disease from the clinico-radiological and neuroscientific perspectives.

Multimodal in vivo staging in amyotrophic lateral sclerosis using artificial intelligence

Background

The underlying neuropathological process of amyotrophic lateral sclerosis (ALS) can be classified in a four‐stage sequential pTDP‐43 cerebral propagation scheme. Using diffusion tensor imaging (DTI), in vivo imaging of these stages has already been shown to be feasible for the specific corticoefferent tract systems. Because both cognitive and oculomotor dysfunctions are associated with microstructural changes at the brain level in ALS, a cognitive and an oculomotor staging classification were developed, respectively. The association of these different in vivo staging schemes has not been attempted to date.

Methods

A total of 245 patients with ALS underwent DTI, video‐oculography, and cognitive testing using Edinburgh Cognitive and Behavioral ALS Screen (ECAS). A set of tract‐related diffusion metrics, cognitive, and oculomotor parameters was selected for further analysis. Hierarchical and k‐means clustering algorithms were used to obtain an optimal cluster solution.

Results

According to cluster analysis, differentiation of patients with ALS into four clusters resulted: Cluster A showed the highest fractional anisotropy (FA) values and thereby the best performances in executive oculomotor tasks and cognitive tests, whereas cluster D showed the lowest FA values, the lowest ECAS scores, and the worst executive oculomotor performance across all clusters. Clusters B and C showed intermediate results regarding parameter values.

Discussion

In a multimodal dataset of technical assessments of brain structure and function in ALS, an artificial intelligence‐based cluster analysis showed high congruence of DTI, executive oculomotor function, and neuropsychological performance for mapping in vivo correlates of neuropathological spreading.

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.

Segmental alterations of the corpus callosum in motor neuron disease: A DTI and texture analysis in 575 patients

INTRODUCTION

Within the core neuroimaging signature of amyotrophic lateral sclerosis (ALS), the corpus callosum (CC) is increasingly recognized as a consistent feature. The aim of this study was to investigate the sensitivity and specificity of the microstructural segmental CC morphology, assessed by diffusion tensor imaging (DTI) and high-resolution T1-weighted (T1w) imaging, in a large cohort of ALS patients including different clinical phenotypes.

METHODS

In a single-centre study, 575 patients with ALS (classical phenotype, N  = 432; restricted phenotypes primary lateral sclerosis (PLS) N = 55, flail arm syndrome (FAS) N = 45, progressive bulbar palsy (PBP) N = 22, lower motor neuron disease (LMND) N = 21) and 112 healthy controls underwent multiparametric MRI, i.e. volume-rendering T1w scans and DTI. Tract-based fractional anisotropy statistics (TFAS) was applied to callosal tracts of CC areas I-V, identified from DTI data (tract-of-interest (TOI) analysis), and texture analysis was applied to T1w data. In order to further specify the callosal alterations, a support vector machine (SVM) algorithm was used to discriminate between motor neuron disease patients and controls.

RESULTS

The analysis of white matter integrity revealed predominantly FA reductions for tracts of the callosal areas I, II, and III (with highest reductions in callosal area III) for all ALS patients and separately for each phenotype when compared to controls; texture analysis demonstrated significant alterations of the parameters entropy and homogeneity for ALS patients and all phenotypes for the CC areas I, II, and III (with again highest reductions in callosal area III) compared to controls. With SVM applied on multiparametric callosal parameters of area III, a separation of all ALS patients including phenotypes from controls with 72% sensitivity and 73% specificity was achieved. These results for callosal area III parameters could be improved by an SVM of six multiparametric callosal parameters of areas I, II, and III, achieving a separation of all ALS patients including phenotypes from controls with 84% sensitivity and 85% specificity.

DISCUSSION

The multiparametric MRI texture and DTI analysis demonstrated substantial alterations of the frontal and central CC with most significant alterations in callosal area III (motor segment) in ALS and separately in all investigated phenotypes (PLS, FAS, PBP, LMND) in comparison to controls, while no significant differences were observed between ALS and its phenotypes. The combination of the texture and the DTI parameters in an unbiased SVM-based approach might contribute as a neuroimaging marker for the assessment of the CC in ALS, including subtypes.

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.

Emerging insights into the complex genetics and pathophysiology of amyotrophic lateral sclerosis

Amyotrophic lateral sclerosis is a fatal neurodegenerative disease. The discovery of genes associated with amyotrophic lateral sclerosis, commencing with SOD1 in 1993, started fairly gradually. Recent advances in genetic technology have led to the rapid identification of multiple new genes associated with the disease, and to a new understanding of oligogenic and polygenic disease risk. The overlap of genes associated with amyotrophic lateral sclerosis with those of other neurodegenerative diseases is shedding light on the phenotypic spectrum of neurodegeneration, leading to a better understanding of genotype-phenotype correlations. A deepening knowledge of the genetic architecture is allowing the characterisation of the molecular steps caused by various mutations that converge on recurrent dysregulated pathways. Of crucial relevance, mutations associated with amyotrophic lateral sclerosis are amenable to novel gene-based therapeutic options, an approach in use for other neurological illnesses. Lastly, the exposome-the summation of lifetime environmental exposures-has emerged as an influential component for amyotrophic lateral sclerosis through the gene-time-environment hypothesis. Our improved understanding of all these aspects will lead to long-awaited therapies and the identification of modifiable risks factors.

Clusters of anatomical disease-burden patterns in ALS: a data-driven approach confirms radiological subtypes

Amyotrophic lateral sclerosis (ALS) is associated with considerable clinical heterogeneity spanning from diverse disability profiles, differences in UMN/LMN involvement, divergent progression rates, to variability in frontotemporal dysfunction. A multitude of classification frameworks and staging systems have been proposed based on clinical and neuropsychological characteristics, but disease subtypes are seldom defined based on anatomical patterns of disease burden without a prior clinical stratification. A prospective research study was conducted with a uniform imaging protocol to ascertain disease subtypes based on preferential cerebral involvement. Fifteen brain regions were systematically evaluated in each participant based on a comprehensive panel of cortical, subcortical and white matter integrity metrics. Using min–max scaled composite regional integrity scores, a two-step cluster analysis was conducted. Two radiological clusters were identified; 35.5% of patients belonging to ‘Cluster 1’ and 64.5% of patients segregating to ‘Cluster 2’. Subjects in Cluster 1 exhibited marked frontotemporal change. Predictor ranking revealed the following hierarchy of anatomical regions in decreasing importance: superior lateral temporal, inferior frontal, superior frontal, parietal, limbic, mesial inferior temporal, peri-Sylvian, subcortical, long association fibres, commissural, occipital, ‘sensory’, ‘motor’, cerebellum, and brainstem. While the majority of imaging studies first stratify patients based on clinical criteria or genetic profiles to describe phenotype- and genotype-associated imaging signatures, a data-driven approach may identify distinct disease subtypes without a priori patient categorisation. Our study illustrates that large radiology datasets may be potentially utilised to uncover disease subtypes associated with unique genetic, clinical or prognostic profiles.

VoxelHop: Successive Subspace Learning for ALS Disease Classification Using Structural MRI

Deep learning has great potential for accurate detection and classification of diseases with medical imaging data, but the performance is often limited by the number of training datasets and memory requirements. In addition, many deep learning models are considered a "black-box," thereby often limiting their adoption in clinical applications. To address this, we present a successive subspace learning model, termed VoxelHop, for accurate classification of Amyotrophic Lateral Sclerosis (ALS) using T2-weighted structural MRI data. Compared with popular convolutional neural network (CNN) architectures, VoxelHop has modular and transparent structures with fewer parameters without any backpropagation, so it is well-suited to small dataset size and 3D imaging data. Our VoxelHop has four key components, including (1) sequential expansion of near-to-far neighborhood for multi-channel 3D data; (2) subspace approximation for unsupervised dimension reduction; (3) label-assisted regression for supervised dimension reduction; and (4) concatenation of features and classification between controls and patients. Our experimental results demonstrate that our framework using a total of 20 controls and 26 patients achieves an accuracy of 93.48 % and an AUC score of 0.9394 in differentiating patients from controls, even with a relatively small number of datasets, showing its robustness and effectiveness. Our thorough evaluations also show its validity and superiority to the state-of-the-art 3D CNN classification approaches. Our framework can easily be generalized to other classification tasks using different imaging modalities.

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.

Classification of amyotrophic lateral sclerosis by brain volume, connectivity, and network dynamics

Emerging studies corroborate the importance of neuroimaging biomarkers and machine learning to improve diagnostic classification of amyotrophic lateral sclerosis (ALS). While most studies focus on structural data, recent studies assessing functional connectivity between brain regions by linear methods highlight the role of brain function. These studies have yet to be combined with brain structure and nonlinear functional features. We investigate the role of linear and nonlinear functional brain features, and the benefit of combining brain structure and function for ALS classification. ALS patients (N = 97) and healthy controls (N = 59) underwent structural and functional resting state magnetic resonance imaging. Based on key hubs of resting state networks, we defined three feature sets comprising brain volume, resting state functional connectivity (rsFC), as well as (nonlinear) resting state dynamics assessed via recurrent neural networks. Unimodal and multimodal random forest classifiers were built to classify ALS. Out-of-sample prediction errors were assessed via five-fold cross-validation. Unimodal classifiers achieved a classification accuracy of 56.35-61.66%. Multimodal classifiers outperformed unimodal classifiers achieving accuracies of 62.85-66.82%. Evaluating the ranking of individual features' importance scores across all classifiers revealed that rsFC features were most dominant in classification. While univariate analyses revealed reduced rsFC in ALS patients, functional features more generally indicated deficits in information integration across resting state brain networks in ALS. The present work undermines that combining brain structure and function provides an additional benefit to diagnostic classification, as indicated by multimodal classifiers, while emphasizing the importance of capturing both linear and nonlinear functional brain properties to identify discriminative biomarkers of ALS.

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.

Multiparametric Microstructural MRI and Machine Learning Classification Yields High Diagnostic Accuracy in Amyotrophic Lateral Sclerosis: Proof of Concept

The potential of multiparametric quantitative neuroimaging has been extensively discussed as a diagnostic tool in amyotrophic lateral sclerosis (ALS). In the past, the integration of multimodal, quantitative data into a useful diagnostic classifier was a major challenge. With recent advances in the field, machine learning in a data driven approach is a potential solution: neuroimaging biomarkers in ALS are mainly observed in the cerebral microstructure, with diffusion tensor imaging (DTI) and texture analysis as promising approaches. We set out to combine these neuroimaging markers as age-corrected features in a machine learning model with a cohort of 502 subjects, divided into 404 patients with ALS and 98 healthy controls. We calculated a linear support vector classifier (SVC) which is a very robust model and then verified the results with a multilayer perceptron (MLP)/neural network. Both classifiers were able to separate ALS patients from controls with receiver operating characteristic (ROC) curves showing an area under the curve (AUC) of 0.87-0.88 ("good") for the SVC and 0.88-0.91 ("good" to "excellent") for the MLP. Among the coefficients of the SVC, texture data contributed the most to a correct classification. We consider these results as a proof of concept that demonstrated the power of machine learning in the application of multiparametric quantitative neuroimaging data to ALS.

Biomarker discovery studies for patient stratification using machine learning analysis of omics data: a scoping review

OBJECTIVE

To review biomarker discovery studies using omics data for patient stratification which led to clinically validated FDA-cleared tests or laboratory developed tests, in order to identify common characteristics and derive recommendations for future biomarker projects.

DESIGN

Scoping review.

METHODS

We searched PubMed, EMBASE and Web of Science to obtain a comprehensive list of articles from the biomedical literature published between January 2000 and July 2021, describing clinically validated biomarker signatures for patient stratification, derived using statistical learning approaches. All documents were screened to retain only peer-reviewed research articles, review articles or opinion articles, covering supervised and unsupervised machine learning applications for omics-based patient stratification. Two reviewers independently confirmed the eligibility. Disagreements were solved by consensus. We focused the final analysis on omics-based biomarkers which achieved the highest level of validation, that is, clinical approval of the developed molecular signature as a laboratory developed test or FDA approved tests.

RESULTS

Overall, 352 articles fulfilled the eligibility criteria. The analysis of validated biomarker signatures identified multiple common methodological and practical features that may explain the successful test development and guide future biomarker projects. These include study design choices to ensure sufficient statistical power for model building and external testing, suitable combinations of non-targeted and targeted measurement technologies, the integration of prior biological knowledge, strict filtering and inclusion/exclusion criteria, and the adequacy of statistical and machine learning methods for discovery and validation.

CONCLUSIONS

While most clinically validated biomarker models derived from omics data have been developed for personalised oncology, first applications for non-cancer diseases show the potential of multivariate omics biomarker design for other complex disorders. Distinctive characteristics of prior success stories, such as early filtering and robust discovery approaches, continuous improvements in assay design and experimental measurement technology, and rigorous multicohort validation approaches, enable the derivation of specific recommendations for future studies.

Feature selection from magnetic resonance imaging data in ALS: a systematic review

Background:

With the advances in neuroimaging in amyotrophic lateral sclerosis (ALS), it has been speculated that multiparametric magnetic resonance imaging (MRI) is capable to contribute to early diagnosis. Machine learning (ML) can be regarded as the missing piece that allows for the useful integration of multiparametric MRI data into a diagnostic classifier. The major challenges in developing ML classifiers for ALS are limited data quantity and a suboptimal sample to feature ratio which can be addressed by sound feature selection.

Methods:

We conducted a systematic review to collect MRI biomarkers that could be used as features by searching the online database PubMed for entries in the recent 4 years that contained cross-sectional neuroimaging data of subjects with ALS and an adequate control group. In addition to the qualitative synthesis, a semi-quantitative analysis was conducted for each MRI modality that indicated which brain regions were most commonly reported.

Results:

Our search resulted in 151 studies with a total of 221 datasets. In summary, our findings highly resembled generally accepted neuropathological patterns of ALS, with degeneration of the motor cortex and the corticospinal tract, but also in frontal, temporal, and subcortical structures, consistent with the neuropathological four-stage model of the propagation of pTDP-43 in ALS.

Conclusions:

These insights are discussed with respect to their potential for MRI feature selection for future ML-based neuroimaging classifiers in ALS. The integration of multiparametric MRI including DTI, volumetric, and texture data using ML may be the best approach to generate a diagnostic neuroimaging tool for ALS.

Molecular Classification and Interpretation of Amyotrophic Lateral Sclerosis Using Deep Convolution Neural Networks and Shapley Values

Amyotrophic lateral sclerosis (ALS) is a prototypical neurodegenerative disease characterized by progressive degeneration of motor neurons to severely effect the functionality to control voluntary muscle movement. Most of the non-additive genetic aberrations responsible for ALS make its molecular classification very challenging along with limited sample size, curse of dimensionality, class imbalance and noise in the data. Deep learning methods have been successful in many other related areas but have low minority class accuracy and suffer from the lack of explainability when used directly with RNA expression features for ALS molecular classification. In this paper, we propose a deep-learning-based molecular ALS classification and interpretation framework. Our framework is based on training a convolution neural network (CNN) on images obtained from converting RNA expression values into pixels based on DeepInsight similarity technique. Then, we employed Shapley additive explanations (SHAP) to extract pixels with higher relevance to ALS classifications. These pixels were mapped back to the genes which made them up. This enabled us to classify ALS samples with high accuracy for a minority class along with identifying genes that might be playing an important role in ALS molecular classifications. Taken together with RNA expression images classified with CNN, our preliminary analysis of the genes identified by SHAP interpretation demonstrate the value of utilizing Machine Learning to perform molecular classification of ALS and uncover disease-associated genes.

Success stories of AI in drug discovery - where do things stand?

INTRODUCTION

Artificial intelligence (AI) in drug discovery and development (DDD) has gained more traction in the past few years. Many scientific reviews have already been made available in this area. Thus, in this review, the authors have focused on the success stories of AI-driven drug candidates and the scientometric analysis of the literature in this field.

AREA COVERED

The authors explore the literature to compile the success stories of AI-driven drug candidates that are currently being assessed in clinical trials or have investigational new drug (IND) status. The authors also provide the reader with their expert perspectives for future developments and their opinions on the field.

EXPERT OPINION

Partnerships between AI companies and the pharma industry are booming. The early signs of the impact of AI on DDD are encouraging, and the pharma industry is hoping for breakthroughs. AI can be a promising technology to unveil the greatest successes, but it has yet to be proven as AI is still at the embryonic stage.

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.

Regional prefrontal cortical atrophy predicts specific cognitive-behavioral symptoms in ALS-FTD

Amyotrophic Lateral Sclerosis-Frontotemporal Dementia (ALS-FTD) may present typical behavioral variant FTD symptoms. This study aims to determine whether profile and severity of cognitive-behavioral symptoms in ALS/ALS-FTD are predicted by regional cortical atrophy. The hypothesis is that executive dysfunction can be predicted by dorsolateral prefrontal cortical (dlPFC) atrophy, apathy by dorsomedial PFC (dmPFC) and anterior cingulate cortical (ACC) atrophy, disinhibition by orbitofrontal cortical (OFC) atrophy. 3.0 Tesla MRI scans were acquired from 22 people with ALS or ALS-FTD. Quantitative cortical thickness analysis was performed with FreeSurfer. A priori-defined regions of interest (ROI) were used to measure cortical thickness in each participant and calculate magnitude of atrophy in comparison to 115 healthy controls. Spearman correlations were used to evaluate associations between frontal ROI cortical thickness and cognitive-behavioral symptoms, measured by Neuropsychiatric Inventory Questionnaire (NPI-Q) and Clinical Dementia Rating (CDR) scale. ALS-FTD participants exhibited variable degrees of apathy (NPI-Q/apathy: 1.6 ± 1.2), disinhibition (NPI-Q/disinhibition: 1.2 ± 1.2), executive dysfunction (CDR/judgment-problem solving: 1.7 ± 0.8). Within the ALS-FTD group, executive dysfunction correlated with dlPFC atrophy (ρ:-0.65;p < 0.05); similar trends were seen for apathy with ACC (ρ:-0.53;p < 0.10) and dmPFC (ρ:-0.47;p < 0.10) atrophy, for disinhibition with OFC atrophy (ρ:-0.51;p < 0.10). Compared to people with ALS, those with ALS-FTD showed more diffuse atrophy involving precentral gyrus, prefrontal, temporal regions. Profile and severity of cognitive-behavioral symptoms in ALS-FTD are predicted by regional prefrontal atrophy. These findings are consistent with established brain-behavior models and support the role of quantitative MRI in diagnosis, management, counseling, monitoring and prognostication for a neurodegenerative disorder with diverse phenotypes.