Identifying patterns in amyotrophic lateral sclerosis progression from sparse longitudinal data

All-in-one wearable drug efficacy assessment systems for bulbar muscle function using amyotrophic lateral sclerosis animal models

Preclinical studies are crucial for developing amyotrophic lateral sclerosis drugs. Current FDA-approved drugs have been created by monitoring limb muscle function and histological analysis of amyotrophic lateral sclerosis model animals. Drug candidates for this disease have yet to be tested for bulbar-onset type due to the limitations of traditional preclinical tools: excessive animal use and discrete detection of disease progress. Here, our study introduces an all-in-one, wireless, integrated wearable system for facilitating continuous drug efficacy assessment of dysphagia-related muscles in animals during natural eating behaviors. By incorporating a kirigami-based strain-isolation mechanism, this device mounted on the skin of animals mitigates electromyography signal contamination caused by unpredictable animal movements. Our findings indicate this system, measuring the progression of motor neuron denervation, offers high precision in monitoring drug effects on dysphagia-responsible bulbar muscles. This study paves the way for more humane and efficient approaches to developing treatment solutions for degenerative neuromuscular diseases.

Multimodal speech biomarkers for remote monitoring of ALS disease progression

Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease that severely impacts affected persons' speech and motor functions, yet early detection and tracking of disease progression remain challenging. The current gold standard for monitoring ALS progression, the ALS functional rating scale - revised (ALSFRS-R), is based on subjective ratings of symptom severity, and may not capture subtle but clinically meaningful changes due to a lack of granularity. Multimodal speech measures which can be automatically collected from patients in a remote fashion allow us to bridge this gap because they are continuous-valued and therefore, potentially more granular at capturing disease progression. Here we investigate the responsiveness and sensitivity of multimodal speech measures in persons with ALS (pALS) collected via a remote patient monitoring platform in an effort to quantify how long it takes to detect a clinically-meaningful change associated with disease progression. We recorded audio and video from 278 participants and automatically extracted multimodal speech biomarkers (acoustic, orofacial, linguistic) from the data. We find that the timing alignment of pALS speech relative to a canonical elicitation of the same prompt and the number of words used to describe a picture are the most responsive measures at detecting such change in both pALS with bulbar (n = 36) and non-bulbar onset (n = 107). Interestingly, the responsiveness of these measures is stable even at small sample sizes. We further found that certain speech measures are sensitive enough to track bulbar decline even when there is no patient-reported clinical change, i.e. the ALSFRS-R speech score remains unchanged at 3 out of a total possible score of 4. The findings of this study have the potential to facilitate improved, accelerated and cost-effective clinical trials and care.

Temporal stratification of amyotrophic lateral sclerosis patients using disease progression patterns

Identifying groups of patients with similar disease progression patterns is key to understand disease heterogeneity, guide clinical decisions and improve patient care. In this paper, we propose a data-driven temporal stratification approach, ClusTric, combining triclustering and hierarchical clustering. The proposed approach enables the discovery of complex disease progression patterns not found by univariate temporal analyses. As a case study, we use Amyotrophic Lateral Sclerosis (ALS), a neurodegenerative disease with a non-linear and heterogeneous disease progression. In this context, we applied ClusTric to stratify a hospital-based population (Lisbon ALS Clinic dataset) and validate it in a clinical trial population. The results unravelled four clinically relevant disease progression groups: slow progressors, moderate bulbar and spinal progressors, and fast progressors. We compared ClusTric with a state-of-the-art method, showing its effectiveness in capturing the heterogeneity of ALS disease progression in a lower number of clinically relevant progression groups.

Multimodal Speech Biomarkers for Remote Monitoring of ALS Disease Progression

Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease that severely impacts affected persons' speech and motor functions, yet early detection and tracking of disease progression remain challenging. The current gold standard for monitoring ALS progression, the ALS functional rating scale - revised (ALSFRS-R), is based on subjective ratings of symptom severity, and may not capture subtle but clinically meaningful changes due to a lack of granularity. Multimodal speech measures which can be automatically collected from patients in a remote fashion allow us to bridge this gap because they are continuous-valued and therefore, potentially more granular at capturing disease progression. Here we investigate the responsiveness and sensitivity of multimodal speech measures in persons with ALS (pALS) collected via a remote patient monitoring platform in an effort to quantify how long it takes to detect a clinically-meaningful change associated with disease progression. We recorded audio and video from 278 participants and automatically extracted multimodal speech biomarkers (acoustic, orofacial, linguistic) from the data. We find that the timing alignment of pALS speech relative to a canonical elicitation of the same prompt and the number of words used to describe a picture are the most responsive measures at detecting such change in both pALS with bulbar (n = 36) and non-bulbar onset (n = 107). Interestingly, the responsiveness of these measures is stable even at small sample sizes. We further found that certain speech measures are sensitive enough to track bulbar decline even when there is no patient-reported clinical change, i.e. the ALSFRS-R speech score remains unchanged at 3 out of a total possible score of 4. The findings of this study have the potential to facilitate improved, accelerated and cost-effective clinical trials and care.

Listener effort quantifies clinically meaningful progression of dysarthria in people living with amyotrophic lateral sclerosis

Amyotrophic lateral sclerosis (ALS) is a neurodegenerative motor neuron disease that causes progressive muscle weakness. Progressive bulbar dysfunction causes dysarthria and thus social isolation, reducing quality of life. The Everything ALS Speech Study obtained longitudinal clinical information and speech recordings from 292 participants. In a subset of 120 participants, we measured speaking rate (SR) and listener effort (LE), a measure of dysarthria severity rated by speech pathologists from recordings. LE intra- and inter-rater reliability was very high (ICC 0.88 to 0.92). LE correlated with other measures of dysarthria at baseline. LE changed over time in participants with ALS (slope 0.77 pts/month; p<0.001) but not controls (slope 0.005 pts/month; p=0.807). The slope of LE progression was similar in all participants with ALS who had bulbar dysfunction at baseline, regardless of ALS site of onset. LE could be a remotely collected clinically meaningful clinical outcome assessment for ALS clinical trials.

Current neuroprotective therapies and future prospects for motor neuron disease

Four medications with neuroprotective disease-modifying effects are now in use for motor neuron disease (MND). With FDA approvals for tofersen, relyvrio and edaravone in just the past year, 2022 ended a quarter of a century when riluzole was the sole such drug to offer to patients. The acceleration of approvals may mean we are witnessing the beginning of a step-change in how MND can be treated. Improvements in understanding underlying disease biology has led to more therapies being developed to target specific and multiple disease mechanisms. Consideration for how the pipeline of new therapeutic agents coming through in clinical and preclinical development can be more effectively evaluated with biomarkers, advances in patient stratification and clinical trial design pave the way for more successful translation for this archetypal complex neurodegenerative disease. While it must be cautioned that only slowed rates of progression have so far been demonstrated, pre-empting rapid neurodegeneration by using neurofilament biomarkers to signal when to treat, as is currently being trialled with tofersen, may be more effective for patients with known genetic predisposition to MND. Early intervention with personalized medicines could mean that for some patients at least, in future we may be able to substantially treat what is considered by many to be one of the most distressing diseases in medicine.

Unsupervised multimodal modeling of cognitive and brain health trajectories for early dementia prediction

Predicting the course of neurodegenerative disorders early has potential to greatly improve clinical management and patient outcomes. A key challenge for early prediction in real-world clinical settings is the lack of labeled data (i.e., clinical diagnosis). In contrast to supervised classification approaches that require labeled data, we propose an unsupervised multimodal trajectory modeling (MTM) approach based on a mixture of state space models that captures changes in longitudinal data (i.e., trajectories) and stratifies individuals without using clinical diagnosis for model training. MTM learns the relationship between states comprising expensive, invasive biomarkers (β-amyloid, grey matter density) and readily obtainable cognitive observations. MTM training on trajectories stratifies individuals into clinically meaningful clusters more reliably than MTM training on baseline data alone and is robust to missing data (i.e., cognitive data alone or single assessments). Extracting an individualized cognitive health index (i.e., MTM-derived cluster membership index) allows us to predict progression to AD more precisely than standard clinical assessments (i.e., cognitive tests or MRI scans alone). Importantly, MTM generalizes successfully from research cohort to real-world clinical data from memory clinic patients with missing data, enhancing the clinical utility of our approach. Thus, our multimodal trajectory modeling approach provides a cost-effective and non-invasive tool for early dementia prediction without labeled data (i.e., clinical diagnosis) with strong potential for translation to clinical practice.

ALSFRS-R decline rate prior to baseline is not useful for stratifying subsequent progression of functional decline

OBJECTIVE

One of the difficulties in developing a novel drug for patients with amyotrophic lateral sclerosis (ALS) is the significant variation in the clinical course. To control this variation, a 12-week run-in period is used in some clinical trials. Based on the Amyotrophic Lateral Sclerosis Functional Rating Scale Revised (ALSFRS-R) change during the run-in period, only moderate progressors are selected in some clinical trials. Some reports showed that the ALSFRS-R progression rate was associated with survival. However, it is unclear whether the ALSFRS-R change in the run-in period is a useful prognostic factor of the ALSFRS-R change from baseline. In addition, we explore the inclusion criteria that could control the variability in ALS-function progression without setting a run-in period.

METHODS

We utilized the Japanese and US ALS registry databases (JaCALS and PRO-ACT). Patients were classified into three populations (rapid, moderate, and slow progressors) based on the ALSFRS-R change prior to baseline. We also classified patients into three prognostic populations based on the ALSFRS-R change from baseline. We confirmed whether each of the three populations were matched with their respective three prognostic populations.

RESULTS

Our data showed that the three groups classified by the ALSFRS-R change during the 12 weeks prior to baseline or by the rate of progression from onset to baseline did not accord with the three prognostic groups.

CONCLUSIONS

Our results showed that the ALSFRS-R change in the run-in period or from onset to baseline is not useful for stratifying subsequent progression of functional decline in clinical trials.

Healthcare Utilization and Supportive Care Timing in South Korean People Living With Amyotrophic Lateral Sclerosis: A Single-Center Retrospective Study

BACKGROUND AND PURPOSE

Despite the growing demands and challenges faced by patients with amyotrophic lateral sclerosis (ALS) in accessing healthcare services, our understanding of this access remains poor. This study aimed to investigate the healthcare utilization patterns and timing of nutritional and respiration support in patients with ALS in South Korea.

METHODS

A retrospective cohort study was conducted on patients diagnosed with ALS at a single tertiary hospital between 2016 and 2019 and followed up for 2 years. We evaluated patient characteristics, healthcare utilization (hospital admissions, outpatient visits, and emergency department [ED] visits), and the timing of nutritional and respiration support (noninvasive positive pressure ventilation [NIPPV], tracheostomy, gastrostomy, and nasogastric tube) at 6-month intervals from the first outpatient visit.

RESULTS

Among the 143 included patients, 73.4% were admitted at least once, 18.9% experienced unplanned admissions, and 30.1% visited the ED at least once during the study period. The most-common reason for ED visits was neurological symptoms during the first 6 months (59.1%), followed by respiratory symptoms. One fifth of patients who visited the ED underwent tracheostomy (20.9%) or NIPPV (20.9%). Two years after the first visit, 32.2% used a ventilator, and 13.3%, 26.6%, and 6.3% had undergone tracheostomy, gastrostomy, and nasogastric tube insertion, respectively.

CONCLUSIONS

During the 2 years following their first outpatient visit, 20% of patients with ALS experienced unplanned admissions and 30% visited the ED. An active and prompt supportive-care program should be implemented to ensure timely functional support in order to reduce these risks of unplanned admissions.

Effect of tauroursodeoxycholic acid on survival and safety in amyotrophic lateral sclerosis: a retrospective population-based cohort study

Background

Oral tauroursodeoxycholic acid (TUDCA) is a commercial drug currently tested in patients with amyotrophic lateral sclerosis (ALS) both singly and combined with sodium phenylbutyrate. This retrospective study aimed to investigate, in a real-world setting, whether TUDCA had an impact on the overall survival of patients with ALS who were treated with this drug compared to those patients who received standard care only.

Methods

This propensity score-matched study was conducted in the Emilia Romagna Region (Italy), which has had an ALS regional registry since 2009. Out of 627 patients with ALS diagnosed from January 1st, 2015 to June 30th, 2021 and recorded in the registry with available information on death/tracheostomy, 86 patients took TUDCA and were matched in a 1:2 ratio with patients who received only usual care according to age at onset, sex, phenotype, diagnostic latency, ALS Functional Rating Scale-Revised (ALSFRS-R) at first visit, disease progression rate at first visit, and BMI at diagnosis. The primary outcome was survival difference (time from onset of symptoms to tracheostomy/death) between TUDCA exposed and unexposed patients.

Findings

A total of 86 patients treated with TUDCA were matched to 172 patients who did not receive treatment. TUDCA-exposed patients were stratified based on dosage (less than or equal to 1000 mg/day or greater) and duration (less than or equal to 12 months or longer) of treatment. The median overall survival was 49.6 months (95% CI 41.7-93.5) among those treated with TUDCA and 36.2 months (95% CI 32.7-41.6) in the control group, with a reduced risk of death observed in patients exposed to a higher dosage (defined as ≥ 1000 mg/day) of TUDCA (HR 0.56; 95% CI 0.38-0.83; p = 0.0042) compared to both the control group and those with lower TUDCA dosages (defined as < 1000 mg/day). TUDCA was generally well-tolerated, except for a minority of patients (n = 7, 8.1%) who discontinued treatment due to side effects, primarily gastrointestinal and mild in severity; only 2 adverse events required hospital access but resolved without sequelae.

Interpretation

In this population-based exploratory study, patients with ALS who were treated with TUDCA may have prolonged survival compared to patients receiving standard care only. Additional prospective randomized studies are needed to confirm the efficacy and safety of this drug.

Funding

Emilia-Romagna Region.

Responsiveness, Sensitivity and Clinical Utility of Timing-Related Speech Biomarkers for Remote Monitoring of ALS Disease Progression

In this study, we describe the responsiveness of timing-related measures extracted from read speech in persons with ALS (pALS) collected via a remote patient monitoring platform in an effort to quantify how long it takes to detect a clinically-meaningful change associated with disease progression. We found that the timing alignment of pALS speech relative to a canonical elicitation of the same prompt is the most responsive measure, of the ones considered in this study, at detecting such change in both pALS with bulbar (n = 35) and non-bulbar onset (n = 94). We further evaluated the sensitivity of speech metrics in tracking disease progression in pALS while their ALSFRS-R speech score remained unchanged at 3 out of a total possible score of 4. We observed that timing-related speech metrics showed significant longitudinal changes even after accounting for learning effects. The findings of this study have the potential to inform disease prognosis and functional outcomes of clinical trials.

Prognostic Usefulness of Motor Unit Number Index (MUNIX) in Patients Newly Diagnosed with Amyotrophic Lateral Sclerosis

The MUNIX technique allows us to estimate the number and size of surviving motor units (MUs). Previous studies on ALS found correlations between MUNIX and several clinical measures, but its potential role as a predictor of disease progression rate (DPR) has not been thoroughly evaluated to date. We aimed to investigate MUNIX's ability to predict DPR at a six-month follow up.

METHODS

24 ALS patients with short disease duration (<24 months from symptoms' onset) were enrolled and divided according to their baseline DPR into two groups (normal [DPR-N] and fast [DPR-F] progressors). MUNIX values were obtained from five muscles (TA, APB, ADM, FDI, Trapezius) and averaged for each subject.

RESULTS

MUNIX was found to predict DPR at follow up in a multivariable linear regression model; namely, patients with lower MUNIX values were at risk of showing greater DPR scores at follow up. The result was replicated in a simple logistic regression analysis, with the dichotomic category "MUNIX-Low" as the independent variable and the outcome "DPR-F" as the dependent variable.

CONCLUSIONS

our results pave the way for the use of the MUNIX method as a prognostic tool in early ALS, enabling patients' stratification according to their rates of future decline.

Computational Methods Summarizing Mutational Patterns in Cancer: Promise and Limitations for Clinical Applications

Since the rise of next-generation sequencing technologies, the catalogue of mutations in cancer has been continuously expanding. To address the complexity of the cancer-genomic landscape and extract meaningful insights, numerous computational approaches have been developed over the last two decades. In this review, we survey the current leading computational methods to derive intricate mutational patterns in the context of clinical relevance. We begin with mutation signatures, explaining first how mutation signatures were developed and then examining the utility of studies using mutation signatures to correlate environmental effects on the cancer genome. Next, we examine current clinical research that employs mutation signatures and discuss the potential use cases and challenges of mutation signatures in clinical decision-making. We then examine computational studies developing tools to investigate complex patterns of mutations beyond the context of mutational signatures. We survey methods to identify cancer-driver genes, from single-driver studies to pathway and network analyses. In addition, we review methods inferring complex combinations of mutations for clinical tasks and using mutations integrated with multi-omics data to better predict cancer phenotypes. We examine the use of these tools for either discovery or prediction, including prediction of tumor origin, treatment outcomes, prognosis, and cancer typing. We further discuss the main limitations preventing widespread clinical integration of computational tools for the diagnosis and treatment of cancer. We end by proposing solutions to address these challenges using recent advances in machine learning.

Current State and Future Directions in the Diagnosis of Amyotrophic Lateral Sclerosis

Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease characterized by loss of upper and lower motor neurons, resulting in progressive weakness of all voluntary muscles and eventual respiratory failure. Non-motor symptoms, such as cognitive and behavioral changes, frequently occur over the course of the disease. Considering its poor prognosis with a median survival time of 2 to 4 years and limited causal treatment options, an early diagnosis of ALS plays an essential role. In the past, diagnosis has primarily been determined by clinical findings supported by electrophysiological and laboratory measurements. To increase diagnostic accuracy, reduce diagnostic delay, optimize stratification in clinical trials and provide quantitative monitoring of disease progression and treatment responsivity, research on disease-specific and feasible fluid biomarkers, such as neurofilaments, has been intensely pursued. Advances in imaging techniques have additionally yielded diagnostic benefits. Growing perception and greater availability of genetic testing facilitate early identification of pathogenic ALS-related gene mutations, predictive testing and access to novel therapeutic agents in clinical trials addressing disease-modified therapies before the advent of the first clinical symptoms. Lately, personalized survival prediction models have been proposed to offer a more detailed disclosure of the prognosis for the patient. In this review, the established procedures and future directions in the diagnostics of ALS are summarized to serve as a practical guideline and to improve the diagnostic pathway of this burdensome disease.