Resource Open-Access Amyotrophic Lateral Sclerosis Clinical Trials Research Articles

Comparison of Demographics: National Amyotrophic Lateral Sclerosis Registry and Clinical Trials Data.

To characterize the participant demographics in the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database compared with the web-portal National Amyotrophic Lateral Sclerosis (ALS) Registry (the Registry). Demographics and ALS symptom information were compared between the self-reported registrant data in the Registry web portal (2010-2021) and the latest available PRO-ACT data (updated August 2022), which is a collection of clinical trials data. Greater percentages of younger (≤ 59years old) but smaller percentages of older (60 + years old) participants were represented in PRO-ACT compared to Registry. Enrollment for minority race groups was greater in the Registry portal data, but race information was largely missing/unknown in PRO-ACT database. Median age at the time of diagnosis and age at the time of symptom onset were significantly higher for Registry enrollees compared to the participants of PRO-ACT. Symptom onset sites were similarly reported, but duration between self-noted symptom onset and diagnosis was slight, but significantly longer for the Registry enrollees (11 vs. 9months). Hispanic were as likely as non-Hispanic to participate in research studies, based on the Registry data. There was a notable difference in the age distribution and minority representation of enrollees between the PRO-ACT and Registry study populations. Age distribution in the PRO-ACT database skewed to a younger and less diverse cohort. Despite the clinical heterogeneity and complex disease mechanism of ALS, identifying the underrepresented demographic niche in the PRO-ACT and Registry study populations can help improve patient participation and criteria for patient selection to enhance generalizability.

Sex Differences in Amyotrophic Lateral Sclerosis Survival and Progression: A Multidimensional Analysis.

To investigate sex-related differences in amyotrophic lateral sclerosis (ALS) prognosis and their contributing factors. Our primary cohort was the Piemonte and Aosta Register for ALS (PARALS); the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) and the Answer ALS databases were used for validation. Survival analyses were conducted accounting for age and onset site. The roles of forced vital capacity and weight decline were explored through a causal mediation analysis. Survival and disease progression rates were also evaluated after propensity score matching. The PARALS cohort included 1,890 individuals (44.8% women). Men showed shorter survival when stratified by onset site (spinal onset HR 1.20, 95% CI 1.00-1.44, p = 0.0439; bulbar onset HR 1.36, 95% CI 1.09-1.70, p = 0.006917), although women had a steeper functional decline (+0.10 ALSFRS-R points/month, 95% CI 0.07-0.15, p < 0.00001) regardless of onset site. Instead, men showed worse respiratory decline (-4.2 forced vital capacity%/month, 95% CI -6.3 to -2.2, p < 0.0001) and faster weight loss (-0.15 kg/month, 95% CI -0.25 to -0.05, p = 0.0030). Causal mediation analysis showed that respiratory function and weight loss were pivotal in sex-related survival differences. Analysis of patients from PRO-ACT (n = 1,394, 40.9% women) and Answer ALS (n = 849, 37.2% women) confirmed these trends. The shorter survival in men is linked to worse respiratory function and weight loss rather than a faster disease progression. These findings emphasize the importance of considering sex-specific factors in understanding ALS pathophysiology and designing tailored therapeutic strategies. ANN NEUROL 2024;96:159-169.

Individualized predictions for clinical milestone in amyotrophic lateral sclerosis: A multialgorithmic approach.

The phenotypic heterogeneity and complex disease trajectory complicate the ability to predict specific clinical milestone for individual patients with amyotrophic lateral sclerosis (ALS). Here we developed individualized prediction models to estimate the time to the loss of autonomy in swallowing function. Utilizing the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database, we built three models of distinct time-to-event prediction algorithms: accelerated failure time (AFT), cox proportional hazard (COX) and random survival forest (RSF) for an individualized risk assessment of the swallowing milestone. The target variable was defined as the time to a decline in the ALSFRS-R swallowing item score to 1 or below, indicating a need for supplementary tube feeding. Internal cross-validation revealed the median concordance index (C-index) of 0.851 (IQR, 0.842-0.859) for AFT, 0.850 (0.841-0.859) for COX and 0.846 (0.839-0.854) for RSF, and all models demonstrated good distributional calibration with predicted and observed event probabilities closely matched across different time intervals. For external validation with a registry dataset with characteristics different from PRO-ACT, the discriminative power was replicated with comparable C-indices for all models, whereas the calibration revealed a left-skewed distribution suggesting a bias towards overestimation of event probabilities in real-world data. While all models were effective at stratifying patients, the results of RSF model, unlike AFT and COX, did not match well with the KM curves of the corresponding risk groups, supporting the importance of nuanced understanding of data structure and algorithmic properties. Our models are implemented into a web application which could be applied to individualized counselling, management and clinical trial design for gastrostomy intervention. Further studies for model optimization will advance personalized care in patients with ALS.

Predicting amyotrophic lateral sclerosis (ALS) progression with machine learning

ObjectiveTo predict ALS progression with varying observation and prediction window lengths, using machine learning (ML).MethodsWe used demographic, clinical, and laboratory parameters from 5030 patients in the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database to model ALS disease progression as fast (at least 1.5 points decline in ALS Functional Rating Scale-Revised (ALSFRS-R) per month) or non-fast, using Extreme Gradient Boosting (XGBoost) and Bayesian Long Short Term Memory (BLSTM). XGBoost identified predictors of progression while BLSTM provided a confidence level for each prediction.ResultsML models achieved area under receiver-operating-characteristics curve (AUROC) of 0.570-0.748 and were non-inferior to clinician assessments. Performance was similar with observation lengths of a single visit, 3, 6, or 12 months and on a holdout validation dataset, but was better for longer prediction lengths. 21 important predictors were identified, with the top 3 being days since disease onset, past ALSFRS-R and forced vital capacity. Nonstandard predictors included phosphorus, chloride and albumin. BLSTM demonstrated higher performance for the samples about which it was most confident. Patient screening by models may reduce hypothetical Phase II/III clinical trial sizes by 18.3%.ConclusionSimilar accuracies across ML models using different observation lengths suggest that a clinical trial observation period could be shortened to a single visit and clinical trial sizes reduced. Confidence levels provided by BLSTM gave additional information on the trustworthiness of predictions, which could aid decision-making. The identified predictors of ALS progression are potential biomarkers and therapeutic targets for further research.

The natural history of ALS: Baseline characteristics from a multicenter clinical cohort

Background Amyotrophic lateral sclerosis (ALS) is a rare disease with urgent need for improved treatment. Despite the acceleration of research in recent years, there is a need to understand the full natural history of the disease. As only 40% of people living with ALS are eligible for typical clinical trials, clinical trial datasets may not generalize to the full ALS population. While biomarker and cohort studies have more generous inclusion criteria, these too may not represent the full range of phenotypes, particularly if the burden for participation is high. To permit a complete understanding of the heterogeneity of ALS, comprehensive data on the full range of people with ALS is needed. Methods The ALS Natural History Consortium (ALS NHC) consists of nine ALS clinics and was created to build a comprehensive dataset reflective of the ALS population. At each clinic, most patients are asked to participate and about 95% do. After obtaining consent, a minimum dataset is abstracted from each participant’s electronic health record. Participant burden is therefore minimal. Results Data on 1925 ALS patients were submitted as of 9 December 2022. ALS NHC participants were more heterogeneous relative to anonymized clinical trial data from the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database. The ALS NHC includes ALS patients of older age of onset and a broader distribution of El Escorial categories, than the PRO-ACT database. Conclusions ALS NHC participants had a higher diversity of diagnostic and demographic data compared to ALS clinical trial participants. Key Messages What is already known on this topic: Current knowledge of the natural history of ALS derives largely from regional and national registries that have broad representation of the population of people living with ALS but do not always collect covariates and clinical outcomes. Clinical studies with rich datasets of participant characteristics and validated clinical outcomes have stricter inclusion and exclusion criteria that may not be generalizable to the full ALS population. What this study adds: To bridge this gap, we collected baseline characteristics for a sample of the population of people living with ALS seen at a consortium of ALS clinics that collect extensive, pre-specified participant-level data, including validated outcome measures. How this study might affect research, practice, or policy: A clinic-based longitudinal dataset can improve our understanding of the natural history of ALS and can be used to inform the design and analysis of clinical trials and health economics studies, to help the prediction of clinical course, to find matched controls for open label extension trials and expanded access protocols, and to document real-world evidence of the impact of novel treatments and changes in care practice.

Evaluating the Effect of Sodium Phenylbutyrate and Taurursodiol on Survival Outcomes in Amyotrophic Lateral Sclerosis Using a Propensity Score–Matched Cohort From the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) Database (S33.005)

Evaluating the Effect of Sodium Phenylbutyrate and Taurursodiol on Survival Outcomes in Amyotrophic Lateral Sclerosis Using a Propensity Score–Matched Cohort From the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) Database (S33.005)

A novel quantitative indicator for disease progression rate in amyotrophic lateral sclerosis

ObjectiveThe current study sought to develop a new indicator for disease progression rate in amyotrophic lateral sclerosis (ALS). MethodsWe used a nonparametric method to score diverse patterns of decline in the percentage of predicted forced vital capacity (%FVC) in patients with ALS. This involved 6317 longitudinal %FVC data sets from 920 patients in the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database volunteered by PRO-ACT Consortium members. To assess the utility of the derived scores as a disease indicator, we examined changes over time, the association with prognosis, and correlation with the Risk Profile of the Treatment Research Initiative to Cure ALS (TRICALS). Our local cohort (n = 92) was used for external validation. ResultsWe derived scores ranging from 35 to 106 points to construct the FVC Decline Pattern scale (FVC-DiP). Individuals' FVC-DiP scores were determined from a single measurement of %FVC and disease duration at assessment. Although the %FVC declined over the disease course (p < 0.0001), the FVC-DiP remained relatively stable. Low FVC-DiP scores were associated with rapid disease progression. Using our cohort, we demonstrated an association between FVC-DiP and the survival prognosis, the stability of the FVC-DiP per individual, and a correlation between FVC-DiP scores and the TRICALS Risk Profile (r2 = 0.904, p < 0.0001). ConclusionsFVC-DiP scores reflected patterns of declining %FVC over the natural course of ALS and indicated the disease progression rate. The FVC-DiP may enable easy assessment of disease progression patterns and could be used for assessing treatment efficacy.

Deep learning methods to predict amyotrophic lateral sclerosis disease progression

Amyotrophic lateral sclerosis (ALS) is a highly complex and heterogeneous neurodegenerative disease that affects motor neurons. Since life expectancy is relatively low, it is essential to promptly understand the course of the disease to better target the patient’s treatment. Predictive models for disease progression are thus of great interest. One of the most extensive and well-studied open-access data resources for ALS is the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) repository. In 2015, the DREAM-Phil Bowen ALS Prediction Prize4Life Challenge was held on PRO-ACT data, where competitors were asked to develop machine learning algorithms to predict disease progression measured through the slope of the ALSFRS score between 3 and 12 months. However, although it has already been successfully applied in several studies on ALS patients, to the best of our knowledge deep learning approaches still remain unexplored on the ALSFRS slope prediction in PRO-ACT cohort. Here, we investigate how deep learning models perform in predicting ALS progression using the PRO-ACT data. We developed three models based on different architectures that showed comparable or better performance with respect to the state-of-the-art models, thus representing a valid alternative to predict ALS disease progression.

Neutrophils-to-Lymphocyte Ratio Is Associated with Progression and Overall Survival in Amyotrophic Lateral Sclerosis.

Background: Amyotrophic lateral sclerosis (ALS) is a devastating and untreatable motor neuron disease, with a 3–5-year survival from diagnosis. Possible prognostic serum biomarkers include albumin, C-reactive protein, ferritin, creatinine, uric acid, hemoglobin, potassium, sodium, calcium, glucose, and the neutrophil-to-lymphocyte ratio (NLR), a marker of subclinical inflammation. Objective: To ascertain the influence of NLR on ALS progression rate and survival. Methods: Cross-sectional multicenter study including 146 consecutive incident and prevalent patients (88 males), aged >18 years, diagnosed according to the El Escorial criteria. The exclusion criteria were: (1) patients with tracheostomy or receiving mechanical ventilation; (2) patients with percutaneous endoscopic gastrostomy; and (3) patients who did not sign the informed consent. The rate of disease progression (ΔFS score) represents the monthly decline of the ALSFRS-R score, and was computed as (48 − total ALSFRS-R at recruitment)/symptom duration in months. Patients were followed up to tracheotomy, death, or the end of the follow-up, whichever occurred first. To validate our findings, we used data retrieved from the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) Database. Results: The median disease duration was 15 (range = 2–30) months. The mean ALSFRS-R score at recruitment was 35.8 ± 8.0 (range: 10–48), and the median ΔFS was 0.66 (range: 0–5.33). Age at onset, at diagnosis, and at recruitment were significantly lower in the lowest NLR tertile. NLR values positively correlated with ΔFS values (r = 0.28): the regression slope of NLR (log-values) was 0.60 (p < 0.001) before and 0.49 (p = 0.006) after adjustment for age at recruitment. The ΔFS score progressively increased from the lowest to the highest NLR tertile: 0.35 (IQR: 0.18–0.93), 0.62 (IQR: 0.25–1.09), and 0.86 (IQR: 0.53–1.92). Patients were followed for a median of 2 years. The mortality rate passed from 15.9 events per 100 person-years in patients belonging to the lowest NLR tertile to 52.8 in those in the highest tertile. The optimal cut-off value which best classified patients with the lowest and the highest mortality rate was set at the NLR value of 2.315. Indeed, the mortality rate of patients with an NLR value above such cut-off was twice the mortality rate of patients with a value below the cut-off (age adjusted hazard ratio (HR): 2.16, 95% confidence interval (CI): 1.32–3.53). In the PRO-ACT validation sample, patients with an NLR value above the cut-off consistently had a higher mortality rate than those with a value below the cut-off (age adjusted HR: 1.17, 95%CI: 1.01–1.35). Conclusions: NLR could be a candidate easy, fast, and low-cost marker of disease progression and survival in ALS. It may be associated with low-grade inflammation either as a direct mirror of the pathological process of disease progression, or as a consequence of neuronal death (reverse causation). However, prospective studies are needed to understand whether NLR changes during the course of the disease, before using it to monitor disease progression in ALS.

King's college progression rate at first clinical evaluation: A new measure of disease progression in amyotrophic lateral sclerosis

BackgroundTo estimate King's college clinical stage progression rate (ΔKC) at first clinical evaluation in order to define its predictive and prognostic role on survival in a large cohort of Amyotrophic Lateral Sclerosis (ALS) patients. MethodsThe ΔKC was calculated with the following formula: 0 - KC clinical stage at first clinical evaluation/disease duration from onset to first evaluation, and each result was reported as absolute value. All the evaluations were performed in two cohorts: one from our tertiary centre for motor neuron disease and the other one from a pooled resource open-access ALS clinical trials (PRO-ACT) database. C-statistic was used to evaluate the model discrimination of survival at different time points (1–3 years). Cox proportional hazard model was used to identify factors associated with survival. ResultsΔKC predicted survival at three years in our centre and in the PRO-ACT cohort (C-statistic 0.83, 95% CI 0.8–0.86, p < 0.0001; 0.7, 95% CI 0.68–0.73, p < 0.0001, respectively). At multivariate analysis, ΔKC was independently associated with survival both in our cohort (HR 3.62 95% CI 2.71–4.83 p = 0.001) and in the PRO-ACT cohort (HR 2.75 95% CI 2.1–3.6 p = 0.001). ConclusionsBased on our results, ΔKC could be used as a novel measure of disease progression, hence as an accurate predictor of survival in ALS patients. Indeed, greater values of ΔKC were associated with a 3.5-fold higher risk to experience the event, confirming its robust prognostic value.

Innovating Clinical Trials for Amyotrophic Lateral Sclerosis: Challenging the Established Order.

Development of effective treatments for amyotrophic lateral sclerosis (ALS) has been hampered by disease heterogeneity, a limited understanding of underlying pathophysiology, and methodologic design challenges. We have evaluated 2 major themes in the design of pivotal, phase 3 clinical trials for ALS—(1) patient selection and (2) analytical strategy—and discussed potential solutions with the European Medicines Agency. Several design considerations were assessed using data from 5 placebo-controlled clinical trials (n = 988), 4 population-based cohorts (n = 5,100), and 2,436 placebo-allocated patients from the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database. The validity of each proposed design modification was confirmed by means of simulation and illustrated for a hypothetical setting. Compared to classical trial design, the proposed design modifications reduce the sample size by 30.5% and placebo exposure time by 35.4%. By making use of prognostic survival models, one creates a potential to include a larger proportion of the population and maximize generalizability. We propose a flexible design framework that naturally adapts the trial duration when inaccurate assumptions are made at the design stage, such as enrollment or survival rate. In case of futility, the follow-up time is shortened and patient exposure to ineffective treatments or placebo is minimized. For diseases such as ALS, optimizing the use of resources, widening eligibility criteria, and minimizing exposure to futile treatments and placebo is critical to the development of effective treatments. Our proposed design modifications could circumvent important pitfalls and may serve as a blueprint for future clinical trials in this population.

Relative effects of forced vital capacity and ALSFRS-R on survival in ALS.

Amyotrophic lateral sclerosis (ALS) is a degenerative neuromuscular disease with marked clinical heterogeneity. This heterogeneity can be partly captured by clinical measures, such as the forced vital capacity (FVC) and ALS Functional Rating Scale-Revised (ALSFRS-R). We aimed to further characterize the performance of these clinical measures, including their independence and additivity, in predicting mortality. We leveraged the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT ALS) database, which includes data from 23 clinical trials (n =2050). The primary exposures were baseline FVC and ALSFRS-R. The primary outcome was 1-y mortality. We performed correlation analyses, survival analyses and assessed classification performance using receiver operator characteristic (ROC) curves. FVC and ALSFRS-R were weakly correlated (r=0.31, p< .001). A 1-SD increase in FVC (hazard ratio [HR]: 0.66; 95% confidence interval [CI]: 0.59-0.74) and ALSFRS-R (HR: 0.75; 95% CI: 0.68-0.82) were associated with reduced risk of 1-y mortality. ROC analyses showed optimal predictive cutoffs at 80% for FVC (area under the curve [AUC]: 0.69) and 38 for ALSFRS-R (AUC: 0.67). After stratifying patients based on these cutoffs, we found a marked reduction (HR: 0.25; 95% CI: 0.19-0.33) in incident mortality for patients in the high FVC and high ALSFRS-R group relative to the low FVC and low ALSFRS-R group. ALSFRS-R and FVC are comparable predictors of survival that are only weakly correlated. When considered together, they synergistically predict survival. As such, consideration of both measures should be a routine part of prognostication in care of patients with ALS.

The cumulative incidence of dysphagia and dysphagia-free survival in persons diagnosed with amyotrophic lateral sclerosis.

Dysphagia worsens mortality and quality of life for persons diagnosed with amyotrophic lateral sclerosis (ALS), yet our understanding of its incidence and timing remains limited. In this study we sought to estimate dysphagia incidence and dysphagia-free survival over time. Using data from the Pooled Resource Open-Access ALS Clinical Trials Database, we compared characteristics of persons with and without dysphagia upon study entry. To account for competing mortality risk, we used Kaplan-Meier curves to estimate the cumulative incidence of dysphagia and the median number of days until the development of dysphagia or death in those without dysphagia at study entry. Patients with dysphagia upon study entry were more likely to have bulbar onset and had faster rates of functional decline and shorter diagnostic delays. The cumulative incidence of new-onset dysphagia was 44% at 1 year and 64% at 2 years after trial enrollment for those with spinal onset, and 85% and 92% for those with bulbar onset. The median duration of dysphagia-free survival after trial enrollment was 11.5 months for those with spinal onset and 3.2months for those with bulbar onset. Our findings underscore the high risk for dysphagia development and support the need for early dysphagia referral and evaluation to minimize the risk of serious dysphagia-related complications.

Use of vitamins by participants in amyotrophic lateral sclerosis clinical trials.

Patients’ vitamin intake is often not documented and is therefore not considered sufficiently in studies of prescribed medication in patients with amyotrophic lateral sclerosis (ALS). We aimed to determine the prevalence of vitamin use by participants in ALS clinical trials. Data about demographics, disease severity (ALS Functional Rating Scale) and concomitant medication were obtained from the Pooled Resource Open-Access ALS Clinical Trials Database, which contains records from more than 6000 ALS patients who participated in 23 phase II/III clinical trials. Information about vitamin intake for all study subjects was coded into major categories. Clinical data of vitamin users and nonusers were compared, and regression analysis was used to explore the associations among clinical parameters, vitamin use and two measures of disease progression. From the 40.996 available medication records from 6274 subjects, 7338 (17.9%) concerned vitamins. One or more vitamins were used by 3331 subjects (53.1%). Most common was vitamin E, vitamin C and multivitamins. Patients who did and did not take vitamins did not differ in terms of disease progression and ALS Functional Rating Scale score. Patients who took vitamins were younger, were more often female, had a shorter time between onset and diagnosis, had shorter disease duration and more frequently had limb-onset types. Disease progression rate and disease aggressiveness were not associated with vitamin use. Despite unclear evidence, the use of vitamins in ALS is common. However, rapid progression was not observed to be associated with vitamin use.

Classifying Patients with Amyotrophic Lateral Sclerosis by Changes in FVC. A Group-based Trajectory Analysis.

Rationale: A model for stratifying progression of respiratory muscle weakness in amyotrophic lateral sclerosis (ALS) would identify disease mechanisms and phenotypes suitable for future investigations. This study sought to categorize progression of FVC after presentation to an outpatient ALS clinic.Objectives: To identify clinical phenotypes of ALS respiratory progression based on FVC trajectories over time.Methods: We derived a group-based trajectory model from a single-center cohort of 837 patients with ALS who presented between 2006 and 2015. We applied our model to the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database with 7,461 patients with ALS. Baseline characteristics at first visit were used as predictors of trajectory group membership. The primary outcome was trajectory of FVC over time in months.Measurements and Main Results: We found three trajectories of FVC over time, termed "stable low," "rapid progressor," and "slow progressor." Compared with the slow progressors, the rapid progressors had shorter diagnosis delay, more bulbar-onset disease, and a lower ALS Functional Rating Scale-Revised (ALSFRS-R) total score at baseline. The stable low group had a shorter diagnosis delay, lower body mass index, more bulbar-onset disease, lower ALSFRS-R total score, and were more likely to have an ALSFRS-R orthopnea score lower than 4 compared with the slow progressors. We found that projected group membership predicted respiratory insufficiency in the PRO-ACT cohort (concordance statistic = 0.78, 95% CI, 0.76-0.79).Conclusions: We derived a group-based trajectory model for FVC progression in ALS, which validated against the outcome of respiratory insufficiency in an external cohort. Future studies may focus on patients predicted to be rapid progressors.

Insights into Amyotrophic Lateral Sclerosis from a Machine Learning Perspective.

Objective: Amyotrophic lateral sclerosis (ALS) disease state prediction usually assumes linear progression and uses a classifier evaluated by its accuracy. Since disease progression is not linear, and the accuracy measurement cannot tell large from small prediction errors, we dispense with the linearity assumption and apply ordinal classification that accounts for error severity. In addition, we identify the most influential variables in predicting and explaining the disease. Furthermore, in contrast to conventional modeling of the patient’s total functionality, we also model separate patient functionalities (e.g., in walking or speaking). Methods: Using data from 3772 patients from the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database, we introduce and train ordinal classifiers to predict patients’ disease state in their last clinic visit, while accounting differently for different error severities. We use feature-selection methods and the classifiers themselves to determine the most influential variables in predicting the disease from demographic, clinical, and laboratory data collected in either the first, last, or both clinic visits, and the Bayesian network classifier to identify interrelations among these variables and their relations with the disease state. We apply these methods to model each of the patient functionalities. Results: We show the error distribution in ALS state prediction and demonstrate that ordinal classifiers outperform classifiers that do not account for error severity. We identify clinical and lab test variables influential to prediction of different ALS functionalities and their interrelations, and specific value combinations of these variables that occur more frequently in patients with severe deterioration than in patients with mild deterioration and vice versa. Conclusions: Ordinal classification of ALS state is superior to conventional classification. Identification of influential ALS variables and their interrelations help explain disease mechanism. Modeling of patient functionalities separately allows relation of variables and their connections to different aspects of the disease as may be expressed in different body segments.

Variation in noninvasive ventilation use in amyotrophic lateral sclerosis.

We sought to examine prevalence and predictors of noninvasive ventilation (NIV) in a composite cohort of patients with amyotrophic lateral sclerosis (ALS) followed in a clinical trials setting (Pooled Resource Open-Access ALS Clinical Trials database). NIV initiation and status were ascertained from response to question 12 of the revised ALS Functional Rating Scale (ALSFRS-R). Factors affecting NIV use in patients with forced vital capacity (FVC) ≤50% of predicted were examined. Predictors of NIV were evaluated by Cox proportional hazard models and generalized linear mixed models. Among 1,784 patients with 8,417 simultaneous ALSFRS-R and FVC% measures, NIV was used by 604 (33.9%). Of 918 encounters when FVC% ≤50%, NIV was reported in 482 (52.5%). Independent predictors of NIV initiation were lower FVC% (hazard ratio [HR] 1.27, 95% confidence interval [CI] 1.17-1.37 for 10% drop), dyspnea (HR 2.62, 95% CI 1.87-3.69), orthopnea (HR 4.09, 95% CI 3.02-5.55), lower bulbar and gross motor subscores of ALSFRS-R (HRs 1.09 [95% CI 1.03-1.14] and 1.13 [95% CI 1.07-1.20], respectively, per point), and male sex (HR 1.73, 95% CI 1.31-2.28). Adjusted for other variables, bulbar onset did not significantly influence time to NIV (HR 0.72, 95% CI 0.47-1.08). Considerable unexplained variability in NIV use was found. NIV use was lower than expected in this ALS cohort that was likely to be optimally managed. Absence of respiratory symptoms and female sex may be barriers to NIV use. Prospective exploration of factors affecting adoption of NIV may help bridge this gap and improve care in ALS.

Development of a prognostic model of respiratory insufficiency or death in amyotrophic lateral sclerosis.

A clinically useful model to prognose onset of respiratory insufficiency in amyotrophic lateral sclerosis (ALS) would inform disease interventions, communication and clinical trial design. We aimed to derive and validate a clinical prognostic model for respiratory insufficiency within 6 months of presentation to an outpatient ALS clinic.We used multivariable logistic regression and internal cross-validation to derive a clinical prognostic model using a single-centre cohort of 765 ALS patients who presented between 2006 and 2015. External validation was performed using the multicentre Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database with 7083 ALS patients. Predictors included baseline characteristics at first outpatient visit. The primary outcome was respiratory insufficiency within 6 months, defined by initiation of noninvasive ventilation, forced vital capacity (FVC) <50% predicted, tracheostomy, or death.Of 765 patients in our centre, 300 (39%) had respiratory insufficiency or death within 6 months. Six baseline characteristics (diagnosis age, delay between symptom onset and diagnosis, FVC, symptom onset site, amyotrophic lateral sclerosis functional rating scale-revised (ALSFRS-R) total score and ALSFRS-R dyspnoea score) were used to prognose the risk of the primary outcome. The derivation cohort c-statistic was 0.86 (95% CI 0.84-0.89) and internal cross-validation produced a c-statistic of 0.86 (95% CI 0.85-0.87). External validation of the model using the PRO-ACT cohort produced a c-statistic of 0.74 (95% CI 0.72-0.75).We derived and externally validated a clinical prognostic rule for respiratory insufficiency in ALS. Future studies should investigate interventions on equivalent high-risk patients.

Model-Based and Model-Free Techniques for Amyotrophic Lateral Sclerosis Diagnostic Prediction and Patient Clustering.

Amyotrophic lateral sclerosis (ALS) is a complex progressive neurodegenerative disorder with an estimated prevalence of about 5 per 100,000 people in the United States. In this study, the ALS disease progression is measured by the change of Amyotrophic Lateral Sclerosis Functional Rating Scale (ALSFRS) score over time. The study aims to provide clinical decision support for timely forecasting of the ALS trajectory as well as accurate and reproducible computable phenotypic clustering of participants. Patient data are extracted from DREAM-Phil Bowen ALS Prediction Prize4Life Challenge data, most of which are from the Pooled Resource Open-Access ALS Clinical Trials Database (PRO-ACT) archive. We employed model-based and model-free machine-learning methods to predict the change of the ALSFRS score over time. Using training and testing data we quantified and compared the performance of different techniques. We also used unsupervised machine learning methods to cluster the patients into separate computable phenotypes and interpret the derived subcohorts. Direct prediction of univariate clinical outcomes based on model-based (linear models) or model-free (machine learning based techniques - random forest and Bayesian adaptive regression trees) was only moderately successful. The correlation coefficients between clinically observed changes in ALSFRS scores relative to the model-based/model-free predicted counterparts were 0.427(random forest) and 0.545(BART). The reliability of these results were assessed using internal statistical cross validation and well as external data validation. Unsupervised clustering generated very reliable and consistent partitions of the patient cohort into four computable phenotypic subgroups. These clusters were explicated by identifying specific salient clinical features included in the PRO-ACT archive that discriminate between the derived subcohorts. There are differences between alternative analytical methods in forecasting specific clinical phenotypes. Although predicting univariate clinical outcomes may be challenging, our results suggest that modern data science strategies are useful in clustering patients and generating evidence-based ALS hypotheses about complex interactions of multivariate factors. Predicting univariate clinical outcomes using the PRO-ACT data yields only marginal accuracy (about 70%). However, unsupervised clustering of participants into sub-groups generates stable, reliable and consistent (exceeding 95%) computable phenotypes whose explication requires interpretation of multivariate sets of features. HIGHLIGHTS: • Used a large ALS data archive of 8,000 patients consisting of 3 million records, including 200 clinical features tracked over 12 months. • Employed model-based and model-free methods to predict ALSFRS changes over time, cluster patients into cohorts, and derive computable phenotypes. • Research findings include stable, reliable, and consistent (95%) patient stratification into computable phenotypes. However, clinical explication of the results requires interpretation of multivariate information. Graphical Abstract ᅟ.

Causal discovery from sequential data in ALS disease based on entropy criteria.

One of the most important issues in predictive modeling is to determine major cause factors of a phenomenon and causal relationships between them. Extracting causal relationships between parameters in a natural phenomenon can be accomplished through checking the parameters' changes in consecutive events. In addition, using information and probabilistic theory help better conception of causal relationships of a phenomenon. Therefore, probabilistic causal discovery from sequential data of a natural phenomenon can be useful for dimension reduction and predicting the future trend of a process. In this paper, we introduce a novel method for causal discovery from a sequential data based on a probabilistic causal graph. In this method, first, Causal Feature Dependency matrix (CFD matrix) is generated based on the features' changes in consecutive events. Then, a probabilistic causal graph is created from CFD matrix. In this graph, some valueless features will be eliminated on the basis of entropy value of each conditional density function. Finally, prediction operation is performed based on the output of causal graph. Experimental results on the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) sequential data set from Amyotrophic Lateral Sclerosis (ALS) disease show that our proposed algorithm can predict the progression rate of ALS disease properly with high precision.