Being PRO-ACTive: What can a Clinical Trial Database Reveal About ALS?

Towards a Machine Learning Empowered Prognostic Model for Predicting Disease Progression for Amyotrophic Lateral Sclerosis

Amyotrophic lateral sclerosis (ALS) is a rare and devastating neurodegenerative disorder that is highly heterogeneous and invariably fatal. Due to the unpredictable nature of its progression, accurate tools and algorithms are needed to predict disease progression and improve patient care. To address this need, we developed and compared an extensive set of screener-learner machine learning models to accurately predict the ALS Function-Rating-Scale (ALSFRS) score reduction between 3 and 12 months, by paring 5 state-of-arts feature selection algorithms with 17 predictive models and 4 ensemble models using the publicly available Pooled Open Access Clinical Trials Database (PRO-ACT). Our experiment showed promising results with the blender-type ensemble model achieving the best prediction accuracy and highest prognostic potential.

Dynamic effects of prognostic factors and individual survival prediction for amyotrophic lateral sclerosis disease

OBJECTIVE

Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disease affecting motor neurons, with broad heterogeneity in disease progression and survival in different patients. Therefore, an accurate prediction model will be crucial to implement timely interventions and prolong patient survival time.

METHODS

A total of 1260 ALS patients from the PRO-ACT database were included in the analysis. Their demographics, clinical variables, and death reports were included. We constructed an ALS dynamic Cox model through the landmarking approach. The predictive performance of the model at different landmark time points was evaluated by calculating the area under the curve (AUC) and Brier score.

RESULTS

Three baseline covariates and seven time-dependent covariates were selected to construct the ALS dynamic Cox model. For better prognostic analysis, this model identified dynamic effects of treatment, albumin, creatinine, calcium, hematocrit, and hemoglobin. Its prediction performance (at all landmark time points, AUC ≥ 0.70 and Brier score ≤ 0.12) was better than that of the traditional Cox model, and it predicted the dynamic 6-month survival probability according to the longitudinal information of individual patients.

INTERPRETATION

We developed an ALS dynamic Cox model with ALS longitudinal clinical trial datasets as the inputs. This model can not only capture the dynamic prognostic effect of both baseline and longitudinal covariates but also make individual survival predictions in real time, which are valuable for improving the prognosis of ALS patients and providing a reference for clinicians to make clinical decisions.

Effectiveness of herbal medicine on patients with amyotrophic lateral sclerosis: Analysis of the PRO-ACT data using propensity score matching

BACKGROUND

Patients with amyotrophic lateral sclerosis (ALS) have restricted pharmacotherapy options and thus resort to herbal medicines (HMs), despite limited and conflicting evidence. Therefore, use of HMs needs to be assessed in patients with ALS.

PURPOSE

This study aimed to evaluate the benefits of HMs in ALS and to describe the characteristics of HM users.

STUDY DESIGN

The correlation between HMs and prognosis was determined based on data obtained from the largest ALS database with high-quality clinical trials. Propensity score (PS) matching was used to address confounding and selection bias.

METHODS

In total, 321 and 231 HM users with at least a 4-week HM prescription were identified and PS-matched with non-HM users at a 1:1 ratio based on predefined confounders. Time-to-event models with censoring at 12 or 18 months were established for survival analyses. For evaluating activity limitation and respiratory function, 320 and 376 HM users were included, respectively, and analyzed using multivariate analysis of variance (MANOVA).

RESULTS

The profiles of 321 HM users indicated a better condition compared with that of non-HM users before PS-matching, including higher weight (median [IQR], 77.90 [21.8] kg vs. 74.00 [21.2] kg, p < 0.01), higher body mass index (26.00 [5.4] vs. 25.20 [5.8], p < 0.01), more percentage of limb onset (261 [81.3%] vs. 2366 [67.2%], p < 0.01), and slower progression (0.47 [0.5] vs. 0.51 [0.5], p = 0.03). HM did not significantly affect survival at 12 months (adjusted hazard ratio [HR] 0.71, 95% confidence interval [CI] 0.49-1.03; log-rank p = 0.069), but it significantly prolonged survival at 18 months (adjusted HR 0.74, 95% CI 0.56-0.98; log-rank p = 0.038). After imputation of missing data, MANOVA revealed significant effectiveness of HMs in improving activity limitation (Pillai trace, 0.0195; p = 0.03).

CONCLUSION

PS-based methods eliminated baseline differences between HM and non-HM users. Overall, the use of HM to treat patients with ALS is favored based on their association with prolonged overall survival within 18 months and improved activity limitation.

Combination of ciprofloxacin/celecoxib as a novel therapeutic strategy for ALS

OBJECTIVE

This study aimed to evaluate the safety and tolerability of a fixed-dose co-formulation of ciprofloxacin and celecoxib (PrimeC) in patients with amyotrophic lateral sclerosis (ALS), and to examine its effects on disease progression and ALS-related biomarkers.

METHODS

In this proof of concept, open-label, phase IIa study of PrimeC in 15 patients with ALS, participants were administered PrimeC thrice daily for 12 months. The primary endpoints were safety and tolerability. Exploratory endpoints included disease progression outcomes such as forced vital capacity, revised ALS functional rating scale, and effect on algorithm-predicted survival. In addition, indications of a biological effect were assessed by selected biomarker analyses, including TDP-43 and LC3 levels in neuron-derived exosomes (NDEs), and serum neurofilaments.

RESULTS

Four participants experienced adverse events (AEs) related to the study drug. None of these AEs were unexpected, and most were mild or moderate (69%). Additionally, no serious AEs were related to the study drug. One participant tested positive for COVID-19 and recovered without complications, and no other abnormal laboratory investigations were found. Participants' survival compared to their predictions showed no safety concerns. Biomarker analyses demonstrated significant changes associated with PrimeC in neural-derived exosomal TDP-43 levels and levels of LC3, a key autophagy marker.

INTERPRETATION

This study supports the safety and tolerability of PrimeC in ALS. Biomarker analyses suggest early evidence of a biological effect. A placebo-controlled trial is required to disentangle the biomarker results from natural progression and to evaluate the efficacy of PrimeC for the treatment of ALS. Summary for social media if publishedTwitter handles: @NeurosenseT, @ShiranZimri•What is the current knowledge on the topic? ALS is a severe neurodegenerative disease, causing death within 2-5 years from diagnosis. To date there is no effective treatment to halt or significantly delay disease progression.•What question did this study address? This study assessed the safety, tolerability and exploratory efficacy of PrimeC, a fixed dose co-formulation of ciprofloxacin and celecoxib in the ALS population.•What does this study add to our knowledge? This study supports the safety and tolerability of PrimeC in ALS, and exploratory biomarker analyses suggest early insight for disease related-alteration.•How might this potentially impact the practice of neurology? These results set the stage for a larger, placebo-controlled study to examine the efficacy of PrimeC, with the potential to become a new drug candidate for ALS.

Ibudilast (MN-166) in amyotrophic lateral sclerosis- an open label, safety and pharmacodynamic trial

Ibudilast (MN-166) is an inhibitor of macrophage migration inhibitory factor (MIF) and phosphodiesterases 3,4,10 and 11 (Gibson et al., 2006; Cho et al., 2010). Ibudilast attenuates CNS microglial activation and secretion of pro-inflammatory cytokines (Fujimoto et al., 1999; Cho et al., 2010). In vitro evidence suggests that ibudilast is neuroprotective by suppressing neuronal cell death induced by microglial activation. People with ALS have increased microglial activation measured by [11C]PBR28-PET in the motor cortices. The primary objective is to determine the impact of ibudilast on reducing glial activation and neuroaxonal loss in ALS, measured by PBR28-PET and serum Neurofilament light (NfL). The secondary objectives included determining safety and tolerability of ibudilast high dosage (up to 100 mg/day) over 36 weeks. In this open label trial, 35 eligible ALS participants underwent ibudilast treatment up to 100 mg/day for 36 weeks. Of these, 30 participants were enrolled in the main study cohort and were included in biomarker, safety and tolerability analyses. Five additional participants were enrolled in the expanded access arm, who did not meet imaging eligibility criteria and were included in the safety and tolerability analyses. The primary endpoints were median change from baseline in (a) PBR28-PET uptake in primary motor cortices, measured by standard uptake value ratio (SUVR) over 12-24 weeks and (b) serum NfL over 36-40 weeks. The secondary safety and tolerability endpoints were collected through Week 40. The baseline median (range) of PBR28-PET SUVR was 1.033 (0.847, 1.170) and NfL was 60.3 (33.1, 219.3) pg/ml. Participants who completed both pre and post-treatment scans had PBR28-PET SUVR median(range) change from baseline of 0.002 (-0.184, 0.156) , P = 0.5 (n = 22). The median(range) NfL change from baseline was 0.4 pg/ml (-1.8, 17.5), P = 0.2 (n = 10 participants). 30(86%) participants experienced at least one, possibly study drug related adverse event. 13(37%) participants could not tolerate 100 mg/day and underwent dose reduction to 60-80 mg/day and 11(31%) participants discontinued study drug early due to drug related adverse events. The study concludes that following treatment with ibudilast up to 100 mg/day in ALS participants, there were no significant reductions in (a) motor cortical glial activation measured by PBR28-PET SUVR over 12-24 weeks or (b) CNS neuroaxonal loss, measured by serum NfL over 36-40 weeks. Dose reductions and discontinuations due to treatment emergent adverse events were common at this dosage in ALS participants. Future pharmacokinetic and dose-finding studies of ibudilast would help better understand tolerability and target engagement in ALS.

Effective Data Sharing as a Conduit for Advancing Medical Product Development

INTRODUCTION

Patient-level data sharing has the potential to significantly impact the lives of patients by optimizing and improving the medical product development process. In the product development setting, successful data sharing is defined as data sharing that is actionable and facilitates decision making during the development and review of medical products. This often occurs through the creation of new product development tools or methodologies, such as novel clinical trial design and enrichment strategies, predictive pre-clinical and clinical models, clinical trial simulation tools, biomarkers, and clinical outcomes assessments, and more.

METHODS

To be successful, extensive partnerships must be established between all relevant stakeholders, including industry, academia, research institutes and societies, patient-advocacy groups, and governmental agencies, and a neutral third-party convening organization that can provide a pre-competitive space for data sharing to occur.

CONCLUSIONS

Data sharing focused on identified regulatory deliverables that improve the medical product development process encounters significant challenges that are not seen with data sharing aimed at advancing clinical decision making and requires the commitment of all stakeholders. Regulatory data sharing challenges and solutions, as well as multiple examples of previous successful data sharing initiatives are presented and discussed in the context of medical product development.

Development and validation of a machine-learning ALS survival model lacking vital capacity (VC-Free) for use in clinical trials during the COVID-19 pandemic

Introduction: Vital capacity (VC) is routinely used for ALS clinical trial eligibility determinations, often to exclude patients unlikely to survive trial duration. However, spirometry has been limited by the COVID-19 pandemic. We developed a machine-learning survival model without the use of baseline VC and asked whether it could stratify clinical trial participants and a wider ALS clinic population. Methods. A gradient boosting machine survival model lacking baseline VC (VC-Free) was trained using the PRO-ACT ALS database and compared to a multivariable model that included VC (VCI) and a univariable baseline %VC model (UNI). Discrimination, calibration-in-the-large and calibration slope were quantified. Models were validated using 10-fold internal cross validation, the VITALITY-ALS clinical trial placebo arm and data from the Emory University tertiary care clinic. Simulations were performed using each model to estimate survival of patients predicted to have a > 50% one year survival probability. Results. The VC-Free model suffered a minor performance decline compared to the VCI model yet retained strong discrimination for stratifying ALS patients. Both models outperformed the UNI model. The proportion of excluded vs. included patients who died through one year was on average 27% vs. 6% (VCI), 31% vs. 7% (VC-Free), and 13% vs. 10% (UNI). Conclusions. The VC-Free model offers an alternative to the use of VC for eligibility determinations during the COVID-19 pandemic. The observation that the VC-Free model outperforms the use of VC in a broad ALS patient population suggests the use of prognostic strata in future, post-pandemic ALS clinical trial eligibility screening determinations.

Quality of Life Structural Equation Model for Patients With Amyotrophic Lateral Sclerosis

PURPOSE

The aim of the study was to propose and test a quality of life model among Korean patients with amyotrophic lateral sclerosis (ALS) using structural equation modeling.

DESIGN

A cross-sectional study was performed.

METHODS

Data from 184 patients with ALS were collected from two university hospitals in Seoul and Busan, South Korea, between June and December 2018.

FINDINGS

The modified model indices indicated adequate data fit. Quality of life predictors were social support, physical functional status, depression, and general health perception.

CONCLUSION

This study improved the understanding of quality of life for Korean patients with ALS, including complex direct and indirect relationships among quality of life factors.

CLINICAL RELEVANCE

Depression was identified as the most influential factor in this population; hence, early assessment and timely intervention for depression are essential for better quality of life in patients with ALS.

Does including machine learning predictions in ALS clinical trial analysis improve statistical power?

Objective

Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disease which leads to progressive muscle weakness and eventually death. The increasing availability of large ALS clinical trial datasets have generated much interest in developing predictive models for disease progression. However, the utility of predictive modeling on clinical trial analysis has not been thoroughly evaluated.

Methods

We evaluated a predictive modeling approach for ALS disease progression measured by ALSFRS‐R using the PRO‐ACT database and validated our findings in a novel test set from a former clinical trial. We examined clinical trial scenarios where model predictions could improve statistical power for detecting treatment effects with simulated clinical trials.

Results

Models constructed with imputed PRO‐ACT data have better external validation results than those fitted with complete observations. When fitted with imputed data, super learner (R² = 0.71, MSPE = 19.7) and random forest (R² = 0.70, MSPE = 19.6) have similar performance in the external validation and slightly outperform the linear mixed effects model (R² = 0.69, MSPE = 20.5). Simulation studies suggest including machine learning predictions as a covariate in the analysis model of a 12‐month clinical study can increase the trial's effective sample size by 16% when there is a hypothetical treatment effect of 25% reduction in ALSFRS‐R mean rate of change.

Interpretation

Predictive modeling approaches for ALSFRS‐R are able to explain a moderate amount of variability in longitudinal change, which is improved by robust missing data handling for baseline characteristics. Including ALSFRS‐R post‐baseline model prediction results as a covariate in the model for primary analysis may increase power under moderate treatment effects.

A novel method for predicting the progression rate of ALS disease based on automatic generation of probabilistic causal chains

Causal discovery is considered as a major concept in biomedical informatics contributing to diagnosis, therapy, and prognosis of diseases. Probabilistic causality approaches in epidemiology and medicine is a common method for finding relationships between pathogen and disease, environment and disease, and adverse events and drugs. Bayesian Network (BN) is one of the common approaches for probabilistic causality, which is widely used in health-care and biomedical science. Since in many biomedical applications we deal with temporal dataset, the temporal extension of BNs called Dynamic Bayesian network (DBN) is used for such applications. DBNs define probabilistic relationships between parameters in consecutive time points in the form of a graph and have been successfully used in many biomedical applications. In this paper, a novel method was introduced for finding probabilistic causal chains from a temporal dataset with the help of entropy and causal tendency measures. In this method, first, Causal Features Dependency (CFD) matrix is created on the basis of parameters changes in consecutive events of a phenomenon, and then the probabilistic causal graph is constructed from this matrix based on entropy criteria. At the next step, a set of probabilistic causal chains of the corresponding causal graph is constructed by a novel polynomial-time heuristic. Finally, the causal chains are used for predicting the future trend of the phenomenon. The proposed model was applied to the Pooled Resource Open-Access Clinical Trials (PRO-ACT) dataset related to Amyotrophic Lateral Sclerosis (ALS) disease, in order to predict the progression rate of this disease. The results of comparison with Bayesian tree, random forest, support vector regression, linear regression, and multivariate regression show that the proposed algorithm can compete with these methods and in some cases outperforms other algorithms. This study revealed that probabilistic causality is an appropriate approach for predicting the future states of chronic diseases with unknown cause.

A Systematic and Comprehensive Review on Disease-Causing Genes in Amyotrophic Lateral Sclerosis

Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disorder and is characterized by degeneration and axon loss from the upper motor neuron, that descends from the lower motor neuron in the brain. Over the period, assorted outcomes from medical findings, molecular pathogenesis, and structural and biophysical studies have abetted in providing thoughtful insights underlying the importance of disease-causing genes in ALS. Consequently, numerous mechanisms were proposed for the pathogenesis of ALS, considering protein mutations, aggregation, and misfolding. Besides, the answers to the majority of ALS cases that happen to be sporadic still remain obscure. The application in discovering susceptibility factors in ALS contemplating the genetic factors is to be further dissevered in the future years with innovation in research studies. Hence, this review targets in revisiting the breakthroughs on the disease-causing genes related with ALS.

Theme 1 Epidemiology and informatics

Background: Identifying mechanisms of neurodegenerative disease causation has for long seemed to be beyond the pale of traditional epidemiological tools. Elucidating a plausible mechanism for initiation of amyotrophic lateral sclerosis (ALS) has appeared particularly elusive (1). The impression, that environmental risk factors for ALS were not providing consistent direction, meant there was no sturdy epidemiologically-based "handle" to grasp when trying to envisage a biological mechanism for triggering sporadic ALS (2). There have been challenges with interpreting the data. At times, generic concerns over potential limitations of traditional epidemiological studies have appeared to overshadow the findings in circumstances where these limitations had been overcome largely. At other times, studies with different degrees of methodological limitations have been lumped together, thereby obscuring the results of the studies with less limitations. On occasion, methodological limitations have been downplayed or ignored entirely.Emergence of Mendelian Randomization (MR) methods has offered the promise of overcoming some of the potential limitations of epidemiological studies that used traditional methods. MR methods apply concepts developed in the field of economics to infer causality in the presence of unmeasured confounding (3). The principal idea is: 1) a genetic pattern is identified that predicts a suspected risk factor - a laboratory value in patients' blood, or a particular behavior; 2) that pattern is sought in patients and controls; 3) excess presence of the pattern in patients suggests that the risk factor plays a causal role in producing the disease.However, application of MR methods requires that several underlying assumptions, specific to these methods, have been satisfied (3). Moreover, epidemiological analyses using MR methods need to adhere to core epidemiological and statistical principles. Finally, findings from MR studies need to be interpreted critically, with close attention to the context from which they arise, and with utilization of internal and external comparators (4,5).This presentation will discuss the assumptions that need to be met to apply MR methods in general and how they relate to studies in patients with ALS, drawing on recently published reports.

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.

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.

Epidemiology of ALS in Korea using nationwide big data

OBJECTIVE

This study aimed to determine the incidence, prevalence and survival time of Korean patients with amyotrophic lateral sclerosis (ALS) using National Health Insurance Service (NHIS) data.

METHODS

Using NHIS data, the Korean nationwide health dataset, we identified patients with motor neuron diseases who were first diagnosed with a KCD-6 code (G12.20-G12.28; modified from ICD-10 codes) between 2011 and 2015. ALS (G12.21 code) epidemiological characteristics, including annual incidence, prevalence, mortality rates and survival time, were analysed and compared with sociodemographic variables.

RESULTS

New patients with ALS (n=3049) were enrolled over 5 years. The mean annual incidence was 1.20/100 000, and the sex ratio was 1.60 (male:female). The mean age at the time of diagnosis was 61.4 years. The prevalence rate was 3.43/100 000 in 2015. In this period, riluzole was prescribed to 53.6% of patients with ALS. Furthermore, 20.3% of patients with ALS underwent tracheostomy. When analysed for age and socioeconomic status, ALS prevalence rate was 10.71 in the aged group (≥60) in 2015 and was lowest in the middle-income group compared with that in the high-income and low-income groups. The estimated mean survival time in this population was 50.0 months, and the 3-year and 5-year mortality rates were 52.1% and 63.7%, respectively.

CONCLUSIONS

This study is the first nationwide survey for epidemiological characteristics of ALS in Korea using national data. The use of these data substantially advances the understanding of Korean and Asian ALS epidemiology and its relationship with socioeconomic status, age and sex.

Stratification of amyotrophic lateral sclerosis patients: a crowdsourcing approach

Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease where substantial heterogeneity in clinical presentation urgently requires a better stratification of patients for the development of drug trials and clinical care. In this study we explored stratification through a crowdsourcing approach, the DREAM Prize4Life ALS Stratification Challenge. Using data from >10,000 patients from ALS clinical trials and 1479 patients from community-based patient registers, more than 30 teams developed new approaches for machine learning and clustering, outperforming the best current predictions of disease outcome. We propose a new method to integrate and analyze patient clusters across methods, showing a clear pattern of consistent and clinically relevant sub-groups of patients that also enabled the reliable classification of new patients. Our analyses reveal novel insights in ALS and describe for the first time the potential of a crowdsourcing to uncover hidden patient sub-populations, and to accelerate disease understanding and therapeutic development.

Using automated electronic medical record data extraction to model ALS survival and progression

BACKGROUND

To assess the feasibility of using automated capture of Electronic Medical Record (EMR) data to build predictive models for amyotrophic lateral sclerosis (ALS) outcomes.

METHODS

We used an Informatics for Integrating Biology and the Bedside search discovery tool to identify and extract data from 354 ALS patients from the University of Kansas Medical Center EMR. The completeness and integrity of the data extraction were verified by manual chart review. A linear mixed model was used to model disease progression. Cox proportional hazards models were used to investigate the effects of BMI, gender, and age on survival.

RESULTS

Data extracted from the EMR was sufficient to create simple models of disease progression and survival. Several key variables of interest were unavailable without including a manual chart review. The average ALS Functional Rating Scale - Revised (ALSFRS-R) baseline score at first clinical visit was 34.08, and average decline was - 0.64 per month. Median survival was 27 months after first visit. Higher baseline ALSFRS-R score and BMI were associated with improved survival, higher baseline age was associated with decreased survival.

CONCLUSIONS

This study serves to show that EMR-captured data can be extracted and used to track outcomes in an ALS clinic setting, potentially important for post-marketing research of new drugs, or as historical controls for future studies. However, as automated EMR-based data extraction becomes more widely used there will be a need to standardize ALS data elements and clinical forms for data capture so data can be pooled across academic centers.

Rasagiline for amyotrophic lateral sclerosis: A randomized, controlled trial

INTRODUCTION

Rasagiline is a monoamine oxidase B (MAO-B) inhibitor with possible neuroprotective effects in patients with amyotrophic lateral sclerosis (ALS).

METHODS

We performed a randomized, double-blind, placebo-controlled trial of 80 ALS participants with enrichment of the placebo group with historical controls (n = 177) at 10 centers in the United States. Participants were randomized in a 3:1 ratio to 2 mg/day rasagiline or placebo. The primary outcome was average slope of decline on the ALS Functional Rating Scale-Revised (ALSFRS-R). Secondary measures included slow vital capacity, survival, mitochondrial and molecular biomarkers, and adverse-event reporting.

RESULTS

There was no difference in the average 12-month ALSFRS-R slope between rasagiline and the mixed placebo and historical control cohorts. Rasagiline did not show signs of drug-target engagement in urine and blood biomarkers. Rasagiline was well tolerated with no serious adverse events.

DISCUSSION

Rasagiline did not alter disease progression compared with controls over 12 months of treatment. Muscle Nerve 59:201-207, 2019.

Unraveling the Complexity of Amyotrophic Lateral Sclerosis Survival Prediction

Objective: The heterogeneity of amyotrophic lateral sclerosis (ALS) survival duration, which varies from <1 year to >10 years, challenges clinical decisions and trials. Utilizing data from 801 deceased ALS patients, we: (1) assess the underlying complex relationships among common clinical ALS metrics; (2) identify which clinical ALS metrics are the "best" survival predictors and how their predictive ability changes as a function of disease progression. Methods: Analyses included examination of relationships within the raw data as well as the construction of interactive survival regression and classification models (generalized linear model and random forests model). Dimensionality reduction and feature clustering enabled decomposition of clinical variable contributions. Thirty-eight metrics were utilized, including Medical Research Council (MRC) muscle scores; respiratory function, including forced vital capacity (FVC) and FVC % predicted, oxygen saturation, negative inspiratory force (NIF); the Revised ALS Functional Rating Scale (ALSFRS-R) and its activities of daily living (ADL) and respiratory sub-scores; body weight; onset type, onset age, gender, and height. Prognostic random forest models confirm the dominance of patient age-related parameters decline in classifying survival at thresholds of 30, 60, 90, and 180 days and 1, 2, 3, 4, and 5 years. Results: Collective prognostic insight derived from the overall investigation includes: multi-dimensionality of ALSFRS-R scores suggests cautious usage for survival forecasting; upper and lower extremities independently degenerate and are autonomous from respiratory decline, with the latter associating with nearer-to-death classifications; height and weight-based metrics are auxiliary predictors for farther-from-death classifications; sex and onset site (limb, bulbar) are not independent survival predictors due to age co-correlation. Conclusion: The dimensionality and fluctuating predictors of ALS survival must be considered when developing predictive models for clinical trial development or in-clinic usage. Additional independent metrics and possible revisions to current metrics, like the ALSFRS-R, are needed to capture the underlying complexity needed for population and personalized forecasting of survival.

Improved stratification of ALS clinical trials using predicted survival

Introduction

In small trials, randomization can fail, leading to differences in patient characteristics across treatment arms, a risk that can be reduced by stratifying using key confounders. In ALS trials, riluzole use (RU) and bulbar onset (BO) have been used for stratification. We hypothesized that randomization could be improved by using a multifactorial prognostic score of predicted survival as a single stratifier.

Methods

We defined a randomization failure as a significant difference between treatment arms on a characteristic. We compared randomization failure rates when stratifying for RU and BO (“traditional stratification”) to failure rates when stratifying for predicted survival using a predictive algorithm. We simulated virtual trials using the PRO‐ACT database without application of a treatment effect to assess balance between cohorts. We performed 100 randomizations using each stratification method – traditional and algorithmic. We applied these stratification schemes to a randomization simulation with a treatment effect using survival as the endpoint and evaluated sample size and power.

Results

Stratification by predicted survival met with fewer failures than traditional stratification. Stratifying predicted survival into tertiles performed best. Stratification by predicted survival was validated with an external dataset, the placebo arm from the BENEFIT‐ALS trial. Importantly, we demonstrated a substantial decrease in sample size required to reach statistical power.

Conclusions

Stratifying randomization based on predicted survival using a machine learning algorithm is more likely to maintain balance between trial arms than traditional stratification methods. The methodology described here can translate to smaller, more efficient clinical trials for numerous neurological diseases.

Using an onset-anchored Bayesian hierarchical model to improve predictions for amyotrophic lateral sclerosis disease progression

BACKGROUND

Amyotrophic Lateral Sclerosis (ALS), also known as Lou Gehrig's disease, is a rare disease with extreme between-subject variability, especially with respect to rate of disease progression. This makes modelling a subject's disease progression, which is measured by the ALS Functional Rating Scale (ALSFRS), very difficult. Consider the problem of predicting a subject's ALSFRS score at 9 or 12 months after a given time-point.

METHODS

We obtained ALS subject data from the Pooled Resource Open-Access ALS Clinical Trials Database, a collection of data from various ALS clinical trials. Due to the typical linearity of the ALSFRS, we consider several Bayesian hierarchical linear models. These include a mixture model (to account for the two potential classes of "fast" and "slow" ALS progressors) as well as an onset-anchored model, in which an additional artificial data-point, using time of disease onset, is utilized to improve predictive performance.

RESULTS

The onset-anchored model had a drastically reduced posterior predictive mean-square-error distributions, when compared to the Bayesian hierarchical linear model or the mixture model under a cross-validation approach. No covariates, other than time of disease onset, consistently improved predictive performance in either the Bayesian hierarchical linear model or the onset-anchored model.

CONCLUSIONS

Augmenting patient data with an additional artificial data-point, or onset anchor, can drastically improve predictive modelling in ALS by reducing the variability of estimated parameters at the cost of a slight increase in bias. This onset-anchored model is extremely useful if predictions are desired directly after a single baseline measure (such as at the first day of a clinical trial), a feat that would be very difficult without the onset-anchor. This approach could be useful in modelling other diseases that have bounded progression scales (e.g. Parkinson's disease, Huntington's disease, or inclusion-body myositis). It is our hope that this model can be used by clinicians and statisticians to improve the efficacy of clinical trials and aid in finding treatments for ALS.

Seeking a better landscape for therapy development in neuromuscular disorders

Although the neuromuscular field has seen accelerated approval of a drug for Duchenne muscular dystrophy (DMD) and full approval of one for spinal muscular atrophy, these experiences have shown that objective data and an adequate level of effect are essential for drug approval and reimbursement. The appropriateness and validity of biomarkers and clinically meaningful endpoints and an understanding of disease progression rates all played essential roles in the levels of evidence for these drugs. Such tools are best developed through integration of clinical data. The siloing of clinical data for rare neuromuscular diseases represents a considerable barrier to achieving better care and novel therapies for patients living with neuromuscular diseases. We discuss a data-sharing model implemented for DMD and urge cultural changes in the ways natural history and clinical trial data are collected and shared across all neuromuscular diseases in order to benefit the primary stakeholder, the patient. Muscle Nerve 57: 16-19, 2018.

The changing picture of amyotrophic lateral sclerosis: lessons from European registers

Prospective population based-registers of amyotrophic lateral sclerosis (ALS) have operated in Europe for over two decades, and have provided important insights into our understanding of ALS. Here, we review the benefits that population registers have brought to the understanding of the incidence, prevalence, phenotype and genetics of ALS and outline the core operating principles that underlie these registers and facilitate international collaboration. Going forward, we offer lessons learned from our collective experience of operating population-based ALS registers in Europe for over two decades, focusing on register design, maintenance, identification and management of bias and the value of cross-national harmonisation and integration.

Predicting functional decline and survival in amyotrophic lateral sclerosis

BACKGROUND

Better predictors of amyotrophic lateral sclerosis disease course could enable smaller and more targeted clinical trials. Partially to address this aim, the Prize for Life foundation collected de-identified records from amyotrophic lateral sclerosis sufferers who participated in clinical trials of investigational drugs and made them available to researchers in the PRO-ACT database.

METHODS

In this study, time series data from PRO-ACT subjects were fitted to exponential models. Binary classes for decline in the total score of amyotrophic lateral sclerosis functional rating scale revised (ALSFRS-R) (fast/slow progression) and survival (high/low death risk) were derived. Data was segregated into training and test sets via cross validation. Learning algorithms were applied to the demographic, clinical and laboratory parameters in the training set to predict ALSFRS-R decline and the derived fast/slow progression and high/low death risk categories. The performance of predictive models was assessed by cross-validation in the test set using Receiver Operator Curves and root mean squared errors.

RESULTS

A model created using a boosting algorithm containing the decline in four parameters (weight, alkaline phosphatase, albumin and creatine kinase) post baseline, was able to predict functional decline class (fast or slow) with fair accuracy (AUC = 0.82). However similar approaches to build a predictive model for decline class by baseline subject characteristics were not successful. In contrast, baseline values of total bilirubin, gamma glutamyltransferase, urine specific gravity and ALSFRS-R item score-climbing stairs were sufficient to predict survival class.

CONCLUSIONS

Using combinations of small numbers of variables it was possible to predict classes of functional decline and survival across the 1-2 year timeframe available in PRO-ACT. These findings may have utility for design of future ALS clinical trials.

Epidemiology of Amyotrophic Lateral Sclerosis: A Population-Based Study in Israel

Background: Globally, the annual incidence and prevalence of amyotrophic lateral sclerosis (ALS) are estimated at 1.9 and 4.5 per 100,000 population, respectively. This study is aimed at describing the epidemiology of ALS in Israel in a real-world setting. Methods: A retrospective study was performed using the databases of Maccabi Healthcare Services (MHS), a 2-million-member health maintenance organization in Israel. The study included all MHS adults diagnosed with ALS between 1997 and 2013. In 2013, characteristics of ALS patients were compared to those of age-sex-matched patients without ALS. Survival after ALS diagnosis was assessed until death and until tracheostomy or death (follow-up through 2014). Results: In 2013 (n = 158), the prevalence of ALS was 8.1 per 100,000 population in MHS. In 1997-2013, a total of 375 ALS patients were diagnosed, corresponding to an average annual incidence of 1.8 per 100,000 population in MHS. The median survival from diagnosis to death was 3.5 years (95% CI 2.9-4.1), with approximately 28% surviving at least 10 years. Median tracheostomy-free survival was 2.5 years (95% CI 2.1-2.9). Conclusions: Results suggest that there is a relatively high prevalence of ALS in Israel. Further research is needed to investigate factors that may contribute to the survival of patients with ALS in Israel.

Predicting disease progression in amyotrophic lateral sclerosis

Objective

It is essential to develop predictive algorithms for Amyotrophic Lateral Sclerosis (ALS) disease progression to allow for efficient clinical trials and patient care. The best existing predictive models rely on several months of baseline data and have only been validated in clinical trial research datasets. We asked whether a model developed using clinical research patient data could be applied to the broader ALS population typically seen at a tertiary care ALS clinic.

Methods

Based on the PRO‐ACT ALS database, we developed random forest (RF), pre‐slope, and generalized linear (GLM) models to test whether accurate, unbiased models could be created using only baseline data. Secondly, we tested whether a model could be validated with a clinical patient dataset to demonstrate broader applicability.

Results

We found that a random forest model using only baseline data could accurately predict disease progression for a clinical trial research dataset as well as a population of patients being treated at a tertiary care clinic. The RF Model outperformed a pre‐slope model and was similar to a GLM model in terms of root mean square deviation at early time points. At later time points, the RF Model was far superior to either model. Finally, we found that only the RF Model was unbiased and was less subject to overfitting than either of the other two models when applied to a clinic population.

Interpretation

We conclude that the RF Model delivers superior predictions of ALS disease progression.