Amyotrophic lateral sclerosis (ALS) is a rapidly progressing neurodegenerative disease that typically leads to death within 3-5 years but for which disease progression is heterogeneous across the patient population. This underlying disease heterogeneity has hindered efforts to assess efficacy for developmental treatments designed to delay disease progression. As such, stratification of ALS patients into meaningful subgroups has been a long-standing interest across the field as a mechanism to enable better drug development using more cost-effective and accurate clinical trials, as well as to derive new and important insights into disease mechanisms and manifestations. So far, this critical inquiry has not yet been sufficiently addressed due to limited access to ALS patient-level data and to sophisticated computational tools.
The establishment of the Pooled Resources Open-Access Clinical Trial (PRO-ACT; funded by ALS Therapy Alliance) database has addressed the problem of limited data. Working with the first iteration of PRO-ACT that featured a dataset of 1,882 ALS patients from past clinical trials, we launched the DREAM Phil Bowen ALS prediction Prize4Life in 2012. That first Challenge asked solvers to predict the rate of ALS disease progression for individuals and featured a $25,000 winner’s prize to maximize participation. Algorithms were developed and evaluated in a statistically rigorous blinded assessment. The Challenge drew over 1,000 solvers from 63 countries and led to meaningful impact for both clinical trials and disease understanding. The team that developed the best performing method was able to develop an algorithm that can now be used to refine patient enrollment in clinical trials – and was able to reduce by 20% the number of patients needed for effective ALS clinical trials: such a reduction translates to millions of dollars saved for future clinical trials that leverage the winning algorithms. Furthermore, the Challenge’s winning algorithms identified novel features of ALS pathology that are predictive of disease progression. The results of this Challenge were recently published in Nature biotechnology.
Since running the first ALS Challenge, Prize4Life has worked to receive, harmonize and merge more data so that now there are more than 9,000 ALS patients represented in the PRO-ACT database including a large amount of previously unpublished data. The DREAM ALS Stratification Prize4Life will utilize this growth in data to address the question of stratifying ALS patients into meaningful subgroups, to enable better understanding of patient profiles and application of personalized ALS treatments. This effort will also work to significantly reduce the costs of future ALS clinical trials, aid clinical care and identify new disease predictors that can lead to novel biomarker development.