Predicting disease progression in amyotrophic lateral sclerosis

Abstract

ObjectiveIt 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.MethodsBased 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.ResultsWe 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.InterpretationWe conclude that the RF Model delivers superior predictions of ALS disease progression.

What causes amyotrophic lateral sclerosis?

“…For example, the p.Asp91Ala variation of the SOD1 gene is associated with very slow progression 63, 64 , while the p.Ala5Val variant is associated with aggressive disease 65 . Statistical models can be used to provide clinically useful information for patients, the strongest message being that survival is extremely unreliably predicted in individuals, even though patterns can be seen in the data 54, 57, 66– 68 .…”

Pilot trial of inosine to elevate urate levels in amyotrophic lateral sclerosis

“…A recent trend in the field of ALS is to explore the utility of prediction algorithms as an adjunct to clinical care and/or clinical trials 21, 50, 51, 52. We evaluated the apparent efficacy of serum urate elevation using a virtual control arm derived using a novel prediction algorithm.…”

“…care and/or clinical trials. 21,[50][51][52] We evaluated the apparent efficacy of serum urate elevation using a virtual control arm derived using a novel prediction algorithm. Observed ALSFRS-R total scores were remarkably close to those predicted for untreated patients based on the baseline characteristics of participants, suggesting no dramatic benefit from serum urate elevation; however, lack of an observable treatment effect of inosine on ALSFRS-R should not be over-interpreted because this trial lacked power to detect all but a very large effect over a short period of observation.…”

Trajectories of impairment in amyotrophic lateral sclerosis: Insights from the Pooled Resource Open‐Access ALS Clinical Trials cohort

“…Prior PRO‐ACT‐related work has attempted to predict future slope of ALSFRS‐R, often using machine‐learning algorithms . This study describes qualitative and quantitative aspects of the variation in ALSFRS‐R and subscore trajectories.…”

“…Prior PRO-ACT-related work has attempted to predict future slope of ALSFRS-R, often using machine-learning algorithms. [18][19][20] This study describes qualitative and quantitative aspects of the variation in ALSFRS-R and subscore trajectories. A recent publication with similar objectives examined the "raw" postslope (a line through 2 measures) and did not examine subscores.…”