Presented at the 27th International Symposium on Amyotrophic Lateral Sclerosis and Motor Neurone Disease, Dublin Ireland, December 2016.
Objectives: We asked whether models trained using PRO-ACT could predict the disease progression of clinic patients and outperform the predictive accuracy of a commonly used nonparametric linear model (Pre-Slope Model) for calculating the slope of the ALSFRS-R. The ultimate goal of these studies is to develop a model useful for predicting the disease course for the full range of ALS patients encountered at a tertiary care clinic.
Conclusions: We conclude that a non-parametric, non-linear machine learning model (RF Model) trained using research patients enrolled in clinical trials could more accurately predict disease progression in a population of patients being treated at a tertiary care clinic than more traditional models (GL and Pre-Slope Models) despite the potential confounds of bias due to trial participation and differences in the clinical and demographic distributions of research vs. tertiary care clinic ALS patient populations. The approach used here should serve as a model for the development of predictive models in additional neurologic diseases.
Authors: Taylor A, Fournier C, Polak M, Wang L, Zach N, Shepperson J, Reichert J, Keymer M, Glass JD, and Ennist D.