RandomForest4Life: A Random Forest for predicting ALS disease progression

Abstract

We describe a method for predicting disease progression in amyotrophic lateral sclerosis (ALS) patients. The method was developed as a submission to the DREAM Phil Bowen ALS Prediction Prize4Life Challenge of summer 2012. Based on repeated patient examinations over a three- month period, we used a random forest algorithm to predict future disease progression. The procedure was set up and internally evaluated using data from 1197 ALS patients. External validation by an expert jury was based on undisclosed information of an additional 625 patients; all patient data were obtained from the PRO-ACT database.

In terms of prediction accuracy, the approach described here ranked third best. Our interpretation of the prediction model confirmed previous reports suggesting that past disease progression is a strong predictor of future disease progression measured on the ALS functional rating scale (ALSFRS). We also found that larger variability in initial ALSFRS scores is linked to faster future disease progression. The results reported here furthermore suggested that approaches taking the multidimensionality of the ALSFRS into account promise some potential for improved ALS disease prediction.

Key words::

• ALSFRS
• ALSFRS-R
• slope
• score ratio
• prognostic factors
• PRO-ACT
• Prize4Life

Acknowledgements

Neta Zach of Prize4Life constantly answered our questions on the PRO-ACT database during the challenge and later during manuscript preparation and we would like to thank her for her invaluable support. Karen A. Brune helped us to improve the language. We thank two anonymous referees for their helpful comments on the initial manuscript.

Declaration of interest: TH was awarded the third prize of $10000 for his contribution to the challenge. Both authors have no further financial interests in the results reported here. The authors alone are responsible for the content and writing of the paper.