This section contains external scientific resources, relevant to the project.
Predicting amyotrophic lateral sclerosis (ALS) progression with machine learning
Machine learning (ML) can model complex heterogeneous relationships and has been used for ALS progression prediction and discovery of potential therapeutic targets. Accurate prediction of ALS progression, typically defined as the decline in the ALS Functional Rating Scale (ALSFRS) or its revised version (ALSFRS-R), can improve the statistical power and reduce the sample size of trials, reducing costs and increasing likelihood of success. Selection of a homogenous group of fast-progressing patients increases the probability that a real treatment effect can be detected in a shorter time. However, previous ML studies on ALS prognosis prediction have several limitations.
Authors: Muzammil Arif Din Abdul Jabbar, Ling Guo, Sonakshi Nag, Yang Guo, Zachary Simmons, Erik P. Pioro, Savitha Ramasamy & Crystal Jing Jing Yeo