Unraveling the Complexity of Amyotrophic Lateral Sclerosis Survival Prediction.

Stephen R Pfohl,Renaid B Kim,Cassie S Mitchell,Grant S Coan

doi:10.3389/fninf.2018.00036

Abstract

Objective: The heterogeneity of amyotrophic lateral sclerosis (ALS) survival duration, which varies from <1 year to >10 years, challenges clinical decisions and trials. Utilizing data from 801 deceased ALS patients, we: (1) assess the underlying complex relationships among common clinical ALS metrics; (2) identify which clinical ALS metrics are the “best” survival predictors and how their predictive ability changes as a function of disease progression.Methods: Analyses included examination of relationships within the raw data as well as the construction of interactive survival regression and classification models (generalized linear model and random forests model). Dimensionality reduction and feature clustering enabled decomposition of clinical variable contributions. Thirty-eight metrics were utilized, including Medical Research Council (MRC) muscle scores; respiratory function, including forced vital capacity (FVC) and FVC % predicted, oxygen saturation, negative inspiratory force (NIF); the Revised ALS Functional Rating Scale (ALSFRS-R) and its activities of daily living (ADL) and respiratory sub-scores; body weight; onset type, onset age, gender, and height. Prognostic random forest models confirm the dominance of patient age-related parameters decline in classifying survival at thresholds of 30, 60, 90, and 180 days and 1, 2, 3, 4, and 5 years.Results: Collective prognostic insight derived from the overall investigation includes: multi-dimensionality of ALSFRS-R scores suggests cautious usage for survival forecasting; upper and lower extremities independently degenerate and are autonomous from respiratory decline, with the latter associating with nearer-to-death classifications; height and weight-based metrics are auxiliary predictors for farther-from-death classifications; sex and onset site (limb, bulbar) are not independent survival predictors due to age co-correlation.Conclusion: The dimensionality and fluctuating predictors of ALS survival must be considered when developing predictive models for clinical trial development or in-clinic usage. Additional independent metrics and possible revisions to current metrics, like the ALSFRS-R, are needed to capture the underlying complexity needed for population and personalized forecasting of survival.

Highlights

The prolific 2014 ALS Association’s Ice Bucket Challenge commenced the world-wide dumping of ice water on the heads of courageous supporters to bring awareness and research funding to a lesser-known yet fatal neurodegenerative disease, Amyotrophic Lateral Sclerosis (ALS) (Wicks, 2014)
The resulting overlapping insights bring into focus a comprehensive view of the complex relationships among variables currently utilized to assess disease progression and predict ALS patient survival
We begin with an exploratory analysis of the raw clinical data to examine relationships, correlations, complexity, and variance that can impart clinical and theoretical insight

Summary

Introduction

The prolific 2014 ALS Association’s Ice Bucket Challenge commenced the world-wide dumping of ice water on the heads of courageous supporters to bring awareness and research funding to a lesser-known yet fatal neurodegenerative disease, Amyotrophic Lateral Sclerosis (ALS) (Wicks, 2014). The multifaceted etiology of ALS is reflected in its sporadic underpinnings, as less than 10% of patients have a familial form (Hrastelj and Robertson, 2016). Inherent heterogeneity of ALS makes it exceedingly difficult to predict and exacerbates anxiety among ALS patients and their families. Heterogeneity increases the physicians’ challenge to develop a timely intervention plan and is blamed for numerous failed clinical trials, as statistical variance drowns all but inconceivable treatment effect sizes (Beghi et al, 2011). The inability to accurately gauge varied outcomes makes the assessment of therapeutic efficacy problematic, slowing curative discovery (Rutkove, 2015). The ability to account for heterogeneity and predict real-time ALS clinical outcomes is a necessity

Methods

Results

Discussion

Conclusion