Predicting functional decline and survival in amyotrophic lateral sclerosis

Abstract

BackgroundBetter predictors of amyotrophic lateral sclerosis disease course could enable smaller and more targeted clinical trials. Partially to address this aim, the Prize for Life foundation collected de-identified records from amyotrophic lateral sclerosis sufferers who participated in clinical trials of investigational drugs and made them available to researchers in the PRO-ACT database.MethodsIn this study, time series data from PRO-ACT subjects were fitted to exponential models. Binary classes for decline in the total score of amyotrophic lateral sclerosis functional rating scale revised (ALSFRS-R) (fast/slow progression) and survival (high/low death risk) were derived. Data was segregated into training and test sets via cross validation. Learning algorithms were applied to the demographic, clinical and laboratory parameters in the training set to predict ALSFRS-R decline and the derived fast/slow progression and high/low death risk categories. The performance of predictive models was assessed by cross-validation in the test set using Receiver Operator Curves and root mean squared errors.ResultsA model created using a boosting algorithm containing the decline in four parameters (weight, alkaline phosphatase, albumin and creatine kinase) post baseline, was able to predict functional decline class (fast or slow) with fair accuracy (AUC = 0.82). However similar approaches to build a predictive model for decline class by baseline subject characteristics were not successful. In contrast, baseline values of total bilirubin, gamma glutamyltransferase, urine specific gravity and ALSFRS-R item score—climbing stairs were sufficient to predict survival class.ConclusionsUsing combinations of small numbers of variables it was possible to predict classes of functional decline and survival across the 1–2 year timeframe available in PRO-ACT. These findings may have utility for design of future ALS clinical trials.

Model-Based and Model-Free Techniques for Amyotrophic Lateral Sclerosis Diagnostic Prediction and Patient Clustering

“…The previous investigations using PRO-ACT data to predict ALS progression or forecast survival have demonstrated mostly marginal prediction accuracy. For instance, the topranked method for predicting survival of individual patients yielded a concordance index of 0.717 [35], the optimal RUS-Boost model predicting ALSFRS-R decline generated a crossvalidation AUC of 0.82, and the best prediction model for slow progressing patients had an overall prediction accuracy of 0.74 [36]. Another recent European study examined longitudinally about 2,000 patients over two decades.…”

Survival forests under test: Impact of the proportional hazards assumption on prognostic and predictive forests for amyotrophic lateral sclerosis survival

“…The availability of such instruments would, for example, allow the planning of more powerful clinical trials by means of efficient patient stratification (Chiò et al 2009). Two approaches have been used in the past, namely the search for prognostic models for the overall survival time after diagnosis (Kimura et al 2006;Zoccolella et al 2008;Fujimura-Kiyono et al 2011;Beaulieu-Jones et al 2016;Mandrioli et al 2017;Ong et al 2017;Pfohl et al 2018, among many others) and the prognosis of a functional assessment of patients via the ordinal ALS functional rating scale (ALSFRS; Brooks et al 1996) and ALSFRS-R scores (Cedarbaum et al 1999;Hothorn and Jung 2014;Küffner et al 2015).…”

Distribution of serum creatine kinase levels in amyotrophic lateral sclerosis

“…7,8 Evidence is conflicting whether CK is predictive of disease progression in ALS. [3][4][5]9 CK correlates with muscle loss and cramping, which is hypothesized to lead to muscle breakdown. 4…”