Predicting functional decline and survival in amyotrophic lateral sclerosis

• Published in: PloS one Vol. 12; no. 4; p. e0174925
• Main Authors: Ong, Mei-Lyn, Tan, Pei Fang, Holbrook, Joanna D
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 13.04.2017; Public Library of Science (PLoS)
• Subjects: Age; Aged; Albumin; Algorithms; Amyotrophic lateral sclerosis; Amyotrophic Lateral Sclerosis - mortality; Analysis; Assaying; Bilirubin; Biology and Life Sciences; Biomarkers; Body mass; Body mass index; Bone diseases; Categories; Central nervous system; Ceramide glucosyltransferase; Cholesterol; Cleaning; Clinical trials; Complications; Computational neuroscience; Computer and Information Sciences; Computer applications; Construction standards; Creatine; Creatine kinase; Databases, Factual; Datasets; Death; Degeneration; Dementia disorders; Design; Diagnosis; Disease; Disease-Free Survival; Female; Frontotemporal dementia; Health aspects; Humans; Lean body mass; Male; Mathematical models; Medicine; Medicine and Health Sciences; Middle Aged; Models, Biological; Mortality; Myopathy; Nervous system; Neurodegeneration; Neurodegenerative diseases; Neurology; Neurons; Nutrition; Open access; Pathogenesis; pH effects; Physical Sciences; Population studies; Prediction models; Predictive Value of Tests; Prognosis; Research and Analysis Methods; Robustness (mathematics); Science; Sensitivity; Specific gravity; Survival; Survival Rate; Technology; Variables; United States; Singapore
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0174925

Better 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. In 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. A 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. Using 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.