Abstract Details

Title Implications and Predictors of Variability of Disease Progression in Amyotrophic Lateral Sclerosis (ALS)

Topic Neuromuscular and Clinical Neurophysiology (EMG)

Presentation(s) P1 - Poster Session 1 (9:00 AM-5:00 PM)

Poster/Presentation
Number 388

Objective Use machine learning to study variability of progression in amyotrophic lateral sclerosis (ALS), its implications on prognosis, and to discover possible predictive biomarkers of variability.

Background ALS is a heterogenous disease with variability in phenotype and disease progression. Individual variability in ALSFRS-R can be due to ‘noise’ from subjective scoring or effects of symptomatic treatment. Whether ALSFRS-R variability represents biological activity affecting prognosis is unknown.

Design/Methods We analyzed ALSFRS and ALSFRS-R data from the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database. The line of best fit based on total sum of root mean square errors was used to determine variability. Scores greater than the median of the standard deviation from this line of best fit were considered "more variable progression", and “less variable progression” otherwise. An XGBoost model was trained to predict variability in ALS progression and identify predictive features of variability.

Results Over 12 months, 35.4% of 7487 ALSFRS-R trajectories remained less variable throughout, 21.3% were more variable throughout; for the first 6 months, 28.7% of ALSFRS-R trajectories were less variable, then became more variable, and 14.5% were more variable, then became less variable. Over the entire disease duration, more variable progressors (59%) had a better prognosis and more often survived >800 days from disease onset compared to less variable progressors(52.3%, P=0.012). XGBoost had an accuracy of 58.5% for more vs. less variable progressor binary classification. Top clinical features predicting variability included: site of disease onset, change in alkaline phosphatase, standard deviation of bilirubin and FVC, and mean AST, absolute basophil count, serum protein and HbA1c.

Conclusions Increased individual variability in ALS disease progression is associated with better prognosis, and possible underlying mechanisms such as compensatory reinnervation remain to be studied. Biomarkers associated with variability deserve further clinical study.

Authors/Disclosures
PRESENTER	No disclosure on file
	No disclosure on file
Erik P. Pioro, MD, DPhil, FAAN (University of British Columbia)	Dr. Pioro has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Avanir Pharmaceutical, Inc.. Dr. Pioro has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Amylyx Pharmaceuticals. Dr. Pioro has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Argenx. Dr. Pioro has received personal compensation in the range of $500-$4,999 for serving as a Consultant for MT Pharma America, Inc.. Dr. Pioro has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for NeuroTherapia, Inc.. Dr. Pioro has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for MT Pharma America, Inc..
	No disclosure on file
Crystal J. Yeo, MD, PhD	Dr. Yeo has nothing to disclose.

��ɫ��

��ɫ��