Risk prediction for ALS using semi-competing risk models with applications to the ALS Natural History Consortium...

Area of Science:

• Neurology
• Biostatistics

Background:

• Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease.
• Key disease progression landmarks can occur before death, impacting patient management and clinical trial design.

Purpose of the Study:

• To develop and validate predictive models for major ALS disease progression landmarks.
• Utilize a semi-competing risks modeling approach to account for mortality.

Main Methods:

• Analysis of 1508 participants from the ALS Natural History Consortium (ALS NHC).
• Employed semi-competing risks modeling to predict time to gastrostomy, noninvasive ventilation (NIV) use, speech loss, and ambulation loss.
• Internal validation using cross-validation and external validation with Emory University data.

Main Results:

• Diagnostic delay, age, and site of onset were significant predictors of disease progression.
• Models demonstrated good predictive capabilities across various outcomes and pathways.
• Results were consistent in both internal and external validation datasets.

Conclusions:

• Semi-competing risks modeling offers a flexible framework for studying ALS progression.
• The developed models show reliable predictive power for crucial disease milestones.
• Validated models can support clinical trial design and patient care strategies in ALS.