What do you think caused your ALS? An analysis of the CDC national amyotrophic lateral sclerosis patient registry qualitative risk factor data using artificial intelligence and qualitative methodology

Affiliates Danielle Boyce [1][2], Jaime Raymond [3], Theodore C. Larson [3], Eddie Kirkland [4], D. Kevin Horton [3], Paul Mehta [3]


  1. Center for Quantitative Methods and Data Science, Institute for Clinical Research and Health Policy Studies, Tufts University School of Medicine, Boston, MA, USA
  2. Johns Hopkins University Schools of Medicine, Baltimore, MD, USA
  3. Centers for Disease Control and Prevention/Agency for Toxic Substances and Disease Registry, Office of Innovation and Analytics, National ALS Registry (CDC/ATSDR), Atlanta, GA, USA
  4. ICF, Inc., Atlanta, GA, USA
Journal Amyotrophic Lateral Sclerosis and Frontotemporal Degeneration
Summary This study from the Center for Quantitative Methods and Data Science, and the National ALS Registry, aims to understand the role artificial intelligence (AI) can play in reinforcing data analysis of the perception of the cause of ALS held by individuals living with the disease. The team used over 3000 narrative responses who answered the question “What do you think caused your ALS?” when joining the National ALS Registry and applied both qualitative methods and natural language processing (NLP) AI methods, specifically Bidirectional Encoder Representations from Transformers (BERT), to assess the responses. The study found that traditional qualitative analysis methods resulted in a more comprehensive theme and subtheme development of the responses, but AI can provide a reinforcing check for traditional analysis methods. The team proposes the union of human and AI analysis methods in future studies of qualitative data in order to approach the data from all angles.
Link to paper Read the paper here!