Machine learning for pattern detection in cochlear implant FDA adverse event reports.

Journal: Cochlear implants international
PMID:

Abstract

Medical device performance and safety databases can be analyzed for patterns and novel opportunities for improving patient safety and/or device design. The objective of this analysis was to use supervised machine learning to explore patterns in reported adverse events involving cochlear implants. Adverse event reports for the top three CI manufacturers were acquired for the analysis. Four supervised machine learning algorithms were used to predict which adverse event description pattern corresponded with a specific cochlear implant manufacturer and adverse event type. U.S. government public database. Adult and pediatric cochlear patients. Surgical placement of a cochlear implant. Classification prediction accuracy (% correct predictions). Most adverse events involved patient injury ( = 16,736), followed by device malfunction ( = 10,760), and death ( = 16). The random forest, linear SVC, naïve Bayes and logistic algorithms were able to predict the specific CI manufacturer based on the adverse event narrative with an average accuracy of 74.8%, 86.0%, 88.5% and 88.6%, respectively. Using supervised machine learning algorithms, our classification models were able to predict the CI manufacturer and event type with high accuracy based on patterns in adverse event text descriptions.

Authors

  • Matthew G Crowson
    Department of Otolaryngology-Head and Neck Surgery, Sunnybrook Health Sciences Center, Toronto, Ontario, Canada.
  • Amr Hamour
    Department of Otolaryngology-HNS, Sunnybrook Health Sciences Center, University of Toronto, Toronto, Ontario.
  • Vincent Lin
  • Joseph M Chen
    Department of Otolaryngology-Head and Neck Surgery, Sunnybrook Health Sciences Center, Toronto, Ontario, Canada.
  • Timothy C Y Chan
    Department of Mechanical and Industrial Engineering, University of Toronto, 5 King's College Road, Toronto, Ontario M5S 3G8, Canada and Techna Institute for the Advancement of Technology for Health, 124 - 100 College Street, Toronto, Ontario M5G 1P5, Canada.