A Hybrid Deep Learning Approach to Identify Preventable Childhood Hearing Loss.

Journal: Ear and hearing
PMID: 37318215

Abstract

OBJECTIVE: Childhood hearing loss has well-known, lifelong consequences. Infection-related hearing loss disproportionately affects underserved communities yet can be prevented with early identification and treatment. This study evaluates the utility of machine learning in automating tympanogram classifications of the middle ear to facilitate layperson-guided tympanometry in resource-constrained communities.

Authors

  • Felix Q Jin
    Department of Biomedical Engineering, Duke University, Durham, NC, USA.
  • Ouwen Huang
    Department of Biomedical Engineering, Duke University, Durham, North Carolina, USA.
  • Samantha Kleindienst Robler
    Department of Audiology, Norton Sound Health Corporation, Nome, Alaska, USA.
  • Sarah Morton
    Duke Global Health Institute, Durham, North Carolina, USA.
  • Alyssa Platt
    Department of Biostatistics Duke University.
  • Joseph R Egger
    Duke Global Health Institute, Durham, North Carolina, USA.
  • Susan D Emmett
    Duke Global Health Institute, Durham, North Carolina, USA.
  • Mark L Palmeri
    Department of Biomedical Engineering, Duke University, Durham, NC, USA.

Keywords

External Resources

Popular Topics
Recent Journals