EUVIMEDEUVIMED entdecken
Multizentrische Studie

Toward an Unbiased Deep Learning Classifier of Pediatric Middle Ear Disease

Sruthi Surapaneni iD, Nikhil Rangarajan, Kyle Davis, Katherine Pletcher, Jeffrey Flowers, Graham Strub, Abby Nolder, Deanne King, Alexander P Marston, Mark Vecchiotti, Kristan Alfonso, Sean Evans und 10 weitere

Otolaryngology–Head and Neck Surgery · 2025

DOI: 10.1002/ohn.70031 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Otolaryngology–Head and Neck Surgery, 2025. Verfasst von Sruthi Surapaneni und 21 weiteren Autor:innen. Beteiligte Einrichtung: College of Human Medicine, Michigan State University, Rochester Hills, Michigan, USA. Hauptthemen laut MEDLINE: Deep Learning, Otitis Media, Otitis Media with Effusion. Die Arbeit nennt 43 Literaturangaben. Gefördert von: National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Otitis media is the leading cause of healthcare visits and antibiotic prescriptions for children in the United States. Differentiating acute otitis media (AOM) from otitis media with effusion (OME) is crucial for antibiotic stewardship but is often difficult. The objective was to train an artificial intelligence algorithm that accurately predicts the presence and nature of middle ear effusion in pediatric patients using pediatric tympanic membrane (TM) images captured with inexpensive, consumer‐grade otoscopes. Study Design Prospective cohort study.

Setting

Tertiary Children's Hospitals.

Methods

A multicenter study gathered ear images from children aged 6 months to 10 years undergoing myringotomy and tube placement at four pediatric hospitals in the United States. Images were taken with over‐the‐counter digital otoscopes. Intraoperative middle ear findings were used to label the images. A deep learning algorithm was trained to classify middle ear disease. Performance was assessed by weighted accuracy.

Results

From a diverse population of 219 children (42.14% black, Hispanic, Asian, and other), 737 images were obtained, categorized as AOM (73), OME (190), no effusion or infection (274), and no TM in image (200). The classification model achieved a weighted accuracy of 92.5%, ranging 88.4% to 98.8% per individual category.

Conclusion

The model demonstrated high accuracy in classifying the middle ear state in young, anesthetized children. Developing an effective deep learning model using diverse, age‐representative images from affordable digital otoscopes may move us closer to real‐world applications of such technology in clinical practice to validate the role of telemedicine and improve antibiotic stewardship.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningOtitis MediaOtitis Media with EffusionHumansChild, PreschoolProspective StudiesChildInfantFemaleMaleMiddle Ear VentilationAlgorithmsTympanic MembraneDiagnosis, Differential

Stichwörter der Autor:innen

acute otitis mediaantibiotic stewardshipartificial intelligencedeep learningmiddle ear effusionotitis mediaotitis media with effusionpediatric otoscopytelemedicinetympanic membrane

Autor:innen und Institutionen

  • College of Human Medicine, Michigan State University, Rochester Hills, Michigan, USA.
  • Glimpse Diagnostics Inc, Minneapolis, Minnesota, USA.
  • Department of Otolaryngology-Head and Neck Surgery, University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA.
  • Department of Otolaryngology-Head and Neck Surgery, Saint Louis University, St. Louis, Missouri, USA.
  • College of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA.
  • Pediatric Otolaryngology, Arkansas Children's Hospital, Little Rock, Arkansas, USA.

ORCID-Profile: Sruthi Surapaneni

Förderung

  • National Science Foundation

Zitieren

APA

Surapaneni, S., Rangarajan, N., Davis, K., Pletcher, K., Flowers, J., Strub, G., Nolder, A., King, D., Marston, A. P., Vecchiotti, M., Alfonso, K., Evans, S., Deshpande, A., Prickett, K., Landry, A., Goudy, S., Govil, N., Messner, A., Richter, G., …, & Hill, C. A. (2025). Toward an Unbiased Deep Learning Classifier of Pediatric Middle Ear Disease. Otolaryngology–Head and Neck Surgery. https://doi.org/10.1002/ohn.70031

Vancouver

Surapaneni S, Rangarajan N, Davis K, Pletcher K, Flowers J, Strub G, et al. Toward an Unbiased Deep Learning Classifier of Pediatric Middle Ear Disease. Otolaryngology–Head and Neck Surgery. 2025. doi:10.1002/ohn.70031

BibTeX
@article{Surapaneni2025,
  author = {Surapaneni, Sruthi and Rangarajan, Nikhil and Davis, Kyle and Pletcher, Katherine and Flowers, Jeffrey and Strub, Graham and Nolder, Abby and King, Deanne and Marston, Alexander P and Vecchiotti, Mark and Alfonso, Kristan and Evans, Sean and Deshpande, Anita and Prickett, Kara and Landry, April and Goudy, Steven and Govil, Nandini and Messner, Anna and Richter, Gresham and Scott, Andrew R and Mehta, Deepak and Hill, Courtney Anne},
  title = {Toward an Unbiased Deep Learning Classifier of Pediatric Middle Ear Disease},
  journal = {Otolaryngology–Head and Neck Surgery},
  year = {2025},
  doi = {10.1002/ohn.70031}
}
Kostenlos starten →