“Human vs Machine” Validation of a Deep Learning Algorithm for Pediatric Middle Ear Infection Diagnosis
Otolaryngology–Head and Neck Surgery · 2023-07 · 169 (1) · 41-46
DOI: 10.1177/01945998221119156 ↗Kurz gefasst
Fachartikel in der Zeitschrift Otolaryngology–Head and Neck Surgery, online erschienen am 16.08.2022. Verfasst von Matthew G Crowson und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Otolaryngology-Head & Neck Surgery, Massachusetts Eye & Ear, Boston, Massachusetts, USA. Hauptthemen laut MEDLINE: Deep Learning, Otitis Media, Otitis Media with Effusion. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NLM NIH HHS, U.S. National Library of Medicine.
Abstract (Originalsprache)
Objective
We compared the diagnostic performance of human clinicians with that of a neural network algorithm developed using a library of tympanic membrane images derived from children taken to the operating room with the intent of performing myringotomy and possible tube placement for recurrent acute otitis media (AOM) or otitis media with effusion (OME). Study Design Retrospective cohort study.
Setting
Tertiary academic medical center from 2018 to 2021.
Methods
A training set of 639 images of tympanic membranes representing normal, OME, and AOM was used to train a neural network as well as a proprietary commercial image classifier from Google. Model diagnostic prediction performance in differentiating normal vs nonpurulent vs purulent effusion was scored based on classification accuracy. A web‐based survey was developed to test human clinicians’ diagnostic accuracy on a novel image set, and this was compared head to head against our model.
Results
Our model achieved a mean prediction accuracy of 80.8% (95% CI, 77.0%‐84.6%). The Google model achieved a prediction accuracy of 85.4%. In a validation survey of 39 clinicians analyzing a sample of 22 endoscopic ear images, the average diagnostic accuracy was 65.0%. On the same data set, our model achieved an accuracy of 95.5%.
Conclusion
Our model outperformed certain groups of human clinicians in assessing images of tympanic membranes for effusions in children. Reduced diagnostic error rates using machine learning models may have implications in reducing rates of misdiagnosis, potentially leading to fewer missed diagnoses, unnecessary antibiotic prescriptions, and surgical procedures.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Otolaryngology-Head & Neck Surgery, Massachusetts Eye & Ear, Boston, Massachusetts, USA.
- Department of Otolaryngology-Head & Neck Surgery, Harvard Medical School, Boston, Massachusetts, USA.
- Division of General Internal Medicine and Primary Care, Brigham and Women's Hospital, Boston, Massachusetts, USA.
- Department of Health Policy and Management, Harvard T. H. Chan School of Public Health, Boston, Massachusetts, USA.
ORCID-Profile: Matthew G Crowson
Förderung
- NLM NIH HHS
- U.S. National Library of Medicine
Zitieren
APA
Crowson, M. G., Bates, D. W., Suresh, K., Cohen, M. S., & Hartnick, C. J. (2023). “Human vs Machine” Validation of a Deep Learning Algorithm for Pediatric Middle Ear Infection Diagnosis. Otolaryngology–Head and Neck Surgery, 169(1), 41-46. https://doi.org/10.1177/01945998221119156
Vancouver
Crowson MG, Bates DW, Suresh K, Cohen MS, Hartnick CJ. “Human vs Machine” Validation of a Deep Learning Algorithm for Pediatric Middle Ear Infection Diagnosis. Otolaryngology–Head and Neck Surgery. 2023;169(1):41-46. doi:10.1177/01945998221119156
BibTeX
@article{Crowson2023,
author = {Crowson, Matthew G and Bates, David W and Suresh, Krish and Cohen, Michael S and Hartnick, Christopher J},
title = {“Human vs Machine” Validation of a Deep Learning Algorithm for Pediatric Middle Ear Infection Diagnosis},
journal = {Otolaryngology–Head and Neck Surgery},
year = {2023},
volume = {169},
number = {1},
pages = {41--46},
doi = {10.1177/01945998221119156}
}
EUVIMED