Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Mar 31;15(2):35.
doi: 10.3390/audiolres15020035.

Using Machine Learning for Analysis of Wideband Acoustic Immittance and Assessment of Middle Ear Function in Infants

Shan Peng  1 , Yukun Zhao  2 , Xinyi Yao  1 , Huilin Yin  1 , Bei Ma  3 , Ke Liu  2 , Gang Li  1 , Yang Cao  2
Affiliations

Using Machine Learning for Analysis of Wideband Acoustic Immittance and Assessment of Middle Ear Function in Infants

Shan Peng et al. Audiol Res. .

Abstract

Objectives: Evaluating middle ear function is essential for interpreting screening results and prioritizing diagnostic referrals for infants with hearing impairments. Wideband Acoustic Immittance (WAI) technology offers a comprehensive approach by utilizing sound stimuli across various frequencies, providing a deeper understanding of ear physiology. However, current clinical practices often restrict WAI data analysis to peak information at specific frequencies, limiting its comprehensiveness.

Design: In this study, we developed five machine learning models-feedforward neural network, convolutional neural network, kernel density estimation, random forest, and support vector machine-to extract features from wideband acoustic immittance data collected from newborns aged 2-6 months. These models were trained to predict and assess the normalcy of middle ear function in the samples.

Results: The integrated machine learning models achieved an average accuracy exceeding 90% in the test set, with various classification performance metrics (accuracy, precision, recall, F1 score, MCC) surpassing 0.8. Furthermore, we developed a program based on ML models with an interactive GUI interface. The software is available for free download.

Conclusions: This study showcases the capability to automatically diagnose middle ear function in infants based on WAI data. While not intended for diagnosing specific pathologies, the approach provides valuable insights to guide follow-up testing and clinical decision-making, supporting the early identification and management of auditory conditions in newborns.

Keywords: hearing of infants; machine learning; middle ear function; wideband acoustic immittance.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Feedforward neural network classification model.
Figure 2
Figure 2
Convolutional neural network classification model.
Figure 3
Figure 3
Cross-validation results of the FNN model.
Figure 4
Figure 4
Cross-validation results of the CNN model.
Figure 5
Figure 5
Cross-validation results of the KDE model.
Figure 6
Figure 6
Cross-validation results of the RF model.
Figure 7
Figure 7
Cross-validation results of SVM model.
Figure 8
Figure 8
Software interface display of WAIpred. (A) WAI file input area; (B) text results display area, including basic input information and the prediction results for each model; (C) visualization of the input WAI data and contrast WAI data; and (D) auxiliary judgment area, including the admittance curve at 226 Hz and 1000 Hz.
Figure 9
Figure 9
Conflict detection between model judgment results and tympanogram curves. (A) The model judges the sample as abnormal, but the 226 Hz tympanogram is type A or there is a peak in the 1000 Hz tympanogram. (B) The model judges the sample as normal, but the 226 Hz tympanogram is not type A, and there is no peak in the 1000 Hz tympanogram [13].
Figure 10
Figure 10
WAI file check display. The red box indicates examples of prompted errors
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Wen C., Huang L.-H. Newborn hearing screening program in China: A narrative review of the issues in screening and management. Front. Pediatr. 2023;11:1222324. doi: 10.3389/fped.2023.1222324. - DOI - PMC - PubMed
    1. Wroblewska-Seniuk K.E., Dabrowski P., Szyfter W., Mazela J. Universal newborn hearing screening: Methods and results, obstacles, and benefits. Pediatr. Res. 2017;81:415–422. doi: 10.1038/pr.2016.250. - DOI - PubMed
    1. Rosenfeld R.M., Shin J.J., Schwartz S.R., Coggins R., Gagnon L., Hackell J.M., Hoelting D., Hunter L.L., Kummer A.W., Payne S.C., et al. Clinical Practice Guideline: Otitis Media with Effusion (Update) Otolaryngol. Head Neck Surg. 2016;154:S1–S41. doi: 10.1177/0194599815623467. - DOI - PubMed
    1. Williams A., Pulsifer M., Tissera K., Mankarious L.A. Cognitive and Behavioral Functioning in Hearing-Impaired Children with and without Language Delay. Otolaryngol. Head Neck Surg. 2020;163:588–590. doi: 10.1177/0194599820915741. - DOI - PubMed
    1. Shelton R.L., Nolan R.M., Monroy G.L., Pande P., Novak M.A., Porter R.G., Boppart S.A. Quantitative Pneumatic Otoscopy Using a Light-Based Ranging Technique. J. Assoc. Res. Otolaryngol. 2017;18:555–568. doi: 10.1007/s10162-017-0629-5. - DOI - PMC - PubMed

LinkOut - more resources