# Age-Stratified Classification of Common Middle Ear Pathologies Using Pressure-Less Acoustic Immittance (PLAI™) and Machine Learning

## TL;DR

This study uses machine learning and a new acoustic method to improve the diagnosis of middle ear issues in different age groups.

## Contribution

The novel use of age-stratified machine learning with Pressure-Less Acoustic Immittance (PLAI™) improves diagnostic accuracy for middle ear pathologies.

## Key findings

- Age-specific models achieved macro F1-scores of 0.79, 0.84, and 0.78 for different age groups.
- Resonant frequency, ear canal volume, and peak admittance were the most informative features for diagnosis.
- Age-based stratification reduced false negatives for conditions like Otitis Media with Effusion.

## Abstract

Background/Objective: This study explores a novel approach for diagnosing common middle ear pathologies using Pressure-Less Acoustic Immittance (PLAI™), a non-invasive alternative to conventional tympanometry. Methods: A total of 516 ear measurements were collected and stratified into three age groups: 0–3, 3–12, and 12+ years, reflecting key developmental stages. PLAI™-derived acoustic parameters, including resonant frequency, peak admittance, canal volume, and resonance peak frequency boundaries, were analyzed using Random Forest classifiers, with SMOTE addressing class imbalance and SHAP values assessing feature importance. Results: Age-specific models demonstrated superior diagnostic accuracy compared to non-stratified approaches, with macro F1-scores of 0.79, 0.84, and 0.78, respectively. Resonant frequency, ear canal volume, and peak admittance consistently emerged as the most informative features. Notably, age-based stratification significantly reduced false negative rates for conditions such as Otitis Media with Effusion and tympanic membrane retractions, enhancing clinical reliability. These results underscore the relevance of age-aware modeling in pediatric audiology and validate PLAI™ as a promising tool for early, pressure-free middle ear diagnostics. Conclusions: While further validation on larger, balanced cohorts is recommended, this study supports the integration of machine learning and acoustic immittance into more accurate, developmentally informed screening frameworks.