JMIR Publications

ABSTRACT

Background:

Autosomal dominant non-syndromic hearing loss (ADNSHL) is highly heterogeneous, with more than 64 genes implicated in its etiology. This complexity limits the diagnostic power of clinical examinations and audiometry alone, while existing computational approaches have achieved only moderate accuracy and often lack interpretability. As precision medicine increasingly emphasizes genotype-phenotype correlations, there is a pressing need for diagnostic tools that provide clinicians with transparent, interpretable outputs.

Objective:

This study aimed to develop and evaluate the AudioGene Translational Dashboard (AGTD), an interpretable clinical informatics tool that integrates machine learning models and interactive visualizations to enhance genotype–phenotype correlation and support diagnostic decision-making in autosomal dominant non-syndromic hearing loss (ADNSHL).

Methods:

We developed the AGTD, integrating two sophisticated machine learning models (AG4 and AG9.1) with six interactive visualization tools. AG4 utilizes a multi-instance support vector machine classifier for patients with multiple audiograms, while AG9.1 combines adaptive boosting, k-nearest neighbors, random forest models, and logistic regression for patients with a single audiogram. Visualizations include audiometric profile plots, Audioprofile surfaces, clustering analyses, and data distribution charts designed to facilitate clinical interpretation.

Results:

AGTD introduced the ‘70/30’ rule, indicating a 74% likelihood that the causative gene is among the top three predicted genes, thereby providing clinicians a clear confidence indicator ('green flag') or caution alert ('red flag') during diagnosis. Visualization tools significantly enhanced clinicians' ability to interpret and correlate phenotypic data with predicted genetic outcomes, improving diagnostic confidence and interpretability.

Conclusions:

The AGTD significantly advances clinical informatics in genetic diagnostics of ADNSHL by integrating explainable AI and interactive visualizations, enhancing clinical interpretability and diagnostic accuracy. This approach facilitates informed clinical decision-making, highlights the translational potential of genotype-phenotype computational models, and supports precision medicine in hearing loss diagnostics. Future enhancements will target improving class balance and incorporating additional user-customizable features to further optimize clinical applicability.