AGTD: The AudioGene Translational Dashboard: A Comprehensive Tool for the Visualization and Analysis of Phenotypic Data for Diagnosing Autosomal Dominant Non-syndromic Hearing Loss (Preprint)
Authors:
- Benjamin DeSollarBDBenjamin DeSollar
- Nathan SchaeferNSNathan Schaefer
- Daniel WallsDWDaniel Walls
- Amanda M. OdellAOAmanda M. Odell
- Kevin T.A. BoothKBKevin T.A. Booth
- Hela AzaiezHAHela Azaiez
- Richard J.H. SmithRSRichard J.H. Smith
- Terry BraunTBTerry Braun
- Thomas CasavantTCThomas Casavant
Preprint
- 3 October 2025
- preprint
- Published by JMIR Publications Inc. in JMIR Preprints
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.Keywords
This publication has 20 references indexed in Scilit:
- Evaluation of CNV detection tools for NGS panel data in genetic diagnosticsEuropean Journal of Human Genetics, 2020
- Install and Configure Docker on Linux2020
- Docker Compose2017
- Genetics of non syndromic hearing lossMedical Journal Armed Forces India, 2015
- A Randomized, Open-Label, Multicenter, 4-Week Study to Evaluate the Tolerability and Pharmacokinetics of ITCA 650 in Patients With Type 2 Diabetes☆☆This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial-No Derivative Works License, which permits non-commercial use, distribution, and reproduction in any medium, provided the original author and source are credited.Clinical Therapeutics, 2013
- AudioGene: Predicting Hearing Loss Genotypes from Phenotypes to Guide Genetic ScreeningHuman Mutation, 2012
- Integrative Genomics Viewer (IGV): high-performance genomics data visualization and explorationBriefings in Bioinformatics, 2012
- Encyclopedia of Distances2009
- Audioprofile-directed screening identifies novel mutations in KCNQ4 causing hearing loss at the DFNA2 locusGenetics in Medicine, 2008
- Sensorineural hearing loss in childrenThe Lancet, 2005