Evaluation of Machine Learning Algorithms and Explainability Techniques to Detect Hearing Loss From a Speech-in-Noise Screening Test

• Published in: American journal of audiology Vol. 31; no. 3S; pp. 961 - 979
• Main Authors: Lenatti, Marta, Moreno-Sánchez, Pedro A., Polo, Edoardo M., Mollura, Maximiliano, Barbieri, Riccardo, Paglialonga, Alessia
• Format: Journal Article
• Language: English
• Published: Rockville American Speech-Language-Hearing Association 15.09.2022
• Subjects: Accuracy; Adults; Algorithms; Artificial intelligence; Audiology; Auditory Evaluation; Decision making; Decision trees; Diagnosis; Ears & hearing; Hearing disorders; Hearing loss; Machine learning; Medical research; Medical screening; Medical tests; Methods; Planning; Prevention; Reaction time; Risk factors; Screening Tests; Speech; Support vector machines; Technology application; Voice recognition; United States
• ISSN: 1059-0889; 1558-9137; 1558-9137
• DOI: 10.1044/2022_AJA-21-00194

Purpose: The aim of this study was to analyze the performance of multivariate machine learning (ML) models applied to a speech-in-noise hearing screening test and investigate the contribution of the measured features toward hearing loss detection using explainability techniques. Method: Seven different ML techniques, including transparent (i.e., decision tree and logistic regression) and opaque (e.g., random forest) models, were trained and evaluated on a data set including 215 tested ears (99 with hearing loss of mild degree or higher and 116 with no hearing loss). Post hoc explainability techniques were applied to highlight the role of each feature in predicting hearing loss. Results: Random forest (accuracy = .85, sensitivity = .86, specificity = .85, precision = .84) performed, on average, better than decision tree (accuracy = .82, sensitivity = .84, specificity = .80, precision = .79). Support vector machine, logistic regression, and gradient boosting had similar performance as random forest. According to post hoc explainability analysis on models generated using random forest, the features with the highest relevance in predicting hearing loss were age, number and percentage of correct responses, and average reaction time, whereas the total test time had the lowest relevance. Conclusions: This study demonstrates that a multivariate approach can help detect hearing loss with satisfactory performance. Further research on a bigger sample and using more complex ML algorithms and explainability techniques is needed to fully investigate the role of input features (including additional features such as risk factors and individual responses to low-/high-frequency stimuli) in predicting hearing loss.