Doctor of Philosophy
Electrical and Computer Engineering
The ability to perceive and understand auditory information is critical for child development. Some children struggle to process sound signals and associate meaning with them, despite having normal hearing sensitivity. These children are suspected of having Auditory Processing Disorder (APD). Unfortunately, children are often misdiagnosed or identified late, after they have already experienced academic failure. Reasons may include complex and subjective assessments; associated comorbidities; testing time; and a lack of clinical training. Machine Learning (ML) algorithms have been successfully employed in other areas to overcome such challenges. This thesis explores the use of ML algorithms to analyze pediatric APD assessment data.
First, a systematic literature review was performed of studies using ML to analyze auditory brainstem responses (ABRs). Next, data collected from 134 school-age children suspected of having APD by the National Centre for Audiology at Western University were used to develop two ML models. The first model aimed to identify abnormal ABRs recorded from children suspected of APD, and the second aimed to categorize data into clinically-relevant subgroups. Both models were found to make predictions that agreed with expert clinical knowledge at an accuracy level of 92% and 90%, respectively.
This work has both clinical and research implications. Categorizing children into subgroups may allow clinicians to intervene selectively. Additionally, the ML workflows derived here can be adopted into future studies. Lastly, this study may provide a basis for multi-centre collaborations to better understand APD and develop a diagnostic gold standard.
Summary for Lay Audience
Auditory processing disorder (APD) is a condition that affects some school-age children. Children with APD have difficulty understanding the sounds in their environment, especially speech sounds, even though they do not have hearing loss. Audiologists have made immense efforts to understand APD; however, it remains a challenging condition to diagnose, and there is currently no gold standard diagnostic method.
Audiologists perform various tests organized in a battery format to assess the auditory processing capabilities of children suspected of having APD. The test battery consists of both objective and behavioral tests. The objective tests evaluate the integrity of the auditory system, while the behavioral tests measure the child’s perceptual ability to process sounds. Audiologists must score and analyze each test in the test battery to deliver a diagnostic report. This analysis takes a lot of time, experience, and knowledge, and there are limited tools available to help. For these reasons, many audiologists do not perform APD assessments.
Machine learning (ML) is a subfield of computer science that utilizes large data sets to train a computer algorithm to identify patterns in the data. These learned patterns can then be used to arrive at conclusions and make predictions with similar accuracy to field experts. ML tools can be useful in healthcare to improve workflows and inter-rater reliability. In this thesis, the use of ML to analyze the data of the APD clinical test battery was explored. First, a systematic literature review was carried out to find available literature on the assessment of APD data using ML techniques. Next, a ML model was developed which can identify abnormal brainstem responses in children with APD. Lastly, a ML model was developed to classify APD children into four clinical subgroups based on their behavioural and physiological performance. Both tools were able to make highly accurate predictions from the data. It is anticipated that this work may aid in the future care of children with auditory processing difficulties.
Wimalarathna, Hasitha, "Using Machine Learning to Assist Clinicians to Diagnose Auditory Processing Disorder in Children" (2023). Electronic Thesis and Dissertation Repository. 9195.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 License.
Available for download on Saturday, April 12, 2025