Predicting hearing help-seeking: What features are important for a profiling module within a hearing mHealth application?

Abstract

Introduction: Mobile health care solutions such as a Virtual Hearing Clinic (VHC) can improve quality, accessibility and equity of health services, fostering early rehabilitation for hearing loss. A VHC might be the first contact with a hearing diagnostic service and should motivate users with hearing loss to seek professional help. A psychological profiling module would secure more efficient treatment recommendations to promote help-seeking, after the diagnostic use of the VHC. Methods: N=185 (106 females) non-aided older individuals (Mage=63.8, SDage=6.6) with subjective hearing loss participated in a large ecological momentary assessment study. We collected cross-sectional and longitudinal data on several psychological- and hearing-related features that were previously found to predict help-seeking. Readiness to seek help was assessed as outcome variable at study-end and after two months. Participants were classified into help-seekers and non-seekers with supervised machine learning algorithms (Random Forest, Naive Bayes and Support Vector Machine). The most relevant features for prediction were identified with feature importance analysis. Results: The algorithms correctly predicted action to seek help at study-end in 66 to 70% of cases, reaching 75% classification accuracy at follow-up. Among the most important features for classifications were the degree of hearing loss and its perceived consequences in daily life, attitude towards hearing aids, personality traits like neuroticism and conscientiousness. Conclusion: This study contributes to the identification of individual characteristics that predict help-seeking in older individuals with self-perceived hearing loss. Suggestions for the implementation of a psychological profiling algorithm and for targeted recommendations in a VHC are derived.

Predicting hearing help-seeking: What features are important for a profiling module within a hearing mHealth application? (Preprint)

“…Analyses scripts are available on Zenodo [56]. The data is available upon request to the corresponding authors.…”

“…The data is available upon request to the corresponding authors. A preprint of the manuscript was published on medRxiv [57] in February 2023 and revised in August 2023. Preliminary results of this research were presented on symposia and conferences of the "Hearing4All" Cluster of Excellence, on the VCCA Conference 2022 and the DGPs Conference 2022.…”

Predicting hearing help-seeking: What features are important for a profiling module within a hearing mHealth application? (Preprint)

“…Analyses scripts are available on Zenodo [83]. The data is available upon request to the corresponding authors.…”

“…The data is available upon request to the corresponding authors. A preprint of the manuscript was published on medRxiv [84] in February 2023 and revised in August 2023. Preliminary results of this research were presented on symposia and conferences of the "Hearing4All" Cluster of Excellence, on the VCCA Conference 2022 and the DGPs Congress 2022.…”