Yu-Hsiang Wu1, Hsu-Chueh Ho2,3, Shih-Hsuan Hsiao2,3, Ryan B Brummet4, Octav Chipara4. 1. a Department of Communication Sciences and Disorders , The University of Iowa , Iowa City , USA . 2. b Department of Otolaryngology , Buddhist Dalin Tzu-Chi General Hospital , Chiayi , Taiwan . 3. c School of Medicine, Tzu-Chi University , Hualien , Taiwan , and. 4. d Department of Computer Science , The University of Iowa , Iowa City , USA.
Abstract
OBJECTIVE: Determine the extent to which pre-fitting acceptable noise level (ANL), with or without other predictors such as hearing-aid experience, can predict real-world hearing-aid outcomes at three and 12 months post-fitting. DESIGN: ANLs were measured before hearing-aid fitting. Post-fitting outcome was assessed using the international outcome inventory for hearing aids (IOI-HA) and a hearing-aid use questionnaire. Models that predicted outcomes (successful vs. unsuccessful) were built using logistic regression and several machine learning algorithms, and were evaluated using the cross-validation technique. STUDY SAMPLE: A total of 132 adults with hearing impairment. RESULTS: The prediction accuracy of the models ranged from 61% to 68% (IOI-HA) and from 55% to 61% (hearing-aid use questionnaire). The models performed more poorly in predicting 12-month than three-month outcomes. The ANL cutoff between successful and unsuccessful users was higher for experienced (∼18 dB) than first-time hearing-aid users (∼10 dB), indicating that most experienced users will be predicted as successful users regardless of their ANLs. CONCLUSIONS: Pre-fitting ANL is more useful in predicting short-term (three months) hearing-aid outcomes for first-time users, as measured by the IOI-HA. The prediction accuracy was lower than the accuracy reported by some previous research that used a cross-sectional design.
OBJECTIVE: Determine the extent to which pre-fitting acceptable noise level (ANL), with or without other predictors such as hearing-aid experience, can predict real-world hearing-aid outcomes at three and 12 months post-fitting. DESIGN: ANLs were measured before hearing-aid fitting. Post-fitting outcome was assessed using the international outcome inventory for hearing aids (IOI-HA) and a hearing-aid use questionnaire. Models that predicted outcomes (successful vs. unsuccessful) were built using logistic regression and several machine learning algorithms, and were evaluated using the cross-validation technique. STUDY SAMPLE: A total of 132 adults with hearing impairment. RESULTS: The prediction accuracy of the models ranged from 61% to 68% (IOI-HA) and from 55% to 61% (hearing-aid use questionnaire). The models performed more poorly in predicting 12-month than three-month outcomes. The ANL cutoff between successful and unsuccessful users was higher for experienced (∼18 dB) than first-time hearing-aid users (∼10 dB), indicating that most experienced users will be predicted as successful users regardless of their ANLs. CONCLUSIONS: Pre-fitting ANL is more useful in predicting short-term (three months) hearing-aid outcomes for first-time users, as measured by the IOI-HA. The prediction accuracy was lower than the accuracy reported by some previous research that used a cross-sectional design.
Entities:
Keywords:
Acceptable noise level; hearing aid; international outcome inventory for hearing aids (IOI-HA); machine learning; outcome
Authors: Anna K Nabelek; Melinda C Freyaldenhoven; Joanna W Tampas; Samuel B Burchfiel; Robert A Muenchen Journal: J Am Acad Audiol Date: 2006-10 Impact factor: 1.664
Authors: Melinda C Freyaldenhoven; Patrick N Plyler; James W Thelin; Robert A Muenchen Journal: J Speech Lang Hear Res Date: 2008-02 Impact factor: 2.297