Exploratory pilot study to investigate the subjective assessment of sound improvement by an AI algorithm trained using self-fitting

Exploratory pilot study to investigate the subjective assessment of sound improvement by an AI algorithm trained using self-fitting - AIHearS-pilot study

Status

Recruiting

Phases

Unknown

Study type

Interventional

Source

DRKS

Registry ID

DRKS00039335

Enrollment

Registered

2026-02-12

Start date

2026-02-12

Completion date

Unknown

Last updated

2026-04-27

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Mild to moderate symmetrical age-related hearing loss

Interventions

Group 1: App-supported training of an AI algorithm via self-fitting of sound preferences in standardized sound situations for older adults with previous experience in using hearing aids Group 2: App-s

Eligibility

Sex/Gender

All

Age

55 Years to No maximum

Inclusion criteria

Inclusion criteria: - Mild to moderate age-related hearing loss (declining hearing loss, hearing curve N2 and N4, assessed as part of the study) - Age: 55 years and older - German-speaking: able to understand German-language texts and instructions - People with and without hearing aids (recorded via questionnaire)

Exclusion criteria

Exclusion criteria: - Asymmetric hearing loss - Legal guardianship - Cognitive impairments (self-reported) - Tinnitus (cause of hearing loss, uncompensated tinnitus) - Visual impairments that hinder the use of smartphones - Hand impairments that hinder the use of smartphones

Design outcomes

Primary

Measure	Time frame
Evaluation of the usability of the user interface for self-fitting hearing aids by test users (aged = 55 with mild to moderate age-related hearing loss, with and without hearing aid experience), measured using a standardized usability scale (SUS).	—

Secondary

Measure	Time frame
1) Prediction accuracy of the individually trained algorithm Accuracy with which the individually trained AIHearS algorithm predicts the preferences of test users in everyday sound scenarios in real time (e.g., agreement between predicted and actual preferred settings). 2) Preference for different sound adjustment algorithms Comparison of user preference for: (a) the individually trained AI-based AIHearS algorithm, (b) the non-individually trained AI-based AIHearS algorithm, and (c) the traditional NAL-NL2 algorithm. 3) Identified usability barriers Type, frequency, and severity of usability barriers reported by test users when using the self-fitting interface. 4) User experience (UX) evaluation Evaluation of the user experience of the self-fitting user interface by test users (e.g., using UX questionnaires, interviews, or observations). 5) Acceptance of the learning AIHearS algorithm Degree of acceptance of the individually learning AIHearS algorithm for fine sound adjustment among test users. 6) Intention to use in everyday life Intended future use of the self-fitting system by test users in their everyday lives. 7) Influence of technology and AI acceptance Correlation between: general technology acceptance and attitude toward AI and (a) usability of the user interface, (b) user experience, (c) acceptance of the system, and (d) intention to use. 8) Effects of automated sound adjustment Perceived effects of automated sound adjustment on: User autonomy, Sense of confidence in using hearing aids, Trust in AI-based systems.	—

Measure

Time frame

1) Prediction accuracy of the individually trained algorithm Accuracy with which the individually trained AIHearS algorithm predicts the preferences of test users in everyday sound scenarios in real time (e.g., agreement between predicted and actual preferred settings). 2) Preference for different sound adjustment algorithms Comparison of user preference for: (a) the individually trained AI-based AIHearS algorithm, (b) the non-individually trained AI-based AIHearS algorithm, and (c) the traditional NAL-NL2 algorithm. 3) Identified usability barriers Type, frequency, and severity of usability barriers reported by test users when using the self-fitting interface. 4) User experience (UX) evaluation Evaluation of the user experience of the self-fitting user interface by test users (e.g., using UX questionnaires, interviews, or observations). 5) Acceptance of the learning AIHearS algorithm Degree of acceptance of the individually learning AIHearS algorithm for fine sound adjustment among test users. 6) Intention to use in everyday life Intended future use of the self-fitting system by test users in their everyday lives. 7) Influence of technology and AI acceptance Correlation between: general technology acceptance and attitude toward AI and (a) usability of the user interface, (b) user experience, (c) acceptance of the system, and (d) intention to use. 8) Effects of automated sound adjustment Perceived effects of automated sound adjustment on: User autonomy, Sense of confidence in using hearing aids, Trust in AI-based systems.

—

Countries

Germany

Contacts

Public ContactLuis Perotti

Charité - Universitätsmedizin Berlin

luis.perotti@charite.de+49 30 450 553 127

Outcome results

None listed

Source: DRKS (via WHO ICTRP) · Data processed: May 1, 2026