WhatsApp AI Support vs Paper Support for First-Time Hearing Aid Users

Official title

A WhatsApp-Delivered AI-Enabled Support Programme Versus Paper-Based Support for First-Time Hearing Aid Users in Low-Resource Communities: A Randomized Controlled Trial

Overview

The purpose of this study is to advance hearing care in low- and middle-income countries (LMICs) through the rigorous evaluation and optimization of innovative interventions and technologies. This study encompasses the following key aim: This study aims to evaluate the effectiveness of a WhatsApp-delivered AI-enabled support and acclimatization programme for adults receiving preset hearing aids in low-resource community settings. The AI-enabled programme combines two complementary components delivered through the same WhatsApp channel: (i) a structured push programme of 16 voice notes and images delivered over four weeks, and (ii) an on-demand artificial-intelligence (AI) conversational support agent available throughout the four-week intervention period. The primary objective is to determine whether this WhatsApp-delivered AI-enabled programme results in superior hearing aid self-efficacy compared to receiving the equivalent core information in a paper-based pamphlet at the time of fitting. By comparing hearing aid self-efficacy, hearing aid outcomes, and user engagement between the intervention (WhatsApp AI-enabled) and control (paper-based) groups, this study seeks to establish whether AI-enabled digital delivery provides superior support and leads to better self-efficacy for first-time hearing aid users compared to traditional paper-based methods.

Detailed description

This study aims to evaluate the effectiveness of a WhatsApp-delivered AI-enabled support and acclimatization programme, compared to traditional paper-based support, for adults receiving preset hearing aids in community-based settings in South Africa. The AI-enabled programme combines two complementary components delivered through the same WhatsApp channel: (i) a structured push component consisting of 16 voice notes and images sent over four weeks, covering hearing aid use, maintenance, troubleshooting, and communication strategies; and (ii) an on-demand AI conversational support agent available throughout the four-week intervention period, enabling participants to ask free-text questions and receive individualized, educationally-bounded responses. The two components are conceived as complementary: structured content delivers a planned curriculum at the right pace for acclimatization, while the AI agent answers ad-hoc questions and addresses individual concerns as they arise. We hypothesize that this WhatsApp-delivered AI-enabled intervention will result in superior hearing aid self-efficacy at five weeks post-fitting compared to receiving the equivalent core information in a paper-based pamphlet at the time of fitting.

To test this hypothesis, we will conduct a two-arm randomized controlled trial with blinded outcome assessment, in which all participants receive preset hearing aids fitted by trained community healthcare workers (CHWs). Participants will be randomly assigned to one of two groups:

* Experimental group (WhatsApp-delivered AI-enabled support): receives the AI-enabled support and acclimatization programme delivered exclusively via WhatsApp, comprising (i) 16 structured voice notes and images delivered over four weeks and (ii) on-demand access to the AI conversational support agent throughout the four-week intervention period. * Control group (paper-based support): receives the equivalent core support information delivered exclusively in a printed pamphlet at the time of fitting.

This design compares two delivery models for hearing aid support information, a WhatsApp-delivered AI-enabled programme versus traditional paper-based provision, for first-time hearing aid users in low-resource community settings. Follow-up occurs one week after completion of the 4-week intervention. Therefore, follow-up visits to complete outcome measures will be conducted at five weeks post-fitting to ensure all experimental group participants have completed the intervention.

The primary outcome will be hearing aid self-efficacy, assessed using the Measure of Audiologic Rehabilitation Self-Efficacy for Hearing Aids (MARS-HA) global score at five weeks post-fitting. Secondary outcomes will include self-reported average daily use assessed using an open-ended question, self-reported hearing aid benefit, use, and satisfaction as measured by the International Outcome Inventory for Hearing Aids (IOI-HA), perceived hearing handicap assessed using the Revised Hearing Handicap Inventory - Screening (RHHI-S), hearing aid skills and knowledge assessed using the Hearing Aid Skills and Knowledge Inventory (HASKI), and social connectedness assessed using the Berkman-Syme Social Network Index (SNI). Device retention and any device-related issues will also be recorded as additional secondary outcomes. All participants will be provided with a contact number for CHWs should they require additional assistance.

Rationale Given the limited access to hearing care in LMICs due to prohibitive costs and scarcity of trained professionals, this study leverages mHealth solutions and task-shifting to CHWs as a sustainable and scalable approach. Preliminary studies have demonstrated the feasibility of CHW-facilitated hearing aid fittings and the potential of digital support programmes to improve user outcomes. However, there is a lack of evidence from randomized controlled trials comparing digital versus traditional paper-based support in LMICs. By evaluating differences in hearing aid self-efficacy, hearing aid benefit, use, satisfaction, perceived handicap, and practical device skills, this study will provide evidence on whether mHealth-delivered support offers superior support compared to standard paper-based information.

If mHealth support demonstrates superior outcomes, it would justify scaling up digital acclimatization programmes as part of community-based hearing care models, leveraging widely available platforms such as WhatsApp to improve hearing aid success in underserved populations.

Interventions

• Device Go Ultra Hearing Aids
  Go Ultras (GoHearing) are rechargeable, BTE pre-set hearing aids with advanced audio features, digital sound processing and Bluetooth-streaming capabilities. Designed for adults with mild-to-moderate hearing loss, these hearing aids have four unique programs that the user can manually change to ensure optimal listening comfort. These devices have both program and volume memory functions, as well as noise and wind noise reduction. Go Ultras will be sourced at a cost of less than $130 USD per pair
• Other WhatsApp-delivered AI-enabled support
  WhatsApp-delivered AI-enabled support and acclimatization programme: A pre-defined sequence of 16 voice notes and images, designed to provide clear and accessible information on the key aspects of hearing aid use, maintenance, troubleshooting, and communication strategies. Messages are delivered on a fixed schedule, sent every second day from the time of fitting over a 30-day period, to promote engagement and to support participants during the early acclimatization period. The voice notes and im
• Other Paper-Based Support Programme
  Printed pamphlet. The pamphlet covers the same content domains as Component 1 of the experimental intervention: hearing aid use, maintenance, troubleshooting, and communication tips, presented in clear and concise language with supporting illustrations. The pamphlet includes information in English, isiXhosa, and Sepedi; participants can read the version in their preferred language. This approach reflects current community-based fitting practice, in which information is typically provided once du

Primary outcome measures

• The Measure of Audiologic Rehabilitation Self-Efficacy for Hearing Aids (MARS-HA) [Time frame: Five-week follow-up]

Secondary outcome measures (4)

• International Outcome Inventory for Hearing Aids (IOI-HA) [Time frame: Five-week follow-up]
• Revised Hearing Handicap Inventory and Screening Tool (RHHI-S) [Time frame: Baseline and five-week follow-up]
• Berkman-Syme Social Network Index (SNI) [Time frame: Baseline and five-week follow-up]
• Hearing Aid Skills and Knowledge Inventory (HASKI-Clin) [Time frame: Five-week follow-up]

Eligibility criteria

Inclusion criteria

• 18 years and older
• Confirmed mild to severe (20 to < 80 dB PTA in both ears) hearing loss (determined during baseline assessments)
• Willing/available to commit to 5-week follow-up
• Must have access to their own personal WhatsApp
• Functional proficiency in English, isiXhosa, or Sepedi sufficient to provide informed consent and to self-complete the study outcome measures in one of these three languages, as judged by the recruiting CHW during the screening conversation.

Exclusion criteria

• Younger than 18 years
• Hearing loss too severe (≥80 dB HL PTA)
• Normal hearing (<20 dB HL PTA)
• Middle ear pathology, such as otitis media, active drainage from the ears.
• Unwilling/unavailable to commit to a 5-week follow-up.
• Unilateral hearing loss
• No access to WhatsApp/only has access via another individual's WhatsApp
• Home language other than English, isiXhosa, or Sepedi, where the individual does not have functional proficiency in any of these three languages.

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Allocation

Randomized

Model

Parallel assignment

Masking

Single blind

Primary purpose

Treatment

Study locations

South Africa · 2 centers

• Atteridgeville Community — Pretoria
• Khayelitsha Community — Cape Town

Publications

• Miola AC, Miot HA. P-value and effect-size in clinical and experimental studies. J Vasc Bras. 2021 Jul 5;20:e20210038. doi: 10.1590/1677-5449.210038. eCollection 2021. No abstract available. PMID 34267792
• Faul F, Erdfelder E, Lang AG, Buchner A. G*Power 3: a flexible statistical power analysis program for the social, behavioral, and biomedical sciences. Behav Res Methods. 2007 May;39(2):175-91. doi: 10.3758/bf03193146. PMID 17695343
• Chadha S, Kamenov K, Cieza A. The world report on hearing, 2021. Bull World Health Organ. 2021 Apr 1;99(4):242-242A. doi: 10.2471/BLT.21.285643. No abstract available. PMID 33953438
• West RL, Smith SL. Development of a hearing aid self-efficacy questionnaire. Int J Audiol. 2007 Dec;46(12):759-71. doi: 10.1080/14992020701545898. PMID 18049965
• Stephens D. The International Outcome Inventory for Hearing Aids (IOI-HA) and its relationship to the Client-oriented Scale of Improvement (COSI). Int J Audiol. 2002 Jan;41(1):42-7. doi: 10.3109/14992020209101311. PMID 12467369
• Mulwafu W, Ensink R, Kuper H, Fagan J. Survey of ENT services in sub-Saharan Africa: little progress between 2009 and 2015. Glob Health Action. 2017;10(1):1289736. doi: 10.1080/16549716.2017.1289736. PMID 28485648
• Meyer C, Hickson L, Fletcher A. Identifying the barriers and facilitators to optimal hearing aid self-efficacy. Int J Audiol. 2014 Feb;53 Suppl 1:S28-37. doi: 10.3109/14992027.2013.832420. Epub 2014 Jan 21. PMID 24447235
• Kelly-Campbell RJ, McMillan A. The Relationship Between Hearing Aid Self-Efficacy and Hearing Aid Satisfaction. Am J Audiol. 2015 Dec;24(4):529-35. doi: 10.1044/2015_AJA-15-0028. PMID 26650773

Identifiers

NCT: NCT07690670 · HUM011/0724 · 5R33DC020134

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗