Innovative Support for Children with Disabilities: High- and Low-Tech Approaches to Auditory Disability in Guinea

Last registered on November 17, 2025

Pre-Trial

Trial Information

General Information

Title
Innovative Support for Children with Disabilities: High- and Low-Tech Approaches to Auditory Disability in Guinea
RCT ID
AEARCTR-0017216
Initial registration date
November 10, 2025

Initial registration date is when the trial was registered.

It corresponds to when the registration was submitted to the Registry to be reviewed for publication.

First published
November 17, 2025, 6:55 AM EST

First published corresponds to when the trial was first made public on the Registry after being reviewed.

Locations

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information

Primary Investigator

Affiliation
World Bank

Other Primary Investigator(s)

PI Affiliation
World Bank
PI Affiliation
World Bank

Additional Trial Information

Status
In development
Start date
2026-09-01
End date
2027-01-11
Secondary IDs
Prior work
This trial does not extend or rely on any prior RCTs.
Abstract
This study evaluates how different levels of technology can improve learning for students with hearing impairments in Guinea. Using a randomized controlled trial, we compare three classroom strategies: a no-tech approach that seats students with hearing loss at the front of the room, a medium-tech approach that provides low-cost hearing aids, and a high-tech approach that uses a speech-to-text tool powered by Artificial Intelligence (Whisper AI) on tablets to display real-time captions. The study measures impacts on student learning, attendance, and sense of belonging. We also collect implementation and cost data to assess which option is most effective and scalable in low-resource schools. Results will contribute to the global evidence base on inclusive education and assistive technology in low-income countries.
External Link(s)

Registration Citation

Citation
Adelman, Melissa, Juan Baron and Lauren Dahlin. 2025. "Innovative Support for Children with Disabilities: High- and Low-Tech Approaches to Auditory Disability in Guinea." AEA RCT Registry. November 17. https://doi.org/10.1257/rct.17216-1.0
Sponsors & Partners

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information
Experimental Details

Interventions

Intervention(s)
The intervention tests three approaches to support middle school students in Guinea with moderate hearing impairments.
1. No-Tech: Students are seated at the front of the classroom to improve hearing access.
2. Medium-Tech: Students receive over-the-counter hearing aids to amplify teacher speech.
3. High-Tech: Students use tablets with Whisper AI, an offline speech-to-text tool that provides real-time captions of classroom instruction.
Intervention Start Date
2026-09-14
Intervention End Date
2027-01-01

Primary Outcomes

Primary Outcomes (end points)
Student learning outcomes – reading and math scores on standardized French and math assessments administered via tablet.
Primary Outcomes (explanation)

Secondary Outcomes

Secondary Outcomes (end points)
1. School attendance – number of absences reported by teachers over the previous two weeks.
2. Student belonging – measured using the Psychological Sense of School Membership (PSSM) scale.
3. Technology usage and fidelity – frequency and duration of use for students in the hearing aid and AI tablet groups.
4. Screening accuracy – concordance between app-based hearing screening (Höra) and professional diagnostic assessments.
Secondary Outcomes (explanation)
For the forth secondary outcome, screening accuracy, a subset of students will be assessed for hearing impairment by both an app and an auditory specialist. The agreement between the app and the specialist will be reported.

Experimental Design

Experimental Design
We first screen all students in about 600 classrooms for moderate hearing impairment using a validated French hearing app (Höra). Classrooms with at least two eligible students enter the study. Eligible classrooms are randomly assigned to one of four arms:
1. No-tech: seat eligible students at the front of the room.
2. Medium-tech: provide over-the-counter hearing aids for use in school.
3. High-tech: provide tablets running an offline speech-to-text tool (Whisper AI).
4. Control: business as usual.
Interventions run for one school term of about six months.
Experimental Design Details
Not available
Randomization Method
Randomization will be conducted by computer after classrooms are screened for eligibility. Eligible classrooms, those with at least two students identified with moderate hearing impairment through the Höra screening app, will be randomly assigned to one of the study arms (no-tech, medium-tech, high-tech, or control).
Randomization Unit
The unit of randomization is the classroom.
Was the treatment clustered?
Yes

Experiment Characteristics

Sample size: planned number of clusters
500 Classrooms
Sample size: planned number of observations
1000 Students
Sample size (or number of clusters) by treatment arms
250 students in 125 classrooms. There may be more students if classrooms have more than two students with hearing impairment.
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
MDE: 0.25 standard deviation in standardized test scores (mean 0, standard deviation 1) This was calculated using 250 students in 125 classrooms per treatment arm, power=0.8, alpha=0.05, ICC=0.1.
IRB

Institutional Review Boards (IRBs)

IRB Name
IRB Approval Date
IRB Approval Number