Development and Beta Validation of an mHealth-Based Hearing Screener (SRESHT) for Young Children in Resource-Limited Countries: Pilot Validation Study
Bibliographic record
Abstract
BACKGROUND: The prevalence of hearing loss in infants in India varies between 4 and 5 per 1000. Objective-based otoacoustic emissions and auditory brainstem response have been used in high-income countries for establishing early hearing screening and intervention programs. Nevertheless, the use of objective screening tests in low- and middle-income countries (LMICs) such as India is not feasible. Mobile health (mHealth) solutions have been demonstrated to be a viable option for hearing screening in LMICs. OBJECTIVE: This study aims to develop and beta-validate an affordable hearing screener for children younger than 6 years of age to identify moderately severe or higher degrees of hearing loss. METHODS: In phase 1, a mHealth-based hearing screener (SRESHT) was developed using a single board computer with wireless commercial headphones and speakers as transducers, which were calibrated according to the standard procedure. Three subjective hearing screening modules were conceptualized and developed for different age groups: (1) behavioral observation audiometry-screening for infants aged from 0 to 1 year; (2) speech spectrum awareness task-screening for children 1 to 3 years old; and (3) speech recognition task-screening for children 3 to 6 years old. Different auditory stimuli for the screening modules were generated and suitability was assessed: (1) noisemakers, animal sounds, and environmental sounds for infants (birth to 1 year old); (2) animal sounds and nonsense syllables for children (1 to 3 years old); and (3) eighteen picturable spondee words for children (3 to 6 years old). In phase 2, the SRESHT screener was beta-validated in children aged below 6 years to establish the agreement between SRESHT modules and the gold-standard procedure in identifying moderately severe and higher degrees of hearing loss. RESULTS: Off-the-shelf commercial speakers and headphones were selected and calibrated. On comparison of stimuli for behavioral observation audiometry on 15 children, Noisemaker stimuli were found suitable based on the average minimum response levels. On comparison of different stimuli for speech spectrum awareness task on 15 children, animal sounds were found to be suitable. On familiarity check of 18 spondee words for speech recognition task among 20 children, 12 spondee words had the eligibility cutoff (85%) and a presentation level of 5 dB SL (re-pure tone threshold) was sufficient to achieve 80% psychometric function. In phase 2, a total of 55 children aged 0 to 6 years (31 normal hearing and 24 hearing impairment) underwent SRESHT screening for beta validation. Cohen κ indicated that the overall SRESHT screener had a very good agreement (κ=0.82) with gold-standard audiometric screening for identifying moderately severe and higher degrees of hearing loss. CONCLUSIONS: The development and beta validation of the SRESHT screener using the selected auditory stimuli showed that the stimuli were suitable for screening children.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.012 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".