Feasibility of a Smartphone-Based Hearing Aid App for Mild-to-Moderate Hearing Loss: Prospective Multicenter Randomized Controlled Trial
Bibliographic record
Abstract
Background: Hearing loss is a growing health concern worldwide. Hearing aids (HAs) are the treatment of choice for hearing rehabilitation in most cases of mild-to-moderate hearing loss. However, many patients with hearing loss do not use HAs due to their high cost, stigma, and inaccessibility. Since smartphones are widely used, many apps that mimic the amplification function of HAs have been introduced. Smartphone-based HA apps (SHAAs) are affordable and easy to access. However, the audiological benefit of SHAAs has not been determined. Objective: We compared the audiological performance between an SHAA and a conventional HA in a prospective, multicenter randomized controlled trial. Methods: Patients with mild-to-moderate hearing loss were prospectively enrolled from 2 tertiary hospitals and randomly assigned to either an SHAA (Petralex; IT4YOU Corp LLC) or a conventional HA (Siya 1 miniRITE; Oticon A/S). For the cross-over study design, participants used the alternate device and repeated the same 2-month trial. Audiological measurements were obtained using hearing tests, real-ear measurements, and the hearing-in-noise test (HINT). Subjective satisfaction was evaluated using the Abbreviated Profile of Hearing Aid Benefit (APHAB) and International Outcome Inventory for Hearing Aids (IOI-HA). Results: Overall, 63 participants were screened and 38 completed the study. In sound-field audiometry testing, the SHAA showed a 20- to 60-dB gain in the low-to-high frequencies of the hearing threshold level. The HA provided adequate gain in the middle-to-high frequencies (55, 65, and 75 dB in real-ear measurements), which is the sound level for most speaking volumes. However, the SHAA could not improve word recognition at 50 dB. The HA showed better audiological performance than the SHAA in both quiet and noisy conditions in the HINT. The IOI-HA scores were significantly improved by both the HA and SHAA versus unaided conditions. Among the SHAA users, 37% (14/38), 42% (16/38), 24% (9/38), and 32% (12/38) showed improvement in APHAB scores for ease of communication, reverberation, background noise, and aversiveness of sounds, respectively. There were no differences in adverse events between the 2 study groups. Conclusions: The HA showed better performance than the SHAA in word recognition and the HINT. However, the SHAA was significantly better than unaided hearing in terms of amplification. The SHAA may be a useful hearing assistance device for patients with mild-to-moderate hearing loss when listening to soft sounds in quiet conditions. The SHAA demonstrated poorer performance than the HA in the mid- to high-frequency sounds that are important for word recognition, sound quality, and hearing in noisy conditions. Further development of the signal technology of SHAAs is needed to improve the sound quality of mid- to high-frequency sounds and overcome noisy environments.
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 | 0.006 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.005 | 0.004 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.004 | 0.003 |
| Insufficient payload (model declined to judge) | 0.010 | 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".