Search Results

The Lexie Lumen Self-Fitting OTC Hearing Aid(s) with Lexie Application is a self-fitting air-conduction hearing aid, intended to amplify sound for individuals 18 years of age or older with perceived mild to moderate hearing impairment. The device is adjusted by the user to meet the user's hearing needs. The device is intended for use without the assistance of a hearing care professional.

The Lexie Lumen Self-Fitting OTC Hearing Aid(s) with Lexie Application is a self-fitting, air conduction hearing aid consisting of the IntriCon hardware, Lexie Software, Lexie Application and accessories supplied in the carton. The Lexie App is available on Android and iOS. The Lumen self-fitting OTC hearing aid is the only model applicable to this 510(k). The Lexie Lumen Self-Fitting OTC Hearing Aid(s) with Lexie Application is a behind the ear device that includes self-adjustable coupling by means of a slim tube and ear tip/dome. The hearing aids can be fine-tuned remotely by trained hearing experts, at the request of the user, in the Lexie contact center. The Lexie app receives custom remote settings as performed through the Lexie adjustment wizard and fitting portal (internet service).

Here's a breakdown of the acceptance criteria and the study details for the Lexie Lumen Self-Fitting OTC Hearing Aid(s) with Lexie Application, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size Used for the Test Set and Data Provenance

• Clinical Study:
  • Sample Size: 64 participants (32 in the Audiologist Fit (AF) group, 32 in the Self-Fit (SF) group).
  • Data Provenance: Prospective, Randomized Controlled Trial conducted at the University of Pretoria, Gauteng, South Africa.
• In-situ Hearing Test Accuracy Validation (separate study):
  • Sample Size: 45 participants (90 ears).
• Human Factors Testing:
  • Sample Size: 29 adult participants.
  • Data Provenance: Simulated-use session, likely within a controlled environment (e.g., laboratory).

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

• Clinical Study:
  • The "ground truth" for the Audiologist Fit (AF) group was established by audiologists who performed standard audiometric evaluations and fitted the hearing aids to match NAL-NL2 prescriptive targets. The text doesn't specify the exact number of audiologists, but refers to "the audiologist" (singular) in descriptions of procedures, implying at least one qualified audiologist was involved in the fitting and orientation for the AF group. The context of a university setting (University of Pretoria) suggests these would be qualified professionals.
  • For the in-situ hearing test validation, "the audiologist-performed audiometry" was used as a reference, again implying qualified audiologist(s).
• Human Factors Testing:
  • No specific experts are mentioned as establishing "ground truth" in the same way as the clinical study. Instead, the "effectiveness and accuracy of the tasks" were assessed by observing participants' performance during simulated use, implying assessment by human factors specialists or researchers.

4. Adjudication Method for the Test Set

• The clinical study was a randomized controlled trial (RCT) comparing two groups (SF vs. AF).
• No explicit "adjudication method" (like 2+1 or 3+1 for expert review) is mentioned for the outcomes of the clinical study, as the primary and secondary endpoints (APHAB, IOI-HA, QuickSIN, DIN) are quantitative measures.
• For the in-situ hearing test accuracy, performance (Mean Absolute Difference) was compared against "audiologist-performed audiometry," where the audiologist's results served as the reference.
• For Human Factors Testing, an "observer" evaluated task success, and a "semi-structured interview" was used for user perceptions.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done

• Yes, a comparative effectiveness study was done, comparing the Lexie Lumen in a self-fit (SF) condition against an audiologist-fit (AF) condition. This is a direct comparison of the device's performance with and without expert assistance in fitting.
• Effect Size of Human Readers Improve with AI vs. without AI assistance:
  • The study compares self-fitting (device with its AI/software-driven fitting strategy) to audiologist-fitting (human expert). It doesn't present an effect size of "human readers improve with AI vs. without AI assistance" in the context of interpretation of medical images.
  • Instead, it evaluates if the self-fitting strategy (which is AI/software-driven) is non-inferior to an audiologist's fitting. The results show that the SF group was equivalent or even slightly better in some aspects (background noise difficulty at 2 weeks, duration of use at 2 weeks) compared to the AF group, and overall achieved equivalence within the defined acceptance criteria for the primary and secondary endpoints. This implies that the device's self-fitting capability largely negates the need for a human professional's direct fitting intervention for achieving comparable outcomes for mild to moderate hearing loss.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

• Yes, the "Self-Fit (SF) group" in the clinical study represents the standalone performance of the device's self-fitting algorithm without human-in-the-loop fitting assistance. Participants in this group were explicitly stated to "set up and manage the devices using the Lexie app, entirely without professional support." Any assistance sought in Phase II was through the Lexie online hearing experts, but the initial fitting and core performance were self-directed via the app's algorithm.

7. The Type of Ground Truth Used

• Clinical Study (Effectiveness):
  • The ground truth was established by comparison with best-practice audiological fitting (NAL-NL2 targets) performed by audiologists. The aim was to demonstrate non-inferiority or equivalence against this established clinical standard.
  • For the in-situ hearing test, the "Reference" was audiologist-performed audiometry.
• Safety:
  • "Ground truth" for safety was the occurrence and nature of Adverse Events (AE) and Serious Adverse Events (SAE), which are reportable objective events.
• Human Factors Testing:
  • "Ground truth" was the observational assessment of task completion and accuracy by study personnel, corroborated by user self-reports and satisfaction.
• Non-clinical Performance Testing:
  • "Ground truth" was defined by the acceptance criteria within the cited national and international consensus standards (e.g., IEC, ISO, ANSI, CTA), against which the device's physical and electrical properties were measured.

8. The Sample Size for the Training Set

• The document does not provide information on the sample size for the training set used to develop the Lexie self-fitting algorithm or its core software. This information is typically proprietary and not usually disclosed in a 510(k) summary, which focuses on validation rather than development.

9. How the Ground Truth for the Training Set Was Established

• The document does not provide information on how the ground truth for the training set was established. The text only states that the fitting algorithm (Lexie Comfort) is "based on National Acoustics Laboratories' Non-Linear Version 2 (NAL-NL2), with additional adjustments aimed for a greater listening comfort." This implies that the NAL-NL2 prescriptive targets likely form a significant part of the foundational "ground truth" or reference for the algorithm's development, but details of specific training data and its ground truth are absent.

Ask a specific question about this device