Search Results

The ADHEAR system is intended to treat patients of all ages with conductive hearing loss or single-sided deafness via bone conduction. The ADHEAR system is a non-invasive bone conduction hearing device which is retained on the patient's head with an elastic headband or an adhesive adapter that is placed behind the auricle.

Indications:

· Unilateral or bilateral conductive hearing loss, either chronic or temporary.

The pure tone average bone-conduction hearing threshold (measured at 0.5. 1. 2, and 3 kHz) should be better than or equal to 25 dB HL.

· Single-sided deafness (i.e. unilateral profound sensorineural deafness) with normal hearing on the contralateral side. Normal hearing is defined as a pure tone average air-conduction hearing threshold (measured at 0.5, 1, 2, and 3 kHz) of better than or equal to 20 dB HL

The ADHEAR system includes a bone conduction audio processor that can be retained on the head with an adhesive adapter or by the headband situated over the mastoid behind the auricle. The ADHEAR system is intended to be used during waking hours. While the adhesive adapter is attached to the skin for 3 to 7 days and then replaced, the audio processor is removed at night. Both the audio processor and the adhesive adapter are necessary components for the system to work. Together the components work as one system to deliver vibrations to the mastoid bone in order to conductively transmit sound to the inner ear for patients with conductive hearing loss or single sided deafness via bone conduction.

The ADHEAR system consists of an adhesive adapter sitting behind the auricle and an audio processor mounted on the attachment. The audio processor contains microphones and signal processing technology as well as a battery. It detects, processes, amplifies and finally transmits sound to the adhesive adapter which transmits vibrations to the mastoid which conducts sounds to the inner ear. The audio processor is equipped with a push button that allows the user to switch between 4 pre-defined settings. A colour sleeve is provided for pediatric use. It features a tamper-proof battery door and dampens potential drops of the processor unit.

The ADHEAR system contains the following components:

• . ADHEAR Audio Processor (model 701)
• Package of ADHEAR Adhesive Adapters
• . ADHEAR Positioning Tool
• ADHEAR Headband
• . Retention clip
• ADHEAR Sleeves

This document is a 510(k) Premarket Notification for the ADHEAR System, a bone conduction hearing device. It primarily focuses on demonstrating substantial equivalence to predicate devices through non-clinical testing.

Based on the provided text, a conventional "study" demonstrating that a device meets acceptance criteria in the context of AI/ML performance (e.g., accuracy, sensitivity, specificity) is not present. The device in question is a physical hearing aid system, not an AI/ML algorithm for image interpretation or diagnosis.

Therefore, many of the requested items related to AI/ML performance studies (like sample size for test sets, number of experts for ground truth, MRMC studies, standalone algorithm performance, training set details) are not applicable to this specific submission.

The document states:
"No clinical testing was needed to support the safety, performance, and substantial equivalence of the ADHEAR System to the predicate devices. All devices are bone conduction hearing aids and all aspects to ensure consistent and safe performance can be shown through non-clinical bench testing." (Page 6)

This confirms that the acceptance criteria and proof of meeting them are based on engineering and safety standards, not clinical performance metrics typically associated with AI/ML systems.

However, I can extract information related to the types of testing and the conclusions regarding the device's performance against its design specifications and relevant standards, which serve as "acceptance criteria" for a hardware medical device.

Here's a breakdown based on the information available:

1. A table of acceptance criteria and the reported device performance

The document describes types of testing performed and concludes that the device complies or meets these criteria. It does not provide specific numerical targets or results in a table format for each criterion. Instead, it offers generalized statements of successful testing.

"The collective results of the non-clinical testing demonstrate that the ADHEAR System meets the established specifications to ensure consistent and safe performance for its intended use." (Page 6) |
| Software Verification and Validation | "Software verification and validation testing were conducted and documentation was provided... The software for this device was considered as a 'minor' level of concern, since failures or latent flaws in the (optional) software are unlikely to result in any harm to the patient or operator." (Page 6) |

Regarding the other requested information:

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Not applicable for AI/ML performance studies. The testing described is hardware and software validation/verification, and biocompatibility, which typically uses defined engineering samples or batches, not "test sets" in the AI/ML sense. No patient data or clinical trial data is mentioned.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Not applicable. Ground truth in the AI/ML sense (e.g., expert annotations of medical images) is not relevant here as no such clinical image interpretation or diagnostic study was performed. The "ground truth" for the non-clinical tests would be the established engineering specifications and international standards.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Not applicable. No expert adjudication of clinical data was performed.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• Not applicable. This device is a hearing aid, not an AI-assisted diagnostic tool for human readers. No MRMC study was performed or required.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• Not applicable. There is no standalone AI algorithm whose performance is being evaluated independently of human interaction. The device's function is to transmit sound, and its standalone performance is evaluated through the non-clinical bench tests (e.g., frequency response, gain).

7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)

• For the non-clinical tests, the "ground truth" implicitly are the established engineering design specifications, safety standards (e.g., IEC 60601-1), and biocompatibility standards (ISO 10993-1). Tests were conducted to verify the device performed according to these pre-defined requirements.

8. The sample size for the training set

• Not applicable. This device is hardware with embedded software, not a machine learning model trained on a dataset.

9. How the ground truth for the training set was established

• Not applicable. No training set for an AI/ML model.

Ask a specific question about this device