Search Results

The Cochlear Baha 7 Sound Processor is intended for the following patients and indications for use:

• Patient of any age for use with the Baha SoundBand, Baha Softband (or headband) or Baha SoundArc. Patients aged 5 and older for use with the Baha auditory osseointegrated implant system.
• Patients who have a conductive or mixed hearing loss and can still benefit from sound amplification. The pure tone average bone-conduction hearing threshold (measured at 0.5, 1, 2, and 3kHz) should be better than or equal to 55 dB HL.
• Bilateral fitting is intended for patients who meet the above criterion in both ears, with bilaterally symmetric moderate to severe conductive or mixed hearing loss. Symmetrical bone-conduction thresholds are defined as less than a 10 dB average difference between ears (measured at 0.5, 1, 2, and 3 kHz), or less than a 15 dB difference at individual frequencies.
• Patients who suffer from unilateral sensorineural deafness in one ear with normal hearing in the other ear (i.e. Single-sided deadness: SSD). 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.
• Baha for SSD is also indicated for any patient who is indicated for an air-conduction contralateral routing of signals (AC CROS) hearing aid, but who for some reason cannot or will not use an AC CROS.

The Cochlear Baha bone conduction hearing system provides an alternate solution for patients who may not benefit from air-conduction hearing aids. Unlike air-conduction hearing aids, the Baha implant system utilizes a natural bone conduction pathway to send sound directly to the inner ear (cochlea), bypassing a damaged outer or middle ear. The Baha bone conduction hearing system has non-surgical and surgical options. For the non-surgical option, the external sound processor, which converts acoustic sound into mechanical vibrations, is securely placed behind the ear with a Baha SoundBand, Baha Softband, or Baha SoundArc. For the surgical option, the external sound processor is coupled with an abutment (Baha Connect) or magnet (Baha Attract). The mechanical vibrations travel through the abutment or magnet to a small, titanium implant, which is surgically placed into the bone. The titanium implant has an osseointegrated bond with the surrounding bone, allowing transmission of high-quality sound directly to the inner ear.

The Baha 7 Sound Processor is a firmware variant of the previously cleared Baha 6 Max Sound Processor (K202048). The changes introduced in this 510(k) are specific to the sound processor and accessories, and do not affect the cleared Baha Connect abutments, Baha Attract magnet, the BI300 titanium implant, Baha Softband, or Baha SoundArc. The Baha 7 Sound Processor does not modify the intended functionality or fundamental operating principles of the bone conduction hearing system. The changes within culminate as the next generation Baha sound processor that supports Bluetooth LE Audio streaming, which enables compatibility with the new generation wireless accessories from GN Hearing.

The Baha 7 Sound Processor will be supported by a new fitting software (Baha Fitting Software 7), an updated app (Baha Smart App), and a new non-surgical retention option (Baha SoundBand).

The provided text describes a 510(k) premarket notification for the Cochlear Baha 7 Sound Processor. It focuses on demonstrating substantial equivalence to a predicate device, the Baha 6 Max Sound Processor. While it mentions various types of testing conducted (biocompatibility, software, electromagnetic compatibility, and bench testing), it does not include specific acceptance criteria or detailed study results for device performance in the format requested.

The document primarily provides:

• A summary of the device and its components (Baha 7 Sound Processor, Baha Fitting Software 7, Baha Smart App, Baha SoundBand).
• Indications for Use.
• A comparison table (Table 1, 2, 3, 4) detailing similarities and differences between the new device and the predicate(s).
• A general statement about performance data: "The testing demonstrated that the software supported the clinician fitting and recipient control of the Baha 7 Sound Processor." and "The bench testing demonstrates that the Baha 7 SP does not result in additional safety or efficacy concerns in comparison to the predicate." and "The results demonstrated the Baha 7 Sound Processor is functionally equivalent to the Baha 6 Max Sound Processor."

Therefore, based on the provided text, it is not possible to fully answer your request regarding specific acceptance criteria, reported device performance in a table, sample sizes, ground truth establishment details, or MRMC study results because this information is not present in the excerpt. The document focuses on demonstrating substantial equivalence through feature comparison and general statements about testing, rather than presenting a performance study with quantitative acceptance criteria and results.

Here's what can be inferred or stated based on the provided text, and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample size used for the test set and the data provenance:

• Not specified. The document mentions "bench functionality and performance testing" and "software testing" but provides no details on the sample size of devices or the data used for these tests.
• Data Provenance: Not specified for any performance testing.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• N/A. This type of information is typically relevant for studies involving human assessment (e.g., diagnostic accuracy studies for AI in imaging). As the device is a hearing aid sound processor, and the submission focuses on functional equivalence, there is no mention of "ground truth" adjudicated by experts in this context within the provided text. The "ground truth" for the device's function would be its measured physical characteristics and software performance against specifications.

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

• N/A. Not applicable given the nature of the device and the type of information presented. Adjudication methods are typically used in clinical studies or AI performance evaluations where human interpretation or consensus is required to establish a definitive ground truth.

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:

• No, an MRMC study was not done or is not reported here. This type of study is primarily relevant for AI-powered diagnostic aids where human readers interpret medical images or data. The Baha 7 Sound Processor is a hearing aid sound processor, not an AI diagnostic tool for human interpretation.

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

• Yes, implied. The "functional and performance testing, hardware and interface testing, reliability and environmental testing" would be considered standalone testing of the device and its software. The document states, "The results demonstrated the Baha 7 Sound Processor is functionally equivalent to the Baha 6 Max Sound Processor," which is a statement about its standalone performance. However, no specific metrics or detailed results of this standalone testing are provided beyond this general statement.

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

• Instrumental measurements and compliance with specifications. For a device like a sound processor, the "ground truth" for performance would be established through calibrated laboratory instruments measuring audio output, frequency response, power consumption, signal processing accuracy, and electromagnetic emissions, compared against engineering specifications and regulatory standards. Biocompatibility is assessed against ISO 10993. Software functionality is tested against design requirements. The text confirms
  • "Biocompatibility evaluation and testing demonstrated that the materials... are biocompatible." (Ground truth: ISO 10993 standards and lab tests).
  • "Software testing was performed... demonstrated that the software supported the clinician fitting and recipient control of the Baha 7 Sound Processor." (Ground truth: Software specifications and functional requirements).
  • "Electromagnetic compatibility testing established that the sound processor did not emit excessive amounts of electromagnetic energy, and that it operated as intended in the presence of interference sources." (Ground truth: EMC standards).
  • "Bench functionality and performance testing... demonstrates that the Baha 7 SP does not result in additional safety or efficacy concerns in comparison to the predicate." (Ground truth: Engineering specifications and direct comparison to predicate device performance).

8. The sample size for the training set:

• N/A. This device does not appear to involve machine learning models that require a "training set" in the context of typical AI device submissions for diagnostic or predictive purposes. The software mentioned (Baha Fitting Software 7, Baha Smart App) are control and interface applications, not described as adaptive or learning algorithms that require large training datasets.

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

• N/A. As no training set for an AI model is indicated, this question is not applicable.

Ask a specific question about this device

The Osia System is intended for the following patients and indications:

· Patients 5 years of age or older.

• Patients who have a conductive or mixed hearing loss and still can benefit from sound amplification. The pure tone average (PTA) bone conduction (BC) threshold (measured at 0.5, 1, 2, and 3 kHz) should be better than or equal to 55 dB HL.

· Bilateral fitting of the Osia System is intents having a symmetrically conductive or mixed hearing loss. The difference between the left and right sides' BC thresholds should be less than 10 dB on average measured at 0.5, 1, 2, and 3 kHz, or less than 15 dB at individual frequencies.

· Patients who have profound sensorineural hearing loss in one ear and normal hearing in the opposite ear (i.e., singlesided deafness or "SSD"). The pure tone average air conduction hearing ear should be better than or equal to 20 dB HL (measured at 0.5, 1, 2, and 3 kHz).

• The Osia System for SSD is also indicated for any patient who is indicated for an air-conduction contralateral routing of signals (AC CROS) hearing aid, but who for some reason cannot or will not use an AC CROS.

· Prior to receiving the device, it is recommended that an individual have experience with appropriately fitted air conduction or bone conduction hearing aids.

The Osia System mechanically vibrates the skull bone and subsequently the cochlea to compensate for conductive hearing loss, mixed hearing loss, or single-sided sensorineural deafness (SSD).

The Osia System is made up of several components. The Osia Implant consists of a receiver/coil and an actuator/stimulator (vibrator) which is surgically implanted on the skull bone. The external component of the Osia System is a sound processor, worn off-the-ear, which picks up the sound from the environment, and sends, after processing, the information to the implant via a transcutaneous inductive link. This link is also referred to as radiofrequency (RF) link. Each Osia System is configured to meet an individual's hearing needs, using dedicated fitting software.

Here's a breakdown of the acceptance criteria and the study details for the Cochlear Osia System, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't explicitly define "acceptance criteria" in a quantitative, pass/fail format for this specific submission, as this submission is for an expanded pediatric indication, not a new device. However, the study aims to demonstrate safety and effectiveness in the expanded population in comparison to the existing predicate. The "acceptance criteria" can be inferred from the study's objectives and the conclusion of substantial equivalence.

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

• Sample Size: Not explicitly stated for the "test set" in a traditional sense. The document refers to a "pivotal, prospective, multi-center study... to determine the safety and effectiveness of the Osia system in children ages 5-11." The number of participants in this study is not numericaly provided.
• Data Provenance: The study was a "pivotal, prospective, multi-center study." The country of origin of the data is not specified.

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

This submission is for a medical device (hearing system), not an AI/software device requiring "ground truth" derived from expert consensus on images or similar data. The "ground truth" is based on clinical outcomes relevant to hearing devices:

• Adverse Events: Clinical reporting by medical professionals during the study.
• Quality of Life: Patient-reported outcomes via parental questionnaires.
• Speech Perception: Objective audiological testing (unaided vs. aided performance).
• Bone Conduction Thresholds: Audiological measurements by qualified audiologists.

The document does not mention a specific number of experts or their qualifications in terms of establishing a "ground truth" for the test set in the same way an imaging AI algorithm might. The clinical data itself serves as the evidence.

4. Adjudication Method for the Test Set

Not applicable in the context of this device and study. The data collected (adverse events, questionnaire results, audiological test results) are direct clinical observations and measurements, not subjective evaluations requiring adjudication by multiple experts.

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

No, an MRMC comparative effectiveness study was not done. This study focuses on the clinical performance of the device itself in a specific patient population, not on human readers' interpretation of data with and without AI assistance.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

Yes, in a way. The device itself (Cochlear Osia System) is the "algorithm only" in the context of its function as an active implantable bone conduction hearing system. Its performance (improvements in hearing, quality of life, speech perception) is measured as a standalone effect of the device on the patient, without human intervention during the hearing process. The human element comes in during the fitting and programming of the device by audiologists. The study's effectiveness measures (parental questionnaires, speech perception tests) evaluate the device's functional outcome.

7. The Type of Ground Truth Used

The "ground truth" for this study is derived from various clinical measures and outcomes:

• Safety: Reports of adverse events during the prospective study.
• Effectiveness (Quality of Life): Patient-reported outcomes from parental questionnaires (SSQ - Speech, Spatial and Qualities of Hearing).
• Effectiveness (Hearing Thresholds): Audiological measurements of bone conduction thresholds.
• Effectiveness (Speech Perception): Audiological tests measuring speech perception in quiet and in adaptive noise.

8. The Sample Size for the Training Set

The document does not mention a "training set." This study is a clinical trial evaluating a medical device, not an AI algorithm that requires training data in the computational sense. The device itself (the Osia System) has undergone prior development and testing, but that is distinct from a "training set" for a machine learning model.

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

Not applicable, as there is no "training set" in the context of this device and the provided document.

Ask a specific question about this device

The Instrument Case is intended for staff involved in reprocessing of reusable instruments, and for surgical teams.
The product shall only be used:

• · in a controlled surgical environment under sterile conditions such as a hospital,
• · in reprocessing environment at sterilization departments or reprocessing centers,
• · and for transport of surgical instruments.
  Sterilization parameters:
  In US: Pre-Vacuum Steam at 132 ℃ (270 °F) for 4 min with a 20 minutes dry time Outside US: See the Reprocessing Guide available in your country
  The worse-case validated load for the Instrument Case, including instruments, is 1700 g.

The Instrument case, Figure 1, is a reusable sterilization container intended for use in health care facilities for the purpose of containing reusable medical devices for sterilization. The specific use for the Instrument case is to hold reusable instruments during transport, the sterilization process, and during surgery.
The Instrument case consists of tray and lid made of stainless steel with a small box included, which is a component tray. The grommets, strips and holders that keep the instruments in place are made of silicone or stainless steel, and the latches in the lid are made of a Thermoplastic resin, Santoprene. The packaging materials are made of polyethylene and polyolefin.

Based on the provided text, the device in question is an "Instrument Case" (K231604) and the performance data presented is for its cleaning, sterilization, and lifecycle durability, not for a complex AI/ML diagnostic or image analysis system. Therefore, many of the typical acceptance criteria and study components for AI-driven medical devices (like MRMC studies, ground truth based on expert consensus/pathology, training set details, etc.) are not applicable here.

This document describes a "Special 510(k)" submission for an updated Instrument Case, where the key is demonstrating substantial equivalence to a predicate device (K223672) through non-clinical data. The updates are minor (additional etchings and validation for a few more instruments).

Acceptance Criteria and Reported Device Performance

1. Table of Acceptance Criteria and Reported Device Performance:

The document provides a clear table (Table 2) outlining the tests, acceptance criteria, and results for the Instrument Case.

Study Details (as applicable to this type of device)

Since this is for a physical medical device (Instrument Case) and not an AI/ML diagnostic, the following points address what's relevant from the provided text and note where typical AI/ML study details are not applicable:

2. Sample sizes used for the test set and the data provenance:

   • Sample Size: The document does not specify exact numbers of Instrument Cases tested for each specific test, but implies multiple units ("All units" met criteria for cleaning, "devices were inoculated" for sterilization, "Validation of 25 cycles of reprocessing" for lifecycle testing). Given the nature of a component, this is likely a small sample (e.g., 3-5 devices) for each test type, subjected to repetitive cycles (e.g., 25 cycles for lifecycle).
   • Data Provenance: Not explicitly stated, but these are laboratory bench tests conducted to regulatory standards (AAMI, ISO). The manufacturer is Cochlear Bone Anchored Solutions AB in Sweden, but the testing would be conducted in certified testing labs, not tied to a specific clinical population or country in the way clinical data for AI/ML devices would be. These are non-clinical, controlled bench tests. The tests themselves are prospective as they are specifically conducted for this submission.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Not Applicable. For a physical device like an instrument case, "ground truth" is established by direct measurement and observation against objective criteria (e.g., visual inspection for soil, chemical analysis for protein/hemoglobin, bacterial growth assessment, physical damage assessment). No human expert interpretation (like a radiologist reading an image) is involved beyond the technician performing the tests and recording the results.

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

   • Not Applicable. As described above, the acceptance criteria are objective and quantitative (e.g., µg/cm², SAL target, visual absence of damage). There is no multi-reader or adjudication process for interpreting "ground truth" for these physical performance tests.

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 is a physical medical device (sterilization case), not an AI/ML diagnostic or image analysis tool that would assist human readers.

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

   • Not Applicable. This is a physical medical device. There is no algorithm. The "standalone" performance here refers to the device's ability to meet its performance specifications (cleaning, sterilization, durability) without human intervention beyond setting up and running the test parameters.

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

   • The "ground truth" for the Instrument Case's performance is based on objective, quantitative measurements and direct visual inspection following standardized protocols and accepted industry standards (AAMI, ISO). Examples include:
     • Chemical assays for residual protein and hemoglobin.
     • Microbiological testing for Sterility Assurance Level (SAL).
     • Physical inspection for moisture, corrosion, and damage.
     • Toxicological assessment based on chemical characterization.

8. The sample size for the training set:

   • Not Applicable. There is no "training set" in the context of a physical device like this. Training sets are specific to AI/ML model development.

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

   • Not Applicable. There is no training set.

Ask a specific question about this device

The Cochlear Osia System uses bone conduction to transmit sounds to the cochlea (inner ear) with the purpose of enhancing hearing. Osia Implants are single use devices intended for long term implantation under the skin in the mastoid region of either side of the head. They are for professional use only.

The Osia System mechanically vibrates the skull bone and subsequently the cochlea to compensate for conductive hearing loss, mixed hearing loss, or single-sided sensorineural deafness (SSD). The Osia System is made up of several components. The Osia Implant (OSI300) consists of a receiver/coil and an actuator/stimulator (vibrator) which is surgically implanted on the skull bone. The external component of the Osia System is a sound processor, worn off-the-ear, which picks up the sound from the environment, and sends, after processing, the information to the implant via a transcutaneous inductive link. This link is also referred to as radiofrequency (RF) link. Each Osia System is configured to meet an individual's hearing needs, using dedicated fitting software.

The provided text describes a 510(k) premarket notification for the Cochlear™ Osia® System, an active implantable bone conduction hearing system. This submission primarily focuses on demonstrating substantial equivalence to a predicate device (Cochlear™ Osia® 2 System) for an updated version of the system.

The core of the submission involves bench testing to compare the updated system with the predicate. There is no evidence of a clinical study or performance study with patients designed to establish specific acceptance criteria directly tied to the device's clinical efficacy or diagnostic accuracy (e.g., sensitivity, specificity, AUC). The acceptance criteria, therefore, appear to be based on functional equivalency, safety, and performance compared to the predicate device through non-clinical means.

Here's a breakdown of the information based on your request, with an emphasis on what is not present in the provided text regarding specific performance criteria as typically understood in a clinical study for diagnostic or AI-based devices:

1. Table of Acceptance Criteria and Reported Device Performance

Since this is a 510(k) submission and the provided text focuses on demonstrating substantial equivalence through non-clinical testing (bench testing), explicit quantitative clinical acceptance criteria like sensitivity, specificity, or AUC are not stated, nor are their corresponding reported device performance values from a clinical study. Instead, the "acceptance criteria" are implied by successful completion of various verification activities ensuring the updated device functions as intended and is as safe and effective as the predicate.

2. Sample size used for the test set and the data provenance

The document explicitly states that bench testing was conducted. This implies that the "test set" consisted of physical devices, prototypes, or simulated scenarios in a lab environment. There is no mention of human subjects, patient data, or a clinical test set. Therefore, information regarding human sample size, country of origin, or retrospective/prospective nature is not applicable to the described study.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

Since the study described is non-clinical bench testing, the concept of "ground truth established by experts" in a clinical context (e.g., radiologist opinions) is not applicable. The "ground truth" for bench testing is derived from engineering specifications, established standards (e.g., ISO, FDA guidance), and physical measurements by engineers and technicians.

4. Adjudication method for the test set

As the evaluation was non-clinical bench testing, an adjudication method like 2+1 or 3+1 for clinical interpretation is not applicable. Test results are typically evaluated against pre-defined engineering criteria and specifications.

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

There is no mention of an MRMC study or any study involving human readers with or without AI assistance. The device is a hearing system, not an AI-assisted diagnostic tool for human interpretation.

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

The device itself is a hearing system that directly assists the patient, not a diagnostic algorithm. Therefore, the concept of "standalone algorithm performance" (in the typical AI/diagnostic sense) is not applicable. The device's performance is inherently "human-in-the-loop" as it's worn by a person to enhance hearing. However, its individual components' functional performance was evaluated independently through bench testing.

7. The type of ground truth used

For the non-clinical bench testing and verification activities, the "ground truth" used was based on:

• Engineering specifications and design requirements of the device.
• Established industry standards (e.g., ISO 10993-1:2018, ISO 14708-7:2013, ISO 11135:2014, EN 45502-1, EN ISO 11607-2009 +A1:2014).
• FDA guidance documents.
• Comparative data against the performance of the predicate device (Cochlear™ Osia® 2 System).

8. The sample size for the training set

This is not applicable as the document does not describe the development of an AI algorithm or model that requires a training set. The descriptions are about hardware revisions, firmware updates, and software modifications for a medical device.

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

This is not applicable as no training set for an AI algorithm or model is described.

Ask a specific question about this device

The Instrument Case is intended for staff involved in reprocessing of reusable instruments, and for surgical teams. The product shall only be used:

• · in a controlled surgical environment under sterile conditions such as a hospital,
• · in reprocessing environment at sterilization departments or reprocessing centers,
• · and for transport of surgical instruments.
  Sterilization parameters: Pre-Vacuum Steam at 132 °C (270 °F) for 4 min with a 20 minutes dry time
  The worse-case validated load for the Instrument Case, including instruments, is 1700 g.

The Instrument case, Figure 1, is a reusable sterilization container intended for use in health care facilities for the purpose of containing reusable medical devices for sterilization. The specific use for the Instrument case is to hold reusable instruments during transport, the sterilization process, and during surgery.
The Instrument case consists of tray and lid made of stainless steel with a small box included, a component tray. The grommets, strips and holders that keep the instruments in place are made of silicone or stainless steel, and the latches in the lid are made of a Thermoplastic resin, Santoprene. The packaging materials are made of polyethylene and polyolefin. The device dimensions are 265 x 160 x 42 mm (length x width x height) and the worst case recommended load is 1700 g.

The provided FDA 510(k) summary for the "Instrument Case" (K223672) describes the performance testing conducted to demonstrate substantial equivalence to a predicate device, primarily focusing on its ability to undergo sterilization and maintain its functional integrity. This document does not describe an AI/ML-driven medical device, nor does it involve a study with human readers, expert consensus for ground truth, or training/test sets in the context of image analysis.

The "acceptance criteria" and "study that proves the device meets the acceptance criteria" in this document refer to the bench testing of a medical device accessory (an instrument case) for its cleaning, sterilization, and lifecycle performance, not the evaluation of an AI algorithm's diagnostic performance. Therefore, many of the requested fields regarding AI/ML study design are not applicable to this submission.

Here's a breakdown of the information that is available in the document, framed as closely as possible to your request, but highlighting where AI/ML concepts do not apply:

Acceptance Criteria and Device Performance for Instrument Case (K223672)

This submission describes the performance validation of a reusable Instrument Case, a medical device accessory, to demonstrate its substantial equivalence to a predicate device regarding its ability to withstand cleaning, sterilization, and repeated use.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: The document does not specify the exact number of Instrument Cases used for each test. For many bench tests, a small number of units (e.g., typically 3 to 10) are used to represent the product.
• Data Provenance: The testing was conducted as part of the regulatory submission process for a medical device. The manufacturer is Cochlear Bone Anchored Solutions AB, located in Mölnlycke, Sweden, and the submitting entity is Cochlear Americas in Lone Tree, Colorado, USA. The data is prospective, generated specifically for this submission.

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

• Not Applicable. This is not an AI/ML diagnostic or image analysis study requiring expert review for "ground truth." The "ground truth" for these tests are objective measurements and observations (e.g., lack of visible soil, specific protein/hemoglobin levels, sterility, absence of moisture, visual integrity, chemical characterization results, cytotoxicity). The test methodologies (e.g., AAMI TIR, ANSI/AAMI ST79, ISO standards) define the criteria and procedures for evaluation.

4. Adjudication Method for the Test Set

• Not Applicable. This is not an AI/ML study involving human readers or subjective interpretations requiring adjudication. The acceptance criteria are objective and quantitative (e.g., µg/cm² levels, SAL ≤10⁻⁶, absence of growth/moisture/visible damage/cytotoxicity).

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• Not Applicable. This is not an AI/ML study. No human readers or comparative effectiveness studies of AI assistance are involved.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance)

• Not Applicable. This document describes the performance of a physical medical device accessory, not an algorithm.

7. Type of Ground Truth Used

• The "ground truth" for this device validation is based on objective measurements, laboratory assays, and adherence to established industry standards (e.g., AAMI, ISO standards) for cleaning efficacy, sterilization efficacy (biological indicator growth, SAL), visual inspection for damage, and biocompatibility (chemical characterization, cytotoxicity assays).

8. Sample Size for the Training Set

• Not Applicable. This is not an AI/ML study; there is no "training set" in this context.

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

• Not Applicable. This is not an AI/ML study; there is no "training set" or corresponding ground truth establishment methodology as would be found in such a study.

Ask a specific question about this device

The Osia System is intended for the following patients and indications:
· Patients 12 years of age or older.
· Patients who have a conductive or mixed hearing loss and still can benefit from sound amplification. The pure tone average (PTA) bone conduction (BC) threshold (measured at 0.5, 1, 2, and 3 kHz) should be better than or equal to 55 dB HL.
· Bilateral fitting of the Osia System is intended for patients having a symmetrically conductive or mixed hearing loss. The difference between the left and right sides' BC thresholds should be less than 10 dB on average measured at 0.5, 1, 2, and 3 kHz, or less than 15 dB at individual frequencies.
· Patients who have profound sensorineural hearing loss in one ear and normal hearing in the opposite ear (i.e., single-sided deafness or "SSD"). The pure tone average air conduction hearing thresholds of the hearing ear should be better than or equal to 20 dB HL (measured at 0.5, 1, 2, and 3 kHz).
· The Osia System for SSD is also indicated for any patient who is indicated for an airconduction contralateral routing of signals (AC CROS) hearing aid, but who for some reason cannot or will not use an AC CROS.
· Prior to receiving the device, it is recommended that an individual have experience with appropriately fitted air conduction or bone conduction hearing aids.

The Osia 2 System, also known as Osia System, mechanically vibrates the skull bone and subsequently the cochlea to compensate for conductive hearing loss, mixed hearing loss, or single-sided sensorineural deafness (SSD).
The Osia 2 System is made up of several components. The Osia implant (OSI200) consists of a receiver/coil and an actuator/stimulator (vibrator) which is surgically implanted on the skull bone. The external component of the Osia 2 System is a sound processor, worn off-the-ear, which picks up the sound from the environment, and sends, after processing, the information to the implant via a transcutaneous inductive link. This link is also referred to as radiofrequency (RF) link. Each Osia 2 System is configured to meet an individual's hearing needs, using dedicated fitting software.
In normal operation, the Osia System functions as follows:

• 1. The external sound processor captures and digitally processes sound.
• 2. The sound processor transmits power and digital information to the implant coil/receiver.
• 3. The implant stimulator/actuator converts the digital information into an electric analogue signal that is converted to vibrations by the implant piezoelectric actuator.
• This implant is fixed to the bone by the BI300 implant (K100360). 4.
  The actuator converts the electrical signal into an amplified mechanical stimulation, bypassing the impaired middle ear (origin of the conductive part of the hearing loss) and providing some level of mechanical amplification in order to compensate for the damaged inner ear (sensorineural part of the hearing loss, in case of mixed hearing loss).
  The updated Osia 2 System consists of modifications to the cleared OSI200 Implant, Osia 2 Sound Processor and Osia Fitting Software 2. All other components of the system remain unchanged from the cleared predicate.
  The Cochlear MRI Kit is being introduced for use by Osia recipients. The MRI Kit is an accessory that enables an MR scan at 1.5T without the need to surgically remove a compatible Osia implant's magnet.

The provided document is a 510(k) Summary for the Cochlear Osia 2 System. It describes the device, its intended use, indications for use, and a comparison to a predicate device. The primary purpose of this submission is seeking clearance for an updated Osia 2 System, which includes modifications to existing components (OSI200 Implant, Osia 2 Sound Processor, Osia Fitting Software 2) and the introduction of a new accessory, the Cochlear MRI Kit.

The core of the "acceptance criteria" and "proof" in a 510(k) submission like this is demonstrating substantial equivalence to a legally marketed predicate device, rather than proving a device meets specific quantitative performance metrics against a defined standard (which would be more typical for a PMA or de novo submission). Therefore, the "acceptance criteria" here largely refers to the criteria for demonstrating substantial equivalence, and the "study" is the collection of non-clinical (bench) testing performed to support this claim.

Here's an attempt to extract and describe the information requested based on the provided text, recognizing that a 510(k) summary primarily focuses on substantial equivalence rather than explicit performance criteria against a predefined threshold:

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

Since this is a 510(k) for an updated device, the primary "acceptance criterion" is functional equivalence and maintaining safety and effectiveness compared to the predicate device. The "reported device performance" is the conclusion that this equivalence was achieved through testing.

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

The document primarily discusses bench testing and verification/validation activities for hardware, software, and accessories. It does not mention clinical trials with human subjects. Therefore, the concept of "sample size" in the context of a "test set" for clinical data or "data provenance" (country/retrospective/prospective) is not directly applicable here. The testing is non-clinical.

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)

This section is not applicable as the document describes non-clinical (bench) testing, software verification, and usability testing for an accessory, not a diagnostic AI system requiring expert-established ground truth on medical images or patient data. The "summative usability testing" for the MRI Kit involved "specialized healthcare professionals," but their specific number, qualifications, or their role in establishing a "ground truth" (rather than evaluating usability) are not detailed.

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

This is not applicable as the device is not software for diagnostic image interpretation or a similar application that would require expert adjudication for ground truth.

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

This is not applicable. The device is an active implantable bone conduction hearing system and an associated MRI kit, not an AI-assisted diagnostic tool. No MRMC study or AI assistance to human readers is mentioned.

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

This is not applicable. The device is a physical hearing implant system and an MRI accessory, not an algorithm. The testing described is performance testing of the device components and system.

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

This is not applicable. For this type of device (hearing implant, MRI accessory), "ground truth" typically relates to engineering specifications, functional performance requirements, regulatory standards (e.g., for MRI compatibility), and safety profiles, which are assessed through bench testing and verification activities. It does not involve "ground truth" from medical images or patient outcomes in the sense of diagnostic accuracy.

8. The sample size for the training set

This is not applicable. The document describes a medical device (hardware and firmware/software) and its accessory, not a machine learning or AI model that requires a "training set."

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

This is not applicable for the same reason as point 8.

Ask a specific question about this device

The Cochlear™ Baha System is intended for the following patients and indications for use:

Patient of any age for use with the Baha Softband (or Baha SoundArc. Patients aged 5 and . older for use with the Baha auditory osseointegrated implant system.

• Patients who have a conductive or mixed hearing loss and can still benefit from sound amplification. The . pure tone average bone-conduction hearing threshold (measured at 0.5, 1, 2, and 3kHz) should be better than or equal to 55 dB HL.
  . Bilateral fitting is intended for patients who meet the above criterion in both ears, with bilaterally symmetric moderate to severe conductive or mixed hearing loss. Symmetrical bone-conduction thresholds are defined as less than a 10 dB average difference between ears (measured at 0.5, 1, 2, and 3 kHz), or less than a 15 dB difference at individual frequencies.

Patients who suffer from unilateral sensorineural deafness in one ear with normal hearing in the other ear . (i.e. Single-sided deadness: SSD). 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.

Baha for SSD is also indicated for any patient who is indicated for an air-conduction contralateral routing . of signals (AC CROS) hearing aid, but who for some reason cannot or will not use an AC CROS.

The Cochlear Baha bone conduction hearing system provides an alternate solution for patients who may not benefit from an air-conduction hearing aids. Unlike air-conduction hearing aids, the Baha implant system utilizes a natural bone conduction pathway to send sound directly to the inner ear (cochlea), bypassing a damaged outer or middle ear. The Baha bone conduction hearing system has non-surgical and surgical options. For the non-surgical option, the external sound processor, which converts acoustic sound into mechanical vibrations, is securely placed behind the ear with a Baha Softband or Baha SoundArc. For the surgical option, the external sound processor is coupled with an abutment (Baha Connect) or magnet (Baha Attract). The mechanical vibrations travel the abutment or magnet to a small, titanium implant, which is surgically placed into the bone. The titanium implant has an osseointegrated bond with the surrounding bone, allowing transmission of high-quality sound directly to the inner ear.

The updates made to Baha Fitting Software 6 and Baha Smart App add Remote Assist capabilities to the previously cleared Baha Fitting Software 6 and Baha Smart App (K202048). The changes introduced in this 510(k) are specific to the fitting software and smart app, and do not affect the cleared Baha 6 Max Sound Processor, Softband, SoundArc, Baha Connect abutments, Baha Attract magnet, or the BI300 titanium implant. Introduction of Remote Assist does not modify the intended functionality or fundamental operating principles of the bone conduction hearing system.

By introducing Remote Assist, the healthcare professional can:

• Communicate in real-time via video, audio, or messaging, and ●
• Connect to and remotely adjust the recipient's Baha 6 Max Sound Processor through the . Baha Fitting Software 6 and Baha Smart App interface.

The provided text describes a 510(k) premarket notification for the Cochlear Baha 6 System, specifically focusing on updates to the Baha Fitting Software 6 and Baha Smart App to introduce "Remote Assist" capabilities.

However, the document does not contain the detailed study information typically associated with acceptance criteria and proof of a device meeting those criteria in the context of advanced AI algorithms for medical image analysis or similar diagnostic tools. The device in question is a hearing aid system, and the "Remote Assist" features relate to remote programming and communication, not to complex diagnostic or predictive AI.

Therefore, many of the requested points relying on AI-specific study designs (like MRMC studies, expert consensus for ground truth on large image datasets, training set details, or standalone algorithm performance) are not applicable to this document. The provided text primarily focuses on demonstrating substantial equivalence to a predicate device for regulatory clearance.

Below, I will answer the applicable questions based on the provided text. For those that are not applicable, I will explicitly state so and explain why.

Device: Cochlear™ Baha® 6 System, Cochlear™ Baha® Fitting Software 6, Cochlear™ Baha® Baha Smart App
Regulatory Clearance: K212136

Acceptance Criteria and Device Performance

The document does not explicitly present a table of predetermined "acceptance criteria" in the format of specific quantifiable metrics (e.g., sensitivity, specificity, AUC values) and then report performance against them. Instead, the "performance data" section focuses on demonstrating functional equivalence and safety/effectiveness compared to a predicate device through various testing types.

The implicit acceptance criterion for this 510(k) submission is that the updated device, with its new "Remote Assist" functionalities, is as safe and as effective for its intended uses compared to the predicate Baha 6 System.

Table of Device Performance (Based on provided text's summary of testing):

• Software testing of new features.
• Regression testing of existing functionality (component and system level).
• Smoke testing.
• Functional test cases (e.g., measurements and programs).
• Non-functional test cases (e.g., cybersecurity and deployment).
• Hazard control verification.
• System-level integration, performance, and design analysis tests. |
  | User Needs & Intended Use | Design validation demonstrated compliance of the new features with user needs and intended use. |
  | Usability Verification | Summative usability testing was conducted. Participants completed a series of tasks throughout a Remote Assist session, and feedback was collected. The results of this testing supported the overall conclusion of safety and effectiveness. (Specific quantitative results or measures of usability are not provided in this summary, but the general statement implies successful completion). |
  | Safety and Effectiveness | The updates have been shown to be as safe and as effective for their intended uses compared to the predicate Baha 6 System. This is the overarching conclusion of the submission, based on all the testing and comparisons. |

Study Details (Applicable points only)

2. Sample size used for the test set and the data provenance:

• Sample Size: The document does not specify a quantitative sample size for any "test set" in terms of number of patients or cases. It mentions "participants" for usability testing, but no number is given. The testing described is primarily software verification and validation, not a clinical trial with a patient-based test set as might be seen for a diagnostic AI.
• Data Provenance: Not explicitly stated in terms way data for an AI would be (e.g., country of origin). The testing seems to be internal development and verification. No mention of retrospective or prospective clinical data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Not Applicable. This device is a hearing aid system with remote programming capabilities, not a diagnostic tool requiring expert interpretation of medical images or clinical data to establish a "ground truth" for disease states. The "ground truth" for its functionality is based on its engineering specifications, user needs, and established audiological principles.

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

• Not Applicable. An adjudication method is typically used in studies involving human readers or multiple experts to resolve discrepancies in ground truth labeling or diagnostic assessments. This type of study design is not described here, as the testing focuses on software functionality, safety, and effectiveness compared to a predicate device.

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. An MRMC study is relevant for evaluating the impact of AI on human diagnostic performance (e.g., radiologists reading images with and without AI assistance). This device is not an AI diagnostic tool and its purpose is to provide hearing assistance and remote fitting, not to aid human "readers" in diagnosis or interpretation.

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

• Not Applicable/Implicit. The "algorithm" here is the software that facilitates remote programming and communication for a hearing aid. The performance described (functional equivalence, cybersecurity, etc.) is inherently "standalone" in the sense that the software's core functions are tested. However, this is not an AI algorithm performing a diagnostic task without human intervention; it's a software system designed to be used by both clinicians (human-in-the-loop for programming) and patients for control. The testing confirmed the software's ability to perform its intended functions.

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

• The "ground truth" for this device's performance is its engineering specifications, functional requirements traceability to user needs, and compliance with general safety and performance principles for medical devices. For example, a "ground truth" for a functional test might be "the software successfully adjusted gain by X dB as per the input, and the sound processor responded correctly." This is based on design documents and expected behavior, not external clinical "ground truth" like pathology.

8. The sample size for the training set:

• Not Applicable. This device description does not mention the use of machine learning or deep learning algorithms that would require a distinct "training set" of data for model development. The software is programmatic, not primarily data-driven in its learning capacity at the point of clearance.

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

• Not Applicable. As there's no stated training set for AI/ML, there's no process described for establishing ground truth for such a set.

Ask a specific question about this device

The Cochlear Baha 6 Max Sound Processor is intended for the following patients and indications for use:

· Patient of any age for use with the Baha Softband (or headband) or Baha SoundArc. Patients aged 5 and older for use with the Baha auditory osseointegrated implant system.

· Patients who have a conductive or mixed hearing loss and can still benefit from sound amplification. The pure tone average bone-conduction hearing threshold (measured at 0.5, 1, 2, and 3kHz) should be better than or equal to 55 dB HL.

· Bilateral fitting is intended for patients who meet the above criterion in both ears, with bilaterally symmetric moderate to severe conductive or mixed hearing loss. Symmetrical bone-conduction thresholds are defined as 10 dB average difference between ears (measured at 0.5, 1, 2, and 3 kHz), or less than a 15 dB difference at individual frequencies.

· Patients who suffer from unilateral sensorineural deafness in one ear with normal hearing in the other ear (i.e. Single-sided deadness: SSD). 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.

· Baha for SSD is also indicated for any patient who is indicated for an air-conduction contralateral routing of signals (AC CROS) hearing aid, but who for some reason cannot or will not use an AC CROS.

The Cochlear Baha bone conduction hearing system provides an alternate solution for patients who may not benefit from an air-conduction hearing aids. Unlike air-conduction hearing aids, the Baha system utilizes a natural bone conduction pathway to send sound directly to the inner ear (cochlea), bypassing a damaged outer or midle ear. The Baha bone conduction hearing system has non-surgical and surgical options. For the non-surgical option, the external sound processor, which converts acoustic sound into mechanical vibrations, is securely placed behind the ear with a Baha Softband or Baha SoundArc. For the surgical option, the external sound processor is coupled with an abutment (Baha Connect) or magnet (Baha Attract). The mechanical vibrations travel through the abutment or magnet to a small, titanium implant, which is surgically placed into the bone. The titanium implant has an osseointegrated bond with the surrounding bone, allowing transmission of high-quality sound directly to the inner ear.

The Baha 6 Max Sound Processor is a modification of the previously cleared Baha 5 Power Sound Processor (K161123). The changes introduced in this 510(k) are specific to the sound processor and accessories, and do not affect the cleared Softband, SoundArc, Baha Connect abutments, Baha Attract magnet, or the B1300 titanium implant. The Baha 6 Max Sound Processor does not modify the intended functionality or fundamental operating principles of the bone conduction hearing system. The changes within culminate as the next generation Baha sound processor that provides recipients with moderate hearing loss, up to 55 dB, access to sound.

The Baha 6 Max Sound Processor will be supported by a new fitting software, Baha Fitting Software 6, and a new app, Baha Smart App.

The provided text describes the Cochlear Baha 6 Max Sound Processor and associated software (Cochlear Baha Fitting Software 6, Cochlear Baha Smart App) and states that they are substantially equivalent to their predicate devices. However, the document does not describe a study involving acceptance criteria and device performance as requested in the prompt.

The content focuses on a 510(k) summary, which outlines the device's indications for use, technological characteristics, and a comparison to a predicate device (Cochlear Baha 5 Power Sound Processor). It mentions "Performance Data" but only states that "Bench testing was conducted to compare the Baha 6 Max Sound Processor with the Baha 5 Power Sound Processor, including use with the predicate implant / abutment systems." It further states that "Substantial equivalence to the predicate device was accomplished through functionality and performance testing, hardware and interface testing, reliability and environmental testing, as well as system and subsystem level testing." Software verification and validation were also completed.

Therefore, I cannot provide a table of acceptance criteria and reported device performance, nor details about sample sizes, ground truth establishment, expert adjudication, or MRMC studies, as these specific details are not present in the provided text.

The document concludes that based on indications for use, technological characteristics, and performance data (without detailing the data itself or the acceptance criteria), the new device is substantially equivalent to the predicate.

Ask a specific question about this device

The Osia 2 System is intended for the following patients and indications:
· Patients 12 years of age or older.
· Patients who have a conductive or mixed hearing loss and still can benefit from sound amplification. The pure tone average (PTA) bone conduction (BC) threshold (measured at 0.5. 1, 2, and 3 kHz) should be better than or equal to 55 dB HL.
· Bilateral fitting of the Osia 2 System is intended for patients having a symmetrically conductive or mixed hearing loss. The difference between the left and right sides' BC thresholds should be less than 10 dB on average measured at 0.5, 1, 2, and 3 kHz, or less than 15 dB at individual frequencies.
· Patients who have profound sensorineural hearing loss in one ear and normal hearing in the opposite ear (i.e., single-sided deafness or "SSD"). The pure tone average air conduction hearing thresholds of the hearing ear should be better than or equal to 20 dB HL (measured at 0.5, 1, 2, and 3 kHz).
· The Osia 2 System for SSD is also indicated for any patient who is indicated for an air-conduction contralateral routing of signals (AC CROS) hearing aid, but who for some reason cannot or will not use an AC CROS.
· Prior to receiving the device, it is recommended that an individual have experience with appropriately fitted air conduction or bone conduction hearing aids.

Cochlear™'s Osia 2 System mechanically vibrates the skull bone and subsequently the cochlea to compensate for conductive hearing loss, mixed hearing loss, or single-sided deafness (SSD).
The Osia 2 System is made up of several components. The Osia Implant (OSI200) consists of a receiver/coil and an actuator/stimulator (vibrator) which is surgically implanted on the skull bone. The external component of the Osia System is a sound processor, worn off-the-ear, which picks up the sound from the environment, and sends, after processing, the information to the implant via a transcutaneous inductive link. This link is also referred to as radiofrequency (RF) link. Each Osia 2 System is configured to meet an individual's hearing needs, using dedicated fitting software.

Here's an analysis of the provided information regarding the acceptance criteria and the study conducted for the Cochlear™ Osia™ 2 System:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document, a 510(k) summary, focuses on demonstrating substantial equivalence to a predicate device rather than explicitly stating acceptance criteria and detailed device performance metrics in a table. However, it does highlight key comparisons and generally indicates that the Osia 2 System either performs "Same" as the predicate or has "improved" features. The clinical study's conclusion also states "did not reveal significant differences in hearing performance."

Below is a reconstructed table based on the information provided, inferring acceptance criteria by the demonstrated equivalence to the predicate. Specific numerical performance values beyond those for hearing loss thresholds are not provided in this summary.

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

The document states: "Clinical performance data was gathered through a simulation study that allowed audiological testing of the Osia 2 Systems and Osia Systems without having to surgically implant the OSI200 Implant and OSI100 Implant, respectively."

• Sample Size: The exact sample size for the "simulation study" is not specified in the provided text.
• Data Provenance: The document does not explicitly state the country of origin. It indicates the study was a prospective simulation designed to assess audiological performance without physical implantation of the investigational device.

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

This information is not provided in the document. The study described is a "simulation study" for audiological testing. If human subjects were involved, the "ground truth" would likely be their measured hearing thresholds and subjective speech recognition scores. There is no mention of experts establishing ground truth in the context of diagnostic performance or image interpretation.

4. Adjudication Method for the Test Set

This information is not applicable and therefore not provided. The study described is an audiological performance simulation, not a diagnostic study requiring adjudication of interpretations.

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

This is not applicable. The device is an active implantable bone conduction hearing system, not an AI-powered diagnostic tool requiring human reader interpretation of images or other data. Therefore, an MRMC comparative effectiveness study involving human readers and AI assistance was not performed or described.

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

This is not applicable. The device is a hearing system, not a standalone algorithm. The "clinical performance data" discussed refers to the audiological efficacy of the device (or its simulated function), not the performance of an independent algorithm.

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

For the audiological performance assessment, the "ground truth" would have been the measured audiological outcomes (e.g., adaptive speech recognition scores) of the participants in the simulation study. This is directly related to hearing function.

8. The sample size for the training set

This information is not applicable and therefore not provided. The device is a physical hearing aid system, not a machine learning algorithm that requires a training set in the conventional sense. The "simulation study" would involve testing against human participants or a defined audiological standard, not training a model.

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

This information is not applicable as there is no training set for a machine learning algorithm.

Ask a specific question about this device

The Osia System is intended for the following patients and indications:

· Patients 12 years of age or older.

· Patients who have a conductive or mixed hearing loss and still can benefit from sound amplification. The pure tone average (PTA) bone conduction (BC) threshold (measured at 0.5. 1, 2, and 3 kHz) should be better than or equal to 55 dB HL.

· Bilateral fitting of the Osia System is intents having a symmetrically conductive or mixed hearing loss. The difference between the left and right sides' BC thresholds should be less than 10 dB on average measured at 0.5, 1, 2, and 3 kHz, or less than 15 dB at individual frequencies.

· Patients who have profound sensorineural hearing loss in one ear and normal hearing in the opposite ear (i.e., singlesided deafness or "SSD"). The pure tone average air conduction hearing thresholds of the hearing ear should be better than or equal to 20 dB HL (measured at 0.5, 1, 2, and 3 kHz).

• The Osia System for SSD is also indicated for any patient who is indicated for an air-conduction contralateral routing of signals (AC CROS) hearing aid, but who for some reason cannot or will not use an AC CROS.

· Prior to receiving the device, it is recommended that an individual have experience with appropriately fitted air conduction or bone conduction hearing aids.

Cochlear's Osia System mechanically vibrates the skull bone and subsequently the cochlea to compensate for conductive hearing loss, mixed hearing loss, or single-sided deafness (SSD).

The Osia System is made up of several components. The Osia Implant (OSI100) consists of a receiver/stimulator and an actuator (vibrator) which is surgically implanted on the skull bone. The external component of the Osia System is a sound processor, worn off-the-ear, which picks up the sound from the environment, and sends, after processing, the information to the implant via a transcutaneous inductive link. This link is also referred to as radiofrequency (RF) link. Each Osia System is configured to meet an individual's hearing needs, using dedicated fitting software.

In normal operation, the Osia System functions as follows:

• The external sound processor captures and digitally processes sound.
• The sound processor transmits power and digital information to the implant.
• The implant receiver-stimulator converts the digital information into an electric analogue signal.
• This electric signal is converted to vibrations by the implant piezoelectric actuator.

The actuator converts the electrical signal into an amplified mechanical stimulation, bypassing the impaired middle ear (origin of the conductive part of the hearing loss) and providing some level of mechanical amplification in order to compensate for the damaged inner ear (sensorineural part of the hearing loss, in case of mixed hearing loss).

The provided document (K190589) describes the Cochlear™ Osia™ System, an active implantable bone conduction hearing system. However, it does not include specific acceptance criteria or a study designed to explicitly prove that the device meets those criteria with numerical performance targets (e.g., a specific sensitivity, specificity, or improvement in a metric).

Instead, the document details a substantial equivalence (SE) submission to the FDA. The purpose of this submission is to demonstrate that the new device (Cochlear™ Osia™ System) is as safe and effective as a legally marketed predicate device (Bonebridge™ System). The document describes the system and presents performance data in the context of supporting this claim of substantial equivalence, rather than hitting pre-defined acceptance criteria for a novel device.

The "performance data" section (Section K) broadly states that clinical performance data was gathered and showed significant improvements, similar to the predicate device. It doesn't present specific acceptance criteria in a table format with corresponding performance metrics.

Therefore, I cannot generate the table as requested because the specific acceptance criteria and their corresponding numerical outcomes are not explicitly stated in the provided text.

However, I can extract the information related to the clinical study and its findings to give you the context of the device's performance as described:

1. Table of Acceptance Criteria and Reported Device Performance:

• Acceptance Criteria: Not explicitly stated as pass/fail numeric targets in the document. The general acceptance criterion for a 510(k) is demonstrating "substantial equivalence" to a predicate device, meaning the new device is as safe and effective.
• Reported Device Performance:
  • Audiometric thresholds: Significant improvements reported when compared to the pre-implant condition.
  • Speech in noise: Significant improvements reported when compared to the pre-implant condition.
  • Speech in quiet: Significant improvements reported when compared to the pre-implant condition.
  • Patient reported outcomes: Significant benefits demonstrated.
  • Hearing Loss Accommodation: The Osia System can accommodate greater degrees of hearing loss (45 dB vs. 55 dB for the predicate, though the document states "greater degrees of hearing loss (45 versus 55 dB)" which seems to be a typo and likely means 55dB for Osia which is higher).
  • Force output measurements: Higher for the Osia System at the same frequencies compared to the predicate device, enabling an expanded fitting range.

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

• Sample Size: Not explicitly stated. The document mentions "data gathered in a multi-center trial."
• Data Provenance:
  • Country of Origin: One site was in the United States; other sites not specified.
  • Retrospective or Prospective: Prospective clinical investigation.

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

• This information is not provided in the document. The study was a clinical trial on human patients, and the "ground truth" would be the patient's actual hearing ability and perceived benefit, measured through audiometric tests and patient-reported outcomes, rather than expert interpretation of data for ground truth establishment.

4. Adjudication Method for the Test Set:

• This information is not provided in the document. The study was an "open, two-armed" clinical investigation. It was not blinded.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

• No, an MRMC study was not described. The study focused on the effectiveness of the device itself by comparing pre-implant conditions to post-implant conditions with the Osia device, and implied similar performance to a predicate device. It did not involve comparing human readers with and without AI assistance, as this is a medical device for hearing, not an AI diagnostic imaging tool.

6. Standalone (Algorithm Only) Performance:

• Not applicable in the typical sense of AI standalone performance. The "algorithm" here is the signal processing within the sound processor. The clinical study did evaluate the performance of the device system (implant + sound processor) in a "standalone" fashion (i.e., its performance in patients), but not in the context of an AI algorithm making a diagnosis without human interaction.

7. Type of Ground Truth Used:

• Clinical Outcomes and Audiometric Data: The "ground truth" was established by objective audiometric measures (pure tone average bone conduction thresholds, air conduction hearing thresholds) and subjective patient-reported outcomes regarding hearing ability and benefit.

8. Sample Size for the Training Set:

• Not applicable. This device is a hearing aid system, not a machine learning model that requires a training set in the conventional sense. The "training" in this context would be the device development and engineering process to optimize its acoustic and mechanical properties, not a machine learning training phase on data.

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

• Not applicable. As above, there isn't a machine learning training set with established ground truth described in this submission.

Ask a specific question about this device