Search Results

ATLANTIS™ ISUS Implant Suprastructures are indicated for attachment to dental implants or abutments in the treatment of partially or totally edentulous jaws for the purpose of restoring chewing function.

ATLANTIS™ ISUS Implant Suprastructures are intended for attachment to a minimum of two (2) implants and are indicated for compatibility with the following implant and abutment systems:

Implants:
Biomet 3i Certain 3.25, 4/3 - Prevail 3/4/3, 4/3
Biomet 3i Certain 4.0, 5/4 – Prevail 4/5/4. 5/4
Biomet 3i Certain 5.0, XP 4/5 - Prevail 5/6/5, 6/5
Biomet 3i Certain 6.0, XP 5/6
BioHorizons Internal/Tapered 3.5, 4.5, 5.7
Camlog Screw-line Implant 3.3
Camlog Screw-line / Root-line Implant 3.8, 4.3, 5.0, 6.0
DENTSPLY Implants XiVE S 3.0, S 3.4, S 3.8, S 4.5, S 5.5
DENTSPLY Implants OsseoSpeed™ TX 3.0, 3.5/4.0, 4.5/5.0
DENTSPLY Implants Osseospeed™ Profile TX 4.5/5.0
DENTSPLY Implants Osseospeed™ EV 3.0, 3.6, 4.2, 4.8, 5.4
DENTSPLY Implants Osseospeed™ Profile EV 4.2, 4.8
Keystone Dental PrimaConnex SD 3.3/3.5
Keystone Dental PrimaConnex RD 4.0/4.1
Keystone Dental PrimaConnex WD 5.0
Keystone Dental Genesis 3.8, 4.5, 5.5/6.5
Nobel Biocare NobelActive NP 3.5 - RP 4.3, 5.0
Nobel Biocare NobelReplace NP-3.5 - RP 4.3 - WP 5.0 – 6.0
Straumann Bone Level 3.3 NC - 4.1, 4.8 NC
Straumann Standard Plus 3.5 NN
Straumann Standard / Standard Plus 4.8 RN – 4.8 WN
Zimmer Dental Tapered Screw Vent S-V 3.5/S-V 3.3, 3.7 / S-V 4.5/ S-V 4.5
Zimmer Dental Tapered Screw Vent 5.7

Abutments:
Biomet 3i Low Profile Abutment
DENTSPLY Implants ATIS Uni Abutment EV
DENTSPLY Implants ATIS UniAbutment 20°, ATIS UniAbutment 45°
DENTSPLY Implants ATIS Angled Abutment EV
DENTSPLY Implants ATIS Angled Abutment 20°
DENTSPLY Implants ANKYLOS Balance Base Narrow D4.2, Balance Base D5.5
DENTSPLY Implants XiVE MP 3.4, MP 3.8, MP 4.5, MP 5.5
DENTSPLY Implants XiVE TG 3.4, TG 3.8, TG 4.5
Nobel Biocare Multi-Unit Abutment RP
Straumann Bone Level Multi-Base Angled Abutment
Straumann Bone Level Multi-Base Abutment D3.5, D4.5
Straumann RN Abutment Level, WN Abutment Level
Straumann Screw-Retained Abutment 3.5, 4.6
Zimmer Dental Tapered Abutment

The ATLANTIS™ ISUS Implant Suprastructures include new implant and abutment interfaces of the predicate ISUS Implant Suprastructures, cleared in K122424.

The ATLANTIS™ ISUS Implant Suprastructures are patient-specific restorative devices that are intended to be attached to dental implants or abutments to facilitate prosthetic restoration in the treatment of partially and totally edentulous patients. The design of the subject device is derived from patient dental models and completed by DENTSPLY technicians using computer-assisted design (CAD) according to the clinician's prescription. The final CAD design of the ATLANTIS™ ISUS suprastructures are fabricated using computer-assisted manufacturing (CAM) to produce a customized, patient-specific device.

The subject ATLANTIS™ ISUS Implant Suprastructures are available in the same design types as cleared for the predicate ISUS Implant Suprastructures in K122424:

1. Bar Intended as a fixed supporting structure for a removable dental prosthesis.
2. Bridge Intended for direct veneering using dental ceramics or resin composites resulting in a fixed, screw-retained prosthesis.
3. Hybrid Intended as a fixed denture framework.

Screws are available for all compatible implant and abutments systems to screw the ATLANTIS™ ISUS Implant Suprastructures into the implant or onto the abutment.

In addition to the introduction of the new interfaces of the ATLANTIS™ ISUS Implant Suprastructures, the product reference names of the compatible interfaces are adjusted in the indications for use for the currently marketed ATLANTIS™ ISUS Implant Suprastructures to better reflect the original manufacturer's product description.

The provided document describes a 510(k) premarket notification for a medical device, specifically the ATLANTIS™ ISUS Implant Suprastructures. This type of submission aims to demonstrate that a new device is as safe and effective as a legally marketed predicate device, rather than proving novel effectiveness. Therefore, the information provided focuses on demonstrating substantial equivalence through non-clinical testing and comparison to existing devices, rather than a clinical study establishing acceptance criteria in the traditional sense of AI performance metrics like sensitivity, specificity, or AUC.

Based on the document, here's a breakdown of the requested information:

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

Since this is a 510(k) for a dental implant component, the "acceptance criteria" are related to mechanical and material equivalence to predicate devices, and "device performance" refers to its ability to meet these engineering standards. There are no performance metrics like sensitivity or specificity.

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

This information is not applicable or not provided in the context of an AI device. This document is for a physical medical device (dental suprastructures). The testing performed is non-clinical, involving mechanical and dimensional analysis of device components themselves, rather than testing on a "test set" of patient data.

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 information is not applicable or not provided. "Ground truth" in the context of an AI device, established by experts, is not relevant here as this is a physical medical device. The "ground truth" for this device's performance would be the universally accepted engineering standards for dental prosthetics and the demonstrable properties of the materials and design.

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

This information is not applicable or not provided. Adjudication methods are typically used in clinical studies or for establishing ground truth in AI studies. The testing described is non-clinical performance data (mechanical design analysis, dimensional analysis, static and dynamic compression-bending testing).

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 information is not applicable or not provided. This is not an AI device, and therefore, an MRMC study comparing human readers with and without AI assistance is not relevant.

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

This information is not applicable or not provided. This is not an algorithm-only device.

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

The "ground truth" here is the established engineering standards for dental prosthetics. This includes:

• Mechanical standards: ISO 14801 Dentistry -- Implants -- Dynamic fatigue test for endosseous dental implants.
• Material standards: Properties of CPTi, CoCr, Ti-6Al-4V ELI, Ti-6Al-7Nb (as listed for abutment and screw materials).
• Biocompatibility: Demonstrated equivalence to the predicate device (K122424) which had prior biocompatibility testing.
• Design principles: Comparison to existing, legally marketed predicate devices to establish substantial equivalence in intended use and fundamental technology.

8. The sample size for the training set

This information is not applicable or not provided. As this is a physical device submission, there is no "training set" in the context of machine learning. The device's design is "derived from patient dental models and completed by DENTSPLY technicians using computer-assisted design (CAD) according to the clinician's prescription," and then fabricated using computer-assisted manufacturing (CAM).

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

This information is not applicable or not provided. There is no machine learning training set for this device. The "ground truth" for the CAD/CAM design process would be the clinician's prescription and the patient's dental models, which guide the creation of the patient-specific device.

Ask a specific question about this device

Disposable Barrier Sleeves and Covers are intended to serve as a disposable barrier for dental instruments and equipment. This device is non-sterile and intended for single patient use only.

The proposed devices. Disposable Barrier Sleeves and Covers, are made of polyethylene film and are used as accessories to dental instruments and equipment used during dental procedures. These disposable barrier sleeves and covers are offered in various shapes and sizes to fit over and cover the intended dental instruments and equipment. The Disposable Barrier Sleeves slip over the ends of the respective devices, allowing for the attachment and/or protrusion (where applicable) of those parts of the devices used during dental procedures. The Disposable Barrier Cover is placed over equipment, such as dental chair head rests and trays, to cover those parts.

The proposed devices, Disposable Barrier Sleeves and Covers, act as a physical barrier, augmenting existing infection control techniques, and facilitate clean-up.

The document provided is a 510(k) premarket notification for "Disposable Barrier Sleeves and Covers" (K160232) by DENTSPLY International. This type of submission is for demonstrating substantial equivalence to a legally marketed predicate device, not for proving the safety and effectiveness of a novel device through extensive clinical trials. Therefore, the information requested regarding acceptance criteria and studies proving a device meets them for a complex AI/ML device is largely not applicable in this context.

However, I can extract the relevant information from the provided document as it pertains to the substantial equivalence determination for this non-AI medical device.

Here's a breakdown based on the provided document and the nature of a 510(k) submission for a non-AI device:

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

The acceptance criteria are generally established by recognized standards for medical device materials and performance. The document defines the "Proposed Device" as "Disposable Barrier Sleeves and Covers" and compares its performance against a "Predicate Device," "TIDIShield™ Curing Light Sleeve (K132953)".

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 does not explicitly state the sample sizes for the mechanical and performance tests. It refers to "samples" being tested. For biocompatibility, it states "the proposed devices, Disposable Barrier Sleeves and Covers" underwent testing.
The data provenance is not specified beyond "testing conducted to support substantial equivalence." It's common for such bench testing to be conducted in-house by the manufacturer or by contract labs. There is no indication of country of origin or whether it was retrospective or prospective, as these are typically not relevant for a 510(k) submission for this type of device.

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 is not applicable. For a physical barrier device like this, ground truth is established by standardized material and performance testing against recognized industry standards (e.g., ASTM, ISO). There are no "experts" establishing a subjective "ground truth" in the way one would for diagnostic imaging.

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

This is not applicable. Adjudication methods like 2+1 or 3+1 are used for expert review of images or data in clinical studies, typically for diagnostic devices. This device is a physical barrier, and its performance is evaluated by objective laboratory tests, not by expert adjudication of subjective assessments.

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 entirely not applicable.
* This device is a disposable physical barrier, not an AI/ML-powered diagnostic device.
* No human "readers" are involved.
* No "cases" are being interpreted.
* No AI assistance is provided or claimed.
* No MRMC study was conducted or is relevant for this device.

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

This is entirely not applicable.
* This device is a physical product, not an algorithm.
* There is no "human-in-the-loop" concept for this device's function.

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

The "ground truth" for this device's performance is based on the objective outcomes of standardized laboratory tests as defined by international standards (e.g., ISO, ASTM). For example:

• Biocompatibility: Demonstrated non-cytotoxicity, non-sensitization, and non-irritation as per ISO 10993 series.
• Performance (Barrier): Demonstrated resistance to synthetic blood and viral penetration as per ASTM F1670/F1670M and ASTM F1671/F1671M.
• Mechanical Properties: Measured tensile strength, puncture resistance, and tear resistance as per ASTM D882, F1342/F1342M, and D1004.

These are quantitative measurements against defined criteria, not subjective expert consensus or clinical outcomes data.

8. The sample size for the training set

This is not applicable. This device is a physical medical device, not an AI/ML algorithm. Therefore, there is no "training set."

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

This is not applicable, as there is no training set for this type of device.

Ask a specific question about this device

ATLANTIS™ ISUS implant suprastructures are indicated for attachment to dental implants or abutments in the treatment of partially or totally edentulous jaws for the purpose of restoring function.

ATLANTIS™ ISUS implant suprastructures are intended for attachment to a minimum of two (2) implants and are indicated for compatibility with the following implant and abutment systems:

Implants:

• 3i Internal Connection: D3.4, D4.1, D5, D6
• Friadent XiVE S: D3.0, D3.4, D3.8, D4.5, D5.5
• Nobel Biocare Active Internal: NP (3.5mm), RP (4.3mm, 5.0mm)
• Nobel Biocare Replace Select: NP (3.5mm), RP (4.3mm), WP (5.0mm) and Replace Select 6.0mm
• Straumann Bone Level: NC (3.3mm), RC (4.1mm, 4.8mm)
• Straumann NN (3.5mm), RN (4.8mm), WN (6.0mm)
• Zimmer Screw Vent: D3.5, D4.5, D5.7

Abutments:

• 3i Low Profile Abutment
• ANKYLOS Balance Base Abutment D5.5 and Narrow Abutment D4.2
• ASTRA TECH 20° and 45° UniAbutment
• Astra Tech UniAbutment EV 3.6
• Friadent XiVE MP D3.8, D4.5, D5.5
• Friadent XiVE TG D3.8,D 4.5, D5.5
• Nobel Biocare Multi-Unit Abutment RP: 4.0 mm
• Straumann Bone Level Angled Abutment: 4.0 mm
• Straumann Bone Level: Multi-Base Abutment D3.5, D4.5
• Straumann RN (4.8 mm), WN (6.5 mm)
• Zimmer Tapered Abutment: 4.5 mm

ATLANTIS™ ISUS is a custom restorative device that is intended to dental implants or abutments to facilitate prosthetic restoration in the treatment of partially and totally edentulous patients. The design of the subject device is derived from patient dental models and completed by DENTSPLY technicians using computer-assisted design (CAD) according to the clinician's prescription. The final CAD design of ATLANTIS™ ISUS is fabricated using computer-assisted manufacturing (CAM) to produce a custom patient specific device.

ATLANTIS™ ISUS is available in four design types: Bar, Bridge, Hybrid, and 2 in 1. It also features Angulated Screw Access (ASA) allowing the screw-channel opening to be angled up to 30° off the implant/abutment axis.

The provided text describes a medical device called ATLANTIS™ ISUS, an implant suprastructure. The document is primarily a 510(k) premarket notification summary, which focuses on demonstrating substantial equivalence to predicate devices rather than providing detailed acceptance criteria and a study design for a new device.

Therefore, the document does not contain the detailed acceptance criteria and a study specifically designed to prove the device meets those criteria in the way one would for a new AI/software device. The information provided is for a physical medical device (dental implant suprastructure).

However, I can extract the information related to the device's "performance" characteristics and the testing performed to demonstrate its safety and effectiveness, which serves a similar purpose to acceptance criteria and performance data for this type of device.

Here's an interpretation based on the provided text, structured to align with your request for acceptance criteria and study information, noting the differences due to the nature of the device:

1. Table of Acceptance Criteria and Reported Device Performance

For this device, "acceptance criteria" are not framed as statistical thresholds for an AI algorithm's output, but rather as meeting specific physical and mechanical performance standards comparable to legally marketed predicate devices. The "reported device performance" refers to the results of non-clinical bench testing.

The following points refer to your specific questions, which are more tailored to AI/software validation studies. Given that this is a physical medical device submission (dental implant suprastructure), some of these questions are not directly applicable or the information is not present in the document.

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

• Sample Size: Not explicitly stated for the non-clinical tests (e.g., how many units were fatigue tested). It refers to "testing" in general.
• Data Provenance: Not applicable for non-clinical bench testing of physical devices. The testing was conducted as part of the submission package for FDA clearance.

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 this context would implicitly be the established engineering standards (like ISO 14801) and accepted dental restoration principles, not expert consensus on image interpretation or diagnosis.

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

• Not applicable for non-clinical bench testing. Performance is measured against physical specifications and standard test methods.

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. This is a physical dental implant suprastructure, not an AI/software device involving human readers.

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

• The performance assessment described is "standalone" in the sense that it's the physical device alone being subjected to tests. However, it's not an algorithm.

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

• For the non-clinical tests, the "ground truth" is based on:
  • International Standards: ISO 14801 (for dynamic fatigue testing).
  • Engineering Principles/Specifications: Performance against specified torque requirements, material properties, and dimensional compatibility.
  • Equivalence to Predicate Devices: The ultimate "truth" for 510(k) is demonstrating that the device is as safe and effective as a legally marketed predicate device.

8. The sample size for the training set

• Not applicable. This device is manufactured using CAD/CAM based on patient dental models and clinician prescriptions. There is no explicit "training set" in the machine learning sense. The "design" is based on established engineering principles and dental prosthetics knowledge, and the "manufacturing" is automated.

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

• Not applicable. There is no "training set" in the AI sense. The design process (CAD) uses patient-specific data to create a custom device according to pre-defined parameters and dental restoration best practices, rather than learning from a dataset.

Ask a specific question about this device

The ATLANTIS™ Crown is intended for use with an ATLANTIS™ Abutment and an endosseous implant to function as a substructure that also serves as the final restoration, in a partially or completely edentulous patient.

The ATLANTIS™ Crown is a patient-specific dental prosthetic component intended for use with an ATLANTISTM Abutment, abutment screw, and an endosseous implant to support a single-tooth prosthetic restoration. The ATLANTIS™ Crown is made of yttria stabilized zirconia powder (Y-TZP) and fabricated according to the clinician's prescription using CAD/CAM technology. The crown can be delivered as a full contour crown or as a cut-back substructure onto which porcelain will be added by the customer. The ATLANTIS™ Crown is finally cemented to the ATLANTIS™ Abutment.

This document describes a 510(k) premarket notification for the ATLANTIS™ Crown, a patient-specific dental prosthetic component. The information provided heavily focuses on comparing the proposed device to predicate devices to establish substantial equivalence, rather than detailing a specific clinical study with acceptance criteria for a novel device.

Therefore, it is important to note that the input document does NOT describe the acceptance criteria and a study that proves the device meets those acceptance criteria in the typical sense for an AI/ML device.

Instead, the document demonstrates that the ATLANTIS™ Crown is substantially equivalent to a legally marketed predicate device based on its intended use, technological characteristics (material, design, manufacturing), and non-clinical performance data (flexural strength, fracture toughness, chemical solubility, radioactivity concentration, and coefficient of thermal expansion).

Here's an analysis based on the available information, addressing the requested points where possible, and noting where information is not present in the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" in the context of a performance study for the ATLANTIS™ Crown as a new device with novel performance claims to be evaluated. Instead, it relies on demonstrating that the ATLANTIS™ Crown meets the established performance characteristics of its predicate devices and complies with relevant standards.

Regarding the remaining points:

The provided document is a 510(k) summary for a medical device (ATLANTIS™ Crown) which is a physical product, not an AI/ML diagnostic or assistive tool. Therefore, many of the requested points related to AI/ML device studies (sample sizes for test/training sets, data provenance, number/qualifications of experts, adjudication methods, MRMC studies, standalone performance, ground truth types) are not applicable and are not found in this document.

Specific responses to the remaining points based on the understanding that this is not an AI/ML device document:

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective): Not applicable. This document reports non-clinical material characterization data (flexural strength, fracture toughness, etc.) against established standards (ISO, ASTM), not a clinical trial with a test set of patient data.
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 context of clinical or diagnostic AI/ML studies is not relevant here. Material properties are measured against physical standards.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable. Material testing involves scientific measurement and comparison to quantitative standards, not expert adjudication.
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 prosthetic device, not an AI-assisted diagnostic tool.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done: Not applicable. This is a physical prosthetic device.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc): Not applicable in the AI/ML sense. The "ground truth" for material properties is the defined limits and test methods of international standards like ISO 6872.
8. The sample size for the training set: Not applicable. There is no "training set" as this is not an AI/ML model.
9. How the ground truth for the training set was established: Not applicable. There is no "training set" or corresponding ground truth establishment process.

Ask a specific question about this device

The ATLANTIS™ Abutment is intended for use with an endosseous implant to support a prosthetic device in a partially or completely edentulous patient. It is intended for use to support single and multiple tooth prosthesis, in the mandible or maxilla. The prosthesis can be cemented or screw retained to the abutment. The abutment screw is intended to secure the ATLANTIS™ Abutment to the endosseous implant.

The ATLANTIS™ Crown Abutment is intended for use with an endosseous implant to function as a substructure that also serves as the final restoration, in a partially or completely edentulous patient. The abutment screw is intended to secure the ATLANTIS™ Crown Abutment to the endosseous implant.

The ATLANTIS™ Conus Abutment is intended for use with an endosseous implant to support a prosthetic device in partially or completely edentulous patients. It is intended for use to support a removable multiple tooth prosthesis, in the mandible or maxilla. The prosthesis is attachmentretained by friction fit to the abutment. The abutment screw is intended to secure the ATLANTIS™ Conus Abutment to the endosseous implant.

ATLANTIS™ Abutment for NobelActive 3.0 is compatible with the NobelActive 3.0 implant.

ATLANTISTM Abutment for NobelActive 3.0 is provided in three designs: ATLANTISTM Abutment for NobelActive, ATLANTIS™ Crown Abutment for NobelActive and ATLANTISTM Conus Abutment for NobelActive. All are patient specific fabricated abutments using CAD/CAM technology. Each abutment is designed according to prescription instructions from the clinician to support a screw-retained. cement-retained or friction fit prosthesis.

The coronal portion of the ATLANTIS™ abutment can be fabricated as a conventional abutment for prosthesis attachment (ATLANTIS™ Abutment or ATLANTISTM Conus Abutment) or fabricated as a single tooth final restoration onto which porcelain is added (ATLANTISTM Crown Abutment). The implant/abutment interface is compatible with the NobelActive 3.0 implant.

ATLANTISTM Abutment for NobelActive 3.0 has an internal connection and is provided for implant platform diameter Ø3.0 mm. The abutment diameter ranges from 3.3 to 13 mm, the maximum abutment height is 15 mm above implant interface and the minimum abutment height is 4 mm above the transmucosal collar. The abutment is provided straight and up to 30° of angulation.

Here's an analysis of the provided text regarding the acceptance criteria and study for the ATLANTIS™ Abutment for NobelActive 3.0.

Important Note: The provided document is a 510(k) premarket notification for a medical device (dental implant abutment). These types of submissions typically focus on demonstrating substantial equivalence to existing legally marketed devices, rather than establishing completely new performance criteria or conducting extensive effectiveness studies for a novel AI algorithm. Therefore, many of the requested categories related to AI performance, ground truth, and expert evaluation are not applicable to this type of traditional medical device submission.

The "studies" described are primarily non-clinical engineering tests to ensure mechanical integrity and compatibility with the predicate device.

Acceptance Criteria and Reported Device Performance

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Not explicitly stated in the summary. For mechanical testing (ISO 14801), devices are typically tested in small batches to statistical significance or to demonstrate compliance with a specific load rating. The exact number of abutments tested is not provided.
• Data Provenance: The "Non-Clinical Performance Data" section (Section 7) describes testing performed by DENTSPLY International, Inc., the manufacturer/submitter, and references predicate devices. This would be considered prospective testing conducted specifically for this 510(k) submission or in support of prior predicate device approvals. The country of origin of the data is implied to be within the company's testing facilities, likely in the US as the submitter is a US company.

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

• N/A. This device is a physical medical device (dental abutment), not an AI algorithm that requires expert annotation for ground truth. The "ground truth" for its performance is established through quantitative mechanical testing and engineering analyses against defined standards (like ISO 14801).

4. Adjudication Method for the Test Set

• N/A. Adjudication methods (like 2+1, 3+1) are relevant for human evaluation processes, especially in clinical trials or AI performance evaluations involving multiple readers. This is a physical device undergoing mechanical and engineering tests, not an interpretive task.

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

• N/A. This is not an AI-powered diagnostic or assistive device. It is a physical dental implant abutment.

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

• N/A. This is a physical dental implant abutment, not an algorithm.

7. The Type of Ground Truth Used

• For Mechanical Strength & Compatibility: The "ground truth" is defined by engineering standards and specifications (e.g., ISO 14801, material properties, dimensional tolerances, fit with the corresponding implant). Performance is measured against these objective standards.
• For Biocompatibility & Sterility: The "ground truth" is derived from established regulatory standards and validated testing protocols (e.g., ISO 10993 for biocompatibility, ISO 11137 or AAMI standards for sterility assurance levels).

8. The Sample Size for the Training Set

• N/A. This is not an AI algorithm that requires a training set. The design of the ATLANTIS™ Abutment is based on CAD/CAM technology, but the "training" in this context refers to the manufacturing process, not machine learning.

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

• N/A. As there is no AI training set, this question is not applicable. The design and manufacturing process for the CAD/CAM abutment are governed by engineering principles and quality control, not ground truth derived from annotated data.

Ask a specific question about this device

1. Prime&Bond Elect® Universal Dental Adhesive (visible light cured):
   • 1.1 Direct, light cured composite and compomer restorations
   • 1.2 Indirect restorations; light cured, resin cemented veneers
   • 1.3 Indirect restorations; acid-tolerant resin cement (dual cure or self-cure) cemented inlays, onlays, crown and bridge retainers
   • 1.4 Composite, ceramic and amalgam repairs
   • 1.5 Cavity varnish for use with fresh amalgam

• 2. Prime&Bond Elect® Universal Dental Adhesive mixed with Self-Cure Activator (dual cure or self-cure):
  • 2.1 Direct, dual cure or self-cure composite restorations and core build-ups
  • 2.2 Indirect restorations; dual cured and self-cured resin cemented inlays, onlays, crown and bridge retainers
  • 2.3 Dual cured and self-cured resin cemented endodontic post cementation
• 3. Prime&Bond Elect® Universal Dental Adhesive mixed with Self-Cure Activator and Amalgam Bonding Base & Catalyst:
  • 3.1 Adhesive bonding of direct amalgam restoration
• 4. Prime&Bond Elect® Universal Dental Adhesive (without Self-Cure Activator or adhesive curing):
  • 4.1 Indirect restorations: acid-tolerant resin cement light-cured cementation; light transmissible inlays, onlays, crown and bridge retainers with light curing of cement
  • 4.2 Indirect restorations; acid-tolerant resin cement dual cure or self-cure cementation; limited light/light opaque inlays, onlays, crown and bridge retainers and endodontic posts with total etch technique

Prime&Bond Elect® Universal Dental Adhesive is a universal self-priming dental adhesive system designed to bond resin based materials to enamel and dentin as well as to metals and ceramic. Prime&Bond Elect® Universal Dental Adhesive combines etchant, primer and adhesive in a one-bottle material. This robust formulation allows the operator to utilize selective phosphoric acid etching of enamel, phosphoric acid etching of both enamel and dentin, or no phosphoric acid etching prior to application, ensuring high bond strength and protection against microleakage.

When mixed with Self-Cure Activator, Prime&Bond Elect® Universal Dental Adhesive is designed to be used with DENTSPLY manufactured dual cure/self-cure resin cements* to bond all indirect restorations and DENTSPLY manufactured dual cured composite restoratives. When used with the Amalgam Bonding Accessory Kit, available separately, Prime&Bond Elect® Universal Dental Adhesive also adhesively bonds fresh amalgam to enamel and dentin.

*Note: Acid-tolerant resin cements may be used following application of Prime&Bond Elect® adhesive without the use of Self-Cure Activator, additionally allowing operator's choice of pre-cementation adhesive curing options (see complete Directions for Use).

The provided text includes information about the DENTSPLY International Inc. device, Prime&Bond Elect® Universal Dental Adhesive. However, it does not describe specific acceptance criteria in the form of numerical thresholds for device performance, nor does it detail a standalone study proving the device meets acceptance criteria.

Instead, the document states that the proposed device (Prime&Bond Elect® Universal Dental Adhesive) has an identical design and formulation to a predicate device (XENO® Adhesive with Activator, K051463), meaning the biocompatibility and performance data of the predicate device support the proposed device. A table of "Physical Properties Tested" is provided, and for each property, the result is simply "Meets specification," without providing the actual specifications or measured values.

Therefore, many of the requested items (sample size, data provenance, number of experts, adjudication method, MRMC study details, ground truth type and establishment for training, and specific acceptance criteria with numerical performance) cannot be extracted from this document, as a typical clinical study with such details was not conducted or reported for this 510(k) submission.

Here's a summary of the available information based on your request:

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

Note: The document states "all of the test results have met the specifications" but does not provide the specific numerical specifications or the measured results.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
Not provided in this document. The document relies on the predicate device's data.

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. No multi-reader, ground truth establishment study is described. The performance claim is based on equivalence to a predicate device and physical property testing.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable.

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, a MRMC comparative effectiveness study was not done. The device is a dental adhesive, not an AI-assisted diagnostic tool.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Physical property testing was done for the standalone device. The results are summarized generically as "Meets specification" without providing numerical values or sample sizes. The biocompatibility and primary performance claims are based on the predicate device.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For the physical properties listed, the "ground truth" would be established by standardized material testing procedures and their associated specifications. No details on these specific standards or how the specifications were derived are provided in this document. For the overall performance, the "ground truth" is the performance of the legally marketed predicate device (K051463), whose data was used as a basis for substantial equivalence.

8. The sample size for the training set
Not applicable. There's no machine learning algorithm described.

9. How the ground truth for the training set was established
Not applicable.

Ask a specific question about this device

Used for ultrasonic procedures:

• All general supra and subgingival scaling applications .
• Periodontal debridement for all types of periodontal diseases .

The Cavitron Touch™ Ultrasonic Scaling System is an ultrasonic scaling unit that is used in all general supra and subgingival scaling applications and periodontal debridement for all types of periodontal diseases. The Cavitron Touch™ Ultrasonic Scaling System includes a digital touch screen interface and Bluetooth technology. This device is equipped with the Tap-On™ Wireless Foot Pedal with Tap-On™ technology.

The provided text describes a medical device, the Cavitron Touch™ Ultrasonic Scaling System, and its substantial equivalence to a predicate device, the Cavitron® RF Ultrasonic Scaler System with Sterimate Handpiece (K052334). However, the document does not contain specific acceptance criteria or a study proving the device meets those criteria with quantitative performance metrics for the reasons listed below for each criterion. This is a 510(k) submission, which focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than undergoing a de novo clinical trial with explicit acceptance criteria for efficacy.

Here's a breakdown of the requested information based on the provided text:

1. Table of acceptance criteria and the reported device performance

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

• The document does not specify sample sizes for any test sets related to performance characteristics (e.g., number of units tested, duration of tests).
• The data provenance is internal testing performed by DENTSPLY International Inc. (Section 7, "Internal specification and testing"). Country of origin is not specified but the company is based in York, Pennsylvania, USA. The testing would be prospective in nature for a new device design.

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. This submission focuses on engineering and performance verification against existing standards and internal specifications, not on establishing ground truth for diagnostic or clinical interpretation using expert readers.

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

• Not applicable. As the "ground truth" and "expert" roles are not relevant in this type of engineering and performance verification submission, there is no adjudication method described.

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 comparative effectiveness study was not done. This device is an ultrasonic scaler; it is a tool used by dental professionals, not an AI-powered diagnostic system that assists human readers in case interpretation. The document explicitly states "No data from human clinical studies has been included to support the substantial equivalence of the Cavitron Touch™ Ultrasonic Scaling System" (Section 9, page 9).

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

• Not applicable. This device is an ultrasonic scaler. Its function is to perform ultrasonic scaling procedures, which inherently involves a human operator (a dental professional). It is not an algorithm that functions in a standalone capacity without human intervention.

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

• Not applicable/Not explicitly defined in the clinical sense. For a device like an ultrasonic scaler, "ground truth" for non-clinical performance would relate to engineering specifications, safety standards (e.g., electrical safety, electromagnetic compatibility), and functional requirements (e.g., power output, water flow, touch screen responsiveness). The closest to "ground truth" would be the standards themselves (e.g., AAMI ANSI ES 60601-1, IEC 60601-1-2) and the internal specifications against which the device was tested.

8. The sample size for the training set

• Not applicable. This device is not an AI/machine learning system that requires a "training set" in the conventional sense. The development likely involved iterative design and testing, but not a formally defined "training set" for an algorithm.

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

• Not applicable. As there is no training set for an AI/ML algorithm, the concept of establishing ground truth for it does not apply.

Summary of Study Type:

The document describes non-clinical performance data (Section 7, page 9) which includes:

• Verification of design
• Ultrasonic scaling performance
• Function of the device
• Adherence to international standards (AAMI ANSI ES 60601-1, IEC 60601-1-2)
• Guidance for software validation (FDA - Guidelines for the Content of Premarket Submissions for Software Contained in Medical Devices- Software Validation)
• Internal specification and testing for handpiece operation, autocycle operation, touch screen/user interface, and radio frequency distance for the wireless foot pedal.

This type of submission relies on demonstrating that the new device is as safe and effective as a legally marketed predicate device through engineering and performance testing, rather than through extensive clinical trials with explicit performance metrics and acceptance criteria for patient outcomes.

Ask a specific question about this device

• A root end filling material
• For the repair of repair of root canals as an apical plug during apexification
• For repair of root perforations during root canal therapy or as a consequence of internal resorption
• As a pulp capping material
• Pulpotomy of primary teeth in the child (ages >2-12 years) and adolescent (ages >12-21 years) pediatric patient populations

ProRoot MTA White and ProRoot MTA Gray is a powder consisting of fine hydrophilic particles that set in the presence of moisture. Hydration of the powder creates a colloidal gel that solidifies to form a strong impermeable barrier that fully cures over a four-week period.

Here's an analysis of the provided text regarding acceptance criteria and the supporting study:

The provided text is a 510(k) premarket notification for a dental device, ProRoot MTA White/Gray (Pediatric Pulpotomy). It focuses on establishing substantial equivalence to previously cleared predicate devices and adding a new indication for use: "Pulpotomy of primary teeth in the child (ages >2-12 years) and adolescent (ages >12-21 years) pediatric patient populations."

It's important to note that this document is not a standalone study report with explicit acceptance criteria and detailed performance metrics as one might find for a diagnostic or imaging AI/software device. Instead, it's a regulatory submission demonstrating the safety and effectiveness of expanding the indications for an existing material based on clinical literature. Therefore, the information requested will be interpreted within this context.

1. Table of acceptance criteria and the reported device performance

The document doesn't explicitly state "acceptance criteria" in a quantitative sense (e.g., "sensitivity must be >90%"). Instead, the acceptance criterion for the new indication is demonstrating safety and effectiveness for pulpotomy in pediatric patients, supported by existing clinical literature.

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

• Sample Size (Test Set): The filing mentions "completed studies (pulpotomy in 171 pediatric patients covering 408 primary teeth)." This represents the total number of patients and teeth across the summarized clinical literature.
• Data Provenance: The data originates from "independently reviewed medical literature" and "relevant clinical data available in independently reviewed medical literature." One specific reference is provided: Srinivasan, V, et al "Mineral trioxide aggregate in paediatric dentistry" International Journal of Paediatric Dentistry, 19:34-47, 2009. The studies are retrospective as they are existing published literature. The country of origin of the data is not specified but is presumably international given the nature of scientific literature.

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

The document does not specify the exact number of experts involved in establishing the ground truth for the collected literature. It refers to studies conducted by "dental professionals." The provided reference is to an "International Journal of Paediatric Dentistry," suggesting the experts involved would be pediatric dentists or dental professionals specializing in pediatric dentistry. Their specific years of experience are not detailed.

4. Adjudication method for the test set

The document does not describe a specific adjudication method (like 2+1, 3+1, none) for the clinical literature review or for establishing ground truth within those studies. The assessment relies on the conclusions and methods presented in the published scientific literature.

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, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This is not an AI/software device designed to assist human readers. It is a dental material used directly in treatment.

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

N/A. This is a dental material, not an algorithm or software. Its performance is evaluated based on its clinical outcomes after application by a dental professional.

7. The type of ground truth used

The ground truth used in the referenced clinical literature would be clinical outcomes data relevant to pulpotomy procedures, such as:

• Clinical success (e.g., absence of pain, swelling, mobility)
• Radiographic success (e.g., absence of periapical or furcal radiolucency, normal root development)
• Histological findings (if biopsies were taken, though less common for outcome assessment in pulpotomy for regulatory purposes).
• Retention rates of the teeth.

8. The sample size for the training set

N/A. This device does not use an "algorithm" in the traditional sense that requires a training set for machine learning. The clinical experience and data from the 171 pediatric patients (408 teeth) constitute the evidence base, not a training set for an algorithm.

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

N/A. As above, there is no training set for an algorithm. The ground truth for the clinical studies (evidence base) was established through standard clinical and radiographic follow-up protocols within the individual studies published in the medical literature.

Ask a specific question about this device

RAYPEX® 6 is a microprocessor controlled device used for locating the apex.

RAYPEX® 6 is a dental apex locator intended for precise localization of root canal apex. The measurements in RAYPEX® 6 are performed utilizing AC signals at two frequencies - 500 Hz and 8 kHz. The frequencies are alternated and not mixed, eliminating the need for signal mixing and frequency discrimination electronic circuits. The patented signal measuring method utilized in RAYPEX® 6 is based on measurements of RMS (Root Mean Square) level of the signal. Advanced user interface implemented in RAYPEX® 6 is based on high resolution touch TFT (Thin Film Transistor) color graphic display with touch panel. RAYPEX® 6 provides clear real time presentation of endodontic file movement inside the canal. RAYPEX® 6 shows the movement of the file inside the canal from the beginning of the measurements to the end, providing uninterrupted feedback to the dentist. File tracking algorithm enables full-scale display of the file movement during the treatment while Apical Zoom feature enables high-resolution indication of the file advance in pre-apical and apical zones. Large, clearly recognizable graphical readings in Apical Zoom are designed to enable precise control over the file advance matching the individual technique of the dentist. Visual information is accompanied by optional audio signals. The bars shown in the Apical Zoom do not represent actual distance from the apex in mm: they serve as a convenient reference to judge the file tip position in relation to the apex. Operation of RAYPEX® 6 is fully automatic. no manual calibrations or adjustments are required. The measured signal is analyzed and automatic adjustments are made if required. The device may operate within different conditions in the root canal: dry or wet. Built-in Demo mode of RAYPEX® 6 enables easy simulation of all stages of the treatment and is designed to simplify familiarization of the user with the device. Optional verification of proper operation of RAYPEX® 6 is possible through built-in Check mode which enables easy automatic check-up of both the device and its accessories. For practitioner's convenience the following user interface features may be set through RAYPEX® 6 device setup menu: display background color, preferred sound type and display brightness.

Here's an analysis of the acceptance criteria and study detailed in the provided text for the RAYPEX® 6 apex locator:

1. Table of Acceptance Criteria and Reported Device Performance

The submission does not explicitly state numerical acceptance criteria in terms of accuracy metrics (e.g., percentage deviation from true apex within a specific range). Instead, the acceptance criterion for RAYPEX® 6 is based on demonstrating substantial equivalence to its predicate device, the BINGO PRO apex locator (K111474). This means the performance of RAYPEX® 6 must be "equivalent to" or "clinically acceptable" compared to the predicate.

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

• Sample Size: The document does not specify the exact number of "extracted teeth" used for the ex-vivo test. It only states that the test was performed "on extracted teeth."
• Data Provenance: The study was conducted "ex-vivo" (meaning outside a living organism, likely in a laboratory setting using extracted human or animal teeth). The country of origin for the data is not specified. It is a retrospective or prospective study from the perspective of how the test set was collected. Given that it's an ex-vivo test on extracted teeth, it would be considered prospective in the sense that the test was specifically designed and executed for this regulatory submission.

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

The document does not provide details on the number of experts or their qualifications used to establish the ground truth for the extracted teeth. The "ground truth" for an apex locator study typically involves physically measuring the true apex after the teeth have been prepared or sectioned.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (such as 2+1, 3+1, or none) for the test set.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly described or performed. This study focuses on the standalone performance of the device compared to a predicate device, not on how human readers improve with AI assistance.

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

Yes, a standalone study was performed. The "ex-vivo test was performed on extracted teeth" directly evaluating the RAYPEX® 6 apex locator's measurements and comparing them to those of the BINGO PRO apex locator. This assesses the device's ability to locate the apex on its own, without direct real-time human intervention influencing its measurement output.

7. Type of Ground Truth Used

The type of ground truth used is implied to be a physical measurement of the true apex on extracted teeth. While not explicitly stated, ex-vivo apex locator studies typically rely on histological or direct microscopic measurement of the true anatomical apex after the tooth has been prepared or sectioned.

8. Sample Size for the Training Set

The document does not provide any information regarding a training set or its sample size. Apex locators like RAYPEX® 6 are typically engineered based on physical principles (impedance measurement at different frequencies) and do not usually involve machine learning models that require a "training set" in the conventional sense (i.e., for supervised learning). The "microprocessor controlled device" refers to its operational logic, not necessarily an AI algorithm trained on data.

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

Not applicable, as no training set (in the context of machine learning) is described for this device.

Ask a specific question about this device

Anchorage of dentures retained by taper friction and supported by ANKYLOS® implants. Immediate loading of an implant supported prosthesis in an edentulous mandible supported by 4 ANKYLOS® implants of at least 11mm in length and placed interforaminally.

The ANK YLOS® SynCone Abutiment 5° is an endosseous dental implant abutment which provides a platform for prosthetic restoration in conjunction with ANKYLOS™ implants. The subject device incorporates an abutment head with a 5° conical taper and is provided in angulations of 0° 7.5° 15° 22.5° and 30° and with gingival heights ranging from J.5mm . 4.5mm. The abutment is connected to the corresponding iniblant. by a central screw which mates with the internal thread of the implant. The abuiment and the abutment screw are machined from Titanium Alloy (Ti6AL4V ELI) conforming 10 ASTM F136 (Standard Specification for Wrought Titannum-6 Aluminim-4 Vanadium ELI (Extra Low Interstitial' Alloy for Surgical Implant Applications). The tapered SynCone® 5° caps which anchor the SynCone® abutment on the fixed denture are made of Gold Alloy of Titanium conforming to ASTM F67 (Standard Specification for Unalloyed Titanium, for Surgical Implant Applications). The SynCone® abutments feature a reatining screw design which allows for the rotation of the abutment head after attachment to the implant in order to achieve rotational alignment for all of the abutments used in the prosthetic restoration.

Here's an analysis of the provided text regarding the acceptance criteria and supporting studies for the ANKYLOS® SynCone® Abutment 5°:

Acceptance Criteria and Study Details for ANKYLOS® SynCone® Abutment 5°

Based on the provided 510(k) summary, the device's acceptance criteria and the studies performed focus on demonstrating substantial equivalence to predicate devices. The primary criteria revolve around material composition, design, and performance characteristics compared to existing, legally marketed products.

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not explicitly state the specific numerical sample sizes for the test sets in the non-clinical performance data (fatigue testing, pull force testing). It mentions "Representative fatigue testing" and "Pull force testing."

The data provenance is non-clinical bench testing, meaning it's laboratory-generated data, not from human subjects. Therefore, country of origin and retrospective/prospective designations for human data are not applicable here.

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

This section is not applicable. The ground truth for this type of submission (demonstrating substantial equivalence through non-clinical bench testing) is defined by established international standards (like ISO 14801) and direct comparison to the performance characteristics of legally marketed predicate devices. It does not involve expert adjudication of human clinical data.

4. Adjudication Method for the Test Set

This section is not applicable as the evaluation relies on objective measurements from bench testing following established standards and direct comparison to predicate device performance. No human adjudication of results is described.

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

No, an MRMC comparative effectiveness study was not done. This type of study is relevant for diagnostic devices where human readers interpret medical images or data. The ANKYLOS® SynCone® Abutment 5° is a dental implant abutment, and its evaluation for this 510(k) submission relied on non-clinical performance data.

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

This section is not applicable. The device is a physical medical device (an implant abutment), not an algorithm or AI system. Its performance is inherent in its physical and mechanical properties, evaluated through bench testing, not through an algorithm's output.

7. The Type of Ground Truth Used

The ground truth used for verifying the device's performance is established engineering and material science standards and metrics, and direct comparative performance against legally marketed predicate devices.

Specifically:

• ISO 14801: Dynamic fatigue test for endosseous dental implants.
• ASTM F136 and ASTM F67: Standard specifications for titanium alloys, defining acceptable material properties.
• Performance of predicate devices: The established and accepted performance of the ANKYLOS SynCone® Abutinents 4º and 6° (K041509) and Angled ANKYLOS® Balance Base Abutments (K122268) serve as the benchmark for equivalence.

8. The Sample Size for the Training Set

The concept of a "training set" is not applicable here. A training set is used in machine learning to teach an algorithm. This submission is for a physical medical device, not an AI/ML algorithm.

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

This section is not applicable for the same reasons as point 8.

Ask a specific question about this device