Search Results

Abutment Design is intended as an aid to the restoration in partially or fully edentulous mandibles and maxillae. Abutment Design is intended for use by a dental practitioner or dental laboratory staff for designing the patient specific component of a two-piece, or hybrid dental implant abutment. The resulting abutment design is intended to be used by the manufacturer of an endosseous dental implant abutment to create the final device.

The Abutment Design software receives scan data containing topographical characteristics of real teeth, dental impressions, or stone models. The software provides the user with the ability to create matching endosseous dental implant abutments using computer aided design.

The Abutment Design is restricted to be used with 510(k) cleared abutment systems, and the design output from Abutment Design (the patient specific part of the abutment) must be manufactured according to the instruction of the selected abutment system.

The Abutment Design software includes design parameters from the 510(k) cleared abutment systems such as implant type, maximum and minimum dimensions (e.g., abutment post height, gingival height, angulation, gingival margin diameter, etc.). The design parameters, provided by abutment system manufacturers, for an abutment system are available via a 3Shape server when documentation of the 510(k) clearance of said implant system is presented to 3Shape.

Abutment Design has no patient contact being a software only device.

I am sorry, but the provided text only discusses the comparability of "Abutment Design" software to a predicate device, and includes general statements about nonclinical testing for verification and validation without providing specific acceptance criteria or study details that would allow me to populate the requested table and answer the detailed questions about sample sizes, ground truth, expert qualifications, and specific study designs.

Therefore, I cannot fulfill your request for the specific information regarding acceptance criteria and study details.

Ask a specific question about this device

3Shape Splint Design for splints and mouthguards is intended for use as a medical front-end device providing tools for systematic inspection, detailed analysis, treatment simulation and virtual appliance design based of 3D models of the patient's dentition before the start of an orthodontic treatment.

The use of Splint Design software requires the user to have the necessary training and domain knowledge in the practice of orthodontics, as well as to have received a dedicated training in the use of the software.

The Splint design software for splints and mouthquards/nightquards is a software system used for the virtual planning of orthodontic treatments by simulating jaw movements, and design of orthodontic appliances based on 3D scanned orthodontic models.

The realization of the above-mentioned orthodontic appliances is done using splint workflow which supports

• Direct production using 3D printer or milling machines with FDA cleared or . listed materials included in the splint workflow.
  The actual production of appliances is done by the user and it is under their control and responsibility.

3Shape Splint Design has no patient contact being a software only device.

I am sorry, but the provided text does not contain the detailed information needed to answer your request about acceptance criteria and the study proving the device meets them. The document is a 510(k) summary for a medical device (3Shape Splint Design) stating that it is substantially equivalent to a predicate device.

Specifically, the text does not include:

1. A table of acceptance criteria and reported device performance.
2. Details on sample size, data provenance, or the nature of any test set used.
3. Information about experts used to establish ground truth or their qualifications.
4. Adjudication methods.
5. A multi-reader multi-case (MRMC) comparative effectiveness study, nor any effect size for human readers with and without AI assistance.
6. Information about a standalone (algorithm only) performance study.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.).
8. The sample size for the training set.
9. How the ground truth for the training set was established.

The document only states that "Software, hardware, and integration verification and validation testing was performed" and "All test results have been reviewed and approved, showing the Ortho System™ to be substantially equivalent to the primary predicate device." It also explicitly states that "Clinical testing is not a requirement and has not been performed."

Therefore, I cannot provide the requested information based on the given input.

Ask a specific question about this device

Ortho System™ for dental retainers and dental cast for sequential aligners is intended for use as a medical front-end device providing tools for management of orthodontic models, systematic inspection, detailed analysis, treatment simulation and virtual appliance design options based on 3D models of the patient's dentition before the start of an orthodontic treatment.

The use of the Ortho System™ requires the user to have the necessary training and domain knowledge in the practice of orthodontics, as well as to have received a dedicated training in the use of the software.

3Shape's Ortho System™ for dental retainers and dental cast for sequential aligners is a software system used for the management of 3D scanned orthodontic models of the patients, orthodontic diagnosis by measuring, analysing, inspecting and visualize 3D scanned orthodontic models, virtual planning of orthodontic treatments by simulating tooth movements, and design of orthodontic appliances based on 3D scanned orthodontic models.

The realization of the orthodontic appliances are done using appliance workflows templates which either supports

• . (Retainers and dental casts for sequential aligners) Thermoforming FDA cleared or listed material on a dental cast. The cast is designed and produced by machines and materials included in the appliance workflow template
• (Retainers) Direct production using 3D printer or milling machines with FDA . cleared or listed materials included in the appliance workflow template.

The Ortho System™ appliance workflow templates with approved machines is available through a dedicated download centre by the software. The instruction for use contains instructions for configuration of additive printers.

The actual production of appliances/casts and any thermoforming is done by the user and is under their control and responsibility – only materials specified in the manual must be used to produce the final appliance.

The Ortho System™ has no patient contact being a software.

The provided text is a 510(k) summary for a medical device called "Ortho System™" from 3Shape A/S. It primarily focuses on demonstrating substantial equivalence to a predicate device rather than detailing specific acceptance criteria and performance data for a new AI/algorithm-based device.

Therefore, the document does not contain the information required to answer the questions regarding acceptance criteria, study details, expert involvement, and ground truth establishment.

Here's why and what's missing:

• No Acceptance Criteria or Performance Table: The document states that "All test results have been reviewed and approved, showing the Ortho System™ to be substantially equivalent to the reference devices," but it does not provide a table of acceptance criteria or actual performance metrics (e.g., accuracy, sensitivity, specificity, AUC) like one would expect for an AI/algorithm-based device clearance.
• No Mention of AI/Algorithm Study: The "Ortho System™" is described as a "medical front-end device providing tools for management of orthodontic models, systematic inspection, detailed analysis, treatment simulation and virtual appliance design options..." It's a software system, but not explicitly stated as an AI/ML algorithm that predicts or classifies. The review is based on "software, hardware, and integration verification and validation testing," and a comparison of features with a predicate device.
• No ML Specifics: There is no mention of training sets, test sets, ground truth establishment, expert adjudication, or MRMC studies, which are typical for AI/ML device submissions. The "Clinical Testing" section explicitly states, "Clinical testing is not a requirement and has not been performed."

In summary, the provided FDA 510(k) clearance document for Ortho System™ does not contain the detailed study information, acceptance criteria, or performance data that would be relevant for an AI/ML powered device, as it seems to be cleared based on substantial equivalence to an existing software device with similar functionalities and technical characteristics, rather than a novel AI algorithm requiring specific performance validation metrics.

Ask a specific question about this device

The 3Shape Ortho System™ is intended for use as a medical front-end device providing tools for management of orthodontic models, systematic inspection, detailed analysis, treatment simulation and virtual applians (Custom Metal Bands, Export of Models, Indirect Bonding Transfer Media) based on 3D models of the patient's dentition before the start of an orthodontic treatment. It can also be applied during the treatment to inspect and analyze the progress of the treatment. It can be used at the treatment to evaluate if the outcome is consistent with the planned/desired treatment objectives.

The use of the Ortho System™ requires the user to have the necessary training and domain knowledge in the practice of orthodontics, as well as to have received a dedicated training in the use of the software.

3Shape's Ortho System™ is a software system used for the management of 3D scanned orthodontic models of the patients, orthodontic diagnosis by measuring, analysing, inspecting and visualize 3D scanned orthodontic models, virtual planning of orthodontic treatments by simulating tooth movements, virtual placement of orthodontic brackets on the 3D models and design of orthodontic appliances based on 3D scanned orthodontic models, including transfer methods for indirect bonding of brackets. Output includes only Export Model (also called dental casts), Custom Metal Bands (also called metal bands), and Indirect Bonding Transfer Trays (also called orthodontic bracket placement trays). All devices are to be fabricated from FDA cleared materials by third party under the responsibility of the user.

The device has no patient contact.

The provided document does not contain information about specific acceptance criteria, a study proving the device meets those criteria, or a detailed breakdown of test set characteristics like sample size, data provenance, expert ground truth, or adjudication methods.

This document is a 510(k) summary for the 3Shape Ortho System™, which primarily focuses on demonstrating substantial equivalence to a predicate device (K152086). The nonclinical testing section states that "Software, hardware, and integration verification and validation testing was performed" and "All test results have been reviewed and approved, showing the Ortho System™ to be substantially equivalent to the primary predicate device." However, it does not provide details of these tests or their results.

Therefore, I cannot populate the requested tables and information.

Here's what I can extract based on the available text:

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

   • Not provided. The document states that testing was performed to show substantial equivalence, but it does not specify performance metrics or acceptance criteria.

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. The document mentions "verification and validation testing" but does not specify the sample size of any test sets or the origin/type of data used.

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 provided. There is no mention of expert-established ground truth or the involvement of experts in evaluating the device's performance.

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

   • Not provided.

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 MRMC study was done or reported. The document states, "Clinical testing is not a requirement and has not been performed." This device is software only for orthodontic planning, not an AI diagnostic tool requiring human reader studies.

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

   • Not explicitly detailed for performance metrics. The document implies standalone testing was performed as part of "software, hardware, and integration verification and validation testing," but it does not provide specific performance results for the algorithm itself.

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

   • Not provided.

8. The sample size for the training set

   • Not applicable / Not provided. This document describes a software system, not a machine learning model that would typically have a "training set" in the context of deep learning. It's a "front-end device providing tools."

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

   • Not applicable / Not provided. (See point 8)

Ask a specific question about this device

3Shape Ortho System™ for dental retainers is intended for use as a medical front-end device providing tools for management of orthodontic models, systematic inspection, detailed analysis, treatment simulation and virtual appliance design based on 3D models of the patient's dentition before the start of an orthodontic treatment.

The use of the Ortho System™ requires the user to have the necessary training and domain knowledge in the practice of orthodontics, as well as to have received a dedicated training in the use of the software.

3Shape's Ortho System™ is a software system used for the management of 3D scanned orthodontic models of the patients, orthodontic diagnosis by measuring, analyzinq, inspecting and visualize 3D scanned orthodontic models, virtual planning of orthodontic treatments by simulating tooth movements, virtual placement of orthodontic brackets on the 3D models and design of orthodontic appliances based on 3D scanned orthodontic models. Output includes Dental Retainers. All devices are to be fabricated from FDA cleared or listed materials currently available in the software.

The device has no patient contact.

Here's an analysis of the provided text regarding the acceptance criteria and the study proving the device meets them:

The document provided is a 510(k) summary for the 3Shape Ortho System™ software. It is a premarket notification to the FDA to demonstrate substantial equivalence to a legally marketed predicate device.

Key takeaway: This document does not describe a study that establishes acceptance criteria for performance metrics (e.g., sensitivity, specificity, accuracy) using a defined test set with human expert adjudicated ground truth. Instead, it focuses on demonstrating substantial equivalence to a predicate device through a comparison of features, technical characteristics, and intended use, along with software verification and validation.

Therefore, many of the requested points cannot be directly extracted from this document as the type of study described (e.g., clinical performance study with AI assistance, standalone algorithm performance) was not performed.

Here's how to address your specific points based on the provided text:

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

The document does not specify quantitative acceptance criteria for device performance (e.g., accuracy, sensitivity, specificity) in the way one would for an AI-driven diagnostic or measurement device. The "performance" demonstrated here is primarily about functional equivalence and safety/effectiveness relative to a predicate device.

The closest to "acceptance criteria" are implied by the comparison table of features and the statement "All test results have been reviewed and approved, showing the Ortho System™ to be substantially equivalent to the predicates."

Implied "Acceptance Criteria" (Substantial Equivalence to Predicate):

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 states "Clinical testing is not a requirement and has not been performed." Therefore, there is no specific test set of patient data used for performance evaluation in the context of diagnostic accuracy, sensitivity, etc.
• The nonclinical testing mentioned is "Software, hardware, and integration verification and validation testing," which refers to standard software quality assurance and testing procedures on the software itself, not on a dataset of patient cases.
• Data Provenance: Not applicable as a clinical test set based on patient data was not used.

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 clinical test set with ground truth established by experts was used for performance evaluation in this 510(k) submission.

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

• Not applicable. No clinical test set.

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. The document explicitly states "Clinical testing is not a requirement and has not been performed." This type of study would fall under clinical testing.

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

• No. This type of performance study was not conducted as "Clinical testing is not a requirement and has not been performed." The device is a software suite providing tools for orthodontists, implying a human-in-the-loop operation for diagnosis and planning.

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

• Not applicable. Since no clinical performance study was conducted on patient data to evaluate diagnostic or measurement accuracy, no "ground truth" for such purposes was established or used. The ground truth for the software testing would be the expected functional behavior and calculations according to the software requirements and design specifications.

8. The sample size for the training set

• Not applicable. The 3Shape Ortho System™ software, as described, appears to be a rule-based or calculative software tool for orthodontic planning, not a machine learning or AI model that requires a "training set" in the sense of a dataset of labeled patient examples to learn from. Its "scientific concept" is described as applying "digital imaging tools."

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

• Not applicable. As it does not appear to be a machine learning model, there is no "training set" and therefore no need to establish ground truth for it.

Ask a specific question about this device

3Shape Ortho System™ is intended for use as a medical front-end device providing tools for management of orthodontic models, systematic inspection, detailed analysis, treatment simulation and virtual appliance design of Splints, Mouthguards / Nightguards based on 3D models of the patient's dentition before the start of an orthodontic treatment.

The use of the Ortho System™ requires the user to have the necessary training and domain knowledge in the practice of orthodontics, as well as to have received a dedicated training in the use of the software.

Not Found

I am sorry, but the provided document does not contain information about the acceptance criteria for a device, nor does it describe a study that proves a device meets such criteria. The document is an FDA 510(k) clearance letter for the 3Shape Ortho System™, indicating that the device has been found substantially equivalent to a legally marketed predicate device.

It includes:

• Device Name: 3Shape Ortho System™
• 510(k) Number: K161884
• Indications for Use: "3Shape Ortho System™ is intended for use as a medical front-end device providing tools for management of orthodontic models, systematic inspection, detailed analysis, treatment simulation and virtual appliance design of Splints, Mouthguards / Nightguards based on 3D models of the patient's dentition before the start of an orthodontic treatment." It also states, "The use of the Ortho System™ requires the user to have the necessary training and domain knowledge in the practice of orthodontics, as well as to have received a dedicated training in the use of the software."
• Regulatory Class: Unclassified
• Product Code: MOC
• Type of Use: Prescription Use

The letter from the FDA confirms market clearance but does not detail the specific performance acceptance criteria or the studies conducted to demonstrate those criteria. To find this information, you would typically need to consult the full 510(k) submission available via the FDA's website, or a more detailed technical document from 3Shape A/S.

Ask a specific question about this device

The 3Shape Abutment Designer Software is intended as an aid to the restoration of chewing function in partially or fully edentulous mandibles and maxillae. The 3Shape Abutment Designer is intended for use by a dental practitioner or dental laboratory staff for designing the patient specific component of a two-piece, or hybrid dental implant abutment. The single or multi-unit abutment design is intended to be used by the manufacturer of an endosseous dental implant abutment to create the final device.

The 3Shape Abutment Designer™ Software receives scan data containing topographical characteristics of real teeth, dental impressions, or stone models. The software provides the user with the ability to create matching endosseous dental implant abutments using computer aided design. The output of the device is a computer file containing the abutment(s) in digital form which can be used by manufacturers that hold an implant abutment 510(k) or are milling per the specific instructions provided by the holder of a 510(k) marketing clearance for a patient specific implant abutment. The 3Shape Abutment Designer Software output is restricted in the U.S. to be manufactured by a holder of an implant abutment 510(k) or milled per the specific instructions provided by the holder of a 510(k) marketing clearance for a patient specific implant abutment. The 3Shape Abutment Designer™ Software can be run on properly configured "off-the-shelf" PC hardware running Microsoft® Windows and using a standard keyboard and mouse. The 3Shape Abutment Designer™ Software requires the loading of implant libraries, which includes information such as implant type, maximum and minimum dimensional parameters for abutments, etc., created by separate abutment manufacturers and cleared by the FDA. In the US, the Implant Libraries are obtained via a 3Shape server after demonstration to 3Shape of the FDA clearance of the Implant Library.

The provided text describes the 3Shape Abutment Designer™ Software, its intended use, and the nonclinical testing performed for its 510(k) submission. However, it does not provide specific details on acceptance criteria or a detailed study proving the device meets those criteria, as typically found in a clinical study report.

The text focuses on the software's substantial equivalence to a predicate device (Sirona Dental CAD/CAM System) by comparing their intended use, technological characteristics, and software output. The "Nonclinical Testing" section broadly mentions "approved acceptance criteria" but without enumerating them or describing a specific study report that would contain the requested details.

Therefore, many of the requested elements cannot be extracted from the provided text.

Here's a breakdown of what can be inferred or extracted, and what is missing:

1. Table of acceptance criteria and the reported device performance

Missing: Specific, quantifiable acceptance criteria (e.g., accuracy metrics, specific error rates, precision targets) are not detailed. The actual performance outcome against numerical targets for these acceptance criteria is also not provided.

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

Missing: The text does not specify the sample size used for any test set or the data provenance (e.g., country of origin, retrospective/prospective nature of the data). "Test set" in this context refers to the data used for the "verification and validation testing" mentioned.

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

Missing: This information is not provided. The testing described is primarily software verification and validation, not a clinical study involving expert ground truth establishment for diagnostic or treatment efficacy.

4. Adjudication method for the test set

Missing: This information is not provided.

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

Missing: No MRMC comparative effectiveness study is mentioned. The device is software for designing abutments, not an AI for diagnosis or interpretation that would typically involve human readers.

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

The device is a standalone software component ("algorithm only" in the sense that it automates design based on input). The "Device Description" states it receives scan data and provides digital output. The "Nonclinical Testing" section confirms "Software, hardware, and integration verification and validation testing was performed." This implies standalone testing of the software's functionality.

However, specific performance metrics for this standalone functionality are not detailed.

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

Missing: The text does not explicitly state the type of "ground truth" used for its verification and validation. Given the nature of the software (CAD for dental abutments), the "ground truth" likely refers to established engineering specifications, design rules, and possibly simulated or physical models that conform to dental anatomical and functional requirements. It is not clinical "ground truth" in the diagnostic sense (like pathology or outcomes data).

8. The sample size for the training set

Missing: This is not applicable in the typical sense of a machine learning "training set." The 3Shape Abutment Designer™ Software appears to be a rule-based CAD software, not a machine learning algorithm that is "trained" on a dataset. It "requires the loading of implant libraries" which contain design information cleared by the FDA, but these are not "training sets."

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

Missing: As per point 8, a "training set" in the machine learning context is not applicable here. The "implant libraries" used by the software are based on information from actual implant manufacturers, cleared by the FDA, which function as pre-defined specifications and constraints rather than a statistical training dataset.

Ask a specific question about this device

3Shape Ortho System™ is intended for use as a medical front-end device providing tools for management of orthodontic models, systematic inspection, detailed analysis, treatment simulation and virtual appliance design options (Custom metal bands, Export of Models, Indirect Bonding Transfer Media) based on 3D models of the patient's dentition before the start of an orthodonic treatment. It can also be applied during the treatment to inspect and analyze the progress of the treatment It can be used at the end of the treatment to evaluate if the outcome is consistent with the planned the amment objectives.

The use of the Ortho System™ requires the user to have the necessary training and domain knowledge in the practice of orthodontics, as well as to have received a dedicated training in the use of the software.

3Shape's Ortho System™ is a software system used for the management of 3D scanned orthodontic models of the patients, orthodontic diagnosis by measuring, analyzinq, inspecting and visualize 3D scanned orthodontic models, virtual planning of orthodontic treatments by simulating tooth movements, virtual placement of orthodontic brackets on the 3D models and design of orthodontic appliances based on 3D scanned orthodontic models, including transfer methods for indirect bonding of brackets. Output includes only Export Model (also called dental casts), Custom Metal Bands (also called metal bands), and Indirect Bonding Transfer Trays (also called orthodontic bracket placement trays). All devices are to be fabricated from FDA cleared materials.

The device has no patient contact.

The provided FDA 510(k) summary for the 3Shape Ortho System™ does not contain acceptance criteria or a study proving the device meets said criteria in the traditional sense of a performance study with defined metrics (sensitivity, specificity, accuracy, etc.) against a specific ground truth.

Instead, this submission focuses on demonstrating substantial equivalence to predicate devices through a comparison of intended use, technical characteristics, and nonclinical testing that confirms the software acts as intended.

Here's a breakdown of the requested information based on the provided text, highlighting what is implicitly or explicitly stated and what is absent:

1. Table of Acceptance Criteria and Reported Device Performance

As noted, the document does not present a table of specific quantitative acceptance criteria (e.g., "accuracy > 95%") nor does it report performance against such criteria. The "performance" assessment is primarily qualitative, focusing on whether the device's features match or are equivalent to the predicate devices.

| Acceptance Criteria Category | Specific Acceptance Criteria (from document) | Reported Device Performance (from document) |
|------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Functional Equivalence | The device must demonstrate the same intended uses and technical characteristics as predicate devices. | The 3Shape Ortho System™ Software is found to have the same intended use as the primary predicate OrthoCAD iQ (K082207) and similar technical characteristics to both OrthoCAD iQ and reference predicate Dolphin Imaging (K110430) across supported anatomic areas, patient/case management, study material collection/alignment/measurement/analysis, treatment simulation, and virtual appliance design. A detailed feature comparison table is provided (Page 5). |
| Safety and Effectiveness | The device must be as safe and effective as the predicate devices. | Based on nonclinical testing (software, hardware, and integration V&V) and comparison to predicates, the Ortho System™ is found to be "as safe and effective as the predicate devices." (Page 7). Risk management procedures related to device hazards were also validated. |
| Software Verification and Validation (V&V) | All verification and validation activities should be performed according to FDA guidance specific to software in medical devices. | Software, hardware, and integration V&V testing was performed according to the "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (Issued on May 11, 2005). All test results were reviewed and approved. |

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

• Sample Size: Not explicitly stated as a separate "test set" in the context of clinical performance evaluation. The "nonclinical testing" involved software, hardware, and integration V&V, which typically uses various test cases and scenarios rather than a dataset of patient cases for clinical performance evaluation.
• Data Provenance: Not mentioned. Since it's a nonclinical V&V, synthetic data or internal test data would likely be used, but this is not specified. It's not a retrospective or prospective study on patient data.

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. As "clinical testing is not a requirement and has not been performed" (Page 7), there was no need for expert ground truth establishment for a patient-level test set.

4. Adjudication Method for the Test Set

• This information is not provided as there was no patient-level test set requiring ground truth 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

• A MRMC comparative effectiveness study was not performed. The document explicitly states: "Clinical testing is not a requirement and has not been performed." (Page 7). The device is a "medical front-end device providing tools" rather than an AI-driven diagnostic aid for human readers.

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

• A standalone performance study in the sense of accuracy metrics (sensitivity, specificity, etc.) was not performed. The V&V testing ensures the software functions as designed (e.g., measurements are calculated correctly, models display properly), but not against a "ground truth" to measure diagnostic or predictive performance. The device is a tool to be used by a trained orthodontist.

7. The Type of Ground Truth Used

• For the nonclinical V&V, the "ground truth" would be the expected output or behavior of the software based on its design specifications and requirements. This is not explicitly detailed but is intrinsic to software testing. There's no use of expert consensus, pathology, or outcomes data, as no clinical study was conducted.

8. The Sample Size for the Training Set

• This device is described as a "software system" programmed in Delphi that applies "digital imaging tools." While it mentions "encrypted libraries of the bracket geometry provided by the manufacturers," this refers to pre-programmed data, not a "training set" for a machine learning model. There is no mention of a training set in the context of machine learning, as this does not appear to be an AI/ML device in the modern sense (e.g., deep learning classification).

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

• Since there's no explicit mention of a training set or machine learning, this information is not applicable or provided.

Ask a specific question about this device