Search Results

RAYDENT SW is a software designed to assist dental professionals in planning patient treatment devices. The software performs simulations based on patient images, allowing reference to treatment plans, and is used as a tool to design treatment devices based on 3D mesh data. Treatment devices include prosthetic devices (Veneer, Crown, Bridge, In/Onlay) and orthodontic devices (Clear Aligner).

To use RAYDENT SW, users must have the necessary education and domain knowledge in orthodontic practice and receive dedicated training in the use of the software.

RAYDENT is a software that provides tools to simulate treatment plans based on patient images generated by compatible scanners and design treatment devices based on appropriate three-dimensional images. It allows dental offices to acquire patient data in conjunction with software on compatible imaging equipment and utilize the acquired images to create treatment plans and devices for skilled dentists and oral and maxillofacial specialists.

The document K233625 is a 510(k) Premarket Notification for the device "RAYDENT SW," a software designed to assist dental professionals in planning patient treatment devices. As such, the document provides information on the device's intended use, comparison to predicate devices, and a summary of performance testing. However, it does NOT include detailed information about acceptance criteria or a specific study proving the device meets those criteria, particularly not in the context of an AI/ML-enabled medical device performance study.

The document states that RAYDENT SW includes "Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices: YES" in its comparison table (Page 7). However, the "Performance Testing" section (Page 9) does not describe an AI/ML-specific performance study with acceptance criteria, sample sizes, ground truth establishment, or human-in-the-loop evaluation. It merely states that "Software, hardware, and integration and validation testing was performed in accordance with the FDA Guidance Document 'Guidance for the Content of Premarket Submissions for Device Software Functions' and 'Guidance for the Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions'." It then concludes that "All test results have been reviewed and approved, showing the RAYDENT SW to be substantially equivalent to the predicate devices."

Therefore, based on the provided text, I cannot extract the information required to answer your prompt about the acceptance criteria and a study proving the device meets those criteria in the context of AI/ML performance.

To answer your specific points:

1. A table of acceptance criteria and the reported device performance: Not found in the provided document. The document mentions general validation testing but no specific performance metrics or acceptance criteria for an AI component.
2. Sample sized used for the test set and the data provenance: Not found.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not found.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not found.
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 found. The document explicitly states "Clinical testing is not a requirement and has not been performed" (Page 9), implying no such MRMC study was conducted.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not explicitly detailed for an AI component. The general performance testing is mentioned, but without specifics for the AI.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not found.
8. The sample size for the training set: Not found.
9. How the ground truth for the training set was established: Not found.

The document focuses on substantiating equivalence primarily through comparison of indications for use, technological characteristics, and general software/hardware validation, rather than an in-depth AI/ML performance study.

Ask a specific question about this device

iOrtho is intended for use as a medical front-end device providing tools for management of orthodontic cases, systematic inspection, detailed analysis, treatment simulation and virtual applians (Export of Models, Indirect Bonding Transfer Media, Sequential aligners) 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 end of the treatment to evaluate if the outcome is consistent with the planned/desired treatment objectives.

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

iOrtho (hereafter referred to as "Proposed Device") includes modifications to the currently marketed software included in K203688, cleared October 8, 2021 (hereafter referred to as "Reference Device"). The Proposed Device is an orthodontic appliance design and treatment simulation software is for use by dental professionals to aid in diagnosis and design solutions for patients. Digital scans (3D) of a patient's dentition can be loaded into the software and the dental professional can then create treatment plans for each individual patient and their needs. The system can be used to fabricate 3D dental models using standard stereolithographic (STL) files for use in 3D printers. These models can then be used as a template for thermoforming aligners or retainers by Angel Align technicians.

The provided text is a 510(k) summary for the iOrtho device. It describes the device, its intended use, and compares it to predicate and reference devices to demonstrate substantial equivalence. However, it does not contain information about acceptance criteria or a specific study that proves the device meets those criteria in detail.

The summary states:
"Utilizing FDA Guidance document "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (issued May 11, 2015) the Proposed Device, iOrtho underwent appropriate integration, verification, and validation testing. The software passed the testing and performed per its intended use."

And:
"The software has been designed, integrated, verified, and validated in accordance with IEC 62304-Medical device software – software life cycle processes."

These statements confirm that testing was performed and passed, and that it followed relevant standards and guidance. However, the document does not provide the specific acceptance criteria, the detailed results (e.g., in a table), sample sizes, ground truth establishment methods, or expert qualifications that are typically found in a clinical or performance study summary.

Therefore, I cannot fulfill your request for a table of acceptance criteria and reported device performance, or details about the study, as this information is not present in the provided document. The 510(k) summary focuses on demonstrating substantial equivalence through comparison of specifications and general statements about passing validation testing, rather than presenting a detailed performance study with specific metrics and methodologies.

Ask a specific question about this device

The AUTOLIGN 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 (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 end of the treatment to evaluate if the outcome is consistent with the planned/desired treatment objectives. The use of the AUTOLIGN 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 AUTOLIGN is stand-alone software which utilizes images of the patient's intraoral anatomy from intraoral cameras and/or desktop laboratory scanners to create a 3D virtual dental model that can be used in the same manner as a traditional physical dental model. AUTOLIGN facilitates the segmentation and editing of the 3D virtual digital model as well as analysis which can be used in secondary orthodontic treatment planning. The software allows for measurement- including Bolton analyses. The models and analysis produced by the proposed Software can be exported to an orthodontic laboratory or directly to orthodontic appliance manufacturers for use in orthodontic treatment planning and design of orthodontic appliances. The material used for vacuum pressing (thermoforming) the final device appliances of sequential aligners on the production cast is DURAN®, but those which satisfy all the requirements specified on the Autoling User Manual can also be used.

The provided text describes the AUTOLIGN device and its comparison to predicate devices, but it does not contain specific acceptance criteria, a detailed study proving the device meets those criteria, or the requested information about sample sizes, ground truth establishment, or clinical study details.

The document is a 510(k) summary for the AUTOLIGN device, which is a software tool for orthodontic treatment planning and design. Its purpose is to demonstrate substantial equivalence to legally marketed predicate devices, not to present a detailed clinical validation study with specific performance metrics.

Here's what can be extracted and what is missing based on your request:

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

• Acceptance Criteria: Not explicitly stated in terms of quantitative performance metrics for the device itself (e.g., accuracy, sensitivity, specificity for specific measurements or analyses). The "acceptance" is implicitly that the software functions as intended and is as safe and effective as the predicate device.
• Reported Device Performance: The document only states that "The software passed the testing and performed per its intended use." No specific performance metrics or quantitative results are provided.

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 mentioned.
• Data Provenance: Not mentioned.

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

• Number of Experts: Not mentioned.
• Qualifications of Experts: Not mentioned.
• Ground Truth Establishment: Not mentioned.

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

• Not mentioned.

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

• An MRMC study is not mentioned. The study described is a non-clinical software verification and validation, along with a comparison to predicate devices. There is no mention of human readers or AI assistance in a comparative effectiveness context.

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

• The document implies standalone testing as it states "The AUTOLIGN underwent software, hardware, integration, verification and validation testing... The software passed the testing and performed per its intended use." However, specific standalone performance metrics (e.g., algorithm accuracy for segmenting teeth, or measuring arch length) are not provided. The device itself is described as "stand-alone software."

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

• Not mentioned.

8. The sample size for the training set

• Not mentioned, as there is no specific mention of a machine learning model or training set in the context of the device's validation.

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

• Not mentioned (for the same reason as point 8).

Summary of what is available from the text:

• Device Name: AUTOLIGN
• Regulatory Status: Class II medical device (K192847)
• Intended Use: Front-end device for managing orthodontic models, systematic inspection, detailed analysis, treatment simulation, and virtual appliance design based on 3D models of patient dentition.
• Non-clinical Tests: Software, hardware, integration, verification, and validation testing were performed according to FDA guidance.
• Result of Non-clinical Tests: "The software passed the testing and performed per its intended use."
• Predicate Device Comparison: The report extensively compares the AUTOLIGN's indications for use and technological characteristics to three predicate devices (Ortho System™, Orchestrate 3D, CEREC Ortho Software) to establish substantial equivalence.

In conclusion, the provided text focuses on regulatory approval through substantial equivalence to predicate devices and general software validation, rather than a detailed clinical study with quantitative acceptance criteria and performance metrics for the AUTOLIGN itself.

Ask a specific question about this device