Search Results

NemoCast 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 treatment. It can be used at the end of the treatment to evaluate if the outcome is consistent with the planned dectives. It can also be applied during the treatment to inspect and analyze the progress of the treatment.

The use of the NemoCast 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.

NemoCast is a software system used for the management of 3D scanned orthodontic models of the patients, orthodontic diagnosis by measuring, analyzing, 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 STL Models (also called dental casts) for thermoforming aligners, STL files for direct printing aligners and Indirect Bonding Transfer Trays (also called orthodontic bracket placement trays). The device has no patient contact.

This document (K232549) is a 510(k) premarket notification for the device "NemoCast," an orthodontic software. It establishes substantial equivalence to existing predicate devices, particularly 3Shape Ortho System™ (K152086) and a previous version of NemoCast (K193003).

The key takeaway is that this is primarily a software validation and substantial equivalency claim, rather than a study proving new clinical performance. The manufacturer is demonstrating that their current software performs similarly to a previously cleared version and a predicate device.

Here's an analysis of the provided information regarding acceptance criteria and performance study:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a "table of acceptance criteria" with corresponding "reported device performance" in the typical format of a clinical study summary. Instead, the acceptance criteria are implicitly met by demonstrating substantial equivalence to predicate devices. The "reported device performance" is the functionality of NemoCast itself, and the "study" is the comparison against the predicate devices.

The "Comparison of Intended Use and Technological Characteristics with the reference Device" table (pages 7-8) serves as the primary evidence of meeting "acceptance criteria" for substantial equivalence. It lists various features and functions, and for each, it aims to show "None" under "Differences" or a difference that does not affect safety and effectiveness.

Here's a condensed version of how that table functions as a de facto "acceptance criteria" and "performance report":

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

The document states: "The performance testing remains unchanged from the company's own reference device submission, NemoCast K193003. The performance testing for the subject device is being leveraged from the company's own reference device including: design verification and validation testing."

This implies that the sample size and data provenance for the current 510(k) submission are not new. They are relying on previous testing. The document does not explicitly state the sample size (number of cases/patients) or the data provenance (e.g., country of origin, retrospective/prospective) for the test set. This information would typically be found in the original K193003 submission or internal validation reports, which are not detailed here.

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

This information is not provided in the document. As this is a software substantial equivalence submission leveraging previous testing, details about the ground truth establishment for the test set (number and qualifications of experts) are not specified here.

4. Adjudication method for the test set

This information is not provided in the document.

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 demonstrating improved human reader performance with AI assistance was not done for this submission. The "NemoCast" device is described as a "medical front-end device providing tools for management... analysis, treatment simulation, and virtual appliance design." It is a planning and design software, not an AI-assisted diagnostic tool that would typically involve a human-in-the-loop MRMC study for assessing reader improvement.

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

The document mentions "The software is thoroughly tested in accordance with a documented test plan. This test plan is derived from the specifications and ensures that all controls and features are functioning properly. The software is validated together with end-users." This general statement indicates functional and validation testing that would assess standalone performance (software functioning as intended). However, specific quantifiable metrics of "algorithm-only" performance (e.g., accuracy of automatic measurements) are not reported in this summary. The focus is on the functional equivalence of the tools provided within the software.

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

The document does not explicitly state the type of "ground truth" used for the underlying validation of the software's measurements or simulations. Given the nature of orthodontic planning software, ground truth for features like measurements or segmentations would typically be established through:

• Expert consensus: Manual measurements or segmentations performed by experienced orthodontists on 3D models.
• Physical measurements/phantom data: Validation against known physical dimensions or phantom models.

However, these details are not provided in this 510(k) summary.

8. The sample size for the training set

This information is not provided. As this is a software product, not necessarily one relying on a large deep learning model needing a defined "training set" in the context of AI development for image interpretation, this detail might not be applicable or explicitly stated. If there are features utilizing machine learning (which is not explicitly detailed but possible for functions like segmentation), the training set details are not included. The submission is focused on demonstrating functional equivalence.

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

This information is not provided and is likely not applicable in the context of this 510(k) submission, as it focuses on demonstrating substantial equivalence of a software tool rather than a novel AI algorithm with a distinct training phase. If machine learning components exist, the process for establishing their "training ground truth" is not disclosed here.

In summary, the provided text details a 510(k) submission for substantial equivalence. It does not contain the detailed clinical study information (like sample sizes, expert qualifications, adjudication methods, or MRMC study results) that would typically accompany a submission for a novel diagnostic AI device where independent performance validation is the primary focus. Instead, it relies on demonstrating that the updated software (NemoCast K232549) is functionally equivalent to its predicate devices (NemoCast K193003, 3Shape Ortho System™ K152086) and that any differences do not impact safety or effectiveness.

Ask a specific question about this device

Biotech Dental SMILERS® aligners are indicated for the alignment of teeth in patients with permanent dentition (i.e., all second molars) during orthodontic treatment of malocclusion. SMILERS® aligners position teeth by way of continuous gentle force.

The Biotech Dental SMILERS® aligners are a series of prescription-only clear plastic removable aligners intended to incrementally move a patient's teeth from an initial position to a different end position using a software-generated sequence of intermediate states. Biotech Dental SMILERS® sequentially reposition teeth by way of continuous gentle force.

The provided text is an FDA 510(k) summary for the Biotech Dental SMILERS® aligners. It focuses on demonstrating substantial equivalence to a predicate device (Byte Aligner System K180346) rather than detailing acceptance criteria and a study that proves the device meets them in the context of an AI/algorithm-driven device.

However, I can extract the information relevant to non-clinical performance testing and conceptualize how it relates to acceptance criteria and "proving the device meets them," even if it’s not an AI performance study.

Key takeaway from the document: This submission is for orthodontic aligners, which are physical medical devices, not an AI/algorithm. The "acceptance criteria" and "study that proves the device meets the acceptance criteria" in this context refer to manufacturing validation, material testing, and shelf-life studies, not clinical performance or AI algorithm performance. The FDA determined that no clinical data was needed due to the well-established nature of sequential aligners.

Therefore, the requested information points 1 through 9, which are largely geared towards AI/algorithm performance studies, are not explicitly present in the provided document in the way they would be for an AI-medical device. I will address them based on the information available and note where it's not applicable.

Acceptance Criteria and Device Performance (Based on Non-Clinical Testing for a Physical Device)

1. Table of Acceptance Criteria and Reported Device Performance

Regarding AI/Algorithm-Specific Questions (Not Applicable to this Device Approval, but addressed for completeness):

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 (N/A): This submission is for a physical medical device (orthodontic aligners), not an AI algorithm. No test set of clinical data (images, etc.) for AI performance was used. The "test set" for this application refers to physical samples used in manufacturing validation and biocompatibility testing. The number of cases for manufacturing validation is not specified, nor is the provenance of those cases.

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):

• N/A: As this is physical device approval, there's no clinical "ground truth" established by experts in the context of an AI algorithm's diagnostic performance. For the fit validation, it states "qualitatively evaluated by a qualified individual," but specific number or detailed qualifications beyond "qualified" are not provided.

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

• N/A: No clinical data or AI performance test set requiring adjudication in this context.

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-assisted device. No MRMC study was performed. The clinical performance of sequential aligners is stated to be "well established" and "no clinical data is included in this submission."

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

• N/A: This is not an algorithm. The Nemocast software (K193003) is mentioned as a tool for planning cases, but the approval is for the aligners themselves, not the software's performance as a standalone diagnostic or treatment algorithm.

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

• N/A (for AI context): For the physical device, "ground truth" for manufacturing and fit would be based on engineering specifications and qualitative assessment of fit by a "qualified individual." Biocompatibility is assessed against published international standards.

8. The sample size for the training set:

• N/A: There is no AI training set for this device approval.

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

• N/A: There is no AI training set for this device approval.

Ask a specific question about this device