Search Results

The Invisalign® System is intended for the orthodontic treatment of malocclusion in patients with primary, mixed (primary and permanent), or permanent dentition. The optional mandibular advancement feature(s) are indicated for the treatment of skeletal malocclusion in patients with mixed or permanent dentition.

The subject device Invisalign® System is a proposed modification to add integrated button, an optional feature into the predicate device, Invisalign System (K241412). The Invisalign® System consists of removable orthodontic appliances (aligners) and proprietary 3D treatment planning software. This submission adds an optional integrated button to aligners which is similar to the predicate device's precision cut feature that allows doctors to add orthodontic accessories such as elastics during treatment. The 3D treatment planning software allows the visualization and button placement on the aligners. The doctor still approves the treatment plan prior manufacturing, which is the same as that in the predicate.

Like the predicate device, the Invisalign® System consists of a series of doctor prescribed, customized, thin, clear plastic aligners that gently move the patient's teeth in small increments from their original state to a more optimal, treated state to address malocclusion. The optional MAF positions patients jaw forward to address skeletal malocclusion. The system is used in patients with primary, mixed, and permanent dentition. There are no changes introduced to the user workflow other than the addition of optional integrated button feature.

This FDA 510(k) clearance letter describes a modification to an existing medical device, the Invisalign System. It does not contain the detailed information typically found in a study report for proving device performance against acceptance criteria, especially for AI/software devices. The provided text primarily focuses on regulatory approval based on "substantial equivalence" to a predicate device for an additional physical feature (integrated button) rather than a software-driven performance claim that would necessitate a rigorous clinical or performance study with acceptance criteria and specific test methodologies for AI.

Therefore, many of the requested elements for describing a study proving the device meets acceptance criteria cannot be extracted from this document because such a study, in the context of an AI/software device, does not appear to be the primary focus of this specific 510(k) submission as presented. The submission is for a physical device modification, not a new AI algorithm.

However, based on the information provided, here's what can be inferred or stated that such an approval did not involve:

Summary of Device Performance Study Based on Provided Text:

This 510(k) clearance letter for the Invisalign System (K252380) primarily concerns a modification to an existing device, specifically the addition of an "integrated button" feature to the aligners. The regulatory pathway is based on substantial equivalence to a predicate device (Invisalign System, K241412). The "study" described is a set of non-clinical tests to demonstrate that this physical modification does not negatively impact the device's safety and effectiveness. It does not present a study proving the performance of an AI/software component against acceptance criteria in the typical sense of a diagnostic or therapeutic AI device.

Therefore, most of the requested information regarding AI algorithm performance (e.g., sample sizes for test sets, data provenance, expert ground truth establishment, MRMC studies, standalone performance, training set details) is not applicable or not provided in this document.

1. Table of Acceptance Criteria and Reported Device Performance:

The document states: "The subject device, Invisalign® System underwent a complete set of functional and performance testing, including durability, shear bond, retention, and biocompatibility testing. All testing passed acceptance criteria and demonstrated the device modification does not affect the safety and effectiveness of Invisalign® System and does not raise any new questions of safety and effectiveness."

However, the specific quantitative acceptance criteria and the corresponding reported performance values for these tests (durability, shear bond, retention, biocompatibility) are not detailed in this 510(k) summary. These are typically listed in an internal test report, not the public-facing FDA clearance letter.

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

• Sample Size: Not specified.
• Data Provenance: Not specified (since the tests are physical and chemical, not clinical data for an AI algorithm).
• Retrospective/Prospective: Not specified.

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

• Not Applicable. The described tests (durability, shear bond, retention, biocompatibility) are laboratory-based engineering and materials tests, not clinical evaluations requiring expert consensus on a test set of patient data as would be the case for an AI diagnostic device.

4. Adjudication Method for the Test Set:

• Not Applicable. See point 3.

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

• No. This document does not mention an MRMC study. The device modification is a physical feature (integrated button) and its impact on human readers or clinical interpretation in an AI-assisted workflow is not discussed.

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

• No, not in the context of AI algorithm performance. The "Invisalign System" does include "proprietary 3D treatment planning software," and this submission notes the software allows "visualization and button placement on the aligners." However, the 510(k) focuses on the physical button's safety and effectiveness, not a new or modified AI algorithm's standalone performance. The software's role is described as "the doctor still approves the treatment plan prior manufacturing," indicating a human-in-the-loop scenario. No standalone algorithm performance evaluation is detailed.

7. The Type of Ground Truth Used:

• For the physical tests (durability, shear bond, retention, biocompatibility): The ground truth would be established through scientific measurement standards and validated laboratory methodologies (e.g., ISO standards for materials testing).
• For any software component related to the new feature: The ground truth for software functionality (e.g., correct button placement visualization, accurate manufacturing instructions) would internally be established through testing against design specifications and requirements. This is not detailed in the document.

8. The Sample Size for the Training Set:

• Not Applicable/Not Specified. This document does not describe the development or training of a new AI algorithm. If the "proprietary 3D treatment planning software" utilizes machine learning, its training set details are not provided as part of this specific 510(k) for a physical modification.

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

• Not Applicable/Not Specified. See point 8.

Ask a specific question about this device

The Invisalign® System is intended for the orthodontic treatment of malocclusion in patients with primary, mixed (primary and permanent dentition. The optional mandibular advancement feature(s) are indicated for the treatment of skeletal malocclusion in patients with mixed or permanent dentition.

The subject device, Invisalign System, is a modification to the predicate device, Invisalign System with Mandibular Advancement Featuring Occlusal Blocks (K232233, cleared on September 26, 2023) to introduce an additional treatment planning workflow that does not require any Align Computer Aided Design (CAD) technician interaction. The Invisalign System consists of removable orthodontic appliances (aligners) and proprietary 3D treatment planning software. As part of this submission, there are no proposed design changes made to standard aligners or aligners with Mandibular Advancement Features (MAF) since the clearance of K232233. Further, there are no proposed changes to the proprietary 3D treatment planning software except for the non-significant changes that were implemented via Letter to File.

Like the predicate device, the Invisalign System consists of a series of doctor prescribed, customized, thin, clear plastic aligners that gently move the patient's teeth in small increments from their original state to a more optimal, treated state to address malocclusion. The optional MAF positions patients jaw forward to address skeletal malocclusion. The system is used in patients with primary, mixed, and permanent dentition.

The proposed modification in this premarket notification is to add a completely automated endto-end treatment planning workflow without CAD technician involvement. The subject device, Invisalign System, is the Invisalign System aligners produced with the additional treatment planning workflow.

There are no proposed design changes to the Invisalign System components as part of this submission.

The provided document is a 510(k) premarket notification summary for the Align Technology Invisalign System. It focuses on demonstrating substantial equivalence to a predicate device (K232233) for an updated version of the Invisalign System that includes an additional, fully automated treatment planning workflow.

Based on the provided text, here's an analysis of the acceptance criteria and the study that proves the device meets them:

The document explicitly states that the submission is for a Special 510(k) notice to introduce an additional treatment planning workflow that does not require Align CAD technician interaction. It emphasizes that no proposed design changes were made to the standard aligners, aligners with Mandibular Advancement Features, or the proprietary 3D treatment planning software, except for non-significant changes previously implemented via Letter to File.

The core of the acceptance criteria and supporting study revolves around demonstrating that this new automated workflow achieves the same treatment plan and aligner output as existing workflows, and that this change does not affect the safety and effectiveness of the Invisalign System, nor does it raise any new questions of safety and effectiveness.

1. Table of acceptance criteria and the reported device performance:

Since this is a Special 510(k) for a workflow change, the acceptance criteria are not presented as numerical performance metrics in a typical table format for accuracy or sensitivity. Instead, they are framed as qualitative equivalency and safety/effectiveness assurances.

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

The document does not provide specific sample sizes for the test set used in the verification and validation (V&V) activities. It also does not specify the data provenance (e.g., country of origin, retrospective or prospective nature of the data). This is typical for a Special 510(k) focused on a software workflow change for an established device, where the primary demonstration is of functional equivalence rather than clinical performance on patient cohorts.

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 number or qualifications of experts used to establish "ground truth" for the V&V of the automated workflow. Given the context, the "ground truth" for the automated workflow's output largely relates to its ability to replicate or achieve the same outcomes as an existing, human-in-the-loop workflow, which is already established by the predicate device's clearance. It's likely that internal engineers and potentially dental professionals (though not explicitly stated as "experts" for ground truth establishment in the V&V) were involved in comparing outputs.

4. Adjudication method for the test set:

The document does not describe any specific adjudication method (e.g., 2+1, 3+1) for the test set. This is consistent with a V&V study focused on functional equivalence of an automated workflow rather than a diagnostic performance study requiring expert consensus on subjective interpretations.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done:

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not performed or described. The nature of this submission (a Special 510(k) for an automated workflow addition to an existing device) does not typically require MRMC studies. The focus is on the functional equivalence of the new automated process to the existing, human-assisted process, not on improving human reader performance with AI assistance.

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

Yes, in the context of this submission, the "additional treatment planning workflow" is described as "completely automated end-to-end treatment planning workflow without CAD technician involvement." This implies a standalone (algorithm-only) performance was evaluated in terms of its ability to generate acceptable treatment plans and aligner outputs, which is then compared for equivalence to the human-in-the-loop processes. The V&V testing would have assessed this algorithm-only output against the established standards of the system.

7. The type of ground truth used:

The "ground truth" here is implied to be the established and accepted output of the predicate device's existing (manual or combined manual/automated) treatment planning workflows. The V&V compared the output of the new automated workflow to these established outputs, ensuring they were "the same treatment plan and aligners output." This is essentially a functional equivalence ground truth. It is not based on pathology, clinical outcomes data, or necessarily a new expert consensus on a novel diagnostic task, but rather on the consistency and correctness of the automated design process relative to the already-cleared, human-assisted process.

8. The sample size for the training set:

The document does not specify the sample size for the training set for the underlying proprietary 3D treatment planning software. This information is typically not provided in a 510(k) for a workflow modification if the core software algorithms (that would require training data) are not being substantially changed. The mention of an "automated end-to-end treatment planning workflow" suggests an AI/ML component, but details on its training are absent from this summary.

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

Since details on the training set are not provided, information on how its ground truth was established is also not available in this document.

Ask a specific question about this device

The Invisalign Palatal Expander System is indicated for the orthodontic treatment of malocclusion. The system is used for rapid expansion and subsequent holding of skeletal and/or dental narrow maxilla (upper jaw, dental arch and tooth, palate) with primary, mixed, or permanent dention during orthopedic treatment in children or adolescents. In adults, it is to be used in conjunction with surgery or other interventions when necessary.

The subject device, Invisalign Palatal Expander (IPE) System (hereafter referred to as the IPE System) is a modification to the legally marketed multiple predicate devices. Invisalign System (Class II; Product Code: NXC; K220287) as Primary and Dentaurum Expansion Screws/Hyrax Expander – Hyrax ® and Hyrax neo® (Class I, Product Code: DYJ, K935154) as Secondary.

The IPE System consists of the Invisalign Palatal Expanders, Invisalign Palatal Holders, the Attachment Template and the proprietary 3D Shape generation software.

Invisalign Palatal Expanders are a staged series of removable orthodontic devices designed to expand the patient's skeletal and/or dental narrow maxilla (upper jaw, dental arch, teeth and palate) in small increments to an optimal position determined by the doctor. Once the desired clinical outcome of the expansion phase has been achieved, patients progress to the holding phase.

The Invisalign Palatal Holder is a copy of the last stage of the expansion phase designed to hold the maxilla post active expansion, to allow the maxilla to stabilize before the patient progresses to the next phase of treatment (retention, phase 2 or other treatment).

The proprietary Align internal personnel-facing 3D software enables Align's computer-aided design (CAD) designers to generate the shape and quantity/stages of the device. Using this software, CAD designers create digital files for the incremental stages of the doctorprescribed expansion amount and the design and quantity of holders per the prescribed holding duration. Each device in the series is fabricated via additive manufacturing (3D printing).

The Attachment Template (also a component of the primary predicate device, the Invisalign System) enables correct placement and bonding of attachments made of dental composite (material provided by doctor) to the tooth surface for IPE engagement and retention.

The provided text is a 510(k) Premarket Notification for the Invisalign Palatal Expander System. It outlines the device's indications for use, comparison to predicate devices, and performance data. However, it does not contain the specific details required to fully address all parts of your request regarding acceptance criteria and a study proving the device meets those criteria for an AI/software component, particularly around metrics like sensitivity, specificity, or reader performance with and without AI.

The document mentions "proprietary 3D Shape generation software" and "includes software algorithms that are used to determine the shape and calculate the quantity of devices required." It also states "successful software verification and validation (V&V) testing at the unit, integration, and system level was performed to qualify the orthodontic software component of the subject device." This suggests that the software is a design and manufacturing tool, generating device shapes based on clinician prescriptions and patient scans, rather than an AI performing diagnostic or assistive tasks that would typically require the comparative performance studies you're asking about (e.g., MRMC studies, standalone performance with ground truth labels).

Therefore, based on the provided text, I can only provide information related to the device's overall performance and safety testing, not specific AI acceptance criteria and studies as if it were a diagnostic AI.

Here's what can be extracted and inferred from the document:

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

The document doesn't provide a table of quantitative acceptance criteria (e.g., specific thresholds for force, retention, etc.) for the various tests. Instead, it states that the test results "met the acceptance criteria and performed as intended" or were "found to be adequately designed."

Regarding the study that proves the device meets the acceptance criteria (specifically concerning the software component, as that's where AI concepts typically apply):

The document describes the software as a "proprietary, 3D Shape generation software" that "enables Align's computer-aided design (CAD) designers to generate the shape and quantity/stages of the device." It clarifies that this is an "internal Align facing only shape generation software which includes software algorithms that are used to determine the shape and calculate the quantity of devices required per the doctor prescribed expansion distance and holding duration." This is a software that designs the physical device based on inputs, not an AI that interprets medical images, flags abnormalities, or assists in diagnosis, which would typically involve the detailed study characteristics you've requested.

Therefore, many of your questions related to multi-reader studies, expert ground truth adjudication for a test set, effect sizes of human improvement with AI, and specific ground truth types (pathology, outcomes data) are not applicable to the description of the software provided in this 510(k) summary, as it's not a diagnostic or AI-assisted diagnostic tool in the typical sense.

Here's an attempt to answer the relevant questions based on the provided text, and state when information is not applicable or provided:

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

• Test Set Sample Size: For the physical device performance tests (durability, stiffness, retention, etc.), specific sample sizes are not provided, only that testing was conducted and met acceptance criteria. For the "Early Feasibility Study," the number of subjects is not specified, only that "desired active expansion of the upper jaw width was observed in all the subjects." For the "real-world data," the sample size is not provided.
• Data Provenance: The document does not specify the country of origin. The "Early Feasibility Study" is mentioned, implying a prospective collection for that specific study. The "real-world data" is described as from "commercially available product," suggesting it is retrospective post-market 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 because the software's function is for device design generation, not for generating 'ground truth' for medical interpretations or diagnoses that would require expert labeling and adjudication. The "doctor-prescribed expansion amount" is the input to the software, implying the clinician dictates the "ground truth" for the device design.

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

• Not applicable for the software as described. The software's output is a device design based on physician input, not a diagnostic finding requiring 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:

• No MRMC study was done or reported for this device's software. The software's role is not described as an AI assisting human readers in diagnostic tasks.

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

• The software's function is described as enabling "CAD designers to generate the shape" based on "doctor-prescribed expansion amount." It's an internal design tool, not a standalone diagnostic algorithm whose performance would typically be evaluated without human input. Software verification and validation (V&V) was performed, which assesses if the software functions as designed from a technical standpoint.

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

• For the software, the "ground truth" for its operation is the "digital scan and doctor/dental practitioner's prescription." The software takes these inputs to generate a 3D model. Clinical performance was evaluated by observing "desired active expansion... in all the subjects" and "no unanticipated or serious adverse events reported," which relates to patient outcomes after using the physical device.

8. The sample size for the training set:

• Not applicable or provided. The document describes software that generates device shapes based on given inputs, rather than a machine learning model that would require a dedicated training set.

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

• Not applicable. The software's function as described does not involve a "training set" in the machine learning sense, where ground truth labels would be established. It is a deterministic design software.

Ask a specific question about this device

The Invisalign System is intended for the orthodontic treatment of malocclusion in patients with primary, mixed (primary and permanent), or permanent dentition. The optional mandibular advancement feature(s) are indicated for the treatment of skeletal malocclusion in patients with mixed or permanent dentition.

The subject device, Invisalian System with Mandibular Advancement Featuring Occlusal Blocks (Invisalign System, MAOB) is a modification to the predicate device, Invisalign System (K220287, cleared on April 07, 2022) and the reference device. Invisalign System with Mandibular Advancement Features (K181739, cleared on October 26th, 2018). The Invisalign System, MAOB (subject device) consists of removable orthodontic appliances (aligners with mandibular advancement features including occlusal blocks), proprietary treatment planning 3D software (doctor facing - ClinCheck and Align employee facing -Treat) and attachment templates.

The provided text describes a 510(k) premarket notification for a medical device (Invisalign System with Mandibular Advancement Featuring Occlusal Blocks) and its substantial equivalence to a predicate device. However, it does not contain the detailed information typically found in a study proving a device meets acceptance criteria, particularly concerning AI or software performance characteristics.

The document primarily focuses on:

• Regulatory Clearance: The FDA's substantial equivalence determination.
• Device Description: What the device is and how it functions.
• Comparison to Predicate: How the modified device compares to existing, cleared devices.
• Testing Summary: High-level statements about bench testing, biocompatibility, and software V&V.

**Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and reported device performance (since specific performance metrics and acceptance thresholds for the software are not detailed).
2. Sample sizes for a test set or data provenance (no specific AI performance study data is presented).
3. Number of experts or their qualifications for ground truth establishment.
4. Adjudication methods.
5. MRMC comparative effectiveness study results.
6. Standalone algorithm performance.
7. Type of ground truth used for specific AI performance.
8. Sample size for the training set.
9. How ground truth for the training set was established.**

The document states:

• Software Testing: "In accordance with IEC 62304, Medical device software - Software life cycle processes; successful software verification and validation (V&V) testing at the unit, integration, and system level was performed to qualify the modified software with the subject device." This indicates that standard software V&V was performed, but details on specific acceptance criteria for performance related to image analysis or treatment planning accuracy that would typically be associated with an AI/ML device are not provided. The phrase "proprietary, 3D treatment planning software" is mentioned, but no performance claims or supporting study data for this software's accuracy are included in this FDA letter/summary.
• No Animal or Clinical Testing: "No animal or clinical testing was required or performed for Invisalign System with Mandibular Advancement Featuring Occlusal Blocks." This further indicates that the detailed performance study you are asking for, especially involving human observers or patient outcomes, was not part of this specific submission.

In summary, the provided text is a regulatory clearance document, not a detailed technical report on AI/ML model performance. It confirms that the device's modifications (addition of occlusal blocks and associated software updates) were deemed substantially equivalent to a predicate device based on bench testing, biocompatibility, and general software V&V, without specific performance metrics or studies relating to AI/ML accuracy or efficacy as you've requested.

Ask a specific question about this device

The Invisalign System is intended for the orthodontic treatment of malocclusion.

The subject device, Invisalign System with Pre-Formed Attachments (PFA) System, is a modification to the predicate device, the Invisalign System (K220287, cleared on April 7th, 2022). The Invisalign System with PFA system consists of removable orthodontic appliances (aligners), proprietary treatment planning 3D software, attachment templates and/or PFA system.

Like the predicate device, the Invisalign system with PFA (subject device) consists of a series of doctor prescribed, customized, thin, clear plastic aligners that gently move the patient's teeth in small increments from their original state to a more optimal, treated state to address dental malocclusion. The Invisalian system aligners are used in patients with primary, mixed (primary and permanent), and permanent dentition. The Invisalign system aligners with mandibular advancement feature(s) are used in patients with mixed and permanent dentition to correct Class II malocclusions. The Invisalign system is intended to treat dental and skeletal malocclusion in patients with Class I, II and III including Antero-Posterior (A-P), vertical (open bite, deep bite), transverse (narrow arch or jaw, crossbite), or inter-arch (spacing and crowding) correction at all severity levels. In some cases, surgical intervention, or addition of other appliances in addition to Invisalign treatment may be needed at the doctor's discretion.

The proprietary ClinCheck (CC) 3-D software is inclusive of both dental practitioner-facing functions and internal Align personnel-facing functions. The Align facing software enables Align's computer-aided design (CAD) designers to create a treatment plan based on a doctor's prescription and inputs (e.g., dental scans). The treatment plans created using the Align personnel-facing software are then reviewed and approved by doctors before the aligners are manufactured. The doctors' reviews and approvals are exchanged via ClinCheck software (dental practitioner-facing software). Once the treatment plan is approved by the dental practitioner, the information is sent to the manufacturing facility for creation of the aligners.

When attachments are prescribed as part of the treatment plan, the subject device has the option of delivering them preformed with PFA system or with a disposable attachment template. The attachment templates are disposable polyurethane appliances which match the patient's existing dentition and include wells for the placement of dental composite (sold separately). During the first visit, the dental practitioner uses the template in bonding dental composite to the tooth surface to create attachments on the teeth. These attachments help create forces on the tooth which can assist aligner retention or optimized aligner force system for tooth movement.

The PFAs are made of a fully cured proprietary photo-polymerizable methacrylate-based resin (similar to dental composite material). PFA system is intended to enable correct placement of attachments and bond attachments to the tooth surface for aligner retention and to optimize aligner force system for tooth movement.

The patient-customized PFA are manufactured using additive manufacturing technologies and configured to individual patient's treatment plans and teeth anatomy using a proprietary internal facing 3D device-generation manufacturing software.

Based on the provided text, the device in question is the "Invisalign System with Pre-Formed Attachment System" (PFA System), which is an alternative attachment delivery mechanism for the existing Invisalign System. The 510(k) submission seeks clearance for this addition.

The provided text does NOT describe a typical AI/ML-based medical device performance study with acceptance criteria related to sensitivity, specificity, accuracy, or human reader improvement. Instead, it describes a modification to an existing medical device and demonstrates its substantial equivalence to a predicate device. The "performance data" section focuses on engineering and biocompatibility testing for the new component, not diagnostic performance metrics or human-AI interaction.

Therefore, many of the requested points related to AI/ML study design (such as sample size for test/training sets, expert ground truth establishment, MRMC studies, standalone performance, etc.) are not applicable to this specific submission, as it focuses on an engineering modification rather than an AI/ML diagnostic algorithm.

Here's a breakdown based on the information available:

1. Table of Acceptance Criteria and Reported Device Performance:

The document describes performance testing for the new PFA system, but it does not specify quantitative acceptance criteria in a table format with corresponding numerical performance results for each criterion. Instead, it makes a general statement that the testing outcomes support substantial equivalence.

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

• Sample Size: Not specified for the performance testing. The study is not a clinical trial or an AI/ML algorithm evaluation using patient data. It's an engineering and biocompatibility assessment of a new component.
• Data Provenance: Not applicable in the context of patient data. The "data" refers to the results of engineering and lab tests (e.g., measuring bond strength, stain resistance).

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

• Not Applicable. This is not an AI/ML diagnostic device where experts establish ground truth for images or clinical cases. The "ground truth" for this device modification is based on engineering specifications and regulatory standards (e.g., successful bond strength test, ISO biocompatibility compliance).

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

• Not Applicable. As there are no human readers establishing ground truth for diagnostic decisions, no adjudication method is 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 study was not done. This submission is about a mechanical/material modification (Pre-Formed Attachment system), not a diagnostic AI that assists human readers. No effect size on human reader improvement is relevant or reported.

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

• Not Applicable / Not a standalone AI algorithm. The new component is an alternative delivery mechanism for attachments in an orthodontic system that relies on a doctor's prescription and approval of treatment plans. It's not a standalone AI algorithm producing a diagnostic output. While there is "proprietary, 3D device-generation manufacturing software," its V&V is mentioned, but its performance is not assessed as a standalone diagnostic tool.

7. The type of ground truth used:

• Engineering Specifications and Standardized Biocompatibility Testing Protocols. The ground truth for this kind of device modification is established by meeting predefined physical/mechanical properties and complying with established biocompatibility standards (e.g., ISO 10993-1, ISO 7405).

8. The sample size for the training set:

• Not Applicable. This is not an AI/ML device that requires a "training set" of data in the sense of machine learning. The term "training set" usually refers to data used to train an algorithm. Performance assessment here relates to manufacturing processes and material properties.

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

• Not Applicable. (See point 8).

In Summary:

The provided document describes a 510(k) submission for a non-AI device modification. The "study that proves the device meets the acceptance criteria" is a series of engineering, materials, and software verification and validation tests (bond strength, stain resistance, wear, force measurement, volume precision, usability, biocompatibility per ISO standards, and software V&V per IEC standards), rather than a clinical performance study evaluating an AI algorithm using patient data and expert ground truth. The acceptance criteria are implicitly met if the test outcomes validate that the new component "does not impact the current safety and effectiveness profile of the Invisalign System" and allows for a finding of "substantial equivalence" to the predicate device.

Ask a specific question about this device

The Invisalign System is intended for the orthodontic treatment of malocclusion.

The Invisalign System (subject device) consists of removable orthodontic appliances (aligners), proprietary 3D software and attachment template. The system consists of a series of doctor prescribed, customized, thin, clear plastic aligners that gently move the patient's teeth in small increments from their original state to a more optimal, treated state to address malocclusion. The optional mandibular advancement feature positions patients iaw forward to address skeletal malocclusion. The system is used in patients with primary, mixed, and permanent dentition. The Invisalign System is intended for treating dental and skeletal malocclusion in patients with Class I, II and III including Antoro-Posterior (A-P), vertical (open bite, transverse (narrow arch or jaw, crossbite), or inter-arch (spacing and crowding) correction at all severity levels. In some cases, surgical intervention, or addition of other appliances in addition treatment may be needed at the doctor's discretion.

The Invisalign System aligners consist of a series of customized orthodontic devices made from proprietary thermoformed polyurethane sheeting material. The first device in the series matches the patient's dentition in its current state and then each subsequent aligner stage has the shape of the dentition shifted gradually toward the final desired position. The aligners can accommodate use of tooth attachments and elastics (through use of precision cut outs or buttons or power arms). The system can also be ordered with additional aligner features such as precision cut outs, bite ramps, compliance indicators, and mandibular advancement features (MAF). MAF is also referred to as precision wings and is prescribed by the dental practitioner to position the lower jaw forward during correction of skeletal malocclusion. The subject device system of this Special 510(k), referred to as the Invisalign System, is a modification to the predicate device the Invisalign System with Mandibular Advancement Feature (MAF) (K181739, cleared on Oct 26, 2018) and is inclusive of both standard aligners and aligners with mandibular advancement feature.

The proprietary ClinCheck (CC) 3-D software is inclusive of both dental practitioner-facing functions and internal Align personnel-facing functions. The Align personnel-facing functions are termed 'Treat' internally. This internal facing software enables Align's computer-aided design (CAD) designers to create a treatment plan based on a doctor's prescription and inputs (e.g., dental scans). The treatment plans created using the Align personnel-facing software are then reviewed and approved by doctors before the aligners are manufactured. The doctors' reviews and approvals are exchanged via ClinCheck software (dental practitioner-facing software). Once the treatment plan is approved by the dental practitioner, the information is sent to the manufacturing facility for creation of the aligners.

When attachments are prescribed as part of the treatment plan, a disposable template is provided to assist the dental practitioner in positioning and forming the attachments from dental composite (sold separately). Attachment templates are disposable polyurethane appliances which match the patient's existing dentition and include wells for the placement of dental composite. During the first visit, the dental practitioner uses the template in bonding dental composite to the tooth surface to create attachments on the teeth. These attachments help create forces on the tooth which can assist in aligner retention or optimized aligner force system for tooth movement.

The provided document is a 510(k) premarket notification from the FDA for the Invisalign System. It outlines the regulatory clearance for the device based on its substantial equivalence to a predicate device.

Crucially, this document states that there were no proposed design changes and that the changes submitted were minor labeling updates. Therefore, no new performance data, clinical testing, or animal testing was required for this particular submission (K220287). The document explicitly states:

• "There are no proposed design changes in the scope of this pre-market notification. The proposed labelling changes do not trigger any performance testing as the changes are minor clarifications and additions that do not impact the current safety and effectiveness profile of the Invisalign System."
• "No animal or clinical testing was required to validate these labeling modifications."

Given this information, it is not possible to describe acceptance criteria or a study that proves the device meets actual performance criteria based on the provided text, as no such study was conducted for this specific 510(k) submission.

The information requested in your prompt (acceptance criteria, sample size, expert ground truth, MRMC studies, standalone performance, training set details) pertains to a typical performance study for a medical device. Since this 510(k) was based on "substantial equivalence" due to minor labeling changes and no design changes, these types of performance studies were not a part of this particular submission for the new clearance (K220287). The safety and effectiveness were considered established by the predicate device (K181739).

Therefore, I cannot fulfill your request to describe acceptance criteria and a study proving device performance using only the provided text, as the text explicitly states no such studies were required or conducted for this specific submission.

Ask a specific question about this device

The iTero Element 5D is a diagnostic aid for the detection of interproximal caries lesions above the gingiva and for monitoring the progress of such lesions.

The iTero Element 5D is an integrated intraoral imaging system capable of 3D confocal optical impressions for CAD/CAM of dental devices, which also captures 2D color images and Near Infrared (NIR) images.

The iTero Element 5D consists of a scanning wand cradle, single-use, disposable, 5D barrier sleeve, iTero Element 5D Sleeve (protective sleeve), software (including GUI), and a computer hardware platform that is offered in two configurations:

1. Laptop Configuration, where the GUI is presented on a customer-provided PC Laptop Touchscreen;
2. Wheel Stand Configuration where the GUI is presented on a display panel that is mounted on a wheel stand base unit.
   The scanning wand and software, including the GUI, are common to both configurations.

The scanning wand which has 3 imaging capabilities: 1) 3D confocal optical impression, 2) 2D color imaging and 3) near infrared imaging (NIRI), is designed to be used with a single-use, disposable, scanning wand barrier sleeve ("5D barrier sleeve") during scans and a protective sleeve during storage. At the beginning of every scan, the single-use, disposable, 5D barrier sleeve is placed on the scanning wand's head. The wand tip is placed slightly above the patient's teeth and the scan is initiated. At the end of the scan, proprietary imaging software converts the scan into an image that is simultaneously presented alongside the 2D color images on the GUI display. The 3D confocal optical impression and 2D color images assist in orientation by providing an enhanced view of the scanned teeth, thus helping the user identify which areas (i.e. occlusal direction/angles) to view as NIR images. The 2D color image displays a close-up view of the teeth while the NIR Image translates the teeth structure (enamel and dentin) to different brightness levels.

Here's an analysis of the provided text regarding the iTero Element 5D device, focusing on its acceptance criteria and the supporting study information.

It is important to note that the provided document is a 510(k) summary for a medical device cleared by the FDA. Such documents often focus on demonstrating substantial equivalence to a predicate device rather than presenting extensive de novo clinical trial data. Therefore, some of the requested information, particularly detailed clinical study specifics, might not be explicitly present.

1. Table of Acceptance Criteria and Reported Device Performance

Based on the non-clinical performance testing section, the acceptance criteria are implicitly defined by the demonstration of "substantially equivalent manner relative to the predicate" for various parameters. The reported performance is a statement of this equivalence.

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

The document does not specify sample sizes for the test sets in the non-clinical performance testing. It mentions "comparison testing" and "system level testing" but does not quantify the number of devices or scenarios tested for each parameter.

Data provenance (e.g., country of origin, retrospective/prospective) is also not mentioned. Given the nature of a 510(k) summary and the non-clinical focus, this information is typically not included.

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

This information is not provided. The performance testing described is non-clinical, primarily focusing on physical and technical characteristics of the device and its components, rather than clinical evaluation against a "ground truth" established by experts in a diagnostic context. This would be more relevant in a clinical study for diagnostic accuracy.

4. Adjudication Method for the Test Set

This information is not provided. As the testing is non-clinical, an adjudication method in the traditional sense (e.g., for expert disagreement on ground truth) is 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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly stated as performed. The document explicitly states: "Clinical performance testing was not conducted/provided." The device is described as a "diagnostic aid" but the primary focus of the submission is non-clinical equivalence. There is no mention of an AI component improving human reader performance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

A standalone performance study in the sense of algorithm-only diagnostic accuracy was not conducted or reported in this document. The device is hardware-based with integrated software and its function relies on a human operator to perform the scan and interpret the images. The testing focused on the performance of the device's imaging capabilities (e.g., image sharpness, signal-to-noise ratio).

7. The Type of Ground Truth Used

For the non-clinical performance tests, the "ground truth" would be objective measurements and established engineering standards. For example:

• Image Quality: Calibrated measurement systems for sharpness, field of view, signal-to-noise ratio against known targets.
• Barrier Testing: Standardized material property tests (e.g., ASTM standards) with defined thresholds for tensile strength, tear resistance, etc.
• Biocompatibility: Adherence to ISO 10993 series for material compatibility.
• Safety/EMC: Compliance with IEC standards.

There is no mention of ground truth established by expert consensus, pathology, or outcomes data, as these typically relate to clinical diagnostic accuracy which was not performed.

8. The Sample Size for the Training Set

The document does not mention a "training set" in the context of machine learning or AI development. The device described appears to leverage established imaging principles (Near Infrared Transillumination) rather than a deep learning model that requires a large training dataset. The software discussed controls display, storage, live stream, and camera functions, rather than performing automated diagnostic interpretations based on trained algorithms.

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

As no training set is mentioned (see point 8), this information is not applicable.

Ask a specific question about this device

The Invisalign System is indicated for the orthodontic treatment of malocclusion.

The Proposed Device is a minor change to the currently marketed Invisalign System (K143630) (hereafter referred to as "Predicate Device") to support repositioning of the mandible.

Invisalign System with Mandibular Advancement Feature consists of a series of doctor prescribed, customized, thin, clear plastic, removable orthodontic appliances (aligners) and proprietary ClinCheck 3-D software. The aligners gently move the patient's teeth in small increments and position the mandible forward from their original state to a more optimal, treated state. The Proposed Device treats patients with Class 1 and Class 2 malocclusion as well as patients with severe open bite, severe overiet, deep bite, skeletally narrow jaw, dental prostheses/implants. and/or those who require surgical correction. The Proposed Device includes two mandibular advancement features, also known as "precision wings", on each upper and lower aligner that function as mandibular repositioners, maintaining the lower jaw in the forward position.

The Proposed Device is made from the same material and utilizes the same manufacturing processes as the Predicate Device, Invisalign System (K143630). The software level of concern for the Predicate Device is moderate. Minor updates have been made to the proprietary ClinCheck 3-D software to enable placement of the mandibular advancement features on the aligners during the MA Phase of treatment. The software level of concern for the Proposed Device is determined to be the same as the Predicate Device: moderate.

I am sorry, but the provided text does not contain the specific information required to complete your request for acceptance criteria and the study details. The document is an FDA 510(k) summary for the Invisalign System with Mandibular Advancement Feature, which focuses on demonstrating substantial equivalence to a predicate device.

While it mentions performance testing and a clinical study, crucial details such as:

• A table of acceptance criteria and reported device performance
• Sample size used for the test set and data provenance
• Number of experts used to establish ground truth and their qualifications
• Adjudication method
• Multi-reader multi-case (MRMC) comparative effectiveness study (effect size with and without AI)
• Standalone algorithm-only performance
• Type of ground truth used (expert consensus, pathology, outcomes data, etc.)
• Sample size for the training set
• How ground truth for the training set was established

are not present within the provided text. The document refers generally to "internal design specification and with the applicable performance standards" and states that "Test results obtained verified the safety and effectiveness of the Proposed Device per design specifications and applicable standards," but does not explicitly enumerate these criteria or their fulfillment in a detailed manner.

Ask a specific question about this device

The Invisalign System is indicated for the alignment of teeth during orthodontic treatment of malocclusion.

The Invisalign System consists of a series of doctor-prescribed, thin, clear plastic removable orthodontic appliances (aligners) and proprietary 3-D software. The aligners gently move the patient's teeth in small increments from their original state to a more optimal, treated state. The Invisalign System is intended as an alternative to conventional wire/bracket technology and fixed appliances for the treatment of patients with malocclusion.

The proprietary Invisalign System 3-D software generates the image of a final, treated state and then interpolates a series of images that represent intermediate teeth states. The dental practitioner then reviews these images to depict, edit, view, monitor, and approve an orthodontic treatment plan. The dental practitioner has the option to reject or request modifications to the set-up prior to approving it for aligner fabrication. Once the doctor approves the set-up, the series of custom-made aligners are then manufactured, packaged, and shipped to the dental practitioner to be dispensed to the patient for treatment.

The provided document is a 510(k) K143630 substantial equivalence determination for the Invisalign System, specifically focusing on modifications to its 3-D software. It does not provide detailed acceptance criteria and a study proving the device meets them in the way one might find in a full clinical trial report or a performance study for a diagnostic device.

However, based on the information provided, here's a breakdown of what can be extracted regarding acceptance criteria and the study:

1. Table of Acceptance Criteria and Reported Device Performance

The core of the "study" described here is a comparison to a predicate device (K081960). The acceptance criteria, implicitly, are that the modified Invisalign System (K143630) performs equivalently to the predicate device, especially considering the changes made to the software's functionality and platform.

The document states:

• "The acceptance criteria were established in order to demonstrate the modified Invisalign System is substantially equivalent to the primary predicate device."
• "Therefore, the results of this testing demonstrate the modified Invisalign System 3-D software is substantial equivalent to the primary predicate 3-D software."

Implicit Acceptance Criteria from Predicate Comparison (Table 4 of the document):

Reported Device Performance:
The document explicitly states: "Results of verification and validation testing demonstrate the Invisalign System showed conformity with pre-established specifications and acceptance criteria." And further, "Therefore, the results of this testing demonstrate the modified Invisalign System 3-D software is substantial equivalent to the primary predicate 3-D software."

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

The document does not specify a "test set" in terms of patient data or specific clinical cases with a numerical sample size. The testing appears to be focused on software verification and validation against pre-established specifications and the predicate device's functionality, rather than a clinical performance study using a sample of patient data.

• Test Set Sample Size: Not specified as a numerical sample of clinical cases or patient data. The testing described is software V&V.
• Data Provenance: Not applicable as the testing described is primarily software engineering verification and validation, not a clinical study on patient data.

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

Since the "test set" and "ground truth" are framed around software functionality and substantial equivalence to a predicate, rather than a diagnostic accuracy claim, the document does not mention experts establishing ground truth in the typical clinical sense. The "ground truth" for the software's functionality would have been its design specifications and comparison to the predicate's known functionality.

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified.

4. Adjudication Method for the Test Set

Not applicable as it's not a clinical study requiring adjudication of expert opinions on patient cases.

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

No, an MRMC comparative effectiveness study is not mentioned. The study described is a software verification and validation, and a comparison against a predicate device for substantial equivalence. It does not evaluate how human readers (dental practitioners) improve with or without AI assistance from this specific version of the software.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

The device explicitly includes a "human-in-the-loop" aspect: "The dental practitioner then reviews these images to depict, edit, view, monitor, and approve an orthodontic treatment plan." The software generates the plan, but the practitioner approves or modifies it. Therefore, a standalone algorithm-only performance assessment in a vacuum is not the design or intent of this system's approval. The focus is on the software supporting the practitioner's workflow.

7. The Type of Ground Truth Used

The "ground truth" for this submission appears to be related to the functional specifications of the software and the established performance/functionality of the predicate device (K081960). The modified software met its design specifications and was deemed functionally equivalent for its intended use, despite some differences in feature implementation and platform. The safety and effectiveness are established by comparison to the predicate and the documented V&V of the modified software.

8. The Sample Size for the Training Set

The document does not describe a "training set" in the context of machine learning model development. This submission is for an updated version of an existing software system, not the initial development or a new AI model requiring a distinct training phase to learn from data.

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

Not applicable, as a training set, in the machine learning sense, is not described.

Ask a specific question about this device