K Number
DEN230035
Device Name
DentalMonitoring
Date Cleared
2024-05-17

(379 days)

Product Code
Regulation Number
872.1770
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdparty
Intended Use
DentalMonitoring is a medical device software using image processing algorithms to analyze pictures of the oral cavity (hereinafter Scans). Scans are taken using the DM App, a smartphone, and the manufacturer's proprietary hardware products. Scans are taken by the patient, a non-healthcare professional, or a healthcare professional. The Scan is taken in healthcare facilities, such as a dental practice, or in a non-healthcare environment, such as the patient's own home. For some clinical parameters. DentalMonitoring requires a 3D Model. The product is designed to assist healthcare professionals in remotely monitoring orthodontic treatments and treatment progress. The results of DentalMonitoring are intended to be used as an aid in diagnosis and monitoring, not on a stand-alone basis for clinical decision-making. DentalMonitoring is indicated for use for patients over the age of 6 and reports results solely on permanent teeth. DentalMonitoring can monitor the following clinical parameters: - . oral hygiene: dental plaque / food residue; - 트 soft tissue statement: gingival recession, black triangle; - . dental statement: closure of extraction space, tooth wear; - . alignment: closure of all anterior spaces; and - . dental occlusion: - o in 2D Monitoring: midline deviation, overbite/open bite, overjet - o in 3D Monitoring: canine class, midline deviation, overbite/open bite, overjet Additionally, the following clinical parameters specific to orthodontic treatment types or phases can be monitored using DentalMonitoring: - for aligner treatments: tracking (seat/unseat), attachment loss, button loss; . - . for braces: bracket debonding, tie loss, self-ligating clips, passive archwire and auxiliaries; and - for thermoformed retainers: tracking (seat/unseat). I Based on an initial 3D Model provided by a healthcare professional. DentalMonitoring can also provide healthcare professionals with 3D Models representative of the patient's dentition and treatment progress. This device is a prescription device and is not intended for over-the-counter use
Device Description
DentalMonitoring is a standalone software with embedded artificial intelligence comprising machine learning and locked neural network algorithms. The product is composed of these parts: the Dashboard, the DM App along with a DM Cheek Retractor and DM ScanBox, and the Data Analysis Platform. The four steps are detailed below: - 1. Patient profile set-up: The healthcare professional sets up the patient profile through a web- based interface, Dashboard, accessible at www.dental-monitoring.com/doctor. During the patient profile set-up, the healthcare professional is prompted to set up a Protocol in order to select the clinical parameters they wish to monitor in accordance with the patient's treatment. During the set-up, the healthcare professional also determines the appropriate frequency at which the patient should use the DM App to take pictures of their intraoral cavity. - 2. Intraoral pictures acquisition: A set of pictures of the patient's intraoral cavity, hereinafter referred to as a Scan, is taken using the DM App along with a DM Cheek Retractor and DM ScanBox. The DM Cheek Retractor is an intraoral retraction device for the cheeks and lips to allow for sufficient space for image capture. The DM ScanBox is an extraoral holding apparatus for the smartphone that attaches to the DM Cheek Retractor. The DM App guides the user through the appropriate steps in order to obtain a complete Scan. This DM App is a mobile application installed on a smartphone; thus, the pictures are captured through the smartphone's main camera allowing the procedure to be totally non-invasive to the patient. - 3. Analysis of acquired intraoral pictures: The Scan is processed through the Data Analysis Platform. The Data Analysis Platform includes a technical processing phase and clinical processing phase, the latter being a clinical analysis to determine if any event has occurred within the clinical parameters the healthcare professional has set up to be monitored. The Data Analysis Platform uses AI comprising image processing algorithms and neural networks. - 4. Communication of results of the analysis performed through the Data Analysis Platform are communicated to the healthcare professional through the Dashboard on one hand, and to the patient through the DM App on the other hand. Results are shared with the healthcare professional in an exhaustive fashion, providing them with detailed information. As for the patient, the results are communicated in accordance with the rules defined by the healthcare professional in the Protocol applied to the patient. DentalMonitoring enables HCPs to adapt the use of the product according to their needs depending on each patient's orthodontic treatment. DentalMonitoring comprises two types of monitoring: 2D Monitoring and 3D Monitoring. Some clinical parameters are specific to either 2D Monitoring, or 3D Monitoring.
More Information

There are no predicate devices with K/DEN numbers listed in the provided text. The text explicitly states "Predicate Device(s) Not Found".

Not Found

Yes
The device description explicitly states that the software has "embedded artificial intelligence comprising machine learning and locked neural network algorithms."

No

The device is designed to assist healthcare professionals in remotely monitoring orthodontic treatments and treatment progress and aid in diagnosis and monitoring, not to provide therapy or treatment itself.

Yes

The "Intended Use / Indications for Use" section explicitly states, "The results of DentalMonitoring are intended to be used as an aid in diagnosis and monitoring." Additionally, it monitors various clinical parameters such as dental plaque, gingival recession, tooth wear, and occlusion, which are all aspects related to diagnosing oral health conditions.

No

The device description explicitly states that the product is composed of the software parts (Dashboard, DM App, Data Analysis Platform) along with the DM Cheek Retractor and DM ScanBox, which are described as proprietary hardware products used for image acquisition. This indicates the device includes hardware components beyond just software.

Based on the provided information, DentalMonitoring is not an In Vitro Diagnostic (IVD) device.

Here's why:

  • IVD Definition: In Vitro Diagnostic devices are used to examine specimens derived from the human body, such as blood, urine, or tissue, to provide information for diagnosis, monitoring, or screening.
  • DentalMonitoring's Function: DentalMonitoring analyzes images of the oral cavity (Scans) and 3D Models. These are not specimens derived from the human body in the way that IVDs use. The analysis is performed on external images and models of the oral cavity.
  • Intended Use: The intended use clearly states that the device is designed to assist healthcare professionals in remotely monitoring orthodontic treatments and treatment progress by analyzing images of the oral cavity. It is an aid in diagnosis and monitoring, not a standalone diagnostic tool based on bodily fluids or tissues.

Therefore, DentalMonitoring falls under the category of a medical device software that uses image processing and AI for monitoring and assisting in diagnosis, but it does not meet the definition of an In Vitro Diagnostic device.

No
The letter mentions "SPECIAL CONTROLS" but does not explicitly state that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device.

Intended Use / Indications for Use

DentalMonitoring is a medical device software using image processing algorithms to analyze pictures of the oral cavity (hereinafter Scans). Scans are taken using the DM App, a smartphone, and the manufacturer's proprietary hardware products. Scans are taken by the patient, a non-healthcare professional, or a healthcare professional. The Scan is taken in healthcare facilities, such as a dental practice, or in a non-healthcare environment, such as the patient's own home. For some clinical parameters. DentalMonitoring requires a 3D Model. The product is designed to assist healthcare professionals in remotely monitoring orthodontic treatments and treatment progress. The results of DentalMonitoring are intended to be used as an aid in diagnosis and monitoring, not on a stand-alone basis for clinical decision-making. DentalMonitoring is indicated for use for patients over the age of 6 and reports results solely on permanent teeth.

DentalMonitoring can monitor the following clinical parameters:

  • . oral hygiene: dental plaque / food residue;

  • 트 soft tissue statement: gingival recession, black triangle;

  • . dental statement: closure of extraction space, tooth wear;

  • . alignment: closure of all anterior spaces; and

  • . dental occlusion:

    • o in 2D Monitoring: midline deviation, overbite/open bite, overjet
  • o in 3D Monitoring: canine class, midline deviation, overbite/open bite, overjet
    Additionally, the following clinical parameters specific to orthodontic treatment types or phases can be monitored using DentalMonitoring:

  • for aligner treatments: tracking (seat/unseat), attachment loss, button loss; .

  • . for braces: bracket debonding, tie loss, self-ligating clips, passive archwire and auxiliaries; and

  • for thermoformed retainers: tracking (seat/unseat). I

Based on an initial 3D Model provided by a healthcare professional. DentalMonitoring can also provide healthcare professionals with 3D Models representative of the patient's dentition and treatment progress. This device is a prescription device and is not intended for over-the-counter use

Product codes

SBC

Device Description

DentalMonitoring is a standalone software with embedded artificial intelligence comprising machine learning and locked neural network algorithms. The product is composed of these parts: the Dashboard, the DM App along with a DM Cheek Retractor and DM ScanBox, and the Data Analysis Platform.

The four steps are detailed below:

    1. Patient profile set-up: The healthcare professional sets up the patient profile through a web- based interface, Dashboard, accessible at www.dental-monitoring.com/doctor. During the patient profile set-up, the healthcare professional is prompted to set up a Protocol in order to select the clinical parameters they wish to monitor in accordance with the patient's treatment. During the set-up, the healthcare professional also determines the appropriate frequency at which the patient should use the DM App to take pictures of their intraoral cavity.
    1. Intraoral pictures acquisition: A set of pictures of the patient's intraoral cavity, hereinafter referred to as a Scan, is taken using the DM App along with a DM Cheek Retractor and DM ScanBox. The DM Cheek Retractor is an intraoral retraction device for the cheeks and lips to allow for sufficient space for image capture. The DM ScanBox is an extraoral holding apparatus for the smartphone that attaches to the DM Cheek Retractor. The DM App guides the user through the appropriate steps in order to obtain a complete Scan. This DM App is a mobile application installed on a smartphone; thus, the pictures are captured through the smartphone's main camera allowing the procedure to be totally non-invasive to the patient.
    1. Analysis of acquired intraoral pictures: The Scan is processed through the Data Analysis Platform. The Data Analysis Platform includes a technical processing phase and clinical processing phase, the latter being a clinical analysis to determine if any event has occurred within the clinical parameters the healthcare professional has set up to be monitored. The Data Analysis Platform uses AI comprising image processing algorithms and neural networks.
    1. Communication of results of the analysis performed through the Data Analysis Platform are communicated to the healthcare professional through the Dashboard on one hand, and to the patient through the DM App on the other hand. Results are shared with the healthcare professional in an exhaustive fashion, providing them with detailed information. As for the patient, the results are communicated in accordance with the rules defined by the healthcare professional in the Protocol applied to the patient.

DentalMonitoring enables HCPs to adapt the use of the product according to their needs depending on each patient's orthodontic treatment. DentalMonitoring comprises two types of monitoring: 2D Monitoring and 3D Monitoring. Some clinical parameters are specific to either 2D Monitoring, or 3D Monitoring.

Mentions image processing

Yes

Mentions AI, DNN, or ML

Yes

Input Imaging Modality

optical camera-based, intraoral images

Anatomical Site

oral cavity, permanent teeth, dentition

Indicated Patient Age Range

patients over the age of 6

Intended User / Care Setting

healthcare professionals in healthcare facilities, such as a dental practice, or patients (or a non-healthcare professional) in a non-healthcare environment, such as the patient's own home.

Description of the training set, sample size, data source, and annotation protocol

Not Found

Description of the test set, sample size, data source, and annotation protocol

Retrospective study (21-001):

  • Sample Size: Contains multiple tables with different sample sizes for each clinical parameter. For example, Dental plaque / food residue had a total of 5,064 comparisons between DM and Reference. Gingival recession had 870 total comparisons. Black triangle had 1,137 comparisons. Closure of extraction space had 478 comparisons. Tooth wear had 1,066 comparisons. Closure of all anterior spaces had 713 comparisons. Tracking (seat/unseat) had 3,323 comparisons. Attachment loss had 765 comparisons. Button loss had 659 comparisons. Bracket debonding had 659 comparisons. Tie loss had 653 comparisons. Self-ligating clips had 647 comparisons.
  • Data Source: Scans retrospectively collected.
  • Annotation Protocol: Scans were reviewed by a panel of three independent orthodontists with an assessment done per tooth / interdental space. In case of non-dominant results, a consensus was established by the same group of three independent orthodontists. Dominant results and result of the consensus review were merged in order to generate the Reference Method initial outcome. Per indication, results presenting discrepancies between the Reference Method and the Candidate Method, i.e., False Positive results and False Negative results, were reviewed by one of the orthodontists among the 15 that took part in the study.

Prospective study (21-002: Occlusion study):

  • Sample Size: 215 patients rendering 297 results for canine class; 277 patients rendering 277 results for midline deviation - 2D; 291 patients rendering 294 results for midline deviation - 3D; 285 patients rendering 301 results for overbite/open bite - 2D; 287 patients rendering 298 results for overbite/open bite - 3D; 208 patients rendering 245 results for overjet - 2D; 263 patients rendering 292 results for overjet - 3D.
  • Data Source: Data collected prospectively from four sites located in the United States: three sites for patient enrollment and one site for generation of the Reference Method results.
  • Annotation Protocol: Reference Method results were generated by measuring the occlusion parameters undergoing evaluation on 3D Models of the patients enrolled in the study. Measurements were done manually and performed in three replicates using a CAD/CAM software.

Prospective study (21-003: Archwire & Auxiliaries study):

  • Sample Size: 273 patients for Passive archwire and auxiliaries - 2D Monitoring and 269 patients for Passive archwire and auxiliaries - 3D Monitoring, both resulting in 730 total comparisons.
  • Data Source: Data collected prospectively from six sites located in the United States: five sites for patient enrollment and one site for generation of the Reference Method results.
  • Annotation Protocol: Reference Method results were generated by performing a best fit on the acquired 3D Models. The best fit was performed per arch and per patient between the 3D Models acquired at two different timepoints. The best fits were done using a CAD/CAM software.

Prospective study (21-004: Updated 3D Model study):

  • Sample Size: 250 patients, resulting in 536 results.
  • Data Source: Data collected prospectively from seven sites located in the United States: six sites for patient enrollment and one site for generation of the study results.
  • Annotation Protocol: Study results were generated by performing a best fit between the acquired 3D Models and the 3D Model generated by DentalMonitoring, i.e. Updated 3D Model. The best fit was performed per arch and per patient. The best fits were done using a CAD/CAM software.

Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)

Summary of Clinical Information: The Sponsor provided data from a Clinical Investigation Program to support the clinical performance of DentalMonitoring.

AI/ML standalone testing:

  • Standalone performance of each network and algorithm was evaluated. Neural networks and algorithms were classified into three families according to the outputs they provide. A unique protocol was established per family in order to perform the evaluation, with acceptance criteria adapted to each neural network and algorithm. DentalMonitoring comprises technical networks and algorithms as well as clinical neural networks and algorithms. The standalone testing showed acceptable performance of critical features to demonstrate the device's ability to perform both its clinical and technological functions.

Retrospective study (21-001):

  • Study type: Retrospective
  • Targeted indications: Qualitative indications with Reference Method compatible with DentalMonitoring picture set review.
    • (dental plaque / food residue: 2D)
    • (gingival recession: 2D)
    • (black triangle: 2D)
    • (closure of extraction space: 2D)
    • (closure of all anterior spaces: 2D)
    • (tracking (seat/unseat): 2D)
    • (attachment loss: 2D)
    • (button loss: 2D)
    • (bracket debonding: 2D)
    • (tie loss: 2D)
    • (self-ligating clips: 2D)
  • Sample Size:
    • Dental plaque / food residue: 5,064 comparisons
    • Gingival recession: 870 comparisons
    • Black triangle: 1,137 comparisons
    • Closure of extraction space: 478 comparisons
    • Tooth wear: 1,066 comparisons
    • Closure of all anterior spaces: 713 comparisons
    • Tracking (seat/unseat): 3,323 comparisons for presence/absence detection; 1,360 for level detection.
    • Attachment loss: 765 comparisons
    • Button loss: 659 comparisons
    • Bracket debonding: 659 comparisons
    • Tie loss: 653 comparisons
    • Self-ligating clips: 647 comparisons

Prospective study (21-002):

  • Study type: Prospective
  • Targeted indications: Occlusion indications
    • (canine class: 3D)
    • (midline deviation: 2D)
    • (midline deviation: 3D)
    • (overbite/open bite: 2D)
    • (overbite/open bite: 3D)
    • (overjet: 2D)
    • (overjet: 3D)
  • Sample Size:
    • Canine class - 3D Monitoring: 215 patients, 297 results
    • Midline deviation - 2D Monitoring: 277 patients, 277 results
    • Midline deviation - 3D Monitoring: 291 patients, 294 results
    • Overbite / open bite - 2D Monitoring: 285 patients, 301 results
    • Overbite / open bite - 3D Monitoring: 287 patients, 298 results
    • Overjet - 2D Monitoring: 208 patients, 245 results
    • Overjet - 3D Monitoring: 263 patients, 292 results

Prospective study (21-003):

  • Study type: Prospective
  • Targeted indications: Passive archwire and auxiliaries indication
    • (passive archwire and auxiliaries: 2D)
    • (passive archwire and auxiliaries: 3D)
  • Sample Size: 730 total comparisons for both 2D and 3D monitoring.

Prospective study (21-004):

  • Study type: Prospective
  • Targeted indications: Updated 3D Model indication
    • (Updated 3D Model: 3D)
  • Sample Size: 250 patients, 536 results.

Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)

Dental plaque / food residue:

  • Sensitivity: 82.5% (95% CI: 79.9%, 84.8%)
  • Specificity: 83.2% (95% CI: 80.5%, 85.5%)

Gingival recession:

  • Sensitivity: 79.9% (95% CI: 70.3%, 86.9%)
  • Specificity: 97.4% (95% CI: 95.8%, 98.4%)

Black triangle:

  • Sensitivity: 81.0% (95% CI: 73.9%, 86.5%)
  • Specificity: 98.4% (95% CI: 96.9%, 99.2%)

Closure of extraction space:

  • Sensitivity: 100.0% (95% CI: 94.2%, /)
  • Specificity: 91.8% (95% CI: 87.2%, 94.9%)

Tooth wear:

  • Sensitivity: 84.5% (95% CI: 74.1%, 91.2%)
  • Specificity: 97.0% (95% CI: 94.9%, 98.2%)

Closure of all anterior spaces:

  • Sensitivity: 98.3% (95% CI: 94.9%, 99.5%)
  • Specificity: 83.3% (95% CI: 79.9%, 86.3%)

Tracking (seat/unseat) - Detection of patients with the evaluated condition (presence/absence):

  • Sensitivity: 93.2% (95% CI: 91.3%, 94.7%)
  • Specificity: 86.2% (95% CI: 83.4%, 88.6%)

Tracking (seat/unseat) - Detection of patients with the level of the condition (slight/noticeable):

  • Sensitivity: 91.1% (95% CI: 85.9%, 94.5%)
  • Specificity: 90.5% (95% CI: 87.7%, 92.7%)

Attachment loss:

  • Sensitivity: 98.2% (95% CI: 94.3%, 99.4%)
  • Specificity: 100.0% (95% CI: 98.7%, /)

Button loss:

  • Sensitivity: 98.4% (95% CI: 94.0%, 99.6%)
  • Specificity: 99.0% (95% CI: 96.9%, 99.7%)

Bracket debonding:

  • Sensitivity: 98.4% (95% CI: 93.8%, 99.6%)
  • Specificity: 99.6% (95% CI: 98.5%, 99.9%)

Tie loss:

  • Sensitivity: 93.3% (95% CI: 85.7%, 97.0%)
  • Specificity: 96.5% (95% CI: 94.0%, 98.0%)

Self-ligating clips:

  • Sensitivity: 91.1% (95% CI: 82.5%, 95.7%)
  • Specificity: 88.3% (95% CI: 84.1%, 91.5%)

Canine class - 3D Monitoring:

  • Slope: 0.95 (95% CI: [0.92, 0.98])
  • Intercept: -0.10 mm (95% CI: [-0.14, -0.04])
  • Bias at 0.00 mm: -0.10 mm (95% CI: [-0.18, 0.00])
  • Bias at -2.00 mm: -0.3% (95% CI: [-4.9, 6.8])
  • Bias at 3.00 mm: -9.4% (95% CI: [-12.9, -5.3])
  • Bias at 5.00 mm: -7.9% (95% CI: [-11.0, -4.4])

Midline deviation - 2D Monitoring:

  • Slope: 0.93 (95% CI: [0.89, 0.97])
  • Intercept: 0.0 mm (-0.03) (95% CI: [0.0, 0.0] [-0.05, 0.01])
  • Bias at 0.0 mm: 0.0 mm (0.03) (95% CI: [0.0, 0.0] [-0.07, 0.03])
  • Bias at -2.0 mm: 5.3% (95% CI: [-0.8, 10.7])
  • Bias at 2.0 mm: -8.9% (95% CI: [-13.6, -3.2])

Midline deviation - 3D Monitoring:

  • Slope: 0.98 (95% CI: [0.96, 1.00])
  • Intercept: -0.01 mm (95% CI: [-0.02, 0.01])
  • Bias at 0.0 mm: -0.01 mm (95% CI: [-0.03, 0.02])
  • Bias at -2.00 mm: 2.0 % (95% CI: [-0.5, 4.8])
  • Bias at 2.00 mm: -2.7% (95% CI: [-5.2, -0.4])

Overbite / open bite - 2D Monitoring:

  • Slope: 0.95 (95% CI: [0.91, 0.99])
  • Intercept: 0.2 mm (95% CI: [0.1, 0.3])
  • Bias at 0.0 mm: 0.2 mm (95% CI: [0.0, 0.3])
  • Bias at 3.0 mm: 0.9% (95% CI: [-2.4, 3.7])
  • Bias at 5.0 mm: -1.3 % (95% CI: [-4.1, 1.2])
  • Bias at 7.0 mm: -2.3 % (95% CI: [-5.5, 0.5])

Overbite / open bite - 3D Monitoring:

  • Slope: 0.97 (95% CI: [0.96, 0.99])
  • Intercept: 0.01 mm (95% CI: [-0.02, 0.05])
  • Bias at 0.00 mm: 0.01 mm (95% CI: [-0.03, 0.05])
  • Bias at 3.00 mm: -2.2% (95% CI: [-3.1, -1.5])
  • Bias at 5.00 mm: -2.4% (95% CI: [-3.3, -1.4])
  • Bias at 7.00 mm: -2.4% (95% CI: [-3.5, -1.3])

Overjet - 2D Monitoring:

  • Slope: 0.84 (95% CI: [0.78, 0.89])
  • Intercept: -0.3 mm (95% CI: [0.1, 0.4])
  • Bias at 0.0 mm: -0.3 mm (95% CI: [0.1, 0.5])
  • Bias at 3.0 mm: -7.0% (95% CI: [-11.5, -3.5])
  • Bias at 5.0 mm: -11.2% (95% CI: [-15.6, -7.1])
  • Bias at 7.0 mm: -13.0% (95% CI: [-18.2, -8.3])
  • Bias at 9.0 mm: -14.1% (95% CI: [-19.8, -8.8])

Overjet - 3D Monitoring:

  • Slope: 1.03 (95% CI: [1.01, 1.05])
  • Intercept: 0.14 mm (95% CI: [0.09, 0.19])
  • Bias at 0.00 mm: 0.14 mm (95% CI: [0.07, 0.23])
  • Bias at 3.00 mm: 7.2% (95% CI: [6.0, 8.9])
  • Bias at 5.00 mm: 5.4% (95% CI: [4.5, 6.7])
  • Bias at 7.00 mm: 4.7% (95% CI: [3.7, 6.0])
  • Bias at 9.00 mm: 4.3% (95% CI: [3.2, 5.6])

Passive archwire and auxiliaries - 2D Monitoring:

  • Sensitivity: 89.0% (95% CI: 84.9%, 92.1%)
  • Specificity: 80.4% (95% CI: 75.1%, 84.8%)

Passive archwire and auxiliaries - 3D Monitoring:

  • Sensitivity: 90.4% (95% CI: 86.7%, 93.2%)
  • Specificity: 85.5% (95% CI: 80.8%, 89.2%)

Updated 3D Model study (MAE):

  • Mean Absolute Error (MAE): 0.10 (95% CI: [0.093; 0.103])

Predicate Device(s)

Not Found

Reference Device(s)

Not Found

Predetermined Change Control Plan (PCCP) - All Relevant Information

Not Found

N/A

0

DE NOVO CLASSIFICATION REQUEST FOR

DentalMonitoring

REGULATORY INFORMATION

FDA identifies this generic type of device as:

Dental Image Analyzer. A dental image analyzer is a prescription home use device that uses software intended to collect and analyze patient-specific. optical camera-based, intraoral images. The analyses are provided to dental health care professionals as an aid to diagnosis of oral health conditions and/or to monitor treatment progress.

NEW REGULATION NUMBER: 872.1770

CLASSIFICATION: Class II

PRODUCT CODE: SBC

BACKGROUND

DEVICE NAME: DentalMonitoring

SUBMISSION NUMBER: DEN230035

DATE DE NOVO RECEIVED: 05/04/2023

SPONSOR INFORMATION:

Dental Monitoring SAS Isabelle Puraye 75 rue de Tocqueville Paris 75017

INDICATIONS FOR USE

DentalMonitoring is a medical device software using image processing algorithms to analyze pictures of the oral cavity (hereinafter Scans). Scans are taken using the DM App, a smartphone, and the manufacturer's proprietary hardware products. Scans are taken by the patient, a non-healthcare professional, or a healthcare professional. The Scan is taken in healthcare facilities, such as a dental practice, or in a non-healthcare environment, such as the patient's own home. For some clinical parameters. DentalMonitoring requires a 3D Model. The product is designed to assist healthcare professionals in remotely monitoring orthodontic treatments and treatment progress. The results of DentalMonitoring are intended to be used as an aid in diagnosis and monitoring, not on a stand-alone basis for clinical decision-making. DentalMonitoring is indicated for use for patients over the age of 6 and reports results solely on permanent teeth.

DentalMonitoring can monitor the following clinical parameters:

  • . oral hygiene: dental plaque / food residue;
  • 트 soft tissue statement: gingival recession, black triangle;
  • . dental statement: closure of extraction space, tooth wear;
  • . alignment: closure of all anterior spaces; and
  • . dental occlusion:
    • o in 2D Monitoring: midline deviation, overbite/open bite, overjet

1

  • o in 3D Monitoring: canine class, midline deviation, overbite/open bite, overjet
    Additionally, the following clinical parameters specific to orthodontic treatment types or phases can be monitored using DentalMonitoring:

  • for aligner treatments: tracking (seat/unseat), attachment loss, button loss; .

  • . for braces: bracket debonding, tie loss, self-ligating clips, passive archwire and auxiliaries; and

  • for thermoformed retainers: tracking (seat/unseat). I

Based on an initial 3D Model provided by a healthcare professional. DentalMonitoring can also provide healthcare professionals with 3D Models representative of the patient's dentition and treatment progress. This device is a prescription device and is not intended for over-the-counter use

LIMITATIONS

DentalMonitoring should not be used on patients under the age of 6.

Dental Monitoring should not be used by patients presenting systemic conditions affective connective tissues not allowing them to open/close their buccal cavity sufficiently to acquire acceptable Scans.

The following population should be assisted by a third party to perform Scans:

  • . Children up to 12;
  • . Adults or children visually impaired;
  • . Adults or children hearing impaired:
  • . Or any condition that might prevent the patient from adopting the right position to take a Scan.

DentalMonitoring is not intended to replace standard practices for treatment. Final clinical decisions remain the sole responsibility of the healthcare professional. In order to establish a diagnosis. further examinations are required according to the current standard of care, such as dental radiographs and/or tactile examinations with instrumentation.

DentalMonitoring results are limited only to elements visible in the input Scans. DentalMonitoring does not provide results on non-visible elements such as potential interproximal and lingual cavities. DentalMonitoring does not provide results on lingual surfaces.

PLEASE REFER TO THE LABELING FOR A COMPLETE LIST OF WARNINGS. PRECAUTIONS AND CONTRAINDICATIONS.

DEVICE DESCRIPTION

DentalMonitoring is a standalone software with embedded artificial intelligence comprising machine learning and locked neural network algorithms. The product is composed of these parts: the Dashboard, the DM App along with a DM Cheek Retractor and DM ScanBox, and the Data Analysis Platform.

2

Image /page/2/Figure/0 description: This image shows a diagram of a 4-step process. The first step is patient profile set-up, which is represented by a computer screen. The second step is intraoral pictures acquisition, which is represented by a smartphone. The third step is analysis of acquired intraoral pictures, which is represented by a tooth and magnifying glass. The fourth step is communication of results, which is represented by a smartphone.

The four steps are detailed below:

    1. Patient profile set-up: The healthcare professional sets up the patient profile through a web- based interface, Dashboard, accessible at www.dental-monitoring.com/doctor. During the patient profile set-up, the healthcare professional is prompted to set up a Protocol in order to select the clinical parameters they wish to monitor in accordance with the patient's treatment. During the set-up, the healthcare professional also determines the appropriate frequency at which the patient should use the DM App to take pictures of their intraoral cavity.
    1. Intraoral pictures acquisition: A set of pictures of the patient's intraoral cavity, hereinafter referred to as a Scan, is taken using the DM App along with a DM Cheek Retractor and DM ScanBox. The DM Cheek Retractor is an intraoral retraction device for the cheeks and lips to allow for sufficient space for image capture. The DM ScanBox is an extraoral holding apparatus for the smartphone that attaches to the DM Cheek Retractor. The DM App guides the user through the appropriate steps in order to obtain a complete Scan. This DM App is a mobile application installed on a smartphone; thus, the pictures are captured through the smartphone's main camera allowing the procedure to be totally non-invasive to the patient.

3

    1. Analysis of acquired intraoral pictures: The Scan is processed through the Data Analysis Platform. The Data Analysis Platform includes a technical processing phase and clinical processing phase, the latter being a clinical analysis to determine if any event has occurred within the clinical parameters the healthcare professional has set up to be monitored. The Data Analysis Platform uses AI comprising image processing algorithms and neural networks.
    1. Communication of results of the analysis performed through the Data Analysis Platform are communicated to the healthcare professional through the Dashboard on one hand, and to the patient through the DM App on the other hand. Results are shared with the healthcare professional in an exhaustive fashion, providing them with detailed information. As for the patient, the results are communicated in accordance with the rules defined by the healthcare professional in the Protocol applied to the patient.

DentalMonitoring enables HCPs to adapt the use of the product according to their needs depending on each patient's orthodontic treatment. DentalMonitoring comprises two types of monitoring: 2D Monitoring and 3D Monitoring. Some clinical parameters are specific to either 2D Monitoring, or 3D Monitoring.

SUMMARY OF NONCLINICAL/BENCH STUDIES

BIOCOMPATIBILITY/MATERIALS

The DM Cheek Retractor were evaluated per ISO 10993-1 (2020): "Biological evaluation of medical devices Part 1: evaluation and testing with a risk management" and ISO 7405-2018 - Dentistry - evaluation of biocompatibility of medical devices used in dentistry. The proposed device passed cytotoxicity tests according to ISO 10993-5, skin sensitization according to ISO 10993-10, and irritation or intracutaneous reactivity according to ISO 10993-23.

SOFTWARE

DentalMonitoring has a Modate Level of Concern (LOC). Appropriate software documentation for was provided in compliance with the FDA guidance document "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (issued in May 2005). Verification and validation (V&V) activities were performed and described at the unit and system level.

CYBER SECURITY

DentalMonitoring approach to cybersecurity aligns with FDA's 2020 guidance titled, "Guidance on Cybersecurity For Medical Devices" The device also conforms to the cybersecurity requirements identified in Section 524B to the FD&C Act.

PERFORMANCE TESTING - BENCH

AI/ML standalone testing

Standalone performance of each network and algorithm was evaluated. Neural networks and algorithms were classified into three families according to the outputs they provide. A unique protocol was established per family in order to perform the evaluation, with acceptance criteria adapted to each neural network and algorithm. DentalMonitoring comprises technical networks and algorithms as well as clinical neural networks and algorithms. The standalone testing showed acceptable performance of critical

4

features to demonstrate the device's ability to perform both it's clinical and technological functions.

SUMMARY OF CLINICAL INFORMATION

The Sponsor provided data from a Clinical Investigation Program to support the clinical performance of DentalMonitoring.

| Study type | Stud
y
code | Study name | Overview of targeted
indications | List
(indication;
monitoring plan)
couples targeted |
|---------------|-------------------|------------------------------|---------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Retrospective | 21-001 | Retrospective | Qualitative indications
with Reference Method
compatible with
DentalMonitoring picture
set review | (dental plaque / food
residue: 2D)
(gingival recession: 2D)
(black triangle: 2D)
(closure of extraction
space: 2D)
(closure of all anterior
spaces: 2D)
(tracking (seat/unseat):
2D)
(attachment loss: 2D)
(button loss: 2D)
(bracket debonding: 2D)
(tie loss: 2D)
(self-ligating clips: 2D) |
| Prospective | 21-002 | Occlusion | Occlusion indications | (canine class: 3D)
(midline deviation: 2D)
(midline deviation: 3D)
(overbite/open bite: 2D)
(overbite/open bite: 3D)
(overjet: 2D)
(overjet: 3D) |
| Prospective | 21-003 | Archwire
&
Auxiliaries | Passive archwire and
auxiliaries indication | (passive archwire and
auxiliaries: 2D)
(passive archwire and
auxiliaries: 3D) |
| Prospective | 21-004 | Updated 3D
Model | Updated 3D Model
indication | (Updated 3D Model: 3D) |

DentalMonitoring Clinical Investigation Program
---------------------------------------------------

Retrospective study

DentalMonitoring evaluated the qualitative indications that were able to have the Reference Method used solely DentalMonitoring picture sets (= Scan). The study was performed using Scans retrospectively collected and involved a total of 15 US orthodontists.

The Reference Method results were generated as follow:

5

  • Scans were reviewed by a panel of three independent orthodontists with an assessment done per tooth ్ల / interdental space.
  • In case of non-dominant results, a consensus was established by the same group of three ਼ independent orthodontists. Dominant results and result of the consensus review were merged in order to generate the Reference Method initial outcome.
  • -Per indication, results presenting discrepancies between the Reference Method and the Candidate Method, i.e., False Positive results and False Negative results, were reviewed by one of the orthodontists among the 15 that took part in the study.

Data was collected in order to qualify the patient demographics.

6

Results per indication

Dental plaque / food residue

Characteristic# (%)
Age group
12- 22 years of age367 (49.5%)
≥ 22 years of age4 (0.6%)
≤12 years old369 (49.8%)
Unknown1 (0.1%)
Location
Central420 (56.7%)
East Coast209 (28.2%)
US - Other5 (0.7%)
West Coast60 (8.1%)
Western30 (4.0%)
Out of US17 (2.3%)
Treatment type
Aligners415 (56.0%)
Brackets - Ceramic9 (1.2%)
Brackets - Self-ligating128 (17.3%)
Brackets - Traditional135 (18.2%)
Mixed32 (4.3%)
None5 (0.7%)
Retainers17 (2.3%)

Final comparison between DentalMonitoring and Reference

| | | Final comparison between DentalMonitoring and Reference
Reference Result | | |
|--------------|------------------------------------|-----------------------------------------------------------------------------|----------|-------|
| | | Positive (Noticeable or Slight) | Negative | Total |
| | Positive (Noticeable or
Slight) | 1,874 | 356 | 2,230 |
| DM
Result | Negative | 362 | 2,472 | 2,834 |
| | Total | 2,236 | 2,828 | 5,064 |

Final study results for dental plaque / food residue

| | Result | 95% CI Lower
Bound | 95% CI Upper
Bound |
|-------------|--------|-----------------------|-----------------------|
| Sensitivity | 82.5% | 79.9% | 84.8% |
| Specificity | 83.2% | 80.5% | 85.5% |

Scans were taken using the following phone manufacturers: Apple, Samsung, Google, Motorola, LG, OnePlus, Huawei, Xiaomi, Essential Phone

7

Gingival recession

Characteristic# (%)
Age group
12- 22 years of age205 (51.3%)
≥ 22 years of age194 (48.5%)
≤12 years old1 (0.2%)
Location
Central236 (59%)
East Coast96 (24%)
West Coast30 (7.5%)
US - Other5 (1.2%)
Out of US12 (3%)
Western21 (5.3%)
Treatment type
Aligners205 (51.2%)
Retainers17 (4.2%)
Brackets - Ceramic7 (1.8%)
Brackets - Self-ligating68 (17%)
Brackets - Traditional82 (20.5%)
Mixed treatment20 (5%)
No treatment1 (0.3%)

Final comparison between DentalMonitoring and Reference

Reference Result
PositiveNegativeTotal
DM
ResultPositive771895
DM
ResultNegative19756775
DM
ResultTotal96774870

Final study results for gingival recession

| | Result | 95% CI Lower
Bound | 95% CI Upper
Bound |
|-------------|--------|-----------------------|-----------------------|
| Sensitivity | 79.9% | 70.3% | 86.9% |
| Specificity | 97.4% | 95.8% | 98.4% |

Scans were taken using the following phone manufacturers: Apple, Samsung, Google, Motorola, LG, Huawei, Essential Phone, Kyocera, OnePlus, and Wiko.

8

Black triangle

Characteristic# (%)
Age group
12 - 22 years of age233 (62%)
≥ 22 years of age140 (37.2%)
≤ 12 years old3 (0.8%)
Location
Central231 (61.4%)
East Coast97 (25.8%)
West Coast23 (6.1%)
Out of US7 (1.9%)
Western14 (3.7%)
US-Other4 (1.1%)
Treatment type
Aligners166 (44.2%)
Retainers12 (3.2%)
Brackets - Ceramic9 (2.4%)
Brackets - Self-ligating79 (21%)
Brackets - Traditional87 (23.1%)
Mixed treatment21 (5.6%)
No treatment2 (0.5%)

Final comparison between DentalMonitoring and Reference

Reference Result
DM ResultPositiveNegativeTotal
Positive17912191
DM
ResultNegative40906946
Total2199181,137

Final study results for black triangle

| | Result | 95% CI Lower
Bound | 95% CI Upper
Bound |
|-------------|--------|-----------------------|-----------------------|
| Sensitivity | 81.0% | 73.9% | 86.5% |
| Specificity | 98.4% | 96.9% | 99.2% |

Scans were taken using the following phone manufacturers: Apple, Samsung, Google, Motorola, LG, OnePlus, Huawei, and Xiaomi.

9

Closure of extraction space

Characteristic# (%)
Age group
12 -22 years of age105 (41.3%)
≥ 22 years of age5 (2.0%)
≤ 12 years old142 (55.9%)
Unknown2 (0.8%)
Location
Central137 (53.9%)
East Coast67 (26.4%)
US - Other6 (2.4%)
West Coast25 (9.8%)
Western11 (4.3%)
out of US8 (3.2%)
Treatment type
Aligners125 (49.2%)
Brackets - Ceramic3 (1.2%)
Brackets - Self-ligating55 (21.7%)
Brackets - Traditional44 (17.3%)
Mixed treatment16 (6.3%)
None1 (0.4%)
Retainers10 (3.9%)

Final comparison between DentalMonitoring and Reference

Reference Result
PositiveNegativeTotal
DM
ResultPositive19824222
Negative0256256
Total198280478

Final study results for closure of extraction space

Result95% CI Lower Bound95% CI Upper Bound
Sensitivity100.0%94.2%/
Specificity91.8%87.2%94.9%

Scans were taken using the following phone manufacturers: Apple, Samsung, LG, Google, Motorola, Essential Phone, Huawei, and Wiko.

10

Tooth wear

Characteristic# (%)
Age group
12 - 22 years of age200 (54.8%)
≥ 22 years of age164 (44.9%)
≤ 12 years old1 (0.3%)
Location
Central232 (63.6%)
East Coast83 (22.7%)
West Coast22 (6.0%)
Western14 (3.8%)
Out of US11 (3.0%)
US-Other3 (0.8%)
Treatment type
Aligners162 (44.4%)
Brackets - Ceramic5 (1.4%)
Brackets - Self-ligating74 (20.3%)
Brackets - Traditional88 (24.1%)
Mixed1 (0.3%)
Mixed treatment22 (6%)
None1 (0.3%)
Retainers12 (3.3%)

Final comparison between DentalMonitoring and Reference

Reference Result
PositiveNegativeTotal
DM
ResultPositive8921110
Negative13943956
Total1029641,066

Final study results for tooth wear

| | Result | 95% CI
Lower Bound | 95% CI
Upper Bound |
|-------------|--------|-----------------------|-----------------------|
| Sensitivity | 84.5% | 74.1% | 91.2% |
| Specificity | 97.0% | 94.9% | 98.2% |

Scans were taken using the following phone manufacturers: Apple, Samsung, LG, Google, Motorola, Huawei, and Essential Phone.

11

Closure of all anterior spaces

Characteristic# (%)
Age group
12 - 22 years of age297 (57.5%)
> 22 years of age213 (41.3%)
≤ 12 years old4 (0.8%)
Unknown2 (0.4%)
Location
Central307 (59.5%)
East Coast131 (25.4%)
West Coast38 (7.4%)
Out of US10 (1.9%)
US - Other4 (0.8%)
Western26 (5.0%)
Treatment type
Aligners248 (48.1%)
Brackets - Ceramic6 (1.2%)
Brackets - Self-ligating114 (22.1%)
Brackets - Traditional106 (20.5%)
Mixed2 (0.4%)
Mixed treatment21 (4.1%)
None6 (1.2%)
Retainers13 (2.5%)

Final comparison between DentalMonitoring and Reference

Reference Result
PositiveNegativeTotal
Positive18088268
DM
ResultNegative3442445
Total183530713

Final study results for anterior space closure

| | Result | 95% CI Lower
Bound | 95% CI Upper
Bound |
|-------------|--------|-----------------------|-----------------------|
| Sensitivity | 98.3% | 94.9% | 99.5% |
| Specificity | 83.3% | 79.9% | 86.3% |

Scans were taken using the following phone manufacturers: Apple, Samsung, Google, Motorola, LG, Huawei, T-Mobile, Essential Phone, and Xiaomi.

12

Tracking (seat/unseat)

Characteristic# (%)
[12; 22[ years of age279 (44.8%)
≥ 22 years of age332 (53.3%)
≤ 12 years old9 (1.4%)
Unknown3 (0.5%)
Location
Central286 (45.9%)
East Coast192 (30.8%)
out of US17 (2.7%)
US - Other8 (1.3%)
West Coast85 (13.7%)
Western35 (5.6%)
Treatment type
Aligners581 (93.3%)
Brackets - Traditional4 (0.6%)
Mixed1 (0.2%)
Mixed treatment9 (1.4%)
Retainers28 (4.5%)

Clinical performances are expressed as two different Sensitivities and Specificities since the parameter outputs three levels.

  • Sensitivity and Specificity of the product in its ability to detect people with the evaluated 미 condition from people without; and
  • Sensitivity and Specificity of the product in its ability to discriminate the evaluated condition l at a slight level from a noticeable level

13

Reference Result
Positive (Noticeable
or Slight)NegativeTotal
Positive (Noticeable or
Slight)1,3601651,525
DM
ResultNegative1011,6971,798
Total1,4611,8623,323

Detection of patients with the evaluated condition (presence/absence)

Result95% CI Lower Bound95% CI Upper Bound
Sensitivity93.2%91.3%94.7%
Specificity86.2%83.4%88.6%

Detection of patients with the level of the condition (slight/noticeable)

Reference Result
NoticeableSlightTotal
DM
ResultNoticeable19399292
Slight181,0501,068
Total2111,1491,360

| | Result | 95% CI Lower
Bound | 95% CI Upper
Bound |
|-------------|--------|-----------------------|-----------------------|
| Sensitivity | 91.1% | 85.9% | 94.5% |
| Specificity | 90.5% | 87.7% | 92.7% |

Scans were taken using the following phone manufacturers: Apple, Samsung, Google, LG, Motorola, OnePlus, Huawei, Essential Phone, Wiko, and Xiaomi.

14

Attachment loss

Characteristic# (%)
Age group
]12; 22[ years of age146 (41.9%)
> 22 years of age200 (57.5%)
≤ 12 years old1 (0.3%)
Unknown1 (0.3%)
Location
Central171 (49.1%)
East Coast109 (31.3%)
West Coast39 (11.2%)
US - Other4 (1.2%)
Out of US8 (2.3%)
Western17 (4.9%)
Treatment type
Aligners330 (94.8%)
Retainers8 (2.3%)
Brackets - Traditional4 (1.2%)
Mixed treatment6 (1.7%)

Final comparison between DentalMonitoring and Reference

Reference Result
PositiveNegativeTotal
DM
ResultPositive1830183
Negative3579582
Total186579765

Final study results for attachment loss

| | Result | 95% CI Lower
Bound | 95% CI Upper
Bound |
|-------------|--------|-----------------------|-----------------------|
| Sensitivity | 98.2% | 94.3% | 99.4% |
| Specificity | 100.0% | 98.7% | |

Scans were taken using the following phone manufacturers: Apple, Samsung, Google, Motorola, LG, Xiaomi, OnePlus, and Essential Phone.

15

Button loss

Characteristic# (%)
Age group
]12; 22[ years of age200 (52.5%)
> 22 years of age158 (41.5%)
≤ 12 years old20 (5.2%)
Unknown3 (0.8%)
Location
Central138 (36.2%)
East Coast125 (32.8%)
West Coast92 (24.1%)
Out of US4 (1%)
Western16 (4.2%)
US - Other6 (1.6%)
Treatment type
Aligners370 (97.1%)
Retainers1 (0.3%)
Brackets - Ceramic1 (0.3%)
Brackets - Traditional3 (0.8%)
Mixed treatment6 (1.6%)

Final comparison between DentalMonitoring and Reference

Reference Result
PositiveNegativeTotal
DM
ResultPositive1275132
Negative2525527
Total129530659

Final study results for button loss

| | Result | 95% CI Lower
Bound | 95% CI Upper
Bound |
|-------------|--------|-----------------------|-----------------------|
| Sensitivity | 98.4% | 94.0% | 99.6% |
| Specificity | 99.0% | 96.9% | 99.7% |

Scans were taken using the following phone manufacturers: Apple, Samsung, LG, Motorola, Google, and Huawei.

16

Bracket debonding

Characteristic# (%)
Age group
]12; 22[ years of age270 (71.3%)
≥ 22 years of age107 (28.2%)
≤ 12 years old2 (0.5%)
Location
Central291 (76.8%)
East Coast60 (15.8%)
West Coast16 (4.2%)
Out of US1 (0.3%)
Western11 (2.9%)
Treatment type
Aligners1 (0.3%)
Brackets - Ceramic10 (2.5%)
Brackets - Self-ligating171 (45.1%)
Brackets - Traditional150 (39.6%)
Mixed treatment45 (11.9%)
None1 (0.3%)
Retainers1 (0.3%)

Final comparison between DentalMonitoring and Reference

Reference Result
PositiveNegativeTotal
DM
ResultPositive1272129
Negative2528530
Total129530659

Final study results for bracket debonding

| | Result | 95% CI Lower
Bound | 95% CI Upper
Bound |
|-------------|--------|-----------------------|-----------------------|
| Sensitivity | 98.4% | 93.8% | 99.6% |
| Specificity | 99.6% | 98.5% | 99.9% |

Scans were taken using the following phone manufacturers: Apple, Samsung, Google, LG, Motorola, One Plus.

17

Tie loss

Characteristic# (%)
Age group
]12; 22[ years of age240 (77.4%)
$\geq$ 22 years of age66 (21.3%)
$\leq$ 12 years old4 (1.3%)
Location
Central255 (82.2%)
East Coast39 (12.6%)
West Coast10 (3.2%)
Western3 (1.0%)
Out of US3 (1.0%)
Treatment type
Aligners1 (0.3%)
Brackets - Ceramic13 (4.2%)
Brackets - Self-ligating5 (1.6%)
Brackets - Traditional267 (86.2%)
Mixed1 (0.3%)
Mixed treatment23 (7.4%)

Final comparison between DentalMonitoring and Reference

Reference Result
PositiveNegativeTotal
DM
ResultPositive11115126
Negative7520527
Total118535653

Final study results for tie loss

| | Result | 95% CI Lower
Bound | 95% CI Upper
Bound |
|-------------|--------|-----------------------|-----------------------|
| Sensitivity | 93.3% | 85.7% | 97.0% |
| Specificity | 96.5% | 94.0% | 98.0% |

Scans were taken using the following phone manufacturers: Apple, Samsung, Motorola, LG, Google.

18

Self-ligating clips

Characteristic#(%)
Age group
]12; 22[ years of age217(66.8%)
≥ 22 years of age103(31.7%)
≤ 12 years old5(1.5%)
Location
Central225(69.3%)
East Coast69(21.2%)
Western16(4.9%)
West Coast12(3.7%)
Out of US3(0.9%)
Treatment type
Brackets - Ceramic5(1.5%)
Brackets - Self-ligating262(80.6%)
Brackets - Traditional21(6.5%)
Mixed2(0.6%)
Mixed treatment35(10.8%)

Final comparison between DentalMonitoring and Reference

Reference Result
PositiveNegativeTotal
DM
ResultPositive7148119
DM
ResultNegative7521528
DM
ResultTotal78569647

Final study results for self-ligating clip

| | Result | 95% CI Lower
Bound | 95% CI Upper
Bound |
|-------------|--------|-----------------------|-----------------------|
| Sensitivity | 91.1% | 82.5% | 95.7% |
| Specificity | 88.3% | 84.1% | 91.5% |

Scans were taken using the following phone manufacturers: Apple, Samsung, Google, LG, Motorola, Huawei, Kyocera, and OnePlus.

19

Occlusion study

DentalMonitoring evaluated the occlusion indications using 3D Models acquired with intraoral scanners as input data to the Reference Method. The study was performed using data collected prospectively. The study involved four sites located in the United States: three sites for patient enrollment and one site for generation of the Reference Method results.

The Reference Method results were generated by measuring the occlusion parameters undergoing evaluation on 3D Models of the patients enrolled in the study. Measurements were done manually and performed in three replicates using a CAD/CAM software.

Analysis was performed according to "Measurement Procedure Comparison and Bias Estimation Using Patient Samples; Clinical and Laboratory Standards Institute guideline", EP09c - Third Edition, 2018. Analysis comprised using a :Passing-Bablok regression analysis, including plots of Candidate Method verses Reference Method to calculate the slope, intercept, and correlation coefficient of the plot. Bias at levels of interest per study group were computed at the levels of interest and confidence intervals were calculated with the 95% Bootstrapping.

Data was collected in order to qualify the patient demographics.

20

Results per indication

Canine class - 3D Monitoring

A total of 215 patients rendering 297 results were included in the analysis. One patient could render multiple results corresponding to left canine class and right canine class.

Characteristic# (%)
Gender
Male153 (71.2%)
Female62 (28.8%)
Age group
[6; 12] years of age23 (10.7%)
]12; 22[ years of age75 (34.9%)
≥ 22 years of age117 (54.4%)
Race*
American Indian or Alaska Native13 (6.0%)
Asian10 (4.7%)
Black or African American12 (5.6%)
Native Hawaiian or Other Pacific Islander0 (0.0%)
White168 (78.1%)
Unknown race14 (6.5%)
Ethnicity
Spanish origin32 (14.9%)
Not Hispanic or Latino183 (85.1%)
Income of the household (annual)
Less than $19,9999 (4.2%)
$20,000-$37,99911 (5.1%)
$38,000-$44,9993 (1.4%)
$45,000-$54,9997 (3.3%)
$55,000-$64,99914 (6.5%)
$65,000-$74,99911 (5.1%)
$75,000-$99,99925 (11.6%)
$100,000 or more69 (32.1%)
Unknown66 (30.7%)
Level of education