FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

The Fluorescence Mode is an accessory to the EXTARO 300 surgical microscope to utilize a kind of LED light that illuminates the tooth surfaces in the blue light region with a narrow band ( around wavelength 405nm). The Fluorescence Mode is not a standalone device. It is a built-in feature (new components) to existing surgical microscope. These components include (1) an additional violet source in existing LED lamp, (2) a bandpass filter in existing OPMI (Operation Microscope) Head and (3) multi-function knob on existing OPMI Head.

AI/ML Overview

The provided text describes information from a 510(k) submission for the "Fluorescence Mode" device, an accessory to the EXTARO 300 surgical microscope. However, it does not contain a discrete acceptance criteria table or a detailed study report proving the device meets specific performance acceptance criteria for detecting dental caries.

The document focuses on demonstrating substantial equivalence to a predicate device (VistaCam iX "Proof" (K150672)) by comparing technological characteristics, intended use, and general performance, rather than presenting a standalone study with defined performance metrics and acceptance thresholds for the "Fluorescence Mode" itself.

Here's a breakdown of the information available based on your request, highlighting what is present and what is missing:

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

Acceptance Criteria: Not explicitly stated as a table with numerical or categorical thresholds for caries detection performance (e.g., sensitivity, specificity, accuracy). The document discusses general compliance with standards and safety.
Reported Device Performance: Instead of performance metrics for caries detection, the document reports on the successful completion of various verification and validation tests to established specifications and standards.
- Light Safety Testing: Conforms to IEC 62471:2006.
- Environmental Testing: Performance not changed after various environmental tests (temperature, simulated transportation, moisture, pressure).
- Usability Testing: Device could be used by intended users without serious errors or problems.
- System Verification Testing: All System Requirement Specifications were met (product stability, ergonomics, dimensions, image quality, image filters, light sources).
- EMC/ES Testing: Conforms to IEC 60601-1-2:2014.
- Software Verification and Validation Testing: Performed in accordance with FDA Guidance for a Moderate Level of Concern.
- Background Light Interference Verification: Expected levels of background light (40lx for CCT 4000K-6500K) do not impact device performance; carious teeth can be differentiated at 40lx and below.

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

Sample Size for Test Set:
- For Usability Testing: Total of 15 clinicians across 12 sites used the Fluorescence Mode to aid in the detection of caries in more than 40 cases in clinical practices.
- For other performance tests like Light Safety, Environmental, System Verification, EMC/ES, Software V&V, and Background Light Interference, the sample sizes are not explicitly stated in terms of patient/tooth count, but rather the tests were conducted on the device hardware/software.
Data Provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective). The "clinical practices" mentioned for usability testing imply real-world usage, but no further details are given.

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

The document does not explicitly describe how ground truth was established for the "more than 40 cases" in usability testing for the purpose of evaluating the carie detection performance of the device. The usability testing primarily assessed the device's usability, not its diagnostic accuracy against a definitive ground truth.
The "clinicians" involved in usability testing are dentists/users, but their role in establishing ground truth for performance evaluation is not detailed, nor are their specific qualifications provided beyond being "clinicians."

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

No adjudication method for establishing ground truth for a test set (in terms of caries detection accuracy) is described. The usability study focused on user experience and safety, not diagnostic performance 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 comparative effectiveness study is mentioned. The device is described as an "aid in the detection of dental caries," implying assistance to a dentist, but no study comparing human readers with and without the device is provided.
The device is a "Fluorescence Mode" and not explicitly stated as an "AI" device, so the comparison of improvement with AI vs. without AI assistance is not applicable here based on the provided text.

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

The document states, "The Fluorescence Mode is intended to be used by dentist as an aid in the detection of dental caries." This explicitly indicates a human-in-the-loop scenario.
No standalone (algorithm only) performance study of the "Fluorescence Mode" for caries detection is described.

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

As mentioned in point 3, the document does not specify the type of ground truth used for evaluating the device's performance in caries detection. The focus of the reported studies is on safety, usability, and system functionality. For the "more than 40 cases" in usability testing, the method of confirming actual caries presence or absence (ground truth) is not detailed.

8. The sample size for the training set

The document describes verification and validation for the "Fluorescence Mode" feature but does not mention any "training set" or "training data." This typically implies that the device is based on a deterministic physical principle (fluorescence) rather than a machine learning model that requires training data.

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

Since no training set is mentioned (as per point 8), the establishment of ground truth for a training set is not applicable.

Summary

Regulation Number and Section

§ 872.1745 Laser fluorescence caries detection device.

(a)
Identification. A laser fluorescence caries detection device is a laser, a fluorescence detector housed in a dental handpiece, and a control console that performs device calibration, as well as variable tone emitting and fluorescence measurement functions. The intended use of the device is to aid in the detection of tooth decay by measuring increased laser induced fluorescence.(b)
Classification. Class II, subject to the following special controls:(1) Sale, distribution, and use of this device are restricted to prescription use in accordance with § 801.109 of this chapter;
(2) Premarket notifications must include clinical studies, or other relevant information, that demonstrates that the device aids in the detection of tooth decay by measuring increased laser induced fluorescence; and
(3) The labeling must include detailed use instructions with precautions that urge users to:
(i) Read and understand all directions before using the device,
(ii) Store probe tips under proper conditions,
(iii) Properly sterilize the emitter-detector handpick before each use, and
(iv) Properly maintain and handle the instrument in the specified manner and condition.