K Number
K181087
Date Cleared
2018-12-18

(237 days)

Product Code
Regulation Number
N/A
Panel
DE
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

Apex Locator, DPEX III is a microprocessor controlled device intended for locating the apex of root canal.

Device Description

Apex Locator, DPEX III is an apex locator intended for precise localization of root canal apex. Operation of Apex Locator, DPEX III is fully automatic, no manual calibrations or adjustments are required. The measuring signal is analyzed, and automatic adjustments are made if needed. The device may operate within different conditions in the root canal. Apex Locator, DPEX III may only be used with stainless steel or nickel titanium endodontic files. The scale indication on the apex locator screen does not represent a distinct length or distance in mm or other linear units. It merely indicates the file progression towards the apex.

AI/ML Overview

The provided text describes a 510(k) premarket notification for the Apex Locator, DPEX III. It aims to demonstrate substantial equivalence to a predicate device, the RAYPEX 6.

Here's an analysis of the acceptance criteria and study information based solely on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document states that the acceptance criteria for performance were met by demonstrating equivalence to the predicate device through performance comparison testing.

Acceptance Criteria CategorySpecific Criteria (Implicitly based on stated equivalence)Reported Device Performance (Apex Locator, DPEX III)
Measurement PerformanceClinically acceptable measurement of apex location, equivalent to predicate device (RAYPEX 6)."The result obtained with the Apex Locator, DPEX III is clinically acceptable since they are equivalent to the results of the predicate device."
Electrical Safety (EMC)Compliance with IEC 60601-1:2005+CORR.1 (2006)+CORR.2(2007)+AM1(2012) and IEC 60601-1-2: 2014."The safety and EMC testing confirm that the subject device complies with the same FDA recognized safety and EMC standards as the primary predicate device. All of the predetermined acceptance criteria were met."
BiocompatibilityCompliance with ISO10993-5 (Cytotoxicity), ISO10993-10 (Skin Irritation), ISO10993-10 (Oral Mucosa Irritation), ISO10993-10 (Skin Sensitization)."The test result shows that the subject device complies with the same FDA recognized biocompatibility standards as predict device. All of the pre-determined acceptance criteria were met."
Sterilization ValidationCompliance with ISO 17665-1:2006, ISO 11737-2:2009, and ANSI AAMI ST79:2017 for accessories."The steam sterilization validation study supports the labeling of sterilization method for the accessories subject to be sterilized at the clinical site. All of the pre-determined acceptance criteria were met."

Note: The document does not provide quantitative specific acceptance criteria (e.g., "accuracy must be within X mm") or numerical performance data for the device. Instead, it relies on demonstrating equivalence to a legally marketed predicate device.

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

  • Sample Size: The document mentions "using extracted tooth" for the performance comparison test, but it does not specify the sample size (i.e., number of extracted teeth) used for this test set.
  • Data Provenance: The data provenance is retrospective, as it involves testing performed by the manufacturer to demonstrate equivalence. The country of origin of the data is not explicitly stated, but the manufacturer is "Guilin Woodpecker Medical Instrument Co., Ltd." in P.R. China.

3. Number of Experts Used to Establish Ground Truth and Qualifications

This information is not provided in the document. The performance comparison test relies on a comparison against the predicate device, and the method for establishing "ground truth" for the apex location is not described beyond "using extracted tooth." There is no mention of human experts defining ground truth for the device's accuracy.

4. Adjudication Method for the Test Set

No adjudication method is described. Given the type of device (apex locator) and the testing described (comparison using extracted teeth), a human adjudication process by multiple experts is not indicated as part of the performance testing.

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

No, an MRMC comparative effectiveness study was not done. The document explicitly states: "No clinical study is included in this submission." This indicates that there was no human-in-the-loop study comparing human readers with and without AI assistance.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

The performance comparison test "using extracted tooth" functions as a standalone performance test for the device's ability to locate the apex. It evaluates the device's accuracy against the predicate without direct human interaction influencing the measurement outcome during the test itself. However, it's not an "algorithm" in the sense of a software AI model; it's a physical device measurement.

7. The Type of Ground Truth Used

The "ground truth" for the performance comparison test appears to be established by the measurement of the predicate device (RAYPEX 6). The aim was to show the new device's measurements were equivalent. For an apex locator, the true anatomical apex location in an extracted tooth would be the actual ground truth, but the document frames the comparison against the predicate as the basis for performance acceptance. It's essentially "predicate device performance" as the de facto standard for this submission.

8. The Sample Size for the Training Set

Not applicable/Not provided. This device is an electrical impedance-based apex locator, not an AI/ML device that requires a training set in the conventional sense. Its "knowledge" is embedded in its electrical design and algorithms, which are determined during engineering and design, not through a data-driven training process.

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

Not applicable/Not provided. As stated above, this is not an AI/ML device that uses a "training set" with established ground truth.

N/A