K Number
K201798
Device Name
myQA iON
Manufacturer
Date Cleared
2020-07-17

(17 days)

Product Code
Regulation Number
892.5050
Panel
RA
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The intended use of the myQA iON product is to perform patient quality assurance activities for radiation therapy treatment delivery systems. myQA iON is a software toolbox allowing the Medical Physicist to perform quality assurance activities before and after the patient treatment fractions for all patients undergoing radiation therapy.

Device Description

The myQA iON product is a server-based software application for performing patient quality assurance for radiation therapy. In its full scope, the product delivers means for the verification of:

  • The patient treatment plan prior to the first treatment fraction by
    • Using an independent dose algorithm to compute a dose map based on the patient treatment plan;
    • Performing measurements using external measurement devices and analyzing the results;
    • Performing machine log analysis during a treatment dry run session and reconstructing the delivered dose.
  • The patient treatment delivery by
    • Performing machine log analysis and reconstructing the delivered dose for each treatment fraction.
      In its full scope, the product interfaces with the Treatment Planning System, the Oncology Information System, the treatment delivery System and the external measurement device.
AI/ML Overview

Here's a breakdown of the acceptance criteria and the study information based on the provided text, using the requested format:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly state specific quantitative acceptance criteria or corresponding reported device performance metrics for the myQA iON. Instead, it describes general testing categories to assess the device's performance. The study aims to demonstrate substantial equivalence, implying that its performance should be comparable to the predicate device but doesn't quantify this in a numerical acceptance table within this document.

Acceptance Criteria CategoryReported Device Performance (as described)
Risk Analysis TestingVerified implementation of identified hazard mitigation.
Software TestingVerified correct software implementation.
Physics TestingVerified correct behavior of physics algorithms.
Integration TestingVerified correct integration of different software components.
System TestingVerified correct implementation of the clinical workflow.
Beta TestingValidated the usability of the software.

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

The document does not specify the sample size used for any of the described tests (Risk Analysis, Software, Physics, Integration, System, or Beta Testing). It also does not mention the country of origin of the data or whether the tests were retrospective or prospective. These tests appear to be internal verification and validation activities conducted by the manufacturer.

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

The document does not provide information on the number of experts used or their qualifications for establishing ground truth within the described non-clinical tests. The tests focus on software functionality, physics algorithms, and workflow, which typically rely on internal validation against established standards or expected behaviors rather than expert consensus on a "ground truth" dataset in the typical clinical AI sense.

4. Adjudication Method for the Test Set

The document does not describe any adjudication method (e.g., 2+1, 3+1, none) for the test set. Given the nature of the described non-clinical tests, such adjudication methods are typically not applicable.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

The document explicitly states: "The subject of this premarket submission, the IBA Dosimetry myQA iON product, did not require clinical testing to support substantial equivalence to the predicate device." Therefore, no MRMC comparative effectiveness study was done, and there is no reported effect size regarding human reader improvement with or without AI assistance.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

The document describes "Physics Testing verifying the correct behavior of the physics algorithms" and "Software Testing verifying the correct software implementation." While these evaluate the algorithm's performance in isolation from a human user in some sense, they are part of non-clinical verification and validation activities, not a formal standalone performance study as would typically be conducted for a diagnostic AI. The device's intended use is as a "software toolbox allowing the Medical Physicist to perform quality assurance activities," implying a human-in-the-loop interaction for its full functionality. However, the core independent dose calculation and analysis features could be considered standalone algorithmic functions. The document does not present a dedicated "standalone performance study" with metrics like sensitivity, specificity, or AUC.

7. Type of Ground Truth Used

The ground truth for the non-clinical tests appears to be based on:

  • Identified hazard mitigations: For Risk Analysis Testing.
  • Expected software implementation and behavior: For Software, Integration, and System Testing.
  • Known physical principles and expected outputs: For Physics Testing verifying the correct behavior of physics algorithms.
  • Usability goals: For Beta Testing.

This is not "expert consensus, pathology, or outcomes data" in the typical clinical context but rather internal validation against design specifications and established scientific/engineering principles.

8. Sample Size for the Training Set

The document does not mention a training set sample size. The myQA iON is described as a "software toolbox" and implies deterministic physics algorithms and analysis tools rather than a machine learning model that would require a distinct training set.

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

Since the document does not indicate the use of a training set for a machine learning model, this information is not applicable and is not provided.

§ 892.5050 Medical charged-particle radiation therapy system.

(a)
Identification. A medical charged-particle radiation therapy system is a device that produces by acceleration high energy charged particles (e.g., electrons and protons) intended for use in radiation therapy. This generic type of device may include signal analysis and display equipment, patient and equipment supports, treatment planning computer programs, component parts, and accessories.(b)
Classification. Class II. When intended for use as a quality control system, the film dosimetry system (film scanning system) included as an accessory to the device described in paragraph (a) of this section, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.