(220 days)
The OARtrac® System with patient specific, reusable, pre-calibrated PSD sensors are intended for use during cancer treatments to measure photon radiation therapy as an adjunct to treatment planning permitting measurement and validation of radiation dose received by the patient to the targeted area of their body, and indicated for use when adhered to the skin with a bolus, or inserted into the rectum to measure the rectal prostatic interface via a specifically designed endorectal balloon device.
The OARtrac® System with patient specific, reusable, pre-calibrated PSD sensors is intended for use in photon radiation therapy to monitor and validate radiation dose during External Beam Therapy and HDR Brachytherapy to the surface of the skin or the rectal prostatic interface. This dose verification information obtained during the treatment is then used to compare with the planned dose that the Radiation Oncologists expect to provide to their patient. The OARtrac® System itself does not stop the radiation treatment to the patient, or change the radiation delivery, but only provides dose data which a trained Radiation Oncologist can decipher and use to adjust a patient's treatment plan accordingly.
The provided text does not contain information about an Artificial Intelligence (AI) device or a study proving its performance against acceptance criteria in the context of AI. The document is a 510(k) premarket notification for a medical device called the "OARtrac® System with Patient Specific Reusable PSD Sensors," which is a radiation dose verification system.
The document focuses on demonstrating substantial equivalence to previously cleared predicate devices, primarily through non-clinical performance data related to material, electrical safety, EMC, software, package shelf-life, risk analysis, dose range verification, and importantly, cleaning and disinfection validation for reusability.
Therefore, I cannot provide the requested information regarding AI device acceptance criteria, study details, sample sizes, ground truth establishment, or multi-reader multi-case studies, as these concepts are not addressed in the provided text.
Specifically:
-
A table of acceptance criteria and the reported device performance: The document lists "Key Performance Specifications/Characteristics" for the device, which includes:
- Photon Energy Based Therapies: Energy Range .37-18 MeV
- Dose Rate Range: 1.3-17.3 cGy/s
- Dose Range: 27-1200 cGy
- Dose Accuracy: +/-6%, 2 σ
It states that the subject device meets these requirements, and that "all the testing" was passed. However, it does not provide detailed performance results in a table format comparing acceptance criteria to reported performance for each specific test item in the same way an AI model's performance metrics (e.g., sensitivity, specificity, accuracy) would be presented against pre-defined thresholds. The key focus of this submission is on the reusability validation.
-
Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective): Not applicable, as this is a non-AI device. The testing described is primarily laboratory-based non-clinical performance validation (e.g., electrical safety, EMC, cleaning/disinfection validation). Specific sample sizes for these types of engineering tests are not detailed in this summary.
-
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): Not applicable. "Ground truth" in the context of expert consensus is relevant for AI diagnostic or prognostic devices. For this device, "ground truth" would relate to verifiable physical measurements in a laboratory setting for dose accuracy, cleaning efficacy, etc. The document does not specify experts for establishing such ground truth.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable for a non-AI device's non-clinical performance testing.
-
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: Not applicable, as this is not an AI device.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable, as this is not an AI algorithm.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc): For the non-clinical tests mentioned, the "ground truth" would be established by standard engineering and scientific methodologies (e.g., calibrated reference instruments for dose measurement, laboratory testing protocols for cleaning/disinfection efficacy, an accredited laboratory for biocompatibility).
-
The sample size for the training set: Not applicable, as this is not an AI device and thus has no training set in that context.
-
How the ground truth for the training set was established: Not applicable, as this is not an AI device.
§ 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.