(100 days)
The device is designed to perform radiographic x-ray examinations on adult patients, in all patient treatment areas.
The device is designed to perform radiographic x-ray examinations on pediatric and adult patients, in all patient treatment areas.
The DRX-Revolution Nano Mobile X-ray System (also referred to as the DRX-Revolution Nano) is a diagnostic mobile x-ray system utilizing digital radiography (DR) technology. The system consists of a self contained x-ray generator, image receptor(s), imaging display and software for acquiring medical diagnostic images outside of a standard stationary x-ray room. The DRX-Revolution Nano system can also be used to expose CR storage phosphor screen or film cassettes.
Here's an analysis of the provided text, focusing on the acceptance criteria and the study details:
Overall Assessment: The provided document is a 510(k) premarket notification for the DRX-Revolution Nano Mobile X-ray System. It describes the device, its intended use, comparison to a predicate device, and performance testing. The clinical study mentioned is a comparative effectiveness study designed to show non-inferiority to the predicate device, not a standalone study demonstrating specific performance metrics against a defined acceptance criterion. The key takeaway is that the diagnostic capability of the new device is statistically equivalent to or better than the predicate.
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state quantitative acceptance criteria for the diagnostic performance of the DRX-Revolution Nano itself, nor does it list specific performance metrics like sensitivity or specificity. Instead, the "acceptance criterion" for the clinical study was to demonstrate statistical equivalence or superiority in diagnostic capability compared to the predicate device.
| Acceptance Criterion (for Clinical Study) | Reported Device Performance |
|---|---|
| Diagnostic capability (of investigational device vs. predicate device) | Statistically equivalent to or better than the predicate device. |
| Compliance with general safety and regulatory standards (non-clinical testing) | Predefined acceptance criteria were met. Device conforms to specifications. |
Note: The document primarily focuses on demonstrating substantial equivalence to a predicate device rather than meeting specific quantitative diagnostic performance thresholds as might be defined for a novel AI algorithm.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set:
- Clinical Study: "Adult cadavers were used to perform pair-wise investigational vs. predicate acquisitions using similar radiographic techniques and body positioning for 2D imaging."
- The specific number of adult cadavers is not provided.
- The images included targeting various exam types such as chest, abdomen, skull, C-spine, L-spine, pelvis, hip, nasal bones, shoulder, and extremity radiographs.
- Pediatric Phantom Images: "In addition, eight pediatric phantom images were acquired on both the investigational and predicate devices in the laboratory at Carestream Health, Inc."
- This suggests 8 unique pediatric phantom images were taken with both devices, resulting in 16 total images from phantoms.
- Clinical Study: "Adult cadavers were used to perform pair-wise investigational vs. predicate acquisitions using similar radiographic techniques and body positioning for 2D imaging."
- Data Provenance:
- Adult Cadaver Images: Not explicitly stated, but implies the studies were conducted by Carestream Health. Not specified if retrospective or prospective, but likely acquired prospectively for the study.
- Pediatric Phantom Images: Acquired in the laboratory at Carestream Health, Inc. (Prospective).
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
The document mentions a "Reader Study" but does not specify the number or qualifications of the experts/readers who established the (presumably diagnostic) ground truth for the test set.
4. Adjudication Method for the Test Set
The document states: "The images were assembled and reviewed in a single stimulus random format in order to perform a Comparative Evaluation to statistically confirm the findings of this evaluation."
This describes the presentation format to the readers but does not specify an adjudication method for establishing a consensus ground truth (e.g., 2+1, 3+1). It implies readers were evaluating images against each other (investigational vs. predicate) rather than against an independently established ground truth.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size
- MRMC Comparative Effectiveness Study: Yes, a comparative study was performed between the DRX-Revolution Nano (investigational) and the DRX-Revolution Mobile X-ray System (predicate). The images were reviewed by readers (implied by "Reader Study").
- Effect Size of Human Readers with AI vs. Without AI Assistance: This question is not applicable here. The DRX-Revolution Nano is an X-ray imaging system, not an AI-powered diagnostic algorithm designed to assist human readers. The study compares the imaging performance of two different X-ray systems.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
This question is not applicable. The device is a mobile X-ray system, not a standalone algorithm. The clinical study evaluated the imaging performance and diagnostic capability of the system in producing images that radiologists would interpret, not an algorithm's performance independent of human interpretation.
7. The Type of Ground Truth Used
The document does not explicitly state the specific type of ground truth used (e.g., pathology, clinical outcomes, expert consensus) for the diagnostic capabilities evaluated in the reader study. It implies that the "diagnostic capability" was assessed by human readers comparing "investigational vs. predicate acquisitions." It's likely that the readers' interpretations, potentially against a "reference standard" if established per case, formed the basis, but this is not detailed.
8. The Sample Size for the Training Set
This question is not applicable. The DRX-Revolution Nano is a hardware X-ray system with embedded software for image acquisition and processing. It is not described as an AI/ML algorithm that requires a "training set" for diagnostic decision-making. The software verification and validation section indicates testing was done on the embedded software for its functionality and safety, not for a learning model.
9. How the Ground Truth for the Training Set Was Established
This question is not applicable for the same reasons as point 8.
§ 892.1720 Mobile x-ray system.
(a)
Identification. A mobile x-ray system is a transportable device system intended to be used to generate and control x-ray for diagnostic procedures. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.