(105 days)
The portable x-ray system may be used for diagnostic imaging of body extremities.
- Not for mammography use
- This device is not intended to replace a stationary radiographic system, which may be required for full optimization of image quality and radiation exposure for different exam types.
This device is a battery-powered portable X-ray System, designed and manufactured by H&abyz. This portable radiographic system (Model: HnX-P1, HnX-PB) consists of an LCD display with up and down soft-keys for controlling kV, an X-ray generator (line-powered transformer), an X-ray tube assembly, a collimator and a cart. It can also use a stand instead of a cart. The HnX-P1 is used with a film-cassette or flat-panel detector. (The film-cassette or flat-panel detector, cart, and stand are not included in the basic components of the product.)
The major components of the X-ray main unit include handle, enclosure, main control panel, system control board, high-voltage tank, inverter, collimator (beam limiter), and system control software running on the system control board. The system control software is for real-time interaction and control with various circuit modules inside the X-ray generator. The software responds to user operations on the control panel. The user can adjust and control the kV and mAs parameters, and the software will display the parameters or directly load the APR parameters. The software loads the control data from X-ray output into the high-voltage generation control circuit of the system control board, and control the high-voltage tank to generate high-voltage to excite the X-ray tube inside to emit X-rays, control the switch of the collimator, and monitor the working status of the device, and control the display of the status indicators.
The system is for X-ray imaging and diagnosis in facilities with portable or fixing sites. The device can be used with an X-ray flat panel detector, a computer for receiving and detecting signal results and an image processing software. This portable X-ray System is designed for handheld or stand-mounted imaging.
It appears there may be a misunderstanding or a gap in the provided document regarding acceptance criteria and the study proving the device meets them. The document is an FDA 510(k) clearance letter for a portable X-ray system (HnX-P1, HnX-PB), and it does not contain information about acceptance criteria for AI/software performance or a study proving the device meets such criteria.
The document explicitly states several times that "Clinical studies were not performed." (Page 10, Section 8 on "Clinical studies"). This means there was no clinical evaluation of diagnostic accuracy or comparative effectiveness with human readers using this specific device.
The "Non-Clinical Test summary" (Page 9, Section 7) mentions:
- "A total of 30 clinical image samples, including elbows, hands, knees, ankles, and feet, were reviewed by qualified clinicians and determined to be of good quality and clinically useful." This sounds like an image quality assessment, not a performance study of an AI algorithm.
- "Software validation and risk analysis was performed." This refers to internal software quality assurance processes.
Therefore, many of the requested points related to AI performance, ground truth, expert adjudication, and MRMC studies cannot be answered from the provided text, as the device described is a hardware X-ray system, not an AI diagnostic algorithm.
However, I can still extract information based on the typical requirements for a 510(k) clearance for a hardware device like an X-ray system. The "acceptance criteria" here would typically relate to meeting performance standards for X-ray output, safety, electrical compatibility, and image quality demonstrations, rather than diagnostic accuracy of an AI algorithm.
Based on the provided FDA 510(k) clearance letter, here's an analysis tailored to what is present and what is absent:
Summary of Device Performance and Acceptance Criteria (as implied for a hardware X-ray system)
The acceptance criteria for a portable X-ray system like the HnX-P1/HnX-PB are primarily focused on safety, technical performance, and image quality adequacy for diagnostic use, rather than the diagnostic accuracy of an AI. The studies proving the device meets these criteria are primarily non-clinical tests and demonstrations of substantial equivalence to a predicate device.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category (Implied for X-ray Hardware) | Specific Criteria (Derived from document) | Reported Device Performance (as stated or implied) |
|---|---|---|
| Safety and Electrical Standards Compliance | IEC 60601-1 (Basic Safety & Essential Performance) | Complies (Laboratory Testing Performed) |
| IEC 60601-1-2 (EMC) | Complies (Laboratory Testing Performed) | |
| IEC 60601-1-3 (Radiation Protection) | Complies (Laboratory Testing Performed) | |
| IEC 60601-2-28 (X-ray Tube Assemblies) | Complies (Laboratory Testing Performed) | |
| IEC 60601-2-54 (Radiography & Radioscopy) | Complies (Laboratory Testing Performed) | |
| Software Quality & Risk Management | IEC 62304 (Software Life Cycle) | Complies (Laboratory Testing Performed, Software Validation & Risk Analysis Performed) |
| IEC 62366 (Usability Engineering) | Complies (Laboratory Testing Performed) | |
| ISO 14971 (Risk Management) | Complies (Laboratory Testing Performed) | |
| Cybersecurity | FDA Guidance (Sept 27, 2023) Compliant | Complies (Review indicated) |
| Labeling Compliance | CFR Part 801 | Complies (Review indicated) |
| Image Quality for Diagnostic Use | Images "good quality and clinically useful" | 30 clinical image samples (extremities) reviewed by qualified clinicians and deemed "good quality and clinically useful" |
| PMR Safety Performance Standard | FDA Performance Standard | Complies |
| Substantial Equivalence | No significant differences affecting intended use compared to predicate K182207 | Claimed and accepted by FDA, based on comparison of technical characteristics and indications for use. |
2. Sample size used for the test set and data provenance:
- Test Set (for "Image Quality" evaluation): 30 clinical image samples.
- Data Provenance: Not explicitly stated regarding country of origin or whether retrospective/prospective. However, the use of "clinical image samples" suggests real patient data, likely retrospective given the lack of a formal clinical study.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- For the "image quality" assessment of the 30 samples: "qualified clinicians" reviewed the images. The exact number of clinicians or their specific qualifications (e.g., "Radiologist with 10 years of experience") are not specified in this document.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not applicable/Not specified for this type of hardware evaluation. The document implies a qualitative assessment ("determined to be of good quality and clinically useful") rather than a 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 study was performed or required. The device is a portable X-ray system, not an AI diagnostic aid for human readers.
- The document explicitly states: "Clinical studies were not performed." (Page 10, Section 8).
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Not applicable. This device is a hardware X-ray imager, not a standalone AI algorithm. It produces images, but does not autonomously interpret them.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
- For the "image quality" assessment, the "ground truth" was effectively the qualitative judgment of "qualified clinicians" that the images were "good quality and clinically useful." This isn't diagnostic "ground truth" (e.g., presence/absence of a disease).
8. The sample size for the training set:
- Not applicable. This document describes a hardware device, not an AI algorithm that requires a training set.
9. How the ground truth for the training set was established:
- Not applicable. As above, no AI training set is described or relevant to this hardware device clearance.
In conclusion, the provided FDA 510(k) clearance letter details the regulatory review for a medical device hardware (portable X-ray system), not an AI or software as a medical device (SaMD) with diagnostic capabilities that underwent a performance study against specific diagnostic acceptance criteria. The "acceptance criteria" discussed are largely compliance with electrical, safety, and performance standards, and a qualitative assessment of image utility.
§ 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.