Search Results

Apply stationary use of ultrasound to: Generate deep heat within body tissues for the treatment of selected medical conditions such as the relief of pain, the relief of muscle spasms, the treatment of joint contractures, and the local increase in circulation.

Apply continuous movement of ultrasound for:

1. Pain.
2. Pain relief, muscle spasms, and joint contractures.
3. Relief of pain, muscle spasms, and joint contractures that may be associated with:
   • Adhesive capsulitis,
   • Bursitis with slight calcification,
   • Myositis,
   • Soft tissue injuries, and
   • Shortened tendons due to past injuries and scar tissues.
4. Relief of pain, muscle spasms, and joint contractures resulting from:
   • Capsular tightness, and
   • Capsular scarring.
5. Localized increase in blood flow.
6. Increased range of motion of contracted joint using heat and stretch techniques.

As a portable and rechargeable prescriptive device in the home or clinical/hospital setting, the subject device is intended to apply ultrasound to the patient's treatment site. It is demonstrated ultrasound can be used to apply therapeutic deep heat for the treatment of medical conditions including relief of pain, muscle spasms, and joint contractures.

It is intended to be used for 30 minutes per cycle (up to 4 cycles) in the home or clinical/hospital setting by or under the direction of a medical professional to apply ultrasound to the patient's treatment site. The device automatically alerts the patient in case of improper application or performance. All the control components and the rechargeable battery of the device are protectively housed, and the device is connected to one or two applicators of ultrasound.

The subject device consists of the main device, the applicator, the charger/adapter, the liquid and/or solid ultrasound gel, and the sticky pad. For the best result, use the ultrasound gel and the sticky pad supplied.

This looks like a fascinating case study. Based on the provided FDA 510(k) clearance letter and summary, here's an analysis of the acceptance criteria and the study that proves the device meets them.

It's important to note that this document is for an Ultrasound Stimulator (Ultrasonic Diathermy), which delivers therapeutic ultrasound, not an AI/Software as a Medical Device (SaMD) that typically involves image analysis or diagnostic support. Therefore, many of the typical acceptance criteria and study designs related to diagnostic accuracy, MRMC studies, and nuanced ground truth establishment for AI models (as implied by the original request's detailed points) are not applicable to this type of physical therapy device.

The "acceptance criteria" here are primarily based on demonstrating substantial equivalence to predicate devices through engineering specifications, performance testing, and safety profiles, rather than clinical efficacy studies in the way an AI diagnostic tool would require.

Acceptance Criteria and Study Proving Device Meets Criteria

Given that the device is an Ultrasound Stimulator aiming for 510(k) clearance based on substantial equivalence, the "acceptance criteria" are not framed in terms of diagnostic performance metrics (e.g., sensitivity, specificity, AUC) but rather in terms of demonstrating that its technical characteristics, performance, and safety are equivalent to legally marketed predicate devices. The "study" proving it meets these criteria is a comprehensive set of non-clinical, bench performance tests and comparisons.

1. Table of Acceptance Criteria and Reported Device Performance

For an Ultrasound Stimulator, the "acceptance criteria" are primarily a demonstration of equivalence to the predicate devices across various technical and functional parameters, and compliance with relevant safety standards. The "reported device performance" are the results of the non-clinical tests and direct comparisons to the predicate devices.

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

• Sample Size for Test Set: This is a physical device (Ultrasound Stimulator), not a diagnostic AI. Therefore, the concept of a "test set" in the context of a dataset for an AI model (like images or patient records) does not apply. The "test set" would be the number of devices/units subjected to engineering and performance verification tests. This information is typically not specified in a 510(k) summary; manufacturers test a representative number of units to ensure compliance with standards.
• Data Provenance (e.g., country of origin of the data, retrospective or prospective): This is not applicable to a physical therapy device like an ultrasound stimulator. The "data" refers to engineering measurements and test results, not patient data. The device is manufactured by JKH Health Co., Ltd. in China, and presumably, the non-clinical tests were conducted at their facilities or accredited test labs.

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

• Not Applicable. For a device like an Ultrasound Stimulator, there is no "ground truth" to be established by experts in the sense of image interpretation for diagnosis. The "ground truth" for performance is based on defined engineering parameters, physical measurements, and compliance with international standards (e.g., IEC, ISO). These are verified by qualified test engineers and technicians using calibrated equipment, not by clinical experts like radiologists.

4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set

• Not Applicable. Adjudication methods like 2+1 or 3+1 are used in studies involving human interpretation (e.g., radiologists reviewing images) to establish a consensus "ground truth." This device does not involve human interpretation as part of its function or testing for 510(k) clearance. Compliance is determined by objective measurements against predefined specifications and standards.

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, an MRMC comparative effectiveness study was not done. This type of study is specifically designed for evaluating diagnostic AI systems (or human performance with and without AI assistance) where human perception and interpretation are key. An Ultrasound Stimulator is a therapeutic device, not a diagnostic one, and its 510(k) clearance path relies on demonstrating substantial equivalence in engineering, performance, and safety, not on improving human diagnostic accuracy.

6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done

• Not Applicable in the traditional sense of AI algorithm performance. This is an Ultrasound Stimulator, a physical device. It has software, but the "performance" tested is its ability to generate ultrasound at specific parameters and safely, not to process data or make diagnostic outputs. Its core function is a physical treatment delivery, verified through bench testing, not an "algorithm-only" diagnostic output. The software verification mentioned (according to FDA Guidance for Software Contained in Medical Devices) ensures the software itself is designed, developed, and tested appropriately, but this isn't analogous to testing the diagnostic performance of an AI algorithm.

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

• Engineering Specifications and International Standards: The "ground truth" for this device is its adherence to predefined engineering specifications and compliance with established international safety and performance standards (e.g., IEC 60601 series, ISO 10993 series). These are objective, measurable criteria. For instance, ground truth for power output is a specific wattage with an allowed tolerance, measured by calibrated equipment, not a clinical diagnosis.

8. The Sample Size for the Training Set

• Not Applicable. This device is not an AI model that requires a "training set" of data for machine learning.

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

• Not Applicable. As there is no training set for an AI model, the question of establishing its ground truth does not apply.

In summary: The provided document is for a Class II Ultrasound Stimulator, a therapeutic device. Its premarket clearance (510(k)) is based on demonstrating substantial equivalence to predicate devices, primarily through comprehensive non-clinical bench testing to verify performance parameters, electrical safety, electromagnetic compatibility, biocompatibility, and thermal safety in accordance with recognized international standards. The evaluation process for such a device does not involve the AI-specific criteria (like test set data provenance, expert adjudication, MRMC studies, or training sets for AI models) that were part of the initial request, as those are typically relevant for diagnostic AI/SaMD submissions.

Ask a specific question about this device