(182 days)
Jintronix is a software system used with the Microsoft Kinect v2 intended to be used to support the physical rehabilitation of adults in the clinic/ at home. The system includes rehabilitation exercises for the upper extremity, trunk, and lower extremity with audio-visual feedback & graphic movement representations for patients as well as remotely accessible patient performance metrics for the medical professional. Patient assessment, exercise guidance and approval by the medical professional is required prior to use.
Jintronix Version 2.0.140905, a software system comprising of a client application and a web application is to be used with the Microsoft Kinect version 2 to support the physical rehabilitation of adults in the clinic/ at home.
Through the client application, the patient engages in their rehabilitation exercises. Using the Microsoft Kinect for Windows, which tracks the patient's upper extremity, trunk, and lower body joint positions as they move, the software provides a graphic representation of the patient's movements, as well as activities that include visual and audio feedback to support the patient in performing therapeutic exercise.
As the patient engages in exercises, the system records performance metrics, such as the speed and precision of their movements. These metrics are then sent to a remote web application.
Clinicians, through a "clinician interface" of the Client application, securely access the remote web application to remotely monitor the progress of their patients, and modify the exercise program through program customizations (for example, difficulty level) based on patients' needs.
Patient assessment, exercise guidance and approval by the medical professional is required prior to use. There is no direct contact with the patient since the device is a software product. No energy is delivered to the subject.
The provided text describes the Jintronix Version 2.0 device and its 510(k) submission. Here's a breakdown of the requested information:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Reported Device Performance |
|---|---|
| Data Processing Accuracy | Jintronix data processing accuracy verified by software testing. Clinician feedback. |
| System Compatibility | System compatibility of Jintronix software, Microsoft Kinect v2 hardware, and the recommended computer operating system in Jintronix labeling assured by software testing. |
| Kinect Performance Accuracy / Effectiveness | Jintronix surpasses predicate JRS in performance. Jintronix uses the Kinect v2 (for optical motion capture) which is more precise over a greater tracking range than Kinect v1 used with predicate JRS. Jintronix can be consistently reproduced within an error tolerance that is comparable to intra-rater precision error of goniometry. Shoulder range of motion measurements can only be used to describe a patient's relative change in joint angle, not absolute joint angle. Shoulder ROM measurements have not been validated in standardized postures associated with goniometric measurements. Bench study recommendations for optimal performance have been incorporated or accounted for. |
| Kinect Electrical Safety | Kinect is deemed electrically safe. It conforms to IEC 60825-1:2007:03 for a Class 1 laser product and 21 CFR 1040.10 & 1040.11 (except for deviations per Laser Notice No. 50). |
| Software Life Cycle Processes | Jintronix conforms partially to AAMI / ANSI / IEC 62304:2006. |
| AGILE Practices Guidance | Jintronix conforms partially to AAMI TIR45:2012. |
| Premarket Submissions for Software Guidance | Jintronix conforms partially to the "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (May 2005). |
| General Principles of Software Validation | Jintronix conforms partially to the "General Principles of Software Validation; Final Guidance for Industry and FDA Staff" (January 2002). |
| FDA Quality System Regulation (QSR) 21 CFR 820 | Jintronix Inc.'s quality system is compliant with FDA's Quality System Regulation 21 CFR 820, with appropriate design and change controls implemented. |
| Labeling Controls | Jintronix is a prescription use device with various labeling precaution statements, including requiring an in-person patient-exercise suitability assessment prior to prescription. |
2. Sample Size Used for the Test Set and Data Provenance
The document mentions a "Bench Study" for Kinect v2 Performance Accuracy/Effectiveness, where "Kinect's accuracy was determined in terms of kinematics over a range of distances between the Kinect and the user." It also states the Kinect v2 was compared to the Optotrak, Kinect v1, and goniometry.
- Sample Size for Test Set: The document does not specify the sample size of "users" or "movements" or "distances" evaluated in the bench study for the test set.
- Data Provenance: The study was "commissioned an independent study to determine the performance accuracy of Microsoft Kinect v2". No country of origin is explicitly stated for the data itself, but the company Jintronix Inc. has offices in Seattle, WA, and Montreal, Canada, while AxSource Consulting Inc. is in Milton, Ontario, Canada. The study is described as a "Bench Study," suggesting it was conducted in a controlled environment. The provenance is internal to the development and testing process, likely involving controlled experimental setups. It is a prospective study in the sense of specifically testing the device's performance.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications
The document states that the Kinect v2 performance was compared to:
- Optotrak: Described as "a gold standard in motion sensing technology with a reported precision of less than 0.5mm." This serves as a high-precision ground truth reference.
- Goniometry: Described as "the clinical standard for range of motion measurements."
The document does not specify the number of human experts used to establish the ground truth for the test set. It mentions "intra-rater precision error of goniometry" but doesn't detail how many raters or their qualifications were involved in the ground truth establishment for the bench study. The focus appears to be on the objective comparison of devices (Kinect v2 vs. Optotrak, goniometry) rather than expert consensus on patient data.
4. Adjudication Method for the Test Set
Not applicable/provided. The bench study described compares the device's measurements against established technical (Optotrak) and clinical (goniometry) standards. There is no mention of human adjudication of results in the traditional sense of medical image or clinical data interpretation.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No, an MRMC comparative effectiveness study involving human readers and AI assistance was not conducted or reported in this document. The study described is a bench study comparing the device's technical performance against other measurement tools.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Yes, the "Bench Study - Kinect v2 Performance Accuracy / Effectiveness" is a standalone algorithm-only performance study. It assessed the Kinect v2's ability to "consistently reproduce" range of motion measurements and its precision compared to Optotrak, Kinect v1, and goniometry. This evaluates the technical capability of the motion capture system inherent to Jintronix without a human clinician actively interpreting or adjudicating the AI's output in a clinical context. The "Data Processing Accuracy" verified by "software testing" also implies standalone evaluation of the software components.
7. The Type of Ground Truth Used
The ground truth used in the bench study was:
- Reference Device Measurement: Optotrak, "a gold standard in motion sensing technology with a reported precision of less than 0.5mm."
- Clinical Standard Measurement: Goniometry, "the clinical standard for range of motion measurements."
8. The Sample Size for the Training Set
The document does not explicitly state the sample size for any training set. As primarily a software and hardware system that tracks movement, Jintronix's core functionality likely relies on the pre-trained models within the Microsoft Kinect v2 for skeletal tracking. The Jintronix software itself integrates this tracking and provides exercises and metrics. The validation described is of the system's integration and accuracy compared to other measurement tools, not necessarily an AI model trained on a specific dataset by Jintronix.
9. How the Ground Truth for the Training Set Was Established
The document does not provide information on how ground truth was established for any training set. Given that Jintronix utilizes the Microsoft Kinect v2, the underlying skeletal tracking and pose estimation within the Kinect v2 would have been trained by Microsoft, and the methods for establishing ground truth for that training are not detailed here. The Jintronix submission focuses on the performance and validation of its application built on top of the Kinect v2.
§ 890.5360 Measuring exercise equipment.
(a)
Identification. Measuring exercise equipment consist of manual devices intended for medical purposes, such as to redevelop muscles or restore motion to joints or for use as an adjunct treatment for obesity. These devices also include instrumentation, such as the pulse rate monitor, that provide information used for physical evaluation and physical planning purposes., Examples include a therapeutic exercise bicycle with measuring instrumentation, a manually propelled treadmill with measuring instrumentation, and a rowing machine with measuring instrumentation.(b)
Classification. Class II (special controls). The device, when it is a measuring exerciser or an interactive rehabilitation exercise device for prescription use only, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 890.9.