(339 days)
A software system used with the Microsoft Kinect intended to support the physical rehabilitation of adults in the clinic/ at home. The system includes rehabilitation exercises for the upper extremity and trunk 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.
The device or software comprises of a client application called JRS Wave and a web application or portal called JRS Portal. The JRS is to be used with the Microsoft Kinect motion sensing technology. JRS Wave includes medically recognized gaming exercises for rehabilitation, audio-visual feedback & graphic movement representations for patients. Using the Microsoft Kinect for Windows to track motion, JRS Wave records performance metrics providing them to qualified medical professionals via JRS Portal. Medical professionals can monitor patient performance, assign or modify rehabilitation exercises in JRS Wave for their patients through the JRS Portal allowing for patients to perform their prescribed rehabilitation program even from the comfort of their home.
Here's a summary of the acceptance criteria and study detailed in the provided document for the Jintronix Rehabilitation System (JRS):
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criterion | Reported Device Performance |
|---|---|
| JRS movements are clinician-recognized rehabilitation movements. | Predominantly 100% of clinicians' responses agreed that JRS activity movements were medically recognized rehabilitation exercises, exceeding the 80% acceptance criterion. |
| Accuracy of JRS in data processing (for rehabilitation movements). | The study results validated the accuracy of the JRS in data processing, also indicated by the predominantly 100% clinician recognition of movements. |
| General Safety (e.g., electrical, mechanical, thermal, chemical, radiation) | The device is a software product; external hardware (Microsoft Kinect) uses 12 watts of energy, delivering no energy to the subject. It is non-invasive and a Class 1 laser (posing no safety issue). No mechanical, thermal, or chemical safety concerns were identified for the JRS system itself. |
| Usability & Effectiveness (Clinician Recommendation of JRS Movements) | 88% of clinicians fully recommended JRS movements. 8.5% recommended depending on patient ability. 3.5% not recommended without clinician intervention. The JRS was predominantly recommended by medical professionals for physical rehabilitation. |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: 20 healthy adult subjects (men and women of various ages).
- Data Provenance: Prospective, conducted in Canada.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- Number of Experts: 4 clinicians.
- Qualifications of Experts: Physical and occupational therapists.
4. Adjudication Method for the Test Set
- Adjudication Method: Each of the 4 clinicians assessed one video (a portion of the overall video recording) and completed 50 online questionnaires (10 activity components per subject x 5 subjects). There is no explicit mention of an adjudication process between the clinicians if their assessments differed. However, the reported results are "predominantly 100%," suggesting a high level of agreement.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No, an MRMC comparative effectiveness study regarding human readers improving with AI vs. without AI assistance was not done. The study focused on validating the JRS movements themselves as rehabilitative and the accuracy of data processing.
6. Standalone Performance
- Yes, a standalone (algorithm only without human-in-the-loop performance) validation was implicitly done as the study aimed to "verify that they [movements recorded by JRS] were rehabilitation movements" and "validating the accuracy of the JRS in data processing." The video recording presented to clinicians excluded the software and hardware, focusing only on the subject's movements as captured by the JRS.
7. Type of Ground Truth Used
- Type of Ground Truth: Expert consensus (clinician assessment). Clinicians were asked to identify the movements seen, potential risks, and if they would recommend the movements to their patients.
8. Sample Size for the Training Set
- The document does not explicitly state a separate "training set" for the JRS algorithm in the context of this clinical study. The system's rehabilitation program was "developed in consultation with clinicians," implying that clinical input guided its initial design and exercise content. The study described functions more as a validation of the pre-existing system.
9. How the Ground Truth for the Training Set Was Established
- As mentioned above, a distinct "training set" with established ground truth for an AI algorithm isn't explicitly described in this context. The JRS rehabilitation program was "developed in consultation with clinicians." This suggests that the "ground truth" for the exercises themselves was established through expert clinical input and recognized medical practices during the system's development.
§ 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.