(112 days)
The Recovr Rehabilitation System is software for use with the Microsoft Kinect motion tracking system that is indicated to support physical rehabilitation of adults in the clinic and at home via performance of therapist-assigned reach exercises for the upper extremities. Patient assessment, exercise guidance, and approval by the medical professional are required prior to use.
The Recovr Rehabilitation System (RRS) is a software system that presents games to facilitate the completion of therapist designed and prescribed upper extremity repetitive reaching exercises and that collects data for the therapist on the user's game play. The system was designed in collaboration with an experienced neurorehabilitation occupational therapist and rehabilitation research team. The RRS is intended for use in the clinic or at home. Patient assessment, exercise guidance, and approval by the medical professional are required prior to use.
The system consists of software, a computer, a primary display monitor, a secondary monitor, and a Microsoft Kinect motion-tracking sensor. Users sit on a bench or stand 6-8 feet away from the primary display monitor. The Kinect sensor is placed along the top or bottom edge of the primary display monitor, and the therapist controls the system from a secondary monitor, mouse, and keyboard off to the side of the primary display monitor. The games are based on a traditional carnival shooting gallery, with targets that pop–up to present reaching tasks. The virtual reality environment incorporates video game principles to engage and motivate users to perform the amount of rehabilitation assigned by the rehabilitation therapist. The system collects data on participant movement and actions throughout each session that allows therapists to track participant performance and improvement across therapy sessions.
The device is not supplied sterile or intended to be sterilized by the operator prior to use, and is not intended for single use.
The Recovr Rehabilitation System (RRS) is a software system intended to support physical rehabilitation for adults, specifically for upper extremity reach exercises, using the Microsoft Kinect motion tracking system.
Acceptance Criteria and Device Performance:
The document explicitly states that "No mandatory performance standards have been established for this device (Section 514 of the Act)." However, it does refer to "Software testing was conducted to verify performance in accordance with FDA's May 2005 guidance document entitled, 'Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices.'"
The device performance is generally described in relation to its intended use and comparison to the predicate device, the Jintronix Rehabilitation System (K130847).
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Facilitate therapist designed and prescribed upper extremity repetitive reaching exercises. | "The Recovr Rehabilitation System (RRS) is a software system that presents games to facilitate the completion of therapist designed and prescribed upper extremity repetitive reaching exercises..." |
| Collect data for the therapist on the user's game play. | "...and that collects data for the therapist on the user's game play." and "The system collects data on participant movement and actions throughout each session that allows therapists to track participant performance and improvement across therapy sessions." (This aligns with the predicate device's capability to report on kinematic parameters). |
| Provide audiovisual feedback and graphic representations of user movement. | "Both platforms... provide audiovisual feedback and graphic representations of the user movement, as well as reporting to the clinician on kinematic parameters like velocity and joint angular changes during movement." (This is stated in comparison to the predicate, implying the subject device also does this). |
| No risk of harm to the user or operator in case of device failure or latent flaw (due to "minor" level of concern for software). | "The software for this device was considered as a 'minor' level of concern, as there is no risk of harm to the user or operator in the case of device failure or latent flaw." This is a categorization of risk rather than a direct performance metric, but it implies the software's performance contributes to this safety profile. Also, "The devices are also identical in safety, as they are software platforms for use with the Microsoft Kinect motion tracking system." |
| Substantial equivalence to the predicate device (Jintronix Rehabilitation System K130847) in terms of intended use, performance, and technology. | "The RRS and the predicate Jintronix Rehabilitation System (JRS) are substantially equivalent in terms of intended use and performance and technology." Minor difference noted: "The Indications for Use statement for RRS is not identical to the predicate device in that the Indications for Use for the subject device do not include 'remotely accessible patient performance metrics for the medical professional' at this time." However, the document concludes this difference "does not affect the intended use... nor do they affect the safety and effectiveness of the device relative to the predicate when used as labeled." and "Software verification and validation demonstrate that the subject device should perform as intended in the specified use conditions." |
Study Details:
The document describes the regulatory submission for premarket notification (510(k)) and a determination of substantial equivalence, rather than a clinical study proving specific performance metrics against acceptance criteria.
-
Sample size used for the test set and the data provenance:
- No specific test set or sample size for performance evaluation by the FDA is mentioned in this document. The FDA's determination is based on the provided information, which includes software verification and validation, but not a separate clinical test set of patients. No data provenance (country of origin, retrospective/prospective) is specified for performance testing.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- This information is not provided in the document. The RRS was "designed in collaboration with an experienced neurorehabilitation occupational therapist and rehabilitation research team," but this refers to the development process, not the establishment of ground truth for a test set for FDA submission.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Not applicable as no specific test set requiring ground truth adjudication is described for the purpose of this FDA submission.
-
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 comparative effectiveness study is mentioned. The device is a rehabilitation system, not a diagnostic imaging device typically associated with MRMC studies or "human readers improving with AI assistance." The software's role is to facilitate exercises and collect data, not to assist human interpretation of medical images or data in an "AI-assisted reading" context.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- The document implies that "software verification and validation" was conducted. However, the system is designed to be "software for use with the Microsoft Kinect motion tracking system" and requires "Patient assessment, exercise guidance, and approval by the medical professional are required prior to use." This means the device is inherently intended for use with a human-in-the-loop (the patient and the medical professional). The document does not describe performance of the algorithm stand-alone without this human interaction context.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc):
- Not explicitly stated for performance testing. The "ground truth" for the device's functionality likely stems from its ability to accurately track motion and present exercises as designed, as verified during software development and validation activities.
-
The sample size for the training set:
- Not applicable. The document describes a software system that facilitates physical rehabilitation exercises, not a machine learning or AI model trained on a dataset. Therefore, there is no "training set" in the conventional sense of AI/ML development.
-
How the ground truth for the training set was established:
- Not applicable, as there is no mention of a training set for an AI/ML model.
§ 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.