FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

The Korebalance™ device is intended for use in balance therapy, only by health care professionals with experience in balance therapy. Patient suitability must be judged by the health professional on a case by case basis.

Device Description

The updated Korebalance™ Kinesthetic Ability Trainer device has the same intended use and incorporates the same balance board (platform) and bladder design technology as the originally cleared device. The modifications are primarily software based and allow:

1. Creation of a patient specific electronic record of patient information via a touchscreen GUI.
Quantitative measurement of patient balance performance while the patient 2. executes a preprogrammed set of maneuvers or protocols with the board. The GUI provides instructions and visual feedback to the patient with regard to the maneuvers to be made and the success in executing the maneuver. The patient results are scored and saved (the information is not a clinical measurement but provides a reproducible quantitative measurement that the therapist can use to plan and monitor therapy) along with the bladder pressure measurement for use by the therapist, in conjunction with the therapist's observations, to assess patient progress over the course of multiple therapy sessions. Specific protocols are provided for vestibular training, orthopedic therapy, and falls prevention. These protocols are similar to those used with the previously cleared device.
1. Patients to play "games" displayed on the GUI that involve performing various maneuvers on the balance platform. Performance is scored. The games provide an additional means for the therapist to provide rehabilitation that is fun and challenging for patients.

AI/ML Overview

The Korebalance™ Kinesthetic Ability Trainer is a device intended for use in balance therapy by health care professionals. This Special 510(k) submission (K070676) is for modifications to the previously cleared K.A.T. 1000 device (K911795), primarily software-based updates.

Here's an analysis of the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance:

Acceptance Criteria Category	Specific Criteria	Reported Device Performance	Comments
Safety and Effectiveness	Maintain fundamental safety and effectiveness of the predicate device.	The modifications "do not materially alter the intended use or fundamental technology of the device, but serve to facilitate the provision of therapy, data collection and management."	This implies that since the core technology and intended use are unchanged, and the modifications are primarily software-based to improve user interaction and data handling, the device is considered as safe and effective as the predicate.
Intended Use	Same intended use as the predicate device (K.A.T. 1000).	"It has the same intended use."	The device continues to be intended for balance therapy, to be used by healthcare professionals for assessing and improving patient balance.
Fundamental Technology	Incorporates the same balance board and bladder design technology as the predicate device.	"It incorporates the same balance board and bladder design technology."	The core hardware component (balance platform) remains identical, ensuring consistent physical interaction and measurement principles.
Performance Measurement	Ability to provide quantitative measure of performance.	"The device provides a quantitative measure of performance."	This functionality is inherent to both the predicate and the modified device, as it's a key aspect of balance assessment and therapy monitoring.
Adjustability	Degree of difficulty is adjustable.	"The degree of difficulty is adjustable."	This feature is retained from the predicate, allowing therapists to customize therapy to individual patient needs.
New Features Functionality	Software modifications (touchscreen GUI, patient specific electronic record, preprogrammed tests, scoring, saving data, "games") function as intended.	"The modifications are primarily software based and allow: 1. Creation of a patient specific electronic record... 2. Quantitative measurement... 3. Patients to play "games"... Performance is scored."	The submission implicitly asserts that these new software features function as described and enhance the device's usability and therapeutic capabilities.
Regulatory Compliance	Modifications made in accordance with design control provisions and applicable guidance documents.	"The modifications to the existing device were made in accordance with the design control provisions of the quality system regulation and applicable guidance documents to show that the modified device is as safe, as effective, and performs as well as or better than the original device."	This statement confirms adherence to regulatory requirements for design changes, which is the primary "study" or justification for a Special 510(k).

2. Sample size used for the test set and the data provenance:

Sample Size: Not applicable. This is a Special 510(k) based on design modifications to a previously cleared device, not a de novo submission requiring extensive new clinical testing with a specific test set of patient data.
Data Provenance: Not applicable. The submission focuses on demonstrating that the modifications themselves do not alter the fundamental safety or effectiveness of the already cleared device. There isn't a "test set" of patient data in the traditional sense for evaluating algorithm performance. The basis for acceptance is regulatory compliance with design controls and a comparison to the predicate device.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

Not applicable. There was no "test set" requiring expert ground truth establishment for this type of submission.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

Not applicable. No adjudication method was used as there was no test set of patient data requiring such.

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 study was not done. The Korebalance Kinesthetic Ability Trainer is a physical balance assessment and training device, not an AI-assisted diagnostic imaging or interpretation tool that would involve "human readers" in that context. The modifications are to its software interface and data management, not its core measurement methodology in a way that would necessitate comparing human interpretation.

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

Not applicable. This device is not an algorithm-only diagnostic tool. It requires human interaction (patient on the board, therapist overseeing). While it has software and algorithms for measurement and scoring, it's not a standalone AI product in the sense of making independent diagnostic or treatment recommendations without human oversight. Its "performance" is tied to its functional accuracy as a balance measurement device, which is considered equivalent to the predicate.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

Not applicable. The "ground truth" for this Special 510(k) is effectively the established safety and effectiveness of the predicate device (K.A.T. 1000) and the demonstration that the new modifications uphold this standard through adherence to design controls and functional verification. There isn't an external clinical "ground truth" in the typical sense for algorithm validation.

8. The sample size for the training set:

Not applicable. This device does not use machine learning algorithms that require a "training set" of data in the common sense. The software modifications are functional enhancements rather than AI models being trained on large datasets.

9. How the ground truth for the training set was established:

Not applicable, as there was no training set in the machine learning context.

Summary

Regulation Number and Section

N/A