Search Results

The indication for use of the BOUNDER Power Wheelchair is to provide mobility to persons limited to a sitting position.

The subject device is an update to the existing previously cleared BOUNDER Power Wheelchair (K901210). The BOUNDER utilizes components found on most power wheelchairs. These include a rigid or "nonfolding", rear wheel drive power wheelchair base with two drive wheels in the rear with two anti-tip wheels mounted behind and two casters in the front. It has two motors and is powered by two 12V DC Batteries (connected in series), and electronic controller. It also includes a seat, footrests, arms, positioning strap and charger. The design offers a modular approach and can be configured in multiple versions to suit different user needs.

The new models will include: BOUNDER 300, BOUNDER Plus 300, BOUNDER 450, BIG BOUNDER 600 & BIG BOUNDER 1000.

The updated subject version of the BOUNDER Power Wheelchair has the following changes:

• Increase in the weight capacity of the previously cleared device from 500 lb to 1000 lb
• Add Power Tilt, Power Anterior Tilt, Power Recline and Power Seat Elevator options
• Addition of LiNX and R-net electronics
• Add Independent Drive Wheel Suspension
• Add an Off-Road tire option for BOUNDER 300, BOUNDER Plus 300 and BOUNDER 450
• Top speed: 8.5 mph

The provided document is a 510(k) summary for the BOUNDER Power Wheelchair. It describes a medical device, specifically a power wheelchair, and the testing conducted to demonstrate its substantial equivalence to a predicate device. The document does not describe an AI/ML powered device, nor does it present acceptance criteria or performance data in a way that aligns with the requested format for such a device.

Therefore, I cannot extract the specific information requested about acceptance criteria and study design for an AI/ML device from this document. The sections you asked for, such as sample size for test and training sets, data provenance, expert ground truth, adjudication methods, MRMC studies, and standalone performance, are not applicable or present in this regulatory submission for a physical medical device.

The document discusses "Design Verification and Validation Testing Data" where the BOUNDER Power Wheelchair was tested against various ANSI/RESNA WC standards. These standards cover aspects like static stability, dynamic stability, brake effectiveness, energy consumption, dimensions, mass, maneuvering space, maximum speed, acceleration, deceleration, climatic tests, obstacle-climbing ability, material properties, and electromagnetic compatibility. The acceptance criteria would be meeting the performance requirements outlined in each of these specific ANSI/RESNA WC standards. The study is essentially the comprehensive suite of tests conducted according to these standards.

Here's what I can provide based on the document, framed to indicate what's present and what is not applicable:

1. A table of acceptance criteria and the reported device performance

   • Acceptance Criteria: Meeting the performance requirements as defined by the "Rehabilitation Engineering and Assistive Technology Society of North America (RESNA) testing standard" (which specifically cites numerous ANSI/RESNA WC-1 and WC-2 standards, and ISO 7176-30:2018[E]). These are detailed engineering and performance specifications for power wheelchairs.
   • Reported Device Performance: The document states, "Design verification and validation testing was performed on the subject device and was found to meet performance requirements. Further, it is substantially equivalent to the predicate device... The acceptance criteria for the full verification of the design and acceptance criteria for each section of the Rehabilitation Engineering and Assistive Technology Society of North America (RESNA) testing standard have been met." Specific numerical performance values for each criterion are not provided in this summary.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

   • Not Applicable / Not Provided: This is a physical device, and testing would typically involve one or more physical units of the wheelchair model(s) undergoing various mechanical and electrical tests. The concept of "test set" or "data provenance" as applied to AI/ML data does not directly translate here. The testing was non-clinical.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

   • Not Applicable / Not Provided: This device relies on standardized performance testing, not expert interpretation or ground truth establishment in a medical imaging or diagnostic context.

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

   • Not Applicable / Not Provided: This concept is for diagnostic interpretation and is not relevant to the physical performance testing of a wheelchair.

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: This is a physical medical device, not an AI-powered diagnostic tool. No MRMC study was performed.

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

   • Not Applicable: This is a physical device, not an algorithm. Therefore, "standalone performance" in the context of an algorithm is not applicable. The device's performance was tested according to standardized methods.

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

   • Standardized Performance Requirements: The "ground truth" here is compliance with established engineering and safety standards (ANSI/RESNA WC, ISO 7176-30). The device must perform within the specified parameters of these standards.

8. The sample size for the training set

   • Not Applicable / Not Provided: This is a physical device and does not involve AI/ML training sets.

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

   • Not Applicable / Not Provided: This device does not have a training set in the context of AI/ML.

Ask a specific question about this device