K Number
K062483
Date Cleared
2006-09-08

(14 days)

Product Code
Regulation Number
890.3860
Panel
PM
Reference & Predicate Devices
Predicate For
N/A
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The Mini Power Chair MN 5000 is intended to provide mobility to persons limited to a sitting position, that have the capability of operating a powered wheelchain. The Mini Power Chair MN 5000 provides an optional means of mobility for mysically chill vendl people.

Device Description

The Mini Power Chair MN 5000 is an indoor/outdoor powered wheelchair that is battery operated. It has four wheels and anti-tip. The design of this wheelchair is basically similar to other power chairs that are already on the market. But the MN 5000 is kind of a new class of lightweight power chair. By providing a power chair that breaks down into four manageable components(seat, battery pack, front frame and rear frame), a user can have a more practical alternative when traveling long distances by auto, bus, train, etc. MN 5000 achieves it by using a lightweight tubular design with quick disapart front and rear frames, easily detachable seat and a quick release battery pack system.

MN 5000 has two motors, an off-board battery charger, a fully programmable controller, and a removable battery pack.

The wheelchair has a sturdy base which contains the motors, provides space for the battery box and supports the padded seat. The breaking system is automatic and clectric. The seat has adjustable armrest and footrest. There is a controller with a joystick that attaches to either armrest and allows the rider to control the movement of the power chair. The Drive wheels (rear wheels) are 8" in diameter and the Caster wheels (from wheels) are 6".

AI/ML Overview

The provided text describes a 510(k) submission for a medical device (Mini Power Chair MN 5000) and its substantial equivalence to a predicate device. It does not contain information about the acceptance criteria or a study proving the device meets those criteria in the way typically expected for AI/ML device performance.

However, I can extract the information relevant to what testing was performed and how the device's performance was evaluated, interpreting "acceptance criteria" as meeting safety and performance standards for powered wheelchairs.

Here's an analysis based on the provided text:

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

Acceptance Criteria (Interpreted as Regulatory Standards)Reported Device Performance
Compliance with appropriate ISO & ANSI/RESNA standardsThe device has been tested to appropriate ISO & ANSI/RESNA standards. Tests were conducted to evaluate:
  • Static and dynamic stability
  • Energy requirements
  • Performance of brakes
  • EMC requirements
  • Flame retardant tests of upholstery materials
    All tests meet requirements.
    Verification and validation testing confirms that a wheelchair fitted with VR2 performs as intended. |
    | Performance and Safety (post-design change assessment) | Detailed testing has confirmed that changes (less powerful batteries due to lightweight design) do not affect the performance or safety of the wheelchair. |

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

The document does not specify the sample size for the tests (e.g., number of wheelchairs tested or number of trials for each test). The provenance of the data (country of origin or retrospective/prospective nature) is also not mentioned. However, the manufacturer is "Line Ind. (Shanghai) Co., Ltd." in China, suggesting the testing likely took place or was overseen by this entity.

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)

This information is not applicable as the document describes non-clinical engineering and materials testing for a physical device, not an AI/ML or diagnostic device that would typically involve expert-established ground truth. Expert involvement would be in the design, testing protocols, and interpretation of engineering results, but not in establishing "ground truth" for a dataset.

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

This information is not applicable. Adjudication methods like 2+1 or 3+1 are used for establishing ground truth in human-in-the-loop or expert consensus studies, which are not relevant to the described non-clinical performance testing of a powered 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

This information is not applicable. An MRMC study is relevant for diagnostic devices involving human readers (e.g., radiologists interpreting images) and AI assistance. This document describes a powered wheelchair, which does not involve "human readers" or AI assistance in this context.

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

This information is not applicable. There is no "algorithm" in the sense of AI/ML being evaluated in a standalone or human-in-the-loop manner for this device. The wheelchair itself has a "fully programmable controller" and motors, but the testing described is of the physical device's performance against engineering standards.

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

For the non-clinical testing, the "ground truth" is established by objective engineering standards and measurements. This includes:

  • ISO & ANSI/RESNA standards: These are internationally recognized standards that define acceptable performance limits for various aspects (e.g., stability, brake performance, energy requirements).
  • Measurement of physical parameters: Tests would involve instruments to measure stability angles, brake distances, energy consumption, material flammability, electromagnetic compatibility, etc., against predefined pass/fail criteria from the standards.

8. The sample size for the training set

This information is not applicable. There is no "training set" in the context of an AI/ML algorithm for this device. The design and manufacturing process for the wheelchair would involve materials selection, engineering design, prototyping, and testing, but not machine learning training.

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

This information is not applicable for the same reasons as point 8.

§ 890.3860 Powered wheelchair.

(a)
Identification. A powered wheelchair is a battery-operated device with wheels that is intended for medical purposes to provide mobility to persons restricted to a sitting position.(b)
Classification. Class II (performance standards).