K Number
K073686
Date Cleared
2008-02-27

(61 days)

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

The C.T.M. Power Chair HS-1500 is an indoor/outdoor powered wheelchair that provides transportation for a disabled or elderly person.

Device Description

The C.T.M. Power Chair HS-1500 is an indoor/outdoor powered wheelchair that is battery operated. It has a base with four wheels, a padded seat with adjustable armrests, and a controller attached to one armrest which allows the rider to control the movement of the chair. It can be disassembled for transport and is provided with an on-board battery charger.

AI/ML Overview

This document, K073686, describes a 510(k) submission for a powered wheelchair, the C.T.M. Power Chair HS-1500. This type of device does not typically involve the kinds of studies and acceptance criteria commonly associated with AI/ML-based medical devices or diagnostic tools. Therefore, much of the requested information regarding AI/ML study design, ground truth, and expert evaluation is not applicable or available in this submission.

Here's a breakdown based on the provided text, addressing the points where information is available:

1. Table of Acceptance Criteria and Reported Device Performance

The submission states: "Tests listed in the Guidance Document for the Preparation of Premarket Notification [510(k)] Applications for Mechanical and Powered Wheelchairs, and Motorized Three Wheeled Vehicles, July 1995, were conducted and the results included in the submission."

However, the specific acceptance criteria (e.g., maximum speed, turning radius, battery life, weight capacity, stability, braking performance) and the reported performance results against these criteria are not detailed in this summary document. They would have been part of the more extensive 510(k) submission not included here.

2. Sample Size Used for the Test Set and Data Provenance

This information is not provided in the summary. For a physical device like a wheelchair, "test set" would refer to the units of the product that underwent performance and safety testing. The number of units tested is not stated, nor is the provenance of the data (e.g., in-house testing, third-party lab). The testing appears to be physical performance and safety testing of the device itself, not data-driven evaluations.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of those Experts

Not applicable. For a powered wheelchair, "ground truth" would refer to established engineering standards, safety regulations, and performance specifications from the relevant guidance documents (as mentioned in the text). There isn't "ground truth" in the sense of expert annotation of medical images or other data for an AI algorithm. The performance is assessed against predefined physical and mechanical thresholds.

4. Adjudication Method for the Test Set

Not applicable. This concept pertains to resolving discrepancies in expert opinions or data labels, which is not relevant for the type of testing described for a powered wheelchair.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No. The submission explicitly states: "Comparative performance testing and clinical evaluations were not submitted as part of this 510(k)." MRMC studies are typically used to evaluate the impact of AI on human reader performance, which is not relevant for this device.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Not applicable. There is no AI algorithm being evaluated for this medical device. The device is a physical powered wheelchair.

7. The Type of Ground Truth Used

The "ground truth" implicitly used would be adherence to the safety and performance standards outlined in the "Guidance Document for the Preparation of Premarket Notification [510(k)] Applications for Mechanical and Powered Wheelchairs, and Motorized Three Wheeled Vehicles, July 1995." This would encompass physical measurements, load testing, endurance testing, braking tests, stability tests, etc. No "expert consensus," "pathology," or "outcomes data" in the typical AI context are mentioned for establishing ground truth for this device.

8. The Sample Size for the Training Set

Not applicable. This device is a physical product, not an AI/ML algorithm. There is no "training set" in the context of machine learning.

9. How the Ground Truth for the Training Set Was Established

Not applicable, as there is no training set for an AI algorithm.

In Summary:

The K073686 submission is for a traditional medical device (a powered wheelchair) seeking substantial equivalence to a predicate device. The evaluation focuses on meeting established physical and mechanical performance standards and safety requirements rather than on the performance of a diagnostic algorithm or AI system. Therefore, most of the detailed questions regarding AI/ML study design are not addressed in this document.

§ 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).