Search Results

The device is intended for medical purposes to provide mobility to persons restricted to a sitting position.

The SUNCO Mechanical Wheelchair, model SKW-9003 is an indoor / outdoor wheelchair that has a base with four-wheeled with a seat. The device can be disassembled for transport and it is foldable easily. The device uses a standard sling type back and seat, and the upholstery fabric meets the EN 1021-1:2006 Furniture --Assessment of ignitability of upholstered furniture - Part 1: Ignition source smouldering cigarette & EN 1021-2:2006 Furniture -- Assessment of ignitability of upholstered furniture - Part 2: Ignition source match flame equivalent. The back upholstery material is resistance-ignitability fabric. The removable desk-length armrest and swing-away detachable footrest.

This document is a 510(k) Premarket Notification from the FDA regarding the SUNCO Mechanical Wheelchair, model SKW-9003. This type of document is a regulatory approval, not a clinical study report. Therefore, it does not describe an AI/ML device or its performance criteria in the way envisioned by the posed questions.

The device in question is a mechanical wheelchair, which is a physical medical device, not a software or AI/ML-driven diagnostic or therapeutic device. The document focuses on demonstrating substantial equivalence to a predicate mechanical wheelchair based on design, materials, and performance against established safety standards.

Consequently, most of the requested information regarding acceptance criteria and a study proving an AI/ML device meets them cannot be extracted from this document. Specifically:

• No AI/ML device: The document pertains to a mechanical wheelchair, not an AI/ML device.
• No performance criteria for AI/ML: The acceptance criteria and performance data are related to the physical and mechanical aspects of the wheelchair (e.g., static stability, brake effectiveness, material ignitability), not AI/ML metrics like sensitivity, specificity, AUC, etc.
• No clinical study for AI/ML effectiveness: The "performance data" refers to non-clinical bench testing against ISO standards for biocompatibility and safety of the wheelchair, not a clinical study involving human readers or AI assistance.

Therefore, I will provide the information that is present in the document related to the wheelchair's acceptance criteria and testing, and explicitly state when the requested AI/ML specific information is not available.

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

The document does not present acceptance criteria in a quantitative table with specific target values and achievement against those targets. Instead, it states that the device was tested against recognized ISO standards and "complied with" them, which implies meeting the requirements of each standard. The predicate device's characteristics are used for comparison to establish substantial equivalence.

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

This information is not applicable in the context of an AI/ML device or a clinical study. The performance data presented refers to bench testing of the physical wheelchair and its components. Specific sample sizes for these engineering tests (e.g., how many wheelchairs were tested for static stability) are not detailed, but the testing was done by the manufacturer (Danyang Sunco Machinery Co., Ltd.) in China. This is not a human subject-based test set.

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 is not applicable as the device is a mechanical wheelchair and no ground truth by human experts interpreting data (as in AI/ML performance evaluation) was established. The "ground truth" for the wheelchair's safety and performance is defined by the technical specifications and test methods within the cited ISO standards.

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

Not applicable. There was no human interpretation or adjudication involved in evaluating the performance of this mechanical device against standard engineering tests.

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

Not applicable. This is a mechanical wheelchair, not an AI-assisted diagnostic or therapeutic device. No MRMC study was conducted.

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

Not applicable. This is a mechanical wheelchair, not an AI algorithm.

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

For the mechanical wheelchair, the "ground truth" or reference for evaluating its performance is based on predefined engineering and safety standards (ISO standards) and the characteristics of a legally marketed predicate device. There is no "ground truth" in the sense of clinical pathology, expert consensus, or outcomes data as would be used for an AI/ML device.

8. The sample size for the training set

Not applicable. This device is a mechanical wheelchair and does not involve AI/ML models that require a training set.

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

Not applicable. This device is a mechanical wheelchair and does not involve AI/ML models that require a training set or ground truth for such a set.

Ask a specific question about this device