Search Results

The intended use of the WHILL Model F powered wheelchair is to provide outdoor and indoor mobility to persons limited to a seated position that are capable of operating a powered wheelchair.

The subject device is an update to the existing previously cleared WHILL Model C2 (K213383) (hereafter the "predicate device"). The WHILL Model F is an indoor/outdoor, foldable battery-operated 2-wheel drive (rear-wheel drive) powered wheelchair. It has two arm rests, a seat belt, a foldable backrest, a seat cushion, a foldable frame, two motors, two electromagnetic brakes, an electric motor controller, and a lithium-ion battery with a dedicated off-board battery charger. The wheelchair is powered by a 25.3 V DC 10.6A rechargeable lithium-ion battery charged by an off-board lithium-ion battery charger. The control system, including the directional controller (joystick), is equipped on the control pad that attaches to the one of the arm rests. When the joystick is released, the electromagnetic brakes will be actuated, and the power wheelchair is slowed to a stop. As with all conventional powered wheelchairs, the user sits in the wheelchair seat and uses the control system such as the control pad positioned on either of the two arms to turn the chair on, control the speed, and direct the movement. Adjustments can be made to the arm rests to fit the user's body. The space between the two arms and the height of the arm rests can be adjusted based on the user's seating requirements. Model F contains a new folding feature, not available on the predicate device. The foldable technology is like the legally marketed DYW30A(D09) powered wheelchair (K170787) (hereafter the "reference device"). The subject device can be controlled by the directional controller or remote control by a smartphone app via Bluetooth Low Energy (BLE) wireless communication interface. The smartphone app can also display the battery's status, adjust the speed and acceleration setting and lock the unattended device. The user can lock and unlock the device remotely via the BLE interface using the smartphone app or using a smart key. The device supports a maximum weight of 253.5lb (115 kg), including the weight of the occupant and any carried items. It has a maximum driving range of 12.4 miles (20 km) with a maximum speed limit of up to 3.7mph (6 km/h).

This document is an FDA 510(k) premarket notification for a powered wheelchair, the WHILL Model F. It focuses on demonstrating substantial equivalence to previously cleared predicate devices rather than proving performance against specific acceptance criteria for a novel AI/software medical device.

Therefore, many of the requested elements for AI/software model testing (like sample sizes for test/training sets, number of experts for ground truth, adjudication methods, MRMC studies, or standalone algorithm performance) are not applicable to this document as it describes a hardware medical device (a powered wheelchair) and its comparison to other similar hardware devices, not an AI/software product.

The acceptance criteria provided in the document revolve around the device's compliance with established performance, electrical safety, biocompatibility, and software standards relevant to powered wheelchairs.

Here's the information extracted from the document, acknowledging that most AI/software-specific questions are not relevant:

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

The document provides extensive tables (Table 1, Table 2, Table 3) comparing the WHILL Model F's compliance with various international standards to its predicate devices. Rather than specific numerical performance metrics, the acceptance is based on "Pass" or "Identical to subject device" for compliance with these standards.

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

• Test Sample Size: Not specified in the context of statistical testing for a software algorithm. The "test set" here refers to physical units of the device that underwent engineering, performance, and safety testing according to ISO, IEC, FCC, and other relevant standards. These are typically engineering samples rather than large cohorts for clinical data analysis. For usability, it mentions "Performed on 20 Subjects" for the predicate device, and implies the same for the subject device ("Same").
• Data Provenance: Not explicitly stated. The testing was performed to international standards (ISO, IEC, FCC/ETSI), which implies the data was collected in certified testing laboratories. The manufacturer is Whill, Inc. in Japan.

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. This document is for a physical medical device (powered wheelchair), not an AI/software device whose performance relies on interpreting medical images or data. Ground truth for a physical device is established through engineering and performance measurements against established technical standards, not expert medical opinion on a dataset.

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

Not applicable. This is a concept used in AI/software medical device studies for establishing expert consensus on ambiguous cases, not for validating engineering performance parameters of a hardware device.

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 physical device, not an AI-assisted diagnostic tool for human readers.

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

Not applicable. This is a fundamental characteristic of an AI/software device. The WHILL Model F is a powered wheelchair and inherently involves human-in-the-loop operation.

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

The "ground truth" for this device's safety and performance is established through compliance with recognized international standards (e.g., ISO 7176 series for wheelchairs, ISO 10993 for biocompatibility, IEC 60601 series for electrical safety and EMC). These standards define the performance and safety requirements. The tests performed are objective, measurable evaluations against these defined requirements, rather than subjective interpretation by experts.

8. The sample size for the training set

Not applicable. This is not an AI/software device that requires a "training set" in the machine learning sense.

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

Not applicable. As above, there is no "training set" for this type of device.

Ask a specific question about this device