Search Results

The Model R is a motor-driven, indoor and outdoor transportation vehicle with the intended use to provide mobility to a disabled or elderly person limited to a seated position.

WHILL Model R is an indoor/outdoor electric scooter that is intended as a mobility aid for elderly persons or persons with reduced mobility. Providing Bluetooth-based radio communications functionalities. Model R is available in two variants, the 3-wheel model and the 4-wheel model. The 3-wheel scooter has a base with metal alloy frame, one front wheels, two rear wheels, two anti-tip wheels, a seat, an adjustable steering column, a tiller console, 2 electric motors, 2 electromagnetic brakes, a rechargeable lithium-ion battery with an off-board charger. The 4-wheel scooter has a base with metal alloy frame, two front wheels, two rear wheels, two anti-tip wheels, a seat, an adjustable steering column, a tiller console, 2 electric motors, 2 electromagnetic brakes, a rechargeable lithium-ion battery with an off-board charger. The only difference between 3-wheel model and 4-wheel model is front drive-base component. The 3-wheel model has a single front tire, while the 4-wheel model has two front tires. Besides this difference in mechanical design, other parts of the device are identical across the two models. Customers can choose a model depending on their preferences and use case. Model R has a removable lithium-ion battery, a swivel 17-inch-wide seat with two armrests and front and rear LED lights. The battery may be charged either when installed within the device or when removed. Some components are adjustable to provide user with a comfortable riding position. The inner width and the height of the armrests are adjustable in 3 positions. The seat position from the tiller is adjustable in 4 positions. The seat height is adjustable in 2 positions and the tiller angle is also adjustable. A lap belt is equipped for posture support and for safety. As with all conventional powered scooters, to drive the Model R, the user sits in the seat and grips the tiller handle around the controller unit which is positioned in front of the user. While gripping the tiller handle, the user uses their fingers to pull the right side of the throttle control lever gently to drive the device forward. The degree at which the throttle control lever is pulled is positively proportional to the speed of the device. When the throttle control lever returns to its original position after the user releases it, the device decelerates and comes to a stop. When the user uses their fingers to pull on the left side of the lever, the device drives backwards. To move to the left, the user turns the tiller handle to the left, and, to the right, the user turns the tiller handle to the right. Model R has Bluetooth-based radio communications capabilities. The user can power on Model R with a physical key, a Bluetooth smart key fob or with a dedicated smartphone app. The user can select speed profiles, turn off and on the front LED light and sound the audible warning device by operating the controller unit. User can disassemble Model R into four components, i.e. drive base, main body, seat base assembly and battery, without the use of tools when loading into a car for transportation. The device supports a maximum weight of 147 kg (325 lbs.), including the weight of the occupant and any carried items. The 3-wheel model has a theoretical continuous driving range of 18.7 km (11.6 miles) while the 4-wheel model has a theoretical continuous driving range of 17.2 km (10.7 miles).

The provided text is a 510(k) Summary for the WHILL Model R, a motor-driven indoor and outdoor transportation vehicle. It details the device's characteristics, comparison to predicate and reference devices, and results of safety and performance testing to demonstrate substantial equivalence.

However, the provided text does not describe "acceptance criteria" or a "study that proves the device meets the acceptance criteria" in the context of an AI/ML medical device performance study.

The document discusses:

• Performance testing of the physical device (e.g., static stability, dynamic stability, braking, electrical safety, biocompatibility) against existing ISO and IEC standards for wheelchairs and motorized three-wheeled vehicles. These are not "acceptance criteria" for an AI/ML algorithm's performance.
• Comparison of technological characteristics between the subject device, a predicate device, and a reference device to demonstrate "substantial equivalence." This is a regulatory pathway for physical medical devices, not a performance study for an AI/ML algorithm.
• Software Verification and Validation Testing according to ANSI AAMI IEC 62304, which is a standard for medical device software lifecycle processes, but doesn't specify performance metrics for an AI/ML model.
• FCC Radio Frequency Testing and Wireless Co-existence Testing for the device's Bluetooth functionalities, which are regulatory compliance tests for wireless communication, not AI/ML performance.
• Usability Testing according to IEC 62366-1, which focuses on user interface and safety, not AI/ML algorithm accuracy.

Therefore, I cannot extract the requested information about AI/ML acceptance criteria or a study proving it, as the provided document does not pertain to the performance evaluation of an AI/ML medical device. It describes the regulatory submission for a physical motorized vehicle.

Ask a specific question about this device

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

The intended use of the WHILL Model C2 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 M (K153543). The WHILL Model C2 is an indoor/outdoor battery-operated 2-wheel drive (rear-wheel drive) powered wheelchair. It consists of four parts: seat system, braking system, and drive system. It consists of two motors drive systems, an electromagnetic braking system, an electric motor controller, and a lithium-ion battery with an off-board battery charger. The wheelchair is powered by a 25.3V DC 10.6A rechargeable lithium-ion battery charged by an offboard lithium-ion battery charger.

The control system, including the directional controller (joystick), is equipped on the control pad that attaches to the armrest. When the joystick is released, the electromagnetic brakes will be actuated, and the power wheelchair is slowed to a stop.

As with all commercially available 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 seating to fit the user's body. Like the predicate device WHILL Model M, the two side-arms can be rotated out of the way to make it easier for the user to get into and out of the device.

Model C2 also contains Bluetooth-based RF wireless technology. The wireless technology is identical to the legally marketed reference device 2, e-motion-M25 (K192618). The 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 is used to drive the chair remotely. (Note: For safety, Joystick control is priority over the remote control by design.) The smartphone app can also view 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 fob.

The device supports a maximum weight of 136Kg (300lbs.), including the weight of the occupant and any carried items. It has a maximum driving range of 11miles (18km) with a maximum speed limit of up to 5mph (8km/h).

The provided document is a 510(k) Summary for the WHILL Model C2 powered wheelchair, seeking to demonstrate its substantial equivalence to previously cleared predicate and reference devices. However, this document does not contain information related to a study proving the device meets acceptance criteria for an AI/algorithm-driven medical device.

Instead, it details the safety and performance testing conducted on the powered wheelchair itself, based on harmonized standards (ISO, IEC, RESNA, etc.), biocompatibility testing, electrical safety, electromagnetic compatibility, and software verification/validation for the control system of the wheelchair. It is a submission for a physical medical device (powered wheelchair), not an AI/algorithm-driven diagnostic/assistive tool.

Therefore, I cannot extract acceptance criteria and study details for an AI/algorithm-driven device from this document. The document describes:

• Device: WHILL Model C2 (a powered wheelchair)
• Purpose of Submission: Demonstrate substantial equivalence of the WHILL Model C2 to predicate and reference powered wheelchairs.
• Testing: Performance tests for wheelchairs (e.g., stability, braking, speed, energy consumption, obstacle climbing, static/impact/fatigue strengths, climatic tests, power/control systems), biocompatibility, electrical safety, EMC, software V&V, FCC RF testing, wireless coexistence testing, and usability testing.
• Ground Truth: For the physical device, "ground truth" is established by adherence to recognized international and national standards (such as ISO 7176 series, IEC 62133-2, ISO 10993, IEC 60601-1-2, ANSI C63.27-2017, etc.). The "results" are typically "Pass" or "Fail" against the requirements of these standards.
• Sample Size: The sample size for testing is implicitly "a sample" of the physical devices, as is typical for medical device regulatory submissions for hardware. Specific numbers are not provided, as the focus is on compliance with standards.
• Experts: Not explicitly stated for each test, but compliance to standards usually involves certified testing labs and engineers with expertise in the relevant standards.
• Adjudication Method: Not applicable in the context of physical product testing against standards.
• MRMC/Standalone AI Study: Not applicable as this is not an AI/algorithm-driven diagnostic or assistive device in the sense typically associated with these types of studies (e.g., for image analysis AI). The "smartphone app" mentioned controls the physical movement of the wheelchair and views status; it's a control interface, not an AI performing medical analysis.
• Training/Test Set for AI: Not applicable for this type of device submission.

In summary, the request for acceptance criteria and study data for an AI/algorithm-driven device cannot be fulfilled by this document as it pertains to a physical powered wheelchair, not an AI medical device.

Ask a specific question about this device

The intended use of the Model M 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 WHILL Model M is an indoor/outdoor battery-operated 4 wheel drive powered wheelchair. It is powered by two 12 VDC 50Ah batteries and controlled by the R-net 120 amp motor controller. As with all commerciallyavailable powered wheelchairs, the user sits in the wheelchair seat and uses controls positioned on the arms to turn the chair on, control the speed, and direct the movement. The directional controller can be mounted on the left or right arm. When the user activates the directional controller the brakes are released and the motors rotate to move the device in the desired direction. When the user releases the directional controller the device is brought to a controlled stop. The chair frame is a welded nut and steel construction and includes two rear wheels with drive units (motor, gear and brake) connected by belts to the front all directional wheels. Adjustments can be made to the two arm supports, foot support, and seat height and depth to position the user correctly in the device. The device supports a maximum weight of 220 lb, and has an approximate driving range of 12 miles. The device can be operated on carpet, tile, wood, vinyl, concrete, blacktop, dirt, gravel, grass, and wet (

This document is a 510(k) Premarket Notification for the WHILL Model M Powered Wheelchair. It describes the device, its intended use, and compares it to a predicate device (Permobil F3 Corpus) to demonstrate substantial equivalence, primarily through technical specifications and adherence to relevant standards.

Here's an analysis of the acceptance criteria and study information provided, structured according to your request:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" in the sense of specific numerical thresholds that are then met by the device's performance data. Instead, the "acceptance criteria" are implied by the adherence to various national and international standards for powered wheelchairs. The "reported device performance" is the successful completion of testing against these standards.

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

The document describes performance testing of the device, not a clinical study on human subjects with a "test set" of patient data. Therefore, the concept of sample size for a test set and data provenance (country of origin, retrospective/prospective) related to patient data is not applicable in this context. The "test set" would refer to the physical WHILL Model M device itself being subjected to various engineering and safety tests as defined by the standards listed. The provenance of the device testing would be from WHILL, Inc.

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

This question is not applicable to the type of device and study described. This document pertains to the regulatory clearance of a physical medical device (powered wheelchair) based on engineering performance and safety standards, not an AI or diagnostic device that requires expert-established ground truth from medical images or clinical data. The "ground truth" for these tests are the objective performance criteria set by the ISO, ANSI/RESNA, ASTM, and UL standards.

4. Adjudication Method for the Test Set

This question is not applicable. The performance testing of a physical device against engineering standards typically involves objective measurements and adherence to specified test protocols, not subjective adjudication methods like those used for expert consensus in clinical data analysis. The "adjudication" is implicitly the objective pass/fail determination based on the standard's criteria.

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 question is not applicable. The WHILL Model M is a powered wheelchair; it is not an AI diagnostic or assistance system that would involve human readers or affect their performance.

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

This question is not applicable. The WHILL Model M is a physical powered wheelchair, not an algorithm. Its performance is inherent to its design and functional capabilities, not an algorithmic output.

7. The Type of Ground Truth Used

The ground truth used for this regulatory submission is adherence to established international and national engineering, safety, and performance standards for powered wheelchairs. These standards (e.g., ANSI/RESNA WC-1, WC-2, WC-4; ISO 7176, ISO 8191, ISO 10993; ASTM D4169; UL 94) define objective metrics, test methodologies, and acceptable performance limits. The "ground truth" is the successful demonstration that the device's physical and functional attributes meet these predefined requirements.

8. The Sample Size for the Training Set

This question is not applicable. The WHILL Model M is a physical medical device, not an AI model that requires a "training set" of data.

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

This question is not applicable, as there is no "training set."

Ask a specific question about this device