Search Results

The Power Wheelchair 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.

This Power wheelchair, W5538, is a motor driven, indoor transportation vehicle, which a device for assisting action handicapped people and disabled people to move. It is suitable for disabled people with mobility difficulties and elderly people.

The device consists of front wheel, drive wheel, frame, controller, motor and drive devices, armrest, push-handle, backrest, seat cushion, footrest, battery box and charger.

The device is powered by a Li-ion Battery pack (24V 12Ah, 288Wh) with 15 Km (9.3 miles) range, which can be recharged by an off-board battery charger that can be plugged into an AC socket outlet (100-240V, 50/60Hz) when the device is not in use.

The user can activate the controller handle (joystick) to control the speed and direction of the wheelchair movement. In addition, when the patient releases the joystick, the joystick will return to the central position and the wheelchair will be automatically stopped soon due to automatic electromagnetic brake system. Once the joystick is activated again move to other position, the wheelchair will be re-energized.

Here's a breakdown of the acceptance criteria and study information for the Power Wheelchair (W5538), based on the provided text:

Important Note: This device is a power wheelchair, a physical product, not an AI/Software as a Medical Device (SaMD). Therefore, many of the requested categories (e.g., sample size for test set, number of experts, adjudication method, MRMC study, standalone performance, ground truth type for test/training set, training set sample size, how ground truth for training set was established) are not applicable to this type of medical device submission. The submission focuses on demonstrating substantial equivalence to a predicate device through adherence to recognized performance standards and comparative analysis of physical and technical specifications.

Acceptance Criteria and Reported Device Performance

Study Details

1. Sample size used for the test set and the data provenance:

   • This information is not directly applicable to a physical power wheelchair submission based on recognized standards. The "test set" here refers to the physical device itself being subjected to various ISO standard tests. The ISO standards specify test methodologies, but typically do not define a "sample size" in the context of clinical trials or data-driven AI systems.
   • The provenance is that the tests were conducted by the manufacturer (or a testing lab on their behalf) to demonstrate compliance with the specified ISO standards for the Power Wheelchair (W5538).

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Not applicable (N/A). This is a hardware device. "Ground truth" in this context would refer to the physical and functional parameters of the wheelchair, which are measured and compared against established engineering standards (ISO 7176 series). There are no "experts" establishing a diagnostic "ground truth" as there would be for an AI-driven diagnostic tool.

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

   • N/A. Adjudication methods like 2+1 or 3+1 are used for establishing ground truth in expert-labeled datasets, typically for AI/software evaluations. In hardware testing, the device's performance is measured against objective, quantifiable criteria defined by the ISO standards. There is no subjective interpretation requiring adjudication.

4. 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:

   • No. This is a power wheelchair, a physical mobility device. An MRMC study is designed for evaluating the impact of AI assistance on human diagnostic performance (e.g., radiologists reading images). It is not relevant to this device.

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

   • N/A. This is not an algorithm or AI system. It's a complete physical device (power wheelchair). However, the "standalone performance" could be viewed as the wheelchair's ability to perform safely and effectively on its own (e.g., maintaining stability, braking distance) when operated by a user, which is what the ISO standards verify.

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

   • International Standards and Engineering Specifications. The "ground truth" for this device's performance is established by widely recognized international standards for wheelchairs (ISO 7176 series) and general medical device standards (ISO 14971 for risk management, IEC 60601-1-2 for electromagnetic compatibility, ISO 10993 series for biocompatibility). These standards define acceptable performance ranges and test methodologies.

7. The sample size for the training set:

   • N/A. This refers to machine learning models. For a physical device, there is no "training set."

8. How the ground truth for the training set was established:

   • N/A. As there is no training set for a physical device, this question is not applicable.

Ask a specific question about this device

The mobility scooter 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.

This mobility scooter 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. The Mobility Scooter, Model N3473, has a base with magnesium alloy frame, two front wheels, two rear wheels, two anti-tip wheels, a seat, a tiller console, an electric motor, an electromagnetic brake, 1 rechargeable Lithium Battery with an off-board charger, a remote control switch. The movement of the scooter is controlled by the rider who operates the throttle lever, speed control dial and handle on the tiller console. The device is installed with an electromagnetic brake that will engage automatically when the scooter is not in use and the brake cannot be used manually. The Scooter only can be operated on the flat road.

The provided text is a 510(k) Summary for a Mobility Scooter (N3473), a medical device. It does not contain information about an AI/ML-driven medical device.

Therefore, I cannot provide information regarding:

• A table of acceptance criteria and reported device performance for an AI/ML device.
• Sample sizes, data provenance, number of experts, adjudication methods for training or test sets in the context of AI/ML.
• Multi-reader multi-case (MRMC) comparative effectiveness studies.
• Standalone algorithm performance.
• Type of ground truth used for AI/ML.
• How ground truth for training sets was established for AI/ML.

The document discusses the non-clinical testing performed for a physical device (mobility scooter) to demonstrate its substantial equivalence to a predicate device. This testing primarily involves adherence to ISO 7176 series standards related to wheelchairs and scooters, covering aspects like stability, brakes, speed, dimensions, strength, climatic tests, obstacle climbing, power/control systems, and electromagnetic compatibility.

Here's what can be extracted from the document regarding the mobility scooter's acceptance criteria and study:

1. Acceptance Criteria and Reported Device Performance (Non-AI Device)

The general acceptance criteria are that the subject device's performance meets the relevant ISO standards and exhibits no deleterious effect on safety and effectiveness compared to the predicate device, despite minor differences. The document asserts that "All test results meet the requirements" of the specified ISO standards for the subject device.

Here's a table based on the explicit comparisons provided, specifically focusing on measurable performance attributes mentioned in the "Comparison with the predicate device" section. While a direct "acceptance criterion" value isn't always given, the "Result" column implies acceptance if "Same" or if the difference is deemed non-deleterious after testing.

Ask a specific question about this device

It 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.

The Mobility Scooter, Model: W3431, has a base with Steal frame, two front wheels, a seat, a tiller console, electromagnetic brake, 2 rechargeable Lead-acid Batteries with an off-board charger. The movement of the scooter is controlled by the rider who operates the throttle lever, speed control dial and handle on the tiller console. The device is installed with an electromagnetic brake that will engage automatically when the scooter is not in use and the brake cannot be used manually. The Scooter only can be operated on the flat road.

The provided document is a 510(k) Premarket Notification for a Mobility Scooter (Model W3431). This document assesses the substantial equivalence of the new device to a predicate device, primarily through non-clinical testing and comparison to established industry standards. Critically, it does not contain information related to a study involving acceptance criteria for an AI/ML device as it pertains to human-in-the-loop performance, algorithmic standalone performance, or the use of expert consensus for ground truth. The device in question is a physical mobility scooter, not an AI/ML-based medical device.

Therefore, I cannot fulfill your request for information on acceptance criteria and study details for an AI/ML device based on the provided text. The document specifically states:

• "No clinical study is included in this submission." (Page 6, Section G)
• The non-clinical tests were conducted to verify that the proposed device met design specifications and was "Substantially Equivalent (SE) to the predicate device." (Page 6, Section F)

The tables presented (Tables 1, 2, and 3) are comparisons between the proposed mobility scooter and its predicate device across various physical and performance characteristics, adhering to ISO 7176 series standards for wheelchairs. These standards cover aspects like static stability, dynamic stability, effectiveness of brakes, energy consumption, dimensions, maximum speed, obstacle-climbing ability, biocompatibility, and electromagnetic compatibility.

To answer your prompt, I would need a document related to the submission or evaluation of an AI/ML medical device.

Ask a specific question about this device

The Power Wheelchair (N5909) is a motor driven, indoor transportation vehicle with the intended use to provide mobility to a disabled or elderly person limited to a seated position.

This Power wheelchair, N5909, is a motor driven, indoor transportation vehicle, which a device for assisting action handicapped people and disabled people to move. It is suitable for disabled people with mobility difficulties. The device consists of front wheel, drive wheel, frame, controller, motor, armrest, push-handle, backrest, seat cushion, footrest, battery box and charger.

The provided text describes the regulatory clearance of a Power Wheelchair (N5909) and establishes its substantial equivalence to a predicate device (K220747). The acceptance criteria are based on various performance standards and safety evaluations, with the study demonstrating compliance through non-clinical testing.

Here's the breakdown of the information requested:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are generally established by compliance with a comprehensive set of ISO and IEC standards for wheelchairs. The reported device performance is demonstrated by the successful completion of tests adhering to these standards, ensuring the subject device meets or exceeds the specifications of the predicate device for relevant attributes.

2. Sample size used for the test set and the data provenance

The document does not explicitly state the sample size for the test set used for the performance testing. The provenance of the data is non-clinical bench testing, conducted according to various international standards (ISO, IEC). The location of the testing is not specified, but the manufacturer is based in China. The testing is implicitly prospective in the sense that the new device was subjected to these tests to demonstrate compliance.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

This information is not applicable. The "ground truth" for a power wheelchair's performance is established by objective engineering measurements against defined international standards (ISO, IEC). It does not involve expert interpretation or clinical judgment in the same way an AI diagnostic device would require.

4. Adjudication method for the test set

This information is not applicable. Adjudication methods like 2+1 or 3+1 are typically used in clinical studies where expert consensus is needed to establish a "ground truth" for medical images or diagnoses. For a physical device like a power wheelchair, adherence to predefined measurement procedures and standards is the primary method of evaluation.

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

No MRMC comparative effectiveness study was done. This type of study is relevant for AI image analysis or diagnostic tools, not for the regulatory clearance of a physical medical device like a powered wheelchair.

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

This information is not applicable. "Standalone" performance refers to AI algorithms operating without human intervention for diagnostic or analytical tasks. The device in question is a physical power wheelchair; its "performance" is its mechanical and electrical function, not an algorithm's output. Software validation was performed, but it's not "algorithm only" performance in the context of an AI diagnostic.

7. The type of ground truth used

The ground truth used is primarily objective engineering measurements and adherence to international performance standards (ISO, IEC). For example, braking distance is measured directly, not subject to expert consensus. Biocompatibility is determined by standardized laboratory tests.

8. The sample size for the training set

The concept of a "training set" is not applicable here because this is not an AI/machine learning device that requires a training phase.

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

Not applicable, as there is no training set for this device.

Ask a specific question about this device

The Power Wheelchair, W5521, is a motor driven, indoor transportation vehicle with the intended use to provide mobility to a disabled or elderly person limited to a seated position.

This Power wheelchair, W5521, is a motor driven, indoor transportation vehicle, which a device for assisting action handicapped people and disabled people to move. It is suitable for disabled people with mobility difficulties and elderly people.

The device consists of front wheel, drive wheel, frame, controller, motor and drive devices, armrest, push-handle, backrest, seat cushion, footrest, battery box and charger.

The device is powered by a Li-ion Battery pack (24V 10Ah, 240Wh) with 10 Km (6.2 miles) range, which can be recharged by an off-board battery charger that can be plugged into an AC socket outlet (100-240V, 50/60Hz) when the device is not in use.

The user can activate the controller handle (joystick) to control the speed and direction of the wheelchair movement. In addition, when the patient releases the joystick will return back to the central position and the wheelchair will be automatically stopped soon due to automatic electromagnetic brake system. Once the joystick is activated again move to other position, the wheelchair will be re-energized.

The provided FDA 510(k) summary for the Power Wheelchair, W5521 (K231508) focuses on demonstrating "substantial equivalence" to a predicate device (Power Wheelchair, N5515B, K220747) through non-clinical testing. It does not involve AI/ML components or clinical effectiveness studies in the typical sense of a comparative effectiveness study with human readers for image-based diagnostics.

Therefore, many of the requested elements pertaining to AI/ML device performance (like acceptance criteria for accuracy, recall, F1-score, sample sizes for test/training sets, expert ground truth adjudication, MRMC studies, standalone performance, etc.) are not applicable to this specific device submission.

The "acceptance criteria" in this context refer to compliance with various ISO and IEC standards for wheelchairs, which are physical and electrical performance benchmarks, not AI model metrics.

Here's a breakdown of the information provided in relation to your questions, noting where information is not applicable:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are the successful compliance with the listed ISO and IEC standards. The "performance" is stated as meeting these standards.

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

• This device is a physical product (power wheelchair), not an AI/ML diagnostic software. The "tests" are performance and safety evaluations against engineering standards, typically involving a limited number of physical units, not a large data set in the usual sense. The document does not specify the number of units tested.
• Data Provenance: Not applicable in the context of clinical data sets (e.g., country of origin, retrospective/prospective). The tests are engineering bench tests.

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

• Not applicable. "Ground truth" in this context is defined by engineering standards (e.g., a specific static stability angle, braking distance, maximum speed). No human experts are establishing "ground truth" for a test set in the way a radiologist would for medical images. Compliance is measured instrumentally against predefined criteria in the standards.

4. Adjudication Method for the Test Set

• Not applicable. Since there are no human interpretations or "readings" to adjudicate, this concept does not apply.

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

• No. This is a power wheelchair, not a diagnostic device involving human readers or AI assistance in interpretation. Thus, MRMC studies and effect sizes related to human reader improvement with AI are not relevant.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

• Not applicable. There is no AI algorithm in the diagnostic sense that performs "standalone." The device itself is a standalone product. It has a control system with software, and the document states "Software validation" was performed, which refers to validating the functional correctness and safety of the embedded software controlling the wheelchair's operations as per ISO 7176-14:2008.

7. The Type of Ground Truth Used

• For physical performance and safety (e.g., stability, braking, speed, obstacle climbing, EMC): The "ground truth" is defined by the technical specifications and limits established in the various ISO and IEC performance standards (e.g., "Maximum safe operational incline degree: 6°", "Braking distance: ≤1 m").
• For material safety (biocompatibility): Ground truth is established by declaration of identical materials to a previously cleared predicate device, which had already demonstrated biocompatibility per ISO 10993 standards.

8. The Sample Size for the Training Set

• Not applicable. This device does not use an AI/ML model trained on a data set.

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

• Not applicable. As there is no AI/ML training set, this question is not relevant.

In summary, this 510(k) submission is for a conventional medical device (a power wheelchair) and relies on compliance with established international performance and safety standards, as well as substantial equivalence to a previously cleared predicate device. It does not involve the type of AI/ML performance evaluation studies that your questions are designed to address.

Ask a specific question about this device

The W5905 Power Wheelchair 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. This product is suitabled people with mobility difficulties and elderly people.

The subject Power Wheelchair is a wheeled personal mobility device that incorporates a seat-support system for a person with a disability or a person without the full capacity to walk designed to be propelled by power from electric motors. The electronic control of speed and direction can be performed by the occupant with the help of controlling joystick. The device can be quickly folded and disassembled, which makes it convenient to be stored or placed at the trunk of vehicles while traveling.

The subject Power Wheelchair is intended to provide mobility to a disabled or elderly limited to a seated position. It is of indoor and outdoor type, suitable for the use indoor and flat path near buildings, but not on grass, gravel roads, large slopes or motorway, neither on muddy, rugged, soft, narrow, icy road, bad roads such as dangerous roads without guardrails or waterways.

The subject Power Wheelchair consists of two parts, the wheelchair main body and the electrical part. The main body includes a main foldable frame, two armrests, a seat cushion, a safety belt, two rear driving wheels and two front wheels. The electrical part is composed of two motors, two brakes, a li-ion battery, a controller and an off-board charger.

The device is powered by a Li-ion battery (24V 12Ah) with 15 Km range, which can be recharged by an off-board battery charger that can be plugged into an AC socket outlet (100-240V, 50/60Hz) when the device is not in use.

The patient can activate the controller handle (joystick) to control the speed and direction of the wheelchair. The further the joystick is pushed from its central position, the faster the wheelchair moves, when it is released, it will automatically reset and brake.

The provided text describes the W5905 Power Wheelchair's equivalence to a predicate device (Y207 Electric Wheelchair) for FDA 510(k) clearance, not the detailed acceptance criteria and study proving its performance in a clinical or AI context. The document focuses on performance requirements according to international standards (ISO and IEC) for wheelchairs.

Here's a breakdown of the information requested, based on the provided text:

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

The document does not explicitly present "acceptance criteria" in a table format directly alongside "reported device performance" from a study. Instead, it refers to compliance with various ISO and IEC standards that define performance requirements for power wheelchairs. The "performance" described is the subject device meeting these standards.

Here's an attempt to extract relevant comparison points, which can be interpreted as the device meeting specific performance specifications relative to the predicate device and relevant standards:

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

The document describes non-clinical testing performed on the device itself to comply with various ISO and IEC standards. These tests are typically performed on a sample of the manufactured device. However, the exact "sample size" (e.g., number of units tested) for each specific test is not explicitly mentioned in the provided text.

Data provenance (country of origin, retrospective/prospective) is not applicable in the context of these engineering and performance standard tests. The tests are focused on the physical device's characteristics and its ability to meet documented engineering and safety standards.

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 question is not applicable. The product is a power wheelchair, and the evaluation is based on engineering and performance standards (e.g., braking distance, stability, battery life), not on human interpretation or diagnosis. Therefore, "ground truth" established by medical experts is not relevant to this type of device clearance. The "ground truth" is the objective measurement against the specified standard.

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

This question is not applicable. Adjudication methods like "2+1" or "3+1" are typically used in clinical studies where multiple human readers interpret data (e.g., medical images) and their disagreements need to be resolved. The evaluation here is based on objective, quantifiable engineering tests, not subjective interpretations.

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 device is a power wheelchair, not an AI-powered diagnostic or assistive technology that involves human readers interpreting cases or data.

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

This question is not applicable. This is not an algorithm or AI system. It's a physical medical device (a power wheelchair).

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

The "ground truth" for the non-clinical tests is defined by the objective, measurable criteria stipulated in the international standards (e.g., ISO 7176 series, IEC 60601-1-2) themselves. For instance, the ground truth for "braking distance" is the actual distance measured under specified conditions, compared against the maximum allowed distance by the standard. For "biocompatibility," the ground truth is whether the materials, when tested, meet the criteria for non-toxicity, non-irritation, and non-sensitization as defined by ISO 10993 standards.

8. The sample size for the training set

This question is not applicable. This is not an AI or machine learning device that requires a training set.

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

This question is not applicable. The device does not utilize a training set or AI.

Ask a specific question about this device

The Power Wheelchair (N5515B) 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.

This Power wheelchair is a motor driven, indoor and outdoor transportation vehicle, which a device for assisting action handicapped people and disabled people to move. It is suitable for disabled people with mobility difficulties and elderly people.

The device consists of front wheel, drive wheel, frame, controller, motor, armrest, backrest, seat cushion, pedal, battery box and charger.

The device is powered by Li-ion Battery pack (24V 12Ah) with 15 Km (9.32 miles) range, which can be recharged by an off-board battery charger that can be plugged into an AC socket outlet (100-240V, 50/60Hz) when the device is not in use.

The patient can activate the controller handle (joystick) to control the speed and direction of the wheelchair movement. In addition, when the patient releases the joystick, the joystick will return back to the central position and the wheelchair will be automatically stopped soon due to automatic electromagnetic brake system. Once the joystick is activated again move to other position, the wheelchair will be re-energized.

This document is a 510(k) Premarket Notification for the Zhejiang Innuovo Rehabilitation Devices Co., Ltd. Power Wheelchair (N5515B). The purpose of the submission is to demonstrate substantial equivalence to a legally marketed predicate device (K113463, Power wheelchair, PL00I by SUZHOU KD Medical Appliance Co. Ltd.).

Based on the provided text, the device in question is a power wheelchair, a device that does not typically use AI or require complex clinical studies for its clearance. Therefore, many of the requested criteria (like sample size for test sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone algorithm performance, and training set information) are not applicable or not provided in the context of a medical device like a power wheelchair. The clearance relies heavily on engineering performance standards and bench testing.

Here's the information that can be extracted from the provided text:

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

The document does not explicitly present specific numerical acceptance criteria for each test alongside the reported device performance. Instead, it states that the device "complied with the requirements" of various ISO and IEC standards. The comparison table (Section VI) highlights attributes where the subject device differs from the predicate but doesn't quantify "reported performance" against a specific, numerical acceptance criterion for each different attribute.

However, the "Braking distance," "Maximum safe operational incline degree," "Maximum speed forward," "Max backward Speed," "Max loading weight," "Maximum distance of travel," "Turning Radius," and "Maximum obstacle climbing" are performance metrics with specific values for both the subject and predicate devices.

Let's synthesize a table based on the explicit performance values and the implicit acceptance of compliance with standards:

Regarding the study that proves the device meets the acceptance criteria:

The study is implicitly a non-clinical performance testing (bench testing) conducted by the manufacturer, Zhejiang Innuovo Rehabilitation Devices Co., Ltd.

2. Sample size used for the test set and the data provenance:

• Sample Size: Not specified. For bench testing of physical products like wheelchairs against ISO standards, typically a representative number of units (often a small sample, e.g., 1-3 devices) are tested to demonstrate compliance and consistency in manufacturing processes. The document does not provide a specific number of devices tested.
• Data Provenance: The document states the tests were "provided to verify that the subject device met all design specifications." This indicates the testing was conducted by or for the manufacturer (Zhejiang Innuovo Rehabilitation Devices Co., Ltd.) to support their submission. The country of origin for the data is China, as the manufacturer is based there. The nature of the testing is prospective in the sense that the tests were performed specifically for this 510(k) submission to demonstrate compliance.

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 device is a power wheelchair, and its performance is evaluated against engineering standards (ISO, IEC) through bench testing, not against medical expert ground truth like in diagnostic imaging. The "ground truth" here is the established pass/fail criteria within the specified engineering standards.

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

Not applicable. This concept is relevant for studies involving human interpretation (e.g., radiologists assessing medical images) where discrepancies need to be resolved. For bench testing against engineering standards, the results are typically objectively measured and compared against predefined thresholds in the standards.

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 type of study is relevant for AI-powered diagnostic or assistive devices involving human readers (e.g., physicians interpreting images). The Power Wheelchair is a physical mobility device that 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:

Not applicable. The device is a physical power wheelchair, not an algorithm. While it has an electronic controller and software, the "performance" is the mechanical and electrical function of the wheelchair itself, not an isolated algorithm. The software validation mentioned is part of the overall device performance verification.

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

The "ground truth" used is defined by the international engineering and safety standards (ISO 7176 series, IEC 60601-1-2, ISO 10993 series). The device's performance is measured against the specifications and test methods outlined in these standards. For biocompatibility, the ground truth is established by the tests themselves according to the ISO 10993 series.

8. The sample size for the training set:

Not applicable. There is no AI algorithm being "trained" in the typical sense for this device. The software validation is likely for embedded control software, which is traditionally developed, tested, and verified against functional requirements, not "trained" on a dataset.

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

Not applicable, as there is no training set for an AI algorithm in this context. The "ground truth" for embedded software validation would be its functional requirement specifications.

Ask a specific question about this device

The Power Wheelchair 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.

This Power wheelchair is a motor driven, indoor and outdoor transportation vehicle, which a device for assisting action handicapped people and disabled people to move. It is suitable for disabled people with mobility difficulties and elderly people. The device consists of front wheel, drive wheel, frame, controller, motor, armrest, push-handle, backrest, seat cushion, pedal, battery box and charger. The device is powered by 2 Li-ion Battery pack (24V 10Ah, 240Wh) with 20 Km (12.5 miles) range, which can be recharged by an off-board battery charger that can be plugged into an AC socket outlet (100-240V, 50/60Hz) when the device is not in use. The patient can activate the controller handle (joystick) to control the speed and direction of the wheelchair movement. In addition, when the patient releases the joystick, the joystick will return back to the central position and the wheelchair will be automatically stopped soon due to automatic electromagnetic brake system. Once the joystick is activated again move to other position, the wheelchair will be re-energized.

The provided text describes the regulatory clearance for a Power Wheelchair, W5907, not an AI/ML powered medical device. Therefore, the information requested about acceptance criteria and studies related to AI/ML device performance (such as sample sizes for test and training sets, expert qualifications, adjudication methods, MRMC studies, standalone performance, and ground truth establishment) is not applicable or present in the document.

The document primarily focuses on demonstrating substantial equivalence to a predicate device (K113463) through non-clinical performance and biocompatibility testing, adhering to various ISO standards relevant to wheelchairs.

However, I can extract and present the performance criteria and reported performance based on the non-clinical testing described for the Power Wheelchair, W5907 as an analogy to acceptance criteria.

Acceptance Criteria and Reported Device Performance (Non-AI/ML Device)

Since this document describes a power wheelchair and not an AI/ML device, the typical acceptance criteria for AI/ML performance metrics (like sensitivity, specificity, AUC) are not applicable. Instead, the "acceptance criteria" here are defined by compliance with established international standards for wheelchairs. The reported device performance is implicitly that the device met these standards.

1. Table of Acceptance Criteria and the Reported Device Performance

2. Sample size used for the test set and the data provenance: Not applicable. The "test set" in this context refers to the physical device undergoing non-clinical bench testing according to international standards (e.g., ISO, IEC). The data provenance is from laboratory testing of the manufactured device.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable, as this is not an AI/ML device requiring expert ground truth for interpretation. Compliance with standards is typically assessed by qualified testing engineers/laboratories.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable, as no human interpretation or adjudication of AI/ML output is involved.

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 not an AI/ML device.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This is not an AI/ML device.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not applicable in the context of AI/ML. For this physical device, "ground truth" is defined by the objective pass/fail criteria specified within each referenced ISO and IEC standard.

8. The sample size for the training set: Not applicable. This is not an AI/ML device.

9. How the ground truth for the training set was established: Not applicable. This is not an AI/ML device.

Ask a specific question about this device