Search Results

The Empulse R90 is intended to be used to provide power assistance to manual wheelchair users. It is designed to augment the manual propulsion provided by the user, reducing the effort required by the user to propel the wheelchair.

The Empulse R90 is an auxiliary power module to provide augmented power to manual wheelchair users. The device utilizes a single electric drive wheel to provide the augmented power. The device mounts to a camber tube (rigid wheelchair) or a compressible axle (folding wheelchair) to provide the assisted power. On-board sensors, including an inclinometer, accelerometer and motor current sensing to determine when the user wishes to move forward and if the system is on an incline or decline. The removable Lithium lon battery pack is easily switched out to an alternate battery pack if additional range is required. The battery can also be removed if the user wishes to reduce the overall weight. The actuator is used to automatically engage and disengage the locking latch as well as compress the pre-load traction spring when the user wishes to disconnect the EMPULSE R90 from the wheelchair. In the extended position, the actuator allows the pre-load spring to provide sufficient pre-load to the drive wheel to ensure sufficient traction.

The provided text is a 510(k) Premarket Notification for a medical device called "Empulse R90", a power assist device for manual wheelchairs. It focuses on demonstrating substantial equivalence to predicate devices through technical comparisons and non-clinical testing.

The document does not contain any information about acceptance criteria or a study proving the device meets acceptance criteria related to an AI/ML-driven medical device, ground truth establishment, sample sizes for training/test sets, expert adjudication methods, or MRMC studies.

Therefore, I cannot fulfill your request for the specific information regarding AI/ML device acceptance criteria and study details. The document pertains to a physical medical device and its equivalent performance to existing physical predicate devices through non-clinical mechanical, electrical, and performance testing, rather than an AI/ML diagnostic or predictive tool.

Ask a specific question about this device

The Sunrise Medical Quickie® Q700-UP M power wheelchairs are battery operated devices, that are indicated for medical purposes to provide mobility and repositioning of the user, including a stand-up feature.

This submission covers the Q700-UP M which includes the following new components to the Sunrise Medical Quickie® Pulse 6SC:

• 1. Requires a knee block that was a previous option
• 2. Adds a stand-up actuator (PG Drives Technology) to power the stand-up feature
• 3. Requires a different version of the power center leg-rest to support the patient's weight when standing.
• 4. Adds a CSXM power seating control module (PG Drives Technology) to control the seating during standing
• 5. A caster / suspension lock-out system to stabilize the base when stand-up is actuated.

The Sunrise Medical Quickie® Q700-UP M power wheelchairs are battery operated devices, that are indicated for medical purposes to provide mobility and repositioning of the user, including a stand-up feature.

The Sunrise Medical Quickie® Q700-UP M power wheelchairs provide seating and standing function for patients who cannot stand on their own.

The document does not describe a study involving a medical device with "acceptance criteria" and "reported device performance" in the typical sense of diagnostic test performance (e.g., sensitivity, specificity, accuracy).

Instead, the document is a 510(k) summary for a medical device called the Quickie® Q700-UP M (a stand-up wheelchair). The "acceptance criteria" and "reported device performance" are presented as compliance with various recognized industry standards and a comparison of technical features to predicate devices to demonstrate substantial equivalence.

Here's the information extracted and formatted according to your request, with clarifications where the terms need to be adapted to the context of a wheelchair 510(k) submission:

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

In the context of this 510(k) submission for a stand-up wheelchair, "acceptance criteria" refers to compliance with recognized consensus standards (primarily ISO 7176 series and RESNA WC-1) and demonstrating substantial equivalence to predicate devices based on technical features. The "reported device performance" is the outcome of testing against these standards and the listed technical specifications.

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

• Sample Size for Test Set: The document does not specify a "sample size" in terms of many individual devices tested for each standard. Instead, it states that "All verification and validation testing conducted demonstrate that the Quickie® Q700-UP M is substantially equivalent..." This implies that at least one device (or a representative number of units) was tested to each listed standard. Standard compliance testing typically involves a small number of units (e.g., 1-3 units) unless otherwise specified by the standard or regulatory body.
• Data Provenance: The document does not explicitly state the country of origin of the test data or whether it was retrospective or prospective. However, given that Sunrise Medical (US) LLC is listed with a Fresno, California address, and the submission is to the U.S. FDA, it is implied that the testing was conducted to meet U.S. regulatory requirements. It is a premarket notification (510(k)), so the testing would have been conducted as part of the development and validation process before market entry, making it prospective testing in anticipation of regulatory submission.

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 section is Not Applicable to this submission. The "ground truth" for a medical device like a wheelchair is not established by expert consensus in the same way as an AI diagnostic tool. Instead, the "ground truth" or acceptable performance is defined by adherence to internationally recognized performance standards for wheelchairs (ISO, RESNA). The experts involved would be engineers and technical specialists performing the tests and verifying compliance with these standards, not clinicians establishing a "diagnosis."

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

This section is Not Applicable. Adjudication methods like 2+1 or 3+1 are used for resolving discrepancies in expert interpretations (e.g., in reading medical images for AI ground truth). For physical device testing against standards, the results are typically objectively measured and either pass or fail the specified 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 section is Not Applicable. This is a physical medical device (wheelchair), not an AI diagnostic tool involving human "readers" or AI assistance. No MRMC study would be relevant here.

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

This section is Not Applicable. This is a physical medical device, not an algorithm.

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

The "ground truth" for this device's performance is established by compliance with recognized international and national consensus standards (listed in Table 4) for wheelchair safety, performance, and functionality. These standards define the acceptable range of physical, mechanical, and electrical performance characteristics. The comparison to predicate devices also serves as a benchmark for demonstrating substantial equivalence based on established features of legally marketed devices.

8. The sample size for the training set

This section is Not Applicable. This is a physical medical device, not an AI model requiring a training set.

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

This section is Not Applicable. As it's not an AI model, there is no "training set" or corresponding ground truth to establish.

Ask a specific question about this device

Quickie® and Zippie® power wheelchairs are battery-operated devices with wheels that are intended for medical purposes to provide mobility to persons restricted to a sitting position. The Zippie power wheelchairs are specifically for people who are slightly smaller in stature—including children.

Quickie and Zippie wheelchairs are battery-powered, user-controlled, electric wheelchairs. All models of these wheelchairs will be offered with an optional wireless pointer control feature. This option entails adding a Bluetooth Mouse Module (BMM)—a small Bluetooth transmitter—mounted to the chair and wired into its control bus. With BMM in place, the wheelchair's controller can then use the pointer-control feature built into the BMM hardware and software. Pointer control can only be activated when the wheelchair is stationary and not actively performing wheelchair functions. The BMM lets users use the chair's joystick, or other input device, to control the pointer functions of Bluetooth-enabled devices (such as personal or tablet computers) while the chair is not in operation. The wireless pointer control feature will be offered on all models of the Quickie Pulse and Zippie ZM-310 series chairs. Technologically, all of these chair designs are identical. Model designations relate to widths and heights of their seats and various components: such as seating, wheels, and other options available. Quickie Pulse chairs are sized to fit medium to large size individuals Zippie ZM-310 chairs fit individuals of smaller stature—including children. These chairs, along with the BMM, are meant for use in healthcare facilities, in the home, outdoors, and other places of individual activity for the disabled.

The provided text is a 510(k) summary for the Quickie Pulse and Zippie ZM-310 power wheelchairs with an optional wireless pointer control feature (Bluetooth Mouse Module - BMM). It describes the device, its intended use, technological characteristics, and performance data to demonstrate substantial equivalence to a predicate device.

Regarding your request for "acceptance criteria and the study that proves the device meets the acceptance criteria," it's important to note that this document is for a medical device (powered wheelchair) and not an AI/ML-driven diagnostic tool. Therefore, the questions related to AI/ML performance metrics (e.g., sample size for test set, number of experts, adjudication methods, MRMC studies, standalone performance, ground truth for training set) are not applicable in this context.

The "acceptance criteria" for this device are implicitly tied to safety and functional performance, particularly regarding the added Bluetooth Mouse Module (BMM) and its impact on the wheelchair's operation and electromagnetic compatibility. The "study" that proves the device meets these criteria is the non-clinical performance testing.

Here's a breakdown of the relevant information from the document, tailored as much as possible to your request, while acknowledging that it's not an AI/ML device:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: The document does not specify a numerical sample size for the test set. The performance data section describes types of tests conducted on the device itself (e.g., "chair's electrical braking," "BMM operation," "EMC testing"). This implies testing was done on the physical device, likely prototypes or production samples, rather than a "data set" in the AI/ML sense.
• Data Provenance: Not explicitly stated, but standard practice for medical device testing like this would be in a controlled laboratory or testing facility within the manufacturer's operational region. It is not "retrospective or prospective" data in the clinical study sense; it's non-clinical engineering and functional testing.

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

• Not Applicable. This is not an AI/ML diagnostic device requiring expert interpretation for ground truth. The "ground truth" here is the physical reality of the device's function (e.g., brakes holding, wireless signal working without interference). This is typically established by engineers, technicians, and potentially regulatory compliance specialists following established test protocols.

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

• Not Applicable. Adjudication methods like 2+1 or 3+1 are used in clinical studies, particularly for interpreting medical images or diagnoses where inter-reader variability exists. This document describes non-clinical performance and safety testing.

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. An MRMC study is relevant for comparing diagnostic performance, often with AI assistance in clinical settings. This device is a powered wheelchair with an added Bluetooth feature; it is not a diagnostic tool requiring human reader performance evaluation.

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

• Not Applicable. This refers to AI/ML algorithm performance. The "BMM" has software, but its "performance" is evaluated as part of the overall wheelchair system's function and electromagnetic compatibility, not as a standalone diagnostic algorithm.

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

• The "ground truth" for this device is based on engineering standards and physical measurements of performance. For example:
  • Brake holding capability is verified against a specific angle/load (engineering spec).
  • EMC is verified against international standards (e.g., ANSI/RESNA WC2, extended frequency ranges) using proper measurement equipment.
  • Wireless pointer function is verified by observing its actual function with compatible external devices.

8. The sample size for the training set

• Not Applicable. This device does not use machine learning, so there is no concept of a "training set."

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

• Not Applicable. As there is no training set for machine learning, this question is not relevant.

In summary, the provided document describes a medical device in the context of a 510(k) submission, confirming its substantial equivalence to a predicate device. The "acceptance criteria" and "studies" are focused on engineering performance, safety, and electromagnetic compatibility for the physical device system, not on AI/ML diagnostic performance metrics.

Ask a specific question about this device

Quickie® and Zippie® power wheelchairs are battery-operated devices with wheels that are intended for medical purposes to provide mobility to persons restricted to a sitting position. The Zippie® power wheelchairs are specifically for people who are slightly smaller in stature-including children.

The Quickie® and Zippie® power wheelchairs are designed for indoor use at care facilities and private residences. The pediatric variant of the Quickie® Pulse 6, branded the Zippie® ZM-310, is intended to provide a slightly broader range of seating size options for people that are smaller in stature-including children. It varies from the Quickie® Pulse 6 only in having smaller seat options.

The Quickie® and Zippie® power wheelchairs are center-wheel-drive battery-powered wheelchairs which will perform optimally on firm even surfaces such as concrete, asphalt and indoor flooring.

The wheelchairs have steel and aluminum frame structure which is welded and utilizes standard foams and covers for the seat.

The braking system can be initiated by either automatic or electric means. The brakes are automatically on except when the wheelchair is turned on and the joystick has been moved away from the neutral position. When the joystick is released or moved back to neutral, the brakes engage again. If the electrical brake system fails, the brakes will default to the closed, or "brakes on" position, thereby stopping the wheelchair.

Actuators allow the seating to be adjusted to suit the user and activity.

A control system (i.e. controller and joystick) controls motor, brakes, drive wheel and batteries. This product is appropriate for use by any individual who has the ability to drive a power wheelchair without having to utilize the services of an attendant. In addition, the controls give the optional capability for attendant control. The optional drive controller R-net system provides further features. The controller is fully programmable.

This document is a 510(k) premarket notification from the FDA, approving a new powered wheelchair model as substantially equivalent to existing predicate devices. It does not contain information about acceptance criteria or a study proving that the device meets those criteria in the way typically seen for AI/ML medical devices. The performance data provided is for traditional medical device testing, not for AI algorithm performance.

Here's why the requested information cannot be fully provided based on the input:

• This is not an AI/ML device: The document describes powered wheelchairs, which are mechanical and electrical devices. There is no mention of any AI or machine learning components within these wheelchairs.
• The "study" referenced is standard medical device testing: The document describes performance data related to biocompatibility, electrical safety, EMC, software verification/validation, and mechanical testing, which are standard for non-AI medical devices. These are not "studies" in the context of proving AI algorithm performance.
• "Acceptance criteria" are for device functionality, not AI metrics: The document implies that the "acceptance criteria" are the successful completion of the described tests and adherence to relevant ANSI/RESNA Wheelchair standards, ensuring the device functions safely and effectively as a powered wheelchair. It does not relate to diagnostic performance metrics like sensitivity, specificity, or AUC, which would be relevant for an AI device.

Therefore, many of the specific fields requested about AI device performance (e.g., sample size for test/training sets, experts for ground truth, MRMC study, standalone performance, type of ground truth for AI) are not applicable to the information contained in this FDA submission for a powered wheelchair.

However, I can extract the relevant information pertaining to the device's acceptance criteria and the tests performed to demonstrate its safety and effectiveness, interpreting them within the context of a non-AI medical device submission.

Acceptance Criteria and Device Performance (Interpreted for a Non-AI Device)

1. Table of Acceptance Criteria and the Reported Device Performance:

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

• Sample Size: Not explicitly stated as a "test set" in the context of an AI algorithm. The testing described (biocompatibility, electrical safety/EMC, mechanical) would typically involve a small number of physical samples of the manufactured device.
• Data Provenance: Not applicable in the context of AI data. The "data" here refers to the results of engineering and material tests performed on the physical wheelchairs, not patient data.

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 pertains to the physical and functional safety of a powered wheelchair, not a diagnostic AI algorithm requiring expert-established ground truth from images or other clinical data.

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

• Not applicable. This term relates to expert review for AI ground truth. For the physical device testing, adherence to standards and test protocols by qualified engineers and technicians would be the "adjudication" mechanism.

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, not applicable. This type of study is specifically for AI diagnostic/interpretive devices where human readers (e.g., radiologists) might use AI assistance. This document is about a powered wheelchair.

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

• No, not applicable. There is no standalone algorithm being evaluated as part of this device submission. The "software" mentioned controls the wheelchair's drive units, embedded in the device itself, and its functionality is assessed as part of the overall device's electrical and mechanical tests.

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

• Not applicable in the AI sense. The "ground truth" for this device would be objective measurements and criteria defined by engineering standards (e.g., ANSI/RESNA Wheelchair standards for braking effectiveness, battery life, structural integrity, electrical safety parameters).

8. The sample size for the training set:

• Not applicable. There is no AI model that requires a training set for this device.

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

• Not applicable. There is no AI model that requires a training set for this device.

Ask a specific question about this device

Breezy Elegance Folding Manual Wheelchairs are manually operated devices with wheels that are intended for medical purposes to provide mobility to persons restricted to a sitting position.

The product offering consists of a standard folding aluminum wheelchair. (Standard in the sense that it is not built to a specific order, rather it will be built to inventory.)
The wheelchairs are

• User-propelled, as such, chair has 24" wheels with attached handrims
• Foldable (using a cross-brace design) for easier transport and stowage
  The device comprises
• Cross-braced folding frame
• Quick-release Axle
• Large rear wheels with handrims for self-propulsion
• Smaller front wheels on casters for stability
• Padded seat sling material designed to support a seat cushion and to fold when the wheelchair frame is folded
• An upholstered backrest designed to fold when the wheelchair frame is folded, pre-set angle to 8
• Push handles at top of backrest to allow attendant to aid mobility of rider
• Swing-away armrests and swing-in/swing-out legrests (with footplates)
  Available Options
  Elevating legrest
  Anti-tip Tubes

The provided text describes the 510(k) summary for the Breezy Elegance Manual Folding Wheelchair, which is a Class I medical device. For such devices, the primary "acceptance criteria" are typically demonstrating substantial equivalence to a predicate device and adherence to general controls and recognized standards, rather than specific performance metrics like sensitivity or specificity that are common for AI/diagnostic devices. The study that proves the device meets these criteria is the submission itself, which outlines how the Breezy Elegance wheelchair is substantially equivalent to the Quickie Q2 Lite.

Here's the information broken down based on your request, keeping in mind the nature of this device:

Acceptance Criteria and Device Performance for Breezy Elegance Folding Manual Wheelchair

1. Table of Acceptance Criteria and Reported Device Performance

Given that this is a Class I mechanical device (manual wheelchair), the "acceptance criteria" revolve around demonstrating substantial equivalence to a legally marketed predicate device and compliance with general safety and performance expectations for such devices. Specific quantitative performance metrics (like sensitivity, specificity, or F1-score) common for AI/diagnostic devices are not applicable.

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

For this type of mechanical device, the "test set" refers to the physical units of the device that underwent design verification and validation. The document states:

• Sample Size for Test Set: Not explicitly specified as a number of units. The testing involved "testing/demonstration" for design verification and "Third-party evaluation" for design validation. This typically implies testing a representative sample or prototypes to ensure manufacturing and performance consistency. Specific numerical sample sizes are not provided in this summary.
• Data Provenance: The testing and evaluation for design verification and validation were conducted by Sunrise Medical (US) LLC (the manufacturer) and a "third-party." The country of origin for this testing data is not explicitly stated, but given the manufacturer's location (Fresno, CA, USA) and the FDA submission, it is assumed to be primarily U.S.-based. The nature of the testing is prospective in that it refers to tests conducted on the proposed device design.

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

For a mechanical wheelchair, "ground truth" is established through engineering and biomechanical testing against recognized standards and functional requirements, as well as human factors and usability evaluations.

• Number of Experts: Not explicitly stated. The document refers to "third-party evaluation" for design validation, which would involve qualified engineers, user groups, and human factors specialists.
• Qualifications of Experts: Not explicitly detailed. These experts would typically include biomedical engineers, mechanical engineers, and potentially physical therapists or other healthcare professionals familiar with wheelchair functionality and user needs for the "human factors and usability" assessment.

4. Adjudication Method for the Test Set

The concept of "adjudication method" (e.g., 2+1, 3+1) is typically used in clinical studies or diagnostic imaging assessments where multiple human readers interpret data, and discrepancies need to be resolved. This is not applicable to the engineering design verification and validation of a mechanical wheelchair. For this device, acceptance is based on meeting pre-defined engineering specifications, performance against recognized standards, and successful completion of human factors evaluations.

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

No, an MRMC comparative effectiveness study was not done. This type of study is relevant for evaluating diagnostic accuracy with human readers, often involving AI assistance. It is not applicable to the regulatory submission for a mechanical wheelchair.

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

No, a standalone (algorithm only) performance evaluation was not done. This concept is specific to AI/software devices. The Breezy Elegance is a purely mechanical device.

7. The Type of Ground Truth Used

The "ground truth" for evaluating the Breezy Elegance wheelchair primarily involved:

• Engineering Specifications and Recognized Standards: The device was tested against design specifications and relevant wheelchair standards (e.g., ISO, ANSI/RESNA standards, though not explicitly listed by name in this summary). The predicate device's performance also serves as a benchmark for equivalence.
• Functional Performance Data: Data from bench tests and evaluations confirming the wheelchair's mechanical integrity, durability, and functional operation (e.g., folding mechanism, wheel performance, brake effectiveness, weight capacity).
• Usability and Human Factors Data: Outcomes from third-party evaluations confirming the device's fitness for intended use from a user's perspective.

There is no "pathology" or "outcomes data" in the clinical trial sense for this type of device submission.

8. The Sample Size for the Training Set

This question is not applicable. The Breezy Elegance is a mechanical device, not an AI or software algorithm that requires a "training set."

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

This question is not applicable, as there is no "training set" for this mechanical device.

Ask a specific question about this device