Search Results

"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 product is a Mobility Scooter which provides transport for the disabled and the elderly and to be used both indoors and outdoors.

This scooter is a battery powered four wheeled vehicle. It consists two Lead-acid batteries (in the battery box) with an off-board battery charger, frame, a seat, a back support, control panel (including the key switch, throttle control lever, horn button, speed adjustment dial, and the battery condition meter), two foldable handles, two rear drive wheels with motor/ e-magnetic brake components, two front wheels, anti-tip devices, an external battery charger, a control panel and a motor controller. For convenience of transportation and reduction of possible damage, the battery and the seat unit can be dismantled and separately packaged.

The front wheels of the scooter are 8 inches and the rear wheels are 9 inches.
The motor of the scooter is 24VDC,150W,4200RPM; the Lead-acid Battery is 12 V, 22 Ah, 18.7 Ah; the charger is 24V/2A.
Max. loading cannot be over than 180kg.
The maximum distance travelled with a fully charged battery is 17.5km and the maximum forward speed is 1.6m/s(5.8km/h).
Braking time is less than 2 seconds, braking distance is ≤1.0 meters.

This document is an FDA 510(k) Clearance Letter for a Mobility Scooter (MS160C). It is not an AI/ML medical device, and therefore does not contain the information typically associated with studies proving the performance of an AI/ML algorithm.

The request asks for details like "sample size used for the test set," "number of experts used to establish ground truth," "adjudication method," "MRMC comparative effectiveness study," and "standalone performance," which are specific to the evaluation of AI/ML software. This information is irrelevant to a physical device like a mobility scooter.

Therefore, I cannot provide the requested information as it is not present in the provided document. The document focuses on demonstrating substantial equivalence to a predicate device through non-clinical performance and safety testing against established standards (ISO, IEC).

Here's why each point in your request cannot be answered based on the provided text:

1. A table of acceptance criteria and the reported device performance: While the document lists performance characteristics in "Table 2 - Performance Comparison", these are not presented as "acceptance criteria" in the sense of accuracy/sensitivity/specificity targets for an AI algorithm. Instead, they are comparisons to a predicate device and compliance with established ISO standards. I can extract performance characteristics, but not "acceptance criteria" for an AI model.
2. Sample sized used for the test set and the data provenance: Not applicable. This refers to data for an AI model. The mobility scooter underwent physical product testing.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth and expert review are for AI model validation.
4. Adjudication method: Not applicable. Adjudication is for resolving discrepancies in AI model output or expert readings.
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. MRMC studies are for evaluating AI's impact on human performance in diagnostic tasks.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done: Not applicable. This device is a physical product, not an algorithm.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc): Not applicable. "Ground truth" is a concept for AI model training and validation.
8. The sample size for the training set: Not applicable. This refers to data for an AI model.
9. How the ground truth for the training set was established: Not applicable. This refers to data for an AI model.

However, I can extract information related to the device's performance testing based on the provided document:

Study that proves the device meets requirements (Non-Clinical Testing):

The study was a series of non-clinical tests conducted to verify that the proposed device (Mobility Scooter MS160C) met all design specifications and was substantially equivalent (SE) to the predicate device (Mobility Scooter Model: W3468, K220207).

1. Table of Acceptance Criteria (as reported performance against standards, not AI-specific criteria) and the Reported Device Performance:

The document describes compliance with various ISO and IEC standards as the basis for demonstrating safety and effectiveness. The "acceptance criteria" are implied by adherence to these standards, and the "reported performance" is demonstrated by the test results confirming this compliance.

Key Performance Characteristics (from Table 2 - Performance Comparison):

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

• Sample Size: The document does not specify the number of units tested. For physical device performance testing against standards, it's common to test a representative number of units, but this specific number is not provided in the summary.
• Data Provenance: The tests are non-clinical, meaning they were conducted in a laboratory or controlled setting, presumably as part of the manufacturer's (Suzhou Master Machinery Manufacturing Co., Ltd., China) quality assurance and regulatory submission process. There is no mention of data from human subjects or specific geographical origin for "data provenance" in the sense of patient data.

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 a physical device, not an AI/ML algorithm requiring expert ground truth for diagnostic or similar tasks. The "ground truth" for the device's performance is established by objective measurements against international standards.

4. Adjudication method:

• Not applicable for a physical medical 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:

• No. This type of study is specific to AI/ML devices interacting with human interpreters.

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

• Not applicable. This is a physical mobility scooter, not an algorithm.

7. The type of ground truth used:

• The "ground truth" for the mobility scooter's performance is established by objective measurements and conformance to international performance, safety, and quality standards (e.g., ISO 7176 series, IEC 60601-1-2, ISO 10993 series). This is not an "expert consensus" or "pathology" in the AI/ML context.

8. The sample size for the training set:

• Not applicable. This device is not an AI/ML algorithm that requires a training set.

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

• Not applicable.

Ask a specific question about this device

The Mobility Scooter (Model: JT10) 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 JT10 is intended to be used by individuals that are able to walk but suffer from mobility limitations. It has a base with steel frame, two front wheels, two rear wheels, two anti-tip wheels, a seat, a tiller console, electric motor, 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 knob 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 FDA 510(k) clearance letter for the Mobility Scooter (JT10) does not contain information related to an AI/ML-driven device or diagnostic study. Instead, it discusses the substantial equivalence of a physical medical device (mobility scooter) to a predicate device, based on engineering aspects and performance standards.

Therefore, I cannot extract the requested information regarding acceptance criteria, study data, sample sizes, expert involvement, ground truth, or MRMC studies, as these concepts are specifically applicable to the evaluation of AI/ML or diagnostic devices. The document focuses on physical and functional comparisons and adherence to relevant ISO standards for wheelchairs and mobility aids.

Essentially, the device cleared here is a mobility scooter, not a software or AI-based diagnostic tool. As such, the performance evaluation relies on physical testing against established ISO standards for mobility devices, not on data analysis of images or other medical data.

Ask a specific question about this device

The intended / indications for use for the FreeStyle Libre 3 system are as follows:

• The FreeStyle Libre 3 Flash Glucose Monitoring System is a continuous glucose monitoring (CGM) device with real-time alarms capability indicated for the management of diabetes in persons aged 4 years and older.
• It is intended to replace blood glucose testing for diabetes treatment decisions unless otherwise indicated.
• The System performs a scan every minute to measure interstitial fluid glucose concentrations.

Google Wifi point and AC2200 router with Ethernet port and USB-C port

This document is an FDA 510(k) Clearance Letter for a Mobility Scooter, not an AI/Software as a Medical Device (SaMD). Therefore, the acceptance criteria and study proving device performance are based on physical and mechanical performance standards, safety, and substantial equivalence to a predicate device, not on artificial intelligence algorithms or human-in-the-loop performance.

The request asks for information typically associated with AI/SaMD submissions, such as:

• Table of acceptance criteria and reported device performance (in terms of AI metrics)
• Sample size for test set and provenance
• Number of experts for ground truth and their qualifications
• Adjudication method
• MRMC comparative effectiveness study results
• Standalone (algorithm only) performance
• Type of ground truth used
• Sample size and ground truth for training set

None of this information related to AI/SaMD studies is applicable or present in the provided 510(k) clearance letter for a mobility scooter.

Instead, the document details non-clinical testing against established international standards (ISO, IEC, EN) for wheelchairs and mobility scooters, and biocompatibility testing.

Here's a breakdown of the relevant acceptance criteria and performance proof from the provided document for the Mobility Scooter:

Acceptance Criteria and Device Performance for Mobility Scooter (K242975)

The acceptance criteria for this Class II Mobility Scooter are primarily based on demonstrating substantial equivalence to a legally marketed predicate device (K201196) and compliance with recognized international performance and safety standards for motorized wheelchairs and scooters. The study's proof of performance relies on non-clinical testing.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly met by demonstrating compliance with the listed ISO, IEC, and EN standards, and by showing comparable performance characteristics to the predicate device. The performance data is presented as reported values from the tests.

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

• Sample Size for Test Set: The document does not specify a numerical sample size (e.g., number of scooters) for the non-clinical tests. These types of tests are typically performed on a limited number of production units, as specified by the respective ISO standards.
• Data Provenance: The device manufacturer, Wuyi Aichi Industry & Trade Co., Ltd., is located in Wuyi, Zhejiang Province, China. The non-clinical testing would have been conducted by the manufacturer or a contracted test lab(s), likely in China, to demonstrate compliance with international standards for regulatory submission. The data is retrospective in the context of the 510(k) submission, meaning the tests were completed prior to the submission.

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

• Not applicable in the context of a mobility scooter's
  non-clinical performance testing. The "ground truth" is defined by the
  established parameters and limits within the specified international
  standards (e.g., ISO 7176 series). Performance is measured objectively
  against these defined criteria.

4. Adjudication Method for the Test Set

• Not applicable. Performance is measured objectively against
  international standards. There is no concept of "adjudication" as there
  would be for human-annotated data in an AI/SaMD context.

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

• No, this is not applicable. MRMC studies are used for evaluating the interaction between human readers (e.g., radiologists) and AI algorithms in diagnostic tasks. This submission is for a physical medical device (mobility scooter), not an AI/SaMD.

6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) Was Done

• No, this is not applicable. There is no "algorithm" in the sense of AI/SaMD for this device's regulatory pathway. The "standalone" performance is the scooter's physical and mechanical performance as measured by the non-clinical tests.

7. The Type of Ground Truth Used

• The "ground truth" is established by internationally recognized performance and safety standards (e.g., ISO 7176 series, IEC 60601-1-2, EN 12184) and biocompatibility standards (ISO 10993 series). These standards define the test methodologies, acceptance limits, and evaluation criteria for safe and effective operation of mobility devices.

8. The Sample Size for the Training Set

• Not applicable. This device is a physical medical device. There is no "training set" in the context of machine learning. The design and manufacturing processes are validated against quality system regulations (21 CFR Part 820), and performance is validated through non-clinical testing on a sample of the manufactured device.

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

• Not applicable. As there is no training set for a machine learning model, there is no ground truth established in that context. The "ground truth" for the device's design and manufacturing is adherence to engineering principles, regulatory requirements, and international consensus standards.

Ask a specific question about this device

The Powered Mobility scooteris intended for medical purposes to provide mobility to persons restricted to a sitting position.

Powered Mobility Scooter

I am sorry, but the provided text from the FDA letter (K250027) does not contain the information requested to describe the acceptance criteria and the study that proves the device meets the acceptance criteria.

The document is a clearance letter for a "Powered Mobility Scooter," a Class II medical device. It primarily covers:

• The FDA's determination of substantial equivalence to a predicate device.
• Regulatory requirements and general controls applicable to the device (e.g., Quality System Regulation, UDI Rule, adverse event reporting, labeling).
• Standard disclaimers regarding FDA's review and the manufacturer's responsibility for compliance.
• The "Indications for Use" for the device, stating it is "intended for medical purposes to provide mobility to persons restricted to a sitting position."

The letter does not include details about:

1. A table of acceptance criteria and reported device performance.
2. Sample sizes used for a test set or data provenance of a study.
3. Number of experts used to establish ground truth or their qualifications.
4. Adjudication methods.
5. Multi-Reader Multi-Case (MRMC) comparative effectiveness studies or effect sizes.
6. Standalone algorithm performance.
7. Type of ground truth used.
8. Sample size for training sets.
9. How ground truth for training data was established.

These details are typically found in the 510(k) submission itself (the "premarket notification"), which is a much more extensive document than the FDA's clearance letter. The clearance letter only announces the outcome of the FDA's review of that submission.

Therefore, I cannot fulfill your request based on the provided input.

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 subject device, Model MS160A scooter is mainly battery-powered and driven by a DC motor, with the speed adjusted by a user-controlled panel.

The motor is driven, and the speed is adjusted by a user-controlled panel and speed knob.

The scooter consists of two folding armrests, a seat cushion, a folding frame, two front wheels, two rear drive wheels with a motor/electromagnetic brake assembly, a rechargeable lithium-ion battery, an off-board battery charger, a control panel, and a motor controller.

The MS160A scooter is designed to provide mobility for people limited to those who walk unchanged or for the elderly.

Folding design: Pull out the seat and backrest fixing pins, push the backrest forward, the seat and backrest fold into each other, release the handlebar locking knob, push the handlebar backward, the handlebar folds down, the whole scooter is folded.

Control panel: Includes speed knob, battery gauge, power key switch, horn button, throttle control lever, headlight switch, charger port, fuse.

Wheel and frame connection method: the motor is connected to the differential, the differential is connected to the frame, the wheels are mounted on both ends of the differential, the motor rotates with the differential, thus driving the scooter.

Frame design:

1. The frame of MS160A is aluminum alloy.
2. The folding mechanism is operated in two ways:
   a. In the non-riding state, pull out the seat fixing pin, push the backrest forward, the seat and backrest can be folded.
   b. Loosen the handlebar locking knob, push the handlebar forward, the handlebar will fold down.

The front wheels of the scooter are 7 inches and the rear wheels are 10 inches.

The motor of the scooter is ST-62D24-120W; the lithium-ion battery is 25.55V 10.4AH; the charger is 24V/2A.

Max. loading cannot be over than 125kg.

The maximum distance travelled with a fully charged battery is 8.2km and the maximum forward speed is 1.8m/s.

Braking time is about 2 seconds, braking distance is ≤1.5 meters.

The provided document (K242982 510(k) Summary for the Mobility Scooter (MS160A)) is a premarket notification to the FDA for a Mobility Scooter. This type of device is a physical product and not typically associated with AI/ML software or studies involving ground truth establishment by experts, multi-reader multi-case (MRMC) comparative effectiveness studies, or standalone algorithm performance.

Therefore, this document does not contain the information requested regarding acceptance criteria and study proving device meets acceptance criteria related to AI/ML product performance. The studies mentioned primarily confirm the device's compliance with physical safety and performance standards (e.g., ISO 7176 series for wheelchairs, biocompatibility).

Here's why the requested information cannot be extracted from this document:

• Device Type: A mobility scooter is a mechanical device, not imaging or diagnostic software that would rely on AI/ML algorithms to generate results requiring expert consensus or ground truth establishment.
• Study Types: The "non-clinical testing" section details adherence to established ISO standards for physical characteristics like stability, braking, dimensions, and biocompatibility. There is explicitly "No clinical study implemented for the scooter."
• Acceptance Criteria: The "acceptance criteria" for this device are its ability to meet the performance specifications outlined in the ISO standards, and to be "substantially equivalent" to a predicate device based on physical and functional comparisons. These are not acceptance criteria for AI model performance metrics like sensitivity, specificity, or AUC, which would be relevant for devices that interpret data or images.
• Ground Truth, Experts, Sample Sizes (for AI/ML): These concepts are entirely absent because they are not applicable to the type of device being submitted.

In summary, the provided document is for a physical medical device (mobility scooter) and does not involve AI/ML components or related performance studies that would utilize the concepts of ground truth, expert review, or statistical metrics like sensitivity/specificity for algorithm output.

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.

Not Found

I apologize, but the provided text from the FDA 510(k) letter for the Mobility Scooter (S-01; S-02) does not contain any information regarding acceptance criteria, device performance studies, or details about artificial intelligence (AI) or machine learning (ML) components.

The letter is a standard FDA clearance document confirming substantial equivalence to predicate devices and outlines general regulatory requirements for medical devices. It focuses on:

• Device Name: Mobility Scooter (S-01); Mobility Scooter (S-02)
• Regulation Number/Name: 21 CFR 890.3800, Motorized Three-Wheeled Vehicle
• Regulatory Class: Class II
• Product Code: INI
• Indications for Use: Provides mobility to a disabled or elderly person limited to a seated position, for indoor and outdoor transportation.
• Regulatory Compliance: References to general controls, quality system regulations, adverse event reporting, UDI, etc.

Therefore, I cannot extract the specific information you requested regarding acceptance criteria, study details, sample sizes, expert qualifications, or AI performance metrics. This type of information would typically be found in the 510(k) summary or the full 510(k) submission document, neither of which is provided in your input.

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.

Not Found

The provided document is a 510(k) clearance letter from the FDA for a Mobility Scooter. It is a regulatory document and does not contain any information regarding acceptance criteria, device performance studies, sample sizes for test or training sets, ground truth establishment, or expert qualifications.

Therefore, I cannot provide the requested information based on the given input. This document is a clearance letter, confirming that the device is substantially equivalent to legally marketed predicate devices, not a study report detailing performance metrics.

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.

Not Found

The provided document is an FDA 510(k) clearance letter for a "Mobility Scooter". It is a regulatory document confirming substantial equivalence to a predicate device, which allows the manufacturer to market the product.

This type of document does not contain information regarding acceptance criteria or a study that proves the device meets specific performance criteria in the way a clinical trial or a detailed technical report would. It is not a performance study report.

Therefore, I cannot provide the requested information, such as:

1. A table of acceptance criteria and the reported device performance: This is not included in an FDA clearance letter.
2. Sample size used for the test set and the data provenance: Not applicable for this type of document.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable.
4. Adjudication method: Not applicable.
5. MRMC comparativeeffectiveness study: Not applicable.
6. Standalone performance: Not applicable.
7. Type of ground truth used: Not applicable.
8. Sample size for the training set: Not applicable.
9. How the ground truth for the training set was established: Not applicable.

The FDA clearance letter primarily focuses on:

• The device's trade name and regulatory classification.
• The determination of substantial equivalence to a legally marketed predicate device.
• The applicable regulatory requirements (e.g., general controls, quality system regulations, UDI rule).
• The stated Indications for Use: "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."

To get the kind of information you are asking for, one would typically need to review the 510(k) summary or the full 510(k) submission (if publicly available and containing such details), which would include details of the design verification and validation testing, risk analyses, and performance data submitted by the manufacturer to demonstrate substantial equivalence and safety/effectiveness. This clearance letter is the result of that review, not the review itself.

Ask a specific question about this device

The Powered Mobility Scooter is intended for medical purposes to provide mobility to persons restricted to a sitting position.

The Powered Mobility Scooter. Models: PMS101. GUT112, is a battery powered three wheeled scooter intended to provide mobility for elderly or disabled individuals in a variety of indoor and outdoor settings. It consists lithium battery with an off-board battery charger, Handle-bar, Brake, Seat, Back support, Frame, One Front wheel and Two Rear wheels. The scooter controlled through a thumb throttle. The left brake handle is controlled mechanical brake which lock the drum brake in the right rear wheel. When actuated brake handle, it will stop scooter and cut power supply to the motor .It has a driving range of 15.6 km between charges. It is capable of carrying a driver weighing up to 125 kg.

The Powered Mobility Scooter, Models: PMS103, GUT140, is a battery powered three wheeled scooter intended to provide mobility for elderly or disabled individuals in a variety of indoor and outdoor settings. It consists lithium battery with an off-board battery charger, Handle-bar, Brake, Seat, Back support, Frame, Armrest, One Front wheel and Two Rear wheels. The scooter controlled through a thumb throttle. The left brake handle is controlled mechanical brake which lock the drum brake in the right rear wheel. When actuated brake handle, it will stop scooter and cut power supply to the motor. It has a driving range of 10.4 km between charges. It is capable of carrying a driver weighing up to 125 kg.

The provided text is an FDA 510(k) summary for a Powered Mobility Scooter. It outlines the safety and performance testing conducted for the device to demonstrate its substantial equivalence to a predicate device. However, this document does not describe a study that uses AI or machine learning, involves diagnostic imaging, or establishes ground truth through expert consensus, pathology, or outcomes data in the way a medical AI device submission would.

Therefore, many of the requested criteria (e.g., sample size for test set, data provenance, number/qualifications of experts, adjudication method, MRMC study, standalone performance, training set details) are not applicable to this document as it pertains to a physical medical device (a mobility scooter) and traditional engineering and biocompatibility testing, not an AI/ML medical device.

Based on the provided text, here is the information that can be extracted, with explanations for why certain criteria cannot be met:

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

The acceptance criteria for this device are compliance with a comprehensive set of ISO standards related to wheelchairs and scooters, along with biocompatibility testing and EMC. The "reported device performance" is the demonstration that the subject device meets the requirements of these standards and is substantially equivalent to the predicate device. The tables provided in the document (Table 1, 2, and 3) show comparisons between the subject device and the predicate device across various parameters and confirm compliance with relevant ISO standards.

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

• Sample Size for Test Set: This document does not specify a "sample size" in terms of cases or subjects in the way an AI/ML study would. Instead, it refers to non-clinical laboratory testing performed on the physical device itself (the Powered Mobility Scooter models PMS101, GUT112, PMS103, GUT140). The testing involves subjecting units of the device to various mechanical, electrical, and biocompatibility tests according to the listed ISO standards. The "sample" is implicitly the physical device units tested to demonstrate compliance.
• Data Provenance: The testing was conducted by Intradin (Shanghai) Machinery Co., Ltd located in Shanghai, China. The data provenance is from non-clinical laboratory tests performed on manufactured units of the device, not from retrospective or prospective patient data.

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 or diagnostic imaging device. "Ground truth" in this context refers to engineering specifications and compliance with established international standards for mobility devices, which are validated through physical testing, not expert interpretation of medical images or data.

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

• Not Applicable. As above, this is not an AI/ML or diagnostic imaging device involving human reviewers or adjudication. Test results are objective measurements against defined engineering 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:

• No. This is not an AI-assisted device for human readers. No MRMC study was performed.

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

• Not Applicable. This is a physical mobility device, not a standalone algorithm.

7. The type of ground truth used:

• Engineering Standards and Specifications: The "ground truth" for this device's performance is adherence to defined parameters within the listed international ISO standards (e.g., ISO 7176 series for wheelchairs, ISO 10993 series for biocompatibility, IEC 60601-1-2 for EMC). Compliance is determined by whether the device's measured performance falls within the acceptable ranges or meets the criteria specified by these widely accepted engineering and safety standards.

8. The sample size for the training set:

• Not Applicable. There is no "training set" as this is a physical medical device, not an AI/ML algorithm.

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

• Not Applicable. No training set exists for this device.

Ask a specific question about this device