(111 days)
The device 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 MOBIE scooter consists of a foldable platform which connects the two front wheels and two rear wheels, an adjustable tiller, a Li-ion battery with an off-board charger, a motor/electromagnetic brake assembly, a electric motor controller and a seat /backrest set. It can be folded for transport in a car trunk. The patient uses the tiller handle/handlebar for steering and a thumb operated potentiometer throttle control lever located at the top of the tiller to engage and disengage the scooter motion in both the forward and reverse directions. When the throttle control lever is released, the electromagnetic brake will be actuated and the scooter is slow to stop.
The provided text is a 510(k) summary for the MOBIE scooter. It describes the device, its intended use, and its substantial equivalence to a predicate device. However, this document does not contain the specific information required to answer your request regarding acceptance criteria for an AI/device performance study.
The MOBIE scooter is a Class II medical device, specifically an electrical scooter for mobility. The "Summary of non-clinical testing" section indicates compliance with various ISO and ANSI/RESNA standards related to wheelchairs and motorized vehicles. These standards generally cover aspects like safety, durability, stability, electromagnetic compatibility, and biocompatibility, but they are not "acceptance criteria" for an AI performance study, nor do they detail a study where device performance is measured against such criteria.
Here's why the requested information cannot be extracted from this document and what each numbered item from your prompt means in the context of an AI device submission:
-
A table of acceptance criteria and the reported device performance: This document lists various ISO and ANSI/RESNA standards that the MOBIE scooter complied with. It does not provide specific numerical acceptance criteria (e.g., sensitivity, specificity, accuracy thresholds for an AI algorithm) nor does it report the device's performance against such metrics. The compliance statement simply says the device met the requirements of these standards, which are qualitative or quantitative tests for physical and electrical safety/performance, not AI algorithm performance.
-
Sample size used for the test set and the data provenance: There is no mention of a "test set" in the context of evaluating an AI algorithm. The testing described for the MOBIE scooter is hardware-focused, likely involving physical devices undergoing tests dictated by the listed standards.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts: This is entirely irrelevant for a physical mobility device like the MOBIE scooter. Ground truth established by experts is crucial for AI/ML medical devices where the AI is performing a diagnostic or prognostic task.
-
Adjudication method: Similar to point 3, this is for AI performance evaluation, not a physical product's safety and performance testing.
-
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: An MRMC study is designed to evaluate the impact of an AI algorithm on human reader performance for tasks involving interpretation (e.g., radiology images). This is not applicable to a mobility scooter.
-
If a standalone (i.e. algorithm only without human-in-the loop performance) was done: "Standalone" performance refers to an AI algorithm operating independently to produce an output. The MOBIE scooter does not contain an AI algorithm that would have standalone performance in a medical decision-making context.
-
The type of ground truth used: As mentioned, the concept of "ground truth" as it applies to AI algorithm validation (e.g., pathology, expert consensus) is not pertinent to the evaluation of a physical medical device like this scooter. The "ground truth" for the scooter's performance would be whether it physically meets the engineering and safety specifications of the relevant standards.
-
The sample size for the training set: This refers to the data used to train an AI algorithm. The MOBIE scooter does not describe any AI component requiring a training set.
-
How the ground truth for the training set was established: Again, this relates to AI algorithm development, which is not discussed in this document regarding the MOBIE scooter.
In summary, the provided 510(k) pertains to a physical medical device (an electrical scooter) and describes its compliance with established safety and performance standards for such devices. It does not contain any information related to the development or validation of an AI/ML medical device, which would involve acceptance criteria, test sets, ground truth, or expert evaluations as outlined in your prompt.
§ 890.3800 Motorized three-wheeled vehicle.
(a)
Identification. A motorized three-wheeled vehicle is a gasoline-fueled or battery-powered device intended for medical purposes that is used for outside transportation by disabled persons.(b)
Classification. Class II (performance standards).