(44 days)
The Escape Control Module is a non-contact, fully proportional, head movement commanded driving control intended to provide mobility to persons restricted to a seated position while operating a variety of powered wheelchairs.
Not Found
The provided text is a 510(k) summary for the "Escape Control Module" and its FDA clearance letter. It does not contain the kind of detailed information requested about acceptance criteria, study methodologies, or performance results that would typically be found in a clinical study report or a more comprehensive technical summary for an AI/CADx device.
This document describes a powered wheelchair control unit, a hardware device, not an AI or imaging diagnostic software. Therefore, many of the questions related to AI-specific testing (like MRMC studies, ground truth establishment for AI, data provenance for AI models) are not applicable.
Here's a breakdown of what can be extracted or inferred from the provided text, and what cannot:
1. A table of acceptance criteria and the reported device performance
- Cannot be provided. The document does not describe specific performance metrics or acceptance criteria for the device itself, beyond its intended function as a "non-contact, fully proportional, head movement commanded driving control intended to provide mobility to persons restricted to a seated position while operating a variety of powered wheelchairs." Performance data or acceptance criteria are not included in this type of summary.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Cannot be provided. This information is not present. The document focuses on regulatory clearance based on substantial equivalence to existing predicate devices, not on a clinical trial with a defined test set.
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 / Cannot be provided. This refers to expert consensus for labelling data, typically for training or evaluating AI models against a 'ground truth'. As this is a hardware device (a wheelchair control module), such an approach to ground truth establishment is not relevant for its regulatory submission as described here.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not applicable / Cannot be provided. Similar to point 3, adjudication methods are used in studies involving expert readers to resolve discrepancies in diagnoses or interpretations, particularly relevant for AI/imaging devices. This is not applicable to the "Escape Control Module."
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. An MRMC study is specifically designed for evaluating diagnostic devices, especially those involving human interpretation, and often to assess the impact of AI assistance. This type of study would not be performed for a power wheelchair control unit.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Not applicable. "Standalone" performance is typically for algorithms that provide a direct output without human intervention, again primarily relevant for AI/software devices. The "Escape Control Module" is a control interface between a user and a wheelchair, inherently involving human-in-the-loop operation.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)
- Not applicable. As a hardware medical device that provides control, the concept of "ground truth" as used in diagnostic AI is not relevant. Its performance would be evaluated based on functional testing (e.g., responsiveness, safety, durability, user control) rather than agreement with a diagnostic truth.
8. The sample size for the training set
- Not applicable / Cannot be provided. This refers to data used to train an AI model. The "Escape Control Module" is a hardware device, not an AI model, so there is no "training set."
9. How the ground truth for the training set was established
- Not applicable / Cannot be provided. As there is no AI model or training set, this question is not relevant.
Summary based on the provided text:
The provided document is a 510(k) summary for the "Escape Control Module," a power wheelchair control unit. It primarily establishes substantial equivalence to predicate devices (Dynamic Systems PHC-2 and PHC-3, Adaptive Switch Laboratories Inc.'s ASL Head Array, Invacare's Sip and Puff head array, and Invacare's Remote Joystick) rather than presenting detailed performance studies against specific acceptance criteria.
The 510(k) clearance process fundamentally relies on demonstrating that a new device is as safe and effective as a legally marketed predicate device, not necessarily on proving performance against a set of predefined acceptance criteria through extensive clinical trials as might be required for novel, high-risk devices or AI/CADx software. Therefore, the specific types of studies and data requested, which are common for AI/CADx devices, are not found in this regulatory document for a hardware device clearing via the substantial equivalence pathway.
§ 890.3860 Powered wheelchair.
(a)
Identification. A powered wheelchair is a battery-operated device with wheels that is intended for medical purposes to provide mobility to persons restricted to a sitting position.(b)
Classification. Class II (performance standards).