FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

a motorized cycle ergometer (RTI part number SA100047 for adults and SA100044 for children)
an FES controller / stimulator (RTI part number SA100090)
a stimulation cable which connects the controller / stimulator to cutaneous electrodes (RTI part number SA100091)
cutaneous electrodes (12 electrodes for 6 stimulation channels, RTI part number FA100015)
an interface to a remote database for the storage and retrieval of therapy settings and the storage of therapy session logs
an optional motorized arm crank (RTI part number PP102663)
an interface to a pulse oximeter for the display and recording of pulse and SpO2 levels and provision of alarming based on the data.

This system allows a person with impaired lower extremity movement to undertake cycle ergometry both actively (utilizing FES evoked lower extremity muscle contractions) and passively (utilizing power developed by the ergometer's motor).

AI/ML Overview

The provided text describes a 510(k) premarket notification for the RT300-S and RT300-SP Functional Electrical Stimulation (FES) cycle ergometers. The submission aims to demonstrate substantial equivalence to a predicate device (RT300-S, K060032). It outlines the device's technological characteristics, intended use, and the performance data gathered to support its safety and effectiveness.

However, it does not include information about acceptance criteria or a detailed study proving the device meets specific performance metrics in the way one might expect for a diagnostic or AI-driven medical device study.

The "performance data" section primarily focuses on demonstrating equivalence to the predicate device through technical reviews and system testing, rather than explicit acceptance criteria and corresponding performance metrics for new or enhanced features.

Here's an analysis based on the provided text, addressing the points where information is available and noting where it's absent:

Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria in the format of a table with specific thresholds for performance metrics (e.g., sensitivity, specificity, accuracy). Instead, the "acceptance" is framed around demonstrating substantial equivalence to the predicate device through technological similarities and confirming the proper functioning of new features.

The "Performance data" section describes the activities undertaken to support equivalence, which are implicitly aimed at "accepting" that the new device performs as intended and is as safe and effective as the predicate.

Acceptance Criteria (Implied)	Reported Device Performance
Equivalence of specified functionality to predicate device	User documentation for the predicate device was reviewed to ensure equivalent functionality is specified and implemented in the new device.
Confirmation of technical specifications for predicate device	510(k) submission for the predicate device was reviewed to confirm technical specifications.
Confirmation of technical specifications for new device	Output characteristic measurements of the new device were performed to confirm technical specifications for comparison tables.
Verification of performance to specification (system testing)	System testing was conducted to verify performance to specification.
Validation of pulse oximeter interface functionality	The RT300-S pulse oximeter interface was validated.
No new questions of safety and effectiveness from technological differences	Safety and effectiveness of using a motor to simulate a mechanical flywheel and provide passive cycling assistance: Demonstrated by ongoing clinical use of motorized ergometer without stimulation component in EU and USA. Safety and effectiveness of the controller: Demonstrated over the development period of the RT300-S. Remote database: Enhances safety and effectiveness by ensuring patients always commence therapy with latest, accurate device settings.

Study Details

Sample size used for the test set and the data provenance:
- Test Set Sample Size: For the pulse oximeter interface validation, the test set consisted of four able-bodied individuals.
- Data Provenance: Not explicitly stated, but given the US submission, it's likely US-based. It does not specify if it was retrospective or prospective, but testing on "able-bodied individuals" suggests a prospective, controlled evaluation for that specific component. Other testing mentioned ("Review of user documentation," "Review of 510(k) submission," "Output characteristic measurement," "Conduct of system testing") does not involve a "test set" in the typical sense of patient data.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
This information is not provided in the document. The document describes technical evaluations and a small-scale validation for a specific interface, not studies requiring expert-established ground truth for diagnostic accuracy.
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
This information is not provided. Adjudication methods are typically relevant for studies involving human interpretation or subjective assessment, which is not the primary focus of the described performance data.
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 or mentioned. This type of study is relevant for AI-driven diagnostic tools, which the RT300-S/SP is not. This device is a therapy delivery system.
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
The document describes device performance in terms of its ability to function according to specifications and equivalence to a predicate, which inherently assesses its standalone operation for its intended therapeutic function. However, it's not "standalone performance" in the context of a diagnostic algorithm's output. The "system testing" and "output characteristic measurement" would fall under this category as they refer to the device's inherent operation.
The type of ground truth used (expert concensus, pathology, outcomes data, etc):
For the technical tests, the "ground truth" was likely the technical specifications and expected outputs of the device based on its design and the predicate device's characteristics. For the pulse oximeter, the ground truth would be the actual physiological parameters (pulse and SpO2) of the able-bodied individuals, measured by a gold standard method if a reference was used. The document does not specify if a gold standard reference was employed for the pulse oximeter validation.
The sample size for the training set:
This information is not applicable/not provided. The RT300-S/SP is a hardware and software system for FES, not an AI or machine learning model that undergoes "training."
How the ground truth for the training set was established:
This information is not applicable/not provided as there is no mention of a training set for an AI/ML model.

Summary

Regulation Number and Section

§ 882.5810 External functional neuromuscular stimulator.

(a)
Identification. An external functional neuromuscular stimulator is an electrical stimulator that uses external electrodes for stimulating muscles in the leg and ankle of partially paralyzed patients (e.g., after stroke) to provide flexion of the foot and thus improve the patient's gait.(b)
Classification. Class II (performance standards).