(24 days)
The EP-4 Cardiac Stimulator is indicated for use during clinical cardiac electrophysiology procedures. The EP-4 Cardiac Stimulator is intended to be used for diagnostic electrical stimulation of the heart for the purpose of refractory measurements, initiation and termination of tachyarrhythmias, and measurements of electrical conduction.
The EP-4 Cardiac Stimulator consists of a touch-screen computer, an AC-powered stimulation module, which provides electrical stimulation to the heart during electrophysiology case studies. The EP-4 consists of a touch-screen computer that controls a two- or four-channel AC-powered stimulation module, and a keyboard. The stimulator is capable of performing single channel, simultaneous, or sequential stimulation at programmed output settings using existing/predicate programmed protocols. The device is independent and self-contained, with the exception of marker outputs and an external sync input connector. It can be configured as a stand-alone system or in conjunction with the EP-WorkMate™ Recording System. It may also be used with other EP recording systems.
The provided document is a 510(k) premarket notification for the EP-4™ Cardiac Stimulator, which is an external programmable pacemaker pulse generator. The purpose of this submission is to demonstrate substantial equivalence to a predicate device, the EP-4™ Clinical Stimulator (K040207).
The document does not contain acceptance criteria in terms of numerical performance metrics (e.g., sensitivity, specificity, accuracy, or specific physiological parameters with defined thresholds) or a formal study designed to "prove" the device meets such criteria through a statistical analysis against a ground truth.
Instead, the submission focuses on demonstrating substantial equivalence to a predicate device. This is a regulatory pathway where a new device is shown to be as safe and effective as a legally marketed device that is not subject to premarket approval (PMA). The "study" described is primarily bench testing to confirm that design changes did not adversely affect safety or efficacy.
Here's a breakdown of the requested information based on the provided text, highlighting what is present and what is not:
-
A table of acceptance criteria and the reported device performance
The document does not provide a table of acceptance criteria with numerical performance metrics. The "acceptance criteria" in the context of this 510(k) submission are implicitly tied to demonstrating that the EP-4 Cardiac Stimulator is "substantially equivalent" to its predicate device (EP-4 Clinical Stimulator).
The reported "performance" is described qualitatively:
- "Bench testing was performed to confirm that the changes met design requirements and did not adversely affect the safety or efficacy of the product."
- "Where design differences exist between the proposed device and the predicate device, performance testing demonstrated that these differences do not adversely affect the device's safety and effectiveness."
- The device has the "same intended use and fundamental scientific technology" and "all technological characteristics... are substantially equivalent" to the predicate.
No specific numerical performance values (e.g., stimulation accuracy within a certain mV or ms, battery life, etc.) that would typically be associated with explicit acceptance criteria are provided in this regulatory summary.
-
Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
Not applicable. The document describes "bench testing," which refers to laboratory testing of the device itself, not a clinical study involving patients or a dataset of patient data. Therefore, there is no "test set" in the context of patient data, nor is there information on data provenance.
-
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. As this was bench testing for substantial equivalence, clinical ground truth establishment in the traditional sense (e.g., by medical experts for diagnostic accuracy) was not the focus. The "ground truth" for bench testing would be engineering specifications and predicate device performance, verified by engineers and quality control personnel. No information on specific expert qualifications for this type of verification is provided.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable, as there is no specific "test set" of patient data requiring clinical adjudication.
-
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. The EP-4 Cardiac Stimulator is a medical device for electrical stimulation, not an AI-assisted diagnostic tool. Therefore, an MRMC study and AI-related effectiveness are not relevant to this submission.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Not applicable. This device is a hardware system with embedded software for cardiac stimulation, not an algorithm being tested in isolation. The device's functionality is inherently "standalone" in operation once programmed, but this is distinct from testing an AI algorithm's performance without human interaction.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For bench testing, the "ground truth" would be established against the design requirements, engineering specifications, and performance characteristics of the predicate device. The goal was to confirm that the changes "met design requirements" and did not "adversely affect the safety or efficacy" when compared to the predicate. This is verified through a combination of standard engineering tests, electrical measurements, and functional checks.
-
The sample size for the training set
Not applicable. The device's software is menu-driven and firmware-based, controlling stimulation functions. It's not described as a machine learning system that requires a "training set" in the AI sense. The software's development followed "St. Jude Medical's Quality System requirements" and "design controls requirements documented in 21 CFR 820.30," which dictate rigorous testing and verification, but not "training data" in the AI context.
-
How the ground truth for the training set was established
Not applicable, as there is no "training set" for an AI algorithm.
§ 870.1750 External programmable pacemaker pulse generator.
(a)
Identification. An external programmable pacemaker pulse generators is a device that can be programmed to produce one or more pulses at preselected intervals; this device is used in electrophysiological studies.(b)
Classification. Class II (performance standards).