K Number
K033365
Date Cleared
2003-11-06

(16 days)

Product Code
Regulation Number
870.1025
Panel
CV
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The ApexPro FH Telemetry System is intended for use under the direct supervision of a licensed healthcare practitioner. The system is designed to acquire and monitor physiological data for ambulating patients within a defined coverage area. The system processes this physiological data to detect various ECG arrhythmia events and select physiological parameter limit violations.

The ApexPro FH Telemetry System is intended to be installed in the hospital or clinical environment in order to provide clinicians with patient physiological data, while allowing for patient mobility. These systems are typically deployed in sub acute care areas in hospitals or clinical sites where patient mobility can enhance the effectiveness of the medical procedures administered.

The physiological parameters monitored include ECG, non-invasive blood pressure, non-invasive temperature and SpO2. The ApexPro FH Telemetry System is intended to provide ECG data via Ethernet to the computer platform for processing. The ApexPro FH is also intended to provide physiologic data over the Unity network to clinical information systems for display.

Device Description

The ApexPro FH Telemetry System is composed of six major components:
Accessories to the patient worn acquisition transceivers
The patient worn data acquisition transceivers
The transceiver access points with antenna
The network infrastructure
A computer platform running the ApexPro Telemetry Application
A computer platform running a central station application (which may be the same computer platform running the ApexPro Telemetry Application)

AI/ML Overview

The provided text does not contain specific acceptance criteria or detailed study results that would traditionally be outlined for a medical device's performance evaluation against such criteria. The document is a 510(k) summary for the GE Medical Systems Information Technologies ApexPro FH Telemetry System, which focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed performance study with acceptance criteria.

However, based on the information provided, here's what can be extracted and inferred regarding the "study" that proves the device meets (implied or general) acceptance criteria:


1. Table of Acceptance Criteria and Reported Device Performance

Since explicit numerical acceptance criteria and a table detailing individual device performance metrics are not present, the "acceptance criteria" are implied by the claim of substantial equivalence and compliance with voluntary standards. The device "performance" is generally stated as being as safe and effective as the predicate.

Acceptance Criteria (Implied/General)Reported Device Performance
Compliance with Voluntary StandardsThe ApexPro FH complies with the voluntary standards as detailed in Section 9 of this submission (details of specific standards not provided in this extract).
Safety and Effectiveness Equivalent to Predicate Device"The results of these measurements demonstrated that the ApexPro FH System is as safe, as effective, and performs as well as the predicate devices." (Predicate: K032369 ApexPro Telemetry System).
Functional Technology Equivalence to Predicate Device"The ApexPro FH employs the same functional technology as the predicate devices."
Improved Performance and Integration via Advanced Technology"The system architecture has taken advantage of improvements in signal processing technology as well as advances in RF component technologies to improve performance and level of integration."
Quality Assurance Measures Applied During Development- Requirements specification review
  • Code inspections
  • Software and hardware testing
  • Safety testing
  • Environmental testing
  • Final validation |
    | Performance of ECG Arrhythmia Event Detection and Parameter Limit Violation Detection | The system processes physiological data "to detect various ECG arrhythmia events and select physiological parameter limit violations." (No specific performance metrics are provided for these detections in the extract.) |
    | Accurate Acquisition and Monitoring of Physiological Data | The system is "designed to acquire and monitor physiological data for ambulating patients within a defined coverage area." Physiological parameters monitored include ECG, non-invasive blood pressure, non-invasive temperature and SpO2. (No specific accuracy metrics are provided for these acquisitions in the extract.) |

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

The provided document does not specify a sample size for a test set for performance evaluation. The "Test Summary" lists various quality assurance measures (software testing, hardware testing, safety testing, environmental testing, final validation) but does not detail a specific clinical or performance test set with a defined sample size.

Data provenance is not mentioned. Given the nature of a 510(k) summary relying on substantial equivalence, the "study" appears to be an internal verification and validation process rather than a multi-site clinical trial. Therefore, information about country of origin or retrospective/prospective data collection is not available in the provided text.


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

This information is not provided in the document. The text refers to "Requirements specification review," "Code inspections," and various types of testing, but it does not describe a process for establishing ground truth for a test set using external experts. The "study" described is largely focused on engineering and quality assurance processes, not clinical evaluation with ground truth established by medical experts for algorithm performance.


4. Adjudication Method for the Test Set

This information is not provided. As there's no mention of a clinical test set with established ground truth by experts, an adjudication method (like 2+1 or 3+1) would not be relevant in the context described.


5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance

This information is not provided. The ApexPro FH Telemetry System is described as a monitoring system that processes data to detect events, but there is no indication that it is an "AI" device in the sense of a diagnostic aid that would be evaluated for human reader improvement in an MRMC study. It's a continuous physiological monitoring system.


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

The document describes the device as processing "physiological data to detect various ECG arrhythmia events and select physiological parameter limit violations." This implies standalone algorithmic detection. However, specific standalone performance metrics (e.g., sensitivity, specificity, accuracy, F1-score for arrhythmia detection) are not provided in this summary. The "Test Summary" mentions "Software and hardware testing" and "Final validation," which would likely include standalone performance aspects, but the results are summarized broadly as being "as safe, as effective, and performs as well as the predicate devices."


7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

The document does not specify the type of ground truth used for any performance evaluation. For a device detecting ECG arrhythmias, ground truth would typically be established by expert cardiologists reviewing ECG waveforms; however, this is not detailed in the provided text.


8. The Sample Size for the Training Set

This information is not provided. If the device indeed uses machine learning or adaptive algorithms, the training set size would be relevant. However, the description states the system "employs the same functional technology as the predicate devices" and "has taken advantage of improvements in signal processing technology." This suggests traditional signal processing and rule-based algorithms more than a data-driven machine learning approach that would necessitate a "training set" in the modern AI sense.


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

This information is not provided, as there is no mention of a training set or how ground truth for such a set would have been established.


§ 870.1025 Arrhythmia detector and alarm (including ST-segment measurement and alarm).

(a)
Identification. The arrhythmia detector and alarm device monitors an electrocardiogram and is designed to produce a visible or audible signal or alarm when atrial or ventricular arrhythmia, such as premature contraction or ventricular fibrillation, occurs.(b)
Classification. Class II (special controls). The guidance document entitled “Class II Special Controls Guidance Document: Arrhythmia Detector and Alarm” will serve as the special control. See § 870.1 for the availability of this guidance document.