K Number
K162012
Manufacturer
Date Cleared
2016-09-15

(56 days)

Product Code
Regulation Number
870.2450
Panel
CV
Reference & Predicate Devices
N/A
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The CARESCAPE Central Station is intended for use under the direct supervision of a licensed healthcare practitioner. The intended use is to provide clinicians with adult, pediatric and neonatal patient data within a hospital or clinical environment.

The CARESCAPE Central Station is intended to collect, display and print information from a network, including patient demographics, physiological parameters and waveforms, alarm annunciation and/or other non-medical information from monitors and telemetry systems. Physiological parameters and waveforms include electrocardiograph (ECG), pulse oximetry (SPO2), invasive blood pressures (IBP), non-invasive blood pressure (NIBP), respiration (RR), ventilator (VNT), carbon dioxide (CO2), oxygen (O2), mass spectrometry (Gas), temperature (Temp) and bispectral index (BIS). Beat to beat patient information for parameters and waveforms from the bedside and telemetry systems can be displayed. Patient monitor and telemetry system settings can be adjusted. Parameter values derived from patient data can be calculated, displayed, and printed.

The CARESCAPE Central Station supports the ability to access information from GE products and hospital intranet in a web browser format. Additionally, CARESCAPE Central Station supports the ability to access patient information collected from the CARESCAPE network and stored on a network server.

Device Description

The CARESCAPE Central Station (CSCS) is based on a PC technology platform and is user friendly for easy operation using a simple logical screen menu. The interactive controls include the use of a computer mouse, keyboard and touch screen. Optional writers for the purpose of graphing waveforms and printing patient information include a 2-inch Direct Digital Writer and/or a laser printer. Internal speakers provide alarm audio indication.
The CSCS provides centralized monitoring of patients connected to GE Medical Systems Information Technologies, Inc.'s monitors and telemetry transmitters. It may be configured to display up to four real-time waveforms per patient for up to 16 patients and up to 9 waveforms for a single selected patient. Waveforms include ECG, SPO2, respiration ventilation flow and pressure, invasive blood pressure and CO2.
The device acts as a (1) viewing station, (2) reviewing station and (3) live monitoring station by obtaining its information from acquisition devices off the CARESCAPE network.
Patients may be admitted to and discharged from monitors and telemetry devices from the central location. The central station is also the control and display device for telemetry monitoring.
The CSCS provides secondary annunciation of alarms from primary bedside monitoring devices and primary annunciation of alarms from wireless telemetry devices.
The display window for each patient shows waveforms and vital information including: patient name, bed number, arrhythmia and alarm visual indicators, system messages, audio pause indicator, audio alarm indicator, alarm message line, heart rate, PVC count, transmitter number, ECG lead label, pacemaker status, ST measurement, and graph status. Physiological parameter values and waveforms from the GE Medical Systems Information Technologies, Inc.s' monitors can be displayed and printed from the CSCS.
Non-real time patient information available for reviewing and printing includes: Graphic Trends, Tabular Numeric Vital SignsTrends, Event HistoryReview, Full Disclosure, Calipers, and ST Review. Data can be printed to a networked laser printer. In the case of Event Review, data can also be printed to a PDF file.
The CARESCAPE Central Station also provides remote control of patient monitor and telemetry device configuration settings that includes:

  • Admitted patient demographics like name and medical record number;
  • Alarm Settings like high/low limit values and alarm priority levels:
  • Printing settings like selection of which waveforms to print on graphs and the printed output destinations;
  • ECG settings like primary lead selection, ST analysis on/off and pace maker detection on/off;
    Initiate and terminate combination monitoring where a bedside patient monitor accepts ECG data from a telemetry transmitter:
  • Non-ECG parameter settings like respiration lead selection and NBP cuff size selection.
    The Full Disclosure option provides up to 144 hours of beat-tobeat patient information from the bedside or telemetry system for parameters and waveforms. Full Disclosure also stores resting ECGs from 16 patients once per minute for 144 hours and up to 2000 alarm histories with waveform snippets for each patient. This information can be displayed at the CSCS in detailed and summary mode formats.
AI/ML Overview

The provided document (K162012) describes the CARESCAPE Central Station v2, a medical device intended for collecting, displaying, and printing patient data. However, the document does not contain specific acceptance criteria, study data, or performance metrics for the device's functionality in a format that would allow the completion of the requested table and detailed study information.

This document is a 510(k) premarket notification letter from the FDA, confirming substantial equivalence based on a review of submitted information. It primarily focuses on the device's intended use, classification, and a high-level comparison to predicate devices, along with a summary of non-clinical testing. It explicitly states: "The subject of this premarket submission, CARESCAPE Central Station, did not require clinical studies to support substantial equivalence."

Therefore, I cannot provide the requested information. The document does not include data like precision, recall, or other performance metrics, nor does it detail how ground truth was established for a testing or training set, or mention any MRMC studies.

However, I can extract the information that is present in the document:


1. A table of acceptance criteria and the reported device performance

This information is not present in the document. The document lists general testing activities but no specific performance metrics or acceptance criteria in a quantitative format.

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

This information is not present in the document. The document mentions "Testing on unit level," "Integration testing," "Performance testing," "Safety testing," and "Simulated use testing," but does not provide details on sample sizes, data provenance, or the nature of the test sets used.

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)

This information is not present in the document. As no clinical studies were deemed necessary, there is no mention of expert-established ground truth for a test set.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

This information is not present in the document.

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

This information is not present in the document. The device description does not indicate the presence of AI, and no MRMC study is mentioned.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

This information is not present in the document. The device is described as a "central station," a viewing, reviewing, and live monitoring station with human-in-the-loop interaction.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

This information is not present in the document.

8. The sample size for the training set

This information is not present in the document. The device is a "software driven device running on a PC platform" and primarily serves to display and manage data from other medical devices; it is not described as involving machine learning or AI models developed through training sets.

9. How the ground truth for the training set was established

This information is not present in the document.


Summary of what can be found regarding testing:

The document states:

  • Non-Clinical Tests: "The CARESCAPE Central Station and its applications were tested to, and comply with, applicable voluntary standards. The CARESCAPE Central Station was tested to assure that the device meets its design specifications."
  • Quality Assurance Measures applied to development and testing:
    • Risk Analysis
    • Requirements Reviews
    • Design Reviews
    • Testing on unit level (Module verification)
    • Integration testing (System verification)
    • Performance testing (Verification)
    • Safety testing (Verification)
    • Simulated use testing (Validation)
  • Clinical Studies: "The subject of this premarket submission, CARESCAPE Central Station, did not require clinical studies to support substantial equivalence."

Based on the nature of the device (a central monitoring station for physiological data) and the fact that no clinical studies were required, the testing likely focused on functional verification, system integration, software validation, and adherence to safety and performance standards for displaying and managing data, rather than on diagnostic accuracy or AI-driven interpretations.

§ 870.2450 Medical cathode-ray tube display.

(a)
Identification. A medical cathode-ray tube display is a device designed primarily to display selected biological signals. This device often incorporates special display features unique to a specific biological signal.(b)
Classification. Class II (performance standards).