Search Results
Found 1 results
510(k) Data Aggregation
(49 days)
The Vision V x C series 4300 central station monitoring system is intended to be used to provide, using a wireless LAN for communication, centralized surveillance and documentation of patient vital sign data and arrhythmia/ST monitoring for a variable number of Escort Bedside Monitors and a variable number of UHF telemetry transmitters in the hospital environment. It is intended for use by healthcare practitioners trained in the use of the equipment only.
The ST algorithm has been tested for accuracy of the ST segment measurement data. The significance of the ST segment changes must be determined by a physician.
The Vision VxC Central Station is designed specifically to provide centralized display for up to 16 patients, storage and recording (or printing) of patient vital sign and waveform data that are being monitored at the bedside by Invivo monitors and telemetry devices.
The Vision VxC Central Station can provide alarm detection and reporting for all vital sign parameters available to the central station for patient alarm surveillance. This alarm surveillance includes alarms reported by the bedside monitors and repeated to the central station as well as primary alarm surveillance for the patient worn WMTS telemetry transmitter device where there is no alarm notification capability on the transmitter worn by the patient.
Arrhythmia monitoring and ST segment detection capability is available as an option. The arrhythmia feature is equipped with password protection to prevent unauthorized users from turning off arrhythmia when a patient is being monitored. When a patient is monitored by arrhythmia the system will provide continuous monitoring of lifethreatening alarms.
Here's a breakdown of the acceptance criteria and study information for the Vision VxC Central Station, based on the provided 510(k) summary:
1. Table of Acceptance Criteria and Reported Device Performance
Parameter | Acceptance Criteria (Requirement) | Reported Device Performance (Results) |
---|---|---|
Central Station | ||
Display Type | Flatpanel 19" LCD | Pass |
Central Processor | Intel Pentium | Pass |
User Interface | Touchscreen and/or mouse | Pass |
Operating System | Microsoft Windows XP Embedded | Pass |
Number of Patients Monitored | 1 to 16 (up to 16 designated for telemetry) | Pass |
Parameters Monitored | ECG, Resp, IBP (SYS, DIA, MEAN), NIBP (SYS, DIAS, MEAN), SpO2, ETCO2, Temp | Pass |
Max Parameters Monitored | 20 | Pass |
Trending | Tabular for 16 patients, all parameters; up to 72 hours at 1, 2, 3, 4, 5, 15, 30, 60, 120, and 180 min. intervals | Pass |
Alarm History Storage | 1000 events within 72 hours per patient; 20 sec per event | Pass |
Documentation | Thermal array recorder and/or laser printer | Pass |
AC Main | 90-130/180-260 VAC, 47-63 Hz selectable, 6 amps@115V | Pass |
Power Supply | 235 W | Pass |
Operating Temperature | 10 to 40° C | Pass |
Storage Temperature | -40 to 75° C | Pass |
Relative Humidity | 5 to 95 % | Pass |
Standards | UL 60950 | Pass |
Telemetry Receiver Platform | ||
Alarm History Storage | 1000 events within 72 hours per patient; 20 sec per event | Pass |
Documentation | Thermal array recorder and/or laser printer | Pass |
AC Main | 115/230 VAC, 60/50 Hz selectable, 4 amps@115V | Pass |
Power Supply | 235 W | Pass |
Input Voltage | 100-120 VAC / 200 - 240 VAC, selectable, 50/60 Hz | Pass |
Input Current | 6 Amp max @ 115V (20A Max inrush cold start), 3 Amp max @ 230 V (10A Max inrush cold start) | Pass |
Telemetry Band | FCC WMTS (608-614 MHz) | Pass |
Operating Temperature | 10 to 40° C | Pass |
Relative Humidity | 10 to 90 % | Pass |
Standards | UL 60950, FCC Part 15 (Spread Spectrum) | Pass |
Arrhythmia Analysis Option | ||
Number of Arrhythmia Channels | 1 to 16 (dual vector) | Pass |
Types of Detected Events | Asystole, VFIB, VTACH, Couplet, High and Low Heart Rate, High Abnormal Count, Bigeminy, Trigeminy, V.RUN, V.Rhythm, Multi-Focal, R-ON-T, Pause | Pass |
Type of Algorithm | Heuristic algorithm using template matching and feature extraction | Pass |
QRS Detection Sensitivity | AHA ≈99.88%, MIT ≈99.93% | Pass |
QRS Detection Positive Predictivity | AHA ≈99.89%, MIT ≈99.85% | Pass |
PVC Detection Sensitivity | AHA ≈94.07%, MIT ≈95.44% | Pass |
PVC Detection Positive Predictivity | AHA ≈97.72%, MIT ≈96.60% | Pass |
PVC Detection False Positive Rate | AHA ≈0.22%, MIT ≈0.23% | Pass |
Alarm Displays | arrhythmia alarm must display | Pass |
Alarm Tones | arrhythmia alarm must sound | Pass |
Alarm Recordings | arrhythmia alarm must generate an alarm recording if configured | Pass |
Alarm Event History | arrhythmia alarm must generate event history record | Pass |
Maximum Patient Load | 16 patient | Pass |
Standard | AAMI/ANSI EC 57: 1998 | Compliant |
ST Analysis Option | ||
Number of ST Channels | 1 to 16, but no more than arrhythmia channels | Pass |
Alarms | high and low for both vectors; can be recorded and/or stored as events | Pass |
Standard | AAMI/ANSI EC 57: 1998 | Compliant |
2. Sample Size Used for the Test Set and Data Provenance
The document states, "This device was validated using patient simulators under simulated use conditions." This indicates that the test set did not consist of real patient data. The provenance for this simulated data is not specified (e.g., country of origin). The testing would be prospective in the sense that the device was evaluated against controlled simulated conditions, but not retrospective using historical clinical patient data.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
Given that "patient simulators" were used, there were likely no human experts required to establish "ground truth" in the traditional sense of clinical diagnosis. The "ground truth" would have been the pre-programmed and known states of the patient simulator, which were then compared against the device's measurements and detections. The qualifications of the individuals who programmed and operated the simulators are not specified.
4. Adjudication Method for the Test Set
No adjudication method is mentioned for the test set, as the evaluation was against known simulator outputs rather than human interpretation that would require adjudication.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done
No, an MRMC comparative effectiveness study was not done. The performance data focuses on the device's technical specifications and algorithm accuracy (for arrhythmia and ST analysis) against predefined standards and simulated conditions, not on comparing human reader performance with or without AI assistance.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done
Yes, a standalone performance evaluation was done, particularly for the arrhythmia and ST analysis algorithms. The document explicitly lists performance metrics for QRS and PVC detection (Sensitivity, Positive Predictivity, False Positive Rate) based on the AHA and MIT databases. This demonstrates the algorithm's performance independent of human interaction.
7. The Type of Ground Truth Used
For the arrhythmia analysis, the ground truth was based on established benchmarks from the AHA (American Heart Association) and MIT (Massachusetts Institute of Technology) databases. These databases contain annotated ECG recordings where events (like QRS complexes and PVCs) have been meticulously identified and marked, often through expert review and consensus. For other general device functions (display, processing, etc.), the ground truth would be conformance to the stated technical specifications and environmental standards.
8. The Sample Size for the Training Set
The document does not explicitly state the sample size for the training set used for the arrhythmia and ST analysis algorithms. It mentions the "current arrhythmia detection and ST segment analysis algorithm library was replaced with the Mortara Instrument Incorporated product." It further states that "This same library is used in the Welch Allyn Acuity Central Station, which was cleared to market via 510(k) K022453." While the training set data is not provided, the implication is that the Mortara algorithm was trained on a significant dataset to achieve the reported performance on standard benchmarks.
9. How the Ground Truth for the Training Set Was Established
The document does not directly describe how the ground truth for the training set of the Mortara algorithms was established. However, given that these algorithms are evaluated against AHA and MIT databases for their "ground truth" performance metrics (as seen in the "Arrhythmia Analysis Option" table), it can be inferred that the training process would have also relied on highly curated and expert-annotated ECG datasets similar to, or including, segments of these recognized benchmark databases. The "heuristic algorithm using template matching and feature extraction" also points to an approach that would benefit from large, labeled datasets for developing and refining performance.
Ask a specific question about this device
Page 1 of 1