(228 days)
The Vios Monitoring System (VMS) is intended for use by medically qualified personnel for physiological vital signs monitoring of adult (18+) patients in healthcare facilities. It is indicated for use in monitoring of 7-lead ECG, heart rate, functional oxygen saturation of arterial hemoglobin, non-invasive blood pressure and activity. VMS allows for the input of body temperature, and can display data from peripheral devices. VMS can generate alerts when the physiological vital signs fall outside of selected parameters.
VMS can also generate alerts when cardias arrhythmias (Tachycardia, Asystole, Ventricular Fibrillation and Atrial Fibrillation/ Atrial Flutter) are detected.
The ECG rhythm analysis is intended for use by medified professionals in the identification of arrhythmia events and to aid in clinical review of arrhythmias and medical interventions.
The Vos CSM/CS Software is indicated for use by healthcare professionals for the purpose of centralized monitoring of patient data within a healthcare facility. The Vios CSMCS SW receives, stores, and displays patient physiological and waveform data and alams generated by Vios proprietary patient vitals monitoring software.
The Vios Monitoring System (VMS) Model 2050 is a wireless mobile medical device platform that allows caregivers in healthcare settings to monitor patient vitals. The VMS includes a proprietary monitoring software, Chest Sensor, Finger Adapter and Central Server and Central Monitoring Station. The VMS BSM SW Model B2050 is stand-alone software that can receive, analyze, and display physiological vitals data from one or more patient-worn sensors via standard communication protocols (Bluetooth™). It runs on a commercial IT platform and is intended to be used in conjunction with the Vios Chest Sensor and Vios Lead Adapters and can support peripheral, medical grade, Bluetooth™-enabled devices. The VMS Chest Sensor Model CS2050 is a small, patient-worn, non-sterile multiple use,
The Vios Monitoring System (VMS) Model 2050 was evaluated for its arrhythmia detection features, specifically assessing its performance against the ANSI/AAMI EC57:2012 standard and additional database records.
Here's a breakdown of the acceptance criteria and study details:
1. Table of Acceptance Criteria and Reported Device Performance:
The document primarily references compliance with the ANSI/AAMI EC57:2012 standard for cardiac rhythm and ST-segment measurement algorithms. While specific numerical acceptance criteria (e.g., minimum sensitivity, positive predictivity) for each arrhythmia are not explicitly listed in the provided summary, the study's conclusion of meeting "performance requirements as outlined in the consensus standard ANSI/AAMI EC57:2012" implies that the device achieved the performance thresholds defined within that standard for the tested arrhythmias.
| Arrhythmia Type | Standard | Reported Device Performance |
|---|---|---|
| Tachycardia | ANSI/AAMI EC57:2012 | Met performance requirements |
| Bradycardia | ANSI/AAMI EC57:2012 | Met performance requirements |
| Asystole | ANSI/AAMI EC57:2012 | Met performance requirements |
| Ventricular Tachycardia/Ventricular Fibrillation | ANSI/AAMI EC57:2012 | Met performance requirements |
| Atrial Fibrillation/Atrial Flutter | ANSI/AAMI EC57:2012 | Met performance requirements |
2. Sample Size for the Test Set and Data Provenance:
The document states that the device's performance was evaluated using:
- Records from the ANSI/AAMI EC57 standard. This standard often utilizes a combination of standard ECG databases (e.g., MIT-BIH Arrhythmia Database).
- Additional records from LTAF, AAEL, and VFDB databases.
The specific sample sizes (number of patients or ECG recordings) for each arrhythmia or for the combined test set are not provided in the summary. The provenance of LTAF, AAEL, and VFDB databases is not detailed; however, these are generally recognized public databases of ECG recordings used for algorithm testing, often comprising retrospective data.
3. Number of Experts Used to Establish Ground Truth and Qualifications:
The document does not state the number of experts used or their specific qualifications for establishing the ground truth of the test set. For publicly available and widely used databases like those mentioned (MIT-BIH, LTAF, AAEL, VFDB), the ground truth labels are typically established by multiple expert cardiologists or electrophysiologists using established criteria, often after multiple review rounds. However, this specific information is not in the provided text.
4. Adjudication Method for the Test Set:
The document does not specify the adjudication method used (e.g., 2+1, 3+1). For standard ECG databases, ground truth is usually established via expert consensus, which inherently involves an adjudication process, but the specific mechanics are not described here.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
The document does not indicate that a multi-reader multi-case (MRMC) comparative effectiveness study was done to assess how much human readers improve with AI vs. without AI assistance. The testing described is focused on the standalone performance of the device's arrhythmia detection algorithm.
6. Standalone (Algorithm Only Without Human-in-the-Loop) Performance:
Yes, a standalone performance evaluation was done. The summary explicitly states: "The non-clinical tests for evaluation of performance of Vios system with the addition of arrhythmia alarms is based on ANSI/AAMI EC57, showing substantial equivalence to the predicate (K180472). The subject device's performance was also evaluated using additional records from LTAF, AAEL, and VFDB database..." This describes the algorithm's performance without direct human intervention as part of the detection process.
7. Type of Ground Truth Used:
The ground truth for the test was established through expert consensus/annotations from well-known ECG databases (ANSI/AAMI EC57, LTAF, AAEL, and VFDB). These databases contain ECG recordings that have been meticulously reviewed and annotated by medical experts (typically cardiologists or electrophysiologists) to identify and label different cardiac events and arrhythmias,
Pathology and outcomes data are not mentioned as sources for ground truth in this context.
8. Sample Size for the Training Set:
The document does not specify the sample size used for the training set of the Vios Monitoring System's arrhythmia detection algorithm.
9. How the Ground Truth for the Training Set Was Established:
The document does not specify how the ground truth for the training set was established. However, it is common practice for such algorithms to be trained on large, expertly annotated ECG datasets, similar to those used for testing (expert consensus/annotations).
§ 870.2300 Cardiac monitor (including cardiotachometer and rate alarm).
(a)
Identification. A cardiac monitor (including cardiotachometer and rate alarm) is a device used to measure the heart rate from an analog signal produced by an electrocardiograph, vectorcardiograph, or blood pressure monitor. This device may sound an alarm when the heart rate falls outside preset upper and lower limits.(b)
Classification. Class II (performance standards).