Search Results

Pulse rate
Respiration rate
Movement
The data from Everion+ is intended to be used in a hospital or home environment in order to support monitoring of wearers under the care of a trained healthcare professional. Everion+ is not intended for use in a critical care environment such as an ICU or operating room. The device information should not be the sole basis for clinical decisions.

Device Description

The Everion+ is a wireless multi-parameter vital-signs monitoring system. The Everion+ was includes an Application Programming Interface (API), which is intended to allow development of user interface applications that enable clinicians and medically-qualified personnel to access recorded vital signs information for active patient monitoring.
The system is comprised of the following components:

Wearable device with multiple sensors
Secure cloud environment with an API .
Charger with accessories .
Armband .
The Everion+ wearable is battery-operated with integrated sensors and wireless transceiver. The wearable is worn on the upper arm via the adjustable armband that snaps to it. The armband is made of a stretchy material and has an adjustable clip to enable fitting to most adults. The wearable continuously gathers multi-parameter vital signs data from the person being monitored and securely transmits the data to the server component of the system, via cellular communication, when in range of a third-party receiver.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study information for the Everion+ System, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Parameter	Acceptance Criteria (Objective)	Reported Device Performance (Result)
Pulse Rate (PR)	RMSE ≤ 3 bpm	RMSE ≤ 3 bpm (met)
Respiration Rate (RR)	RMSE < 3 brpm	RMSE < 3 brpm (met)
Movement Detection (Rest vs. Non-Rest)	Accuracy objective implied by general performance claims	Accuracy: 88.9%
Movement Detection (Level 1 – REST)	(Not explicitly defined with a numerical objective, but performance reported)	Accuracy: 88.9%, Sensitivity: 66.8%, Specificity: 98.8%
Movement Detection (Level 2 – LOW)	(Not explicitly defined with a numerical objective, but performance reported)	Accuracy: 77.7%, Sensitivity: 59.5%, Specificity: 84.4%
Movement Detection (Level 3 – MODERATE)	(Not explicitly defined with a numerical objective, but performance reported)	Accuracy: 80.1%, Sensitivity: 92.6%, Specificity: 75.0%
Movement Detection (Level 4 – HIGH)	(Not explicitly defined with a numerical objective, but performance reported)	Accuracy: 91.3%, Sensitivity: 70.3%, Specificity: 99.9%

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

Sample Size: 50 collective subjects (M/F)
- Ages: 46 ± 17 years (range: 21-80 years)
- BMI: 18.6-49.3
- Skin tones: Range 1-6 on Fitzpatrick scale (though not explicitly stated as a characteristic of the 50 subjects, it's mentioned to indicate diversity)
- Disease conditions: Wide ranges (not specified beyond "wide ranges")
Data Provenance: The text states "two clinical studies," but does not explicitly mention the country of origin. The study appears to be prospective due to the description of subjects wearing devices for assessment.

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

The text does not explicitly state the number of experts or their qualifications for establishing ground truth. It mentions:

"ECG monitor (for PR reference)"
"end-tidal CO2 capnograph monitor (for RR reference)"

These devices are used as the reference standard, implying that their output is considered the "ground truth" rather than expert interpretation of raw data for these vital signs.

For movement detection, the "actual" categories (Rest_a, Low_a, Mod_a, High_a) in the confusion matrix imply a ground truth for movement, but the method and number/qualifications of experts involved in establishing this ground truth are not detailed.

4. Adjudication Method for the Test Set

The document does not describe an adjudication method for the test set. For Pulse Rate (PR) and Respiration Rate (RR), direct comparisons were made to instrumental reference standards (ECG and capnograph). For movement, the "Actual" categories define the ground truth, but the process of establishing these categories is not detailed, so no adjudication method is mentioned.

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

No, an MRMC comparative effectiveness study involving human readers and AI assistance was not mentioned or performed according to this document. The study focuses on the standalone performance of the Everion+ device.

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

Yes, a standalone performance study was done. The "Clinical Study Validation Summary" describes the assessment of the Everion+ device's accuracy for Pulse Rate, Respiration Rate, and Movement by comparing its outputs to reference standards. This is a standalone evaluation of the device's algorithms.

7. The Type of Ground Truth Used

Pulse Rate (PR): ECG monitor
Respiration Rate (RR): End-tidal CO2 capnograph monitor
Movement: "Actual" movement categories (Rest, Low, Moderate, High), but the method of establishing these categories (e.g., expert observation, synchronized video analysis, or another objective measure) is not specified. It is likely an objective measure rather than expert consensus on device output.

8. The Sample Size for the Training Set

The document does not provide information on the sample size used for the training set. The clinical study described appears to be for validation/testing, not training.

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

Since information on the training set sample size is not provided, the method for establishing its ground truth is also not mentioned.

Ask a Question

Ask a specific question about this device

Page 1 of 1