Search Results

The Wellvii VitalDetect™ is a device designed for spot measurements with recorded results of non-invasive blood pressure (NIBP), pulse rate (PR), and temperature (TMP).

This device uses an infra-red sensor for non-contact temperature measurement at the forehead. All other measurements use finger-based technology.

The VitalDetectTM is applicable for prescription home use by individuals 18 years of age or older for monitoring.

The device is not intended for continuous monitoring.

VitalDetect is a Bluetooth® connected, hand-held, portable vital sign monitor for prescription home use. The monitoring device can read physiological parameters, including: Pulse Rate (PR), Non-Invasive Blood Pressure (NIBP), and Body Temperature (TEMP).

The device uses a lithium-polymer battery which is rechargeable by the User. The battery is replaceable only by service personnel.

The VitalDetect monitoring system consists of a measurement device with inflatable finger-cuff, 5 finger shims, USB charging cord, and a downloadable application (APP) for use on a mobile device.

Here's a breakdown of the acceptance criteria and study details for the Wellvii VitalDetect device, based on the provided FDA 510(k) summary:

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria for the VitalDetect device are primarily based on clinical accuracy, aligning with relevant ISO standards for blood pressure, pulse rate, and temperature measurement.

Table of Acceptance Criteria and Reported Device Performance:

Notes on Acceptance Criteria:

• NIBP: The acceptance criteria for NIBP (Non-Invasive Blood Pressure) are implied by the reported performance and the specific mention of compliance with IEC 80601-2-30:2018, which sets these highly specific accuracy standards. The two criteria (Mean Difference and Standard Deviation for Criterion 1, and only Standard Deviation for Criterion 2) are standard for BP device validation.
• Pulse Rate and Temperature: For these parameters, the "Accuracy" values directly stated in the comparison table and the clinical testing results are considered the acceptance criteria based on standard medical device performance expectations.

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

• Sample Size for Test Set: Not explicitly stated in terms of number of participants, but the clinical testing details mention "The VitalDetect showed compliance with basic safety and accuracy requirements of the standard," and "The study was conducted in accordance with 21 CFR 812 for Non-significant Risk Investigational Studies, following ISO 14155:2011 Clinical Investigation of medical devices for human subjects – Good clinical practice, as appropriate." The tables provided are summaries of the results, not raw data or cohort sizes. For blood pressure, ISO 80601-2-30 typically requires a minimum of 85 subjects with specific age and blood pressure distribution.
• Data Provenance: The document does not explicitly state the country of origin. However, given the FDA submission and the use of US regulatory standards (21 CFR 812), it is highly probable the study was conducted within the United States or under US-equivalent Good Clinical Practice (GCP) standards. The study was prospective as it involved "Clinical trials were completed to validate the clinical accuracy and functionality of the proposed device."

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

• The document does not provide information on the number of experts or their qualifications used to establish the ground truth.
• For blood pressure validation, ground truth is typically established by trained technicians or clinicians using an auscultatory method (trained observers listening for Korotkoff sounds) with a mercury sphygmomanometer or validated reference device. For temperature, a highly accurate reference thermometer is used.

4. Adjudication Method for the Test Set

• The document does not specify an adjudication method.
• For blood pressure validation studies, ground truth determination often involves at least two trained observers taking simultaneous or near-simultaneous measurements to ensure accuracy and inter-observer reliability, which acts as a form of "adjudication."

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

• No, an MRMC comparative effectiveness study was not done.
• This device is a measurement device for vital signs (BP, PR, Temp), not an AI-assisted diagnostic imaging or interpretation tool. Therefore, a study comparing human readers with and without AI assistance is not applicable to its validation.

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

• Yes, in essence, standalone performance was assessed.
• The clinical testing summarized in the table (Section 12.0) directly reports the accuracy of the VitalDetect device's measurements (NIBP, Pulse Rate, Temperature) against a true reference. This is a measure of the device's inherent, standalone performance in taking these vital sign measurements. The device is intended for the human user to operate it, but the accuracy assessment itself is of the device's capability to measure, not assist human interpretation.

7. The Type of Ground Truth Used

• Expert Consensus / Reference Standards:
  • For blood pressure, the ground truth is established by an established reference method, typically the auscultatory method performed by trained observers using a reference sphygmomanometer, calibrated according to standards (e.g., as per ISO 80601-2-30).
  • For pulse rate, the ground truth would be from a highly accurate reference ECG or plethysmograph.
  • For temperature, the ground truth would be established using a calibrated reference thermometer (e.g., rectal or oral mercury thermometer or highly accurate electronic thermometer).
  • The term "Clinical Testing" and "validate the clinical accuracy" strongly implies comparison against accepted clinical reference standards or expert measurements.

8. The Sample Size for the Training Set

• The document does not disclose any information regarding a training set.
• For a traditional vital signs monitor like the VitalDetect, the "training" (development and calibration) typically occurs during the engineering and design phase, often using laboratory measurements and sometimes human subjects for initial algorithm tuning, rather than a distinct "training set" of patient data in the way an AI/ML algorithm would. The listed clinical study is for validation after the device's design is finalized.

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

• As a distinct "training set" as understood in AI/ML is not explicitly discussed, the method for establishing ground truth for such a set is not detailed.
• Any internal development and calibration (analogous to "training") would utilize highly controlled measurements against known, precise reference standards in laboratory and potentially initial human studies.

Ask a specific question about this device