(165 days)
The Informed Vital Core Application (IVC App) is intended for non-invasive spot measurement of pulse rate of adult patients in home use, hospitals, clinics, and long-term care settings.
The Informed Vital Core Application is indicated for use on adults 22 years of age or older who do not require critical care or continuous vital signs monitoring.
Informed Vital Core is not intended to independently direct therapy.
The IVC App is a Software as a Medical Device (SaMD) progressive web application that utilizes existing optical camera technology embedded in a smart-phone, tablet, laptop, or desktop computer to estimate an individual's vital signs including pulse rate (PR) developed by Mindset Medical. The IVC App software algorithms will provide spot checks for PR of the individual. The IVC App software uses proprietary software algorithms to extract a raw video signal through remote plethysmography (rPPG) by detecting subtle color variations in the microvasculature around a patient's face that occur with each cardiac cycle due to changes in blood volume to measure PR.
Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The acceptance criterion for the device's accuracy is clearly stated: pulse rates measured with the IVC App must be accurate to within ±3 beats per minute (BPM) Average Root Mean Square (ARMS) of heart rates (HR) measured with a reference ECG device.
| Acceptance Criteria (Pulse Rate Accuracy) | Reported Device Performance (Pulse Rate Accuracy) |
|---|---|
| Within ±3 BPM Average Root Mean Square (ARMS) of Heart Rate (HR) measured with a reference ECG device | The hypothesis that the IVC App can measure PR within ± 3 BPM ARMS is accepted. (Implicitly, the performance met this criterion.) |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: 67 subjects were enrolled in the clinical study.
- Data Provenance:
- Country of Origin: United States (recruited from six study sites located in the United States).
- Retrospective or Prospective: Prospective. The study is described as a "multicenter, prospective, open-label clinical study."
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
The document does not mention the use of experts to establish ground truth for the test set. Instead, the ground truth was established by a legally marketed, electrocardiogram (ECG) device, which serves as the reference standard for heart rate measurement. Therefore, no human experts were involved in creating the ground truth for the clinical study's primary endpoint.
4. Adjudication Method for the Test Set
No adjudication method is mentioned or relevant, as the ground truth was established by an objective medical device (ECG), not by human readers requiring consensus or adjudication.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No, an MRMC comparative effectiveness study was not done. The study focused on the standalone performance of the IVC App compared to an ECG device. There is no mention of human readers assisting with the device or comparing human reader performance with and without AI assistance.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
Yes, a standalone study was performed. The "Primary endpoint" states: "The primary objective of the study was to establish that pulse rates measured with the IVC App are accurate to within ±3 beats per minute (BPM) average root mean square (ARMS) of heart rates (HR) measured with the reference ECG device." This directly assesses the algorithm's performance without human intervention in the measurement process itself, beyond initial setup.
7. Type of Ground Truth Used
The ground truth used was objective measurement from a legally marketed medical device, specifically an electrocardiogram (ECG) device. The document explicitly states: "The PR obtained by the IVC App was compared to the heart rate obtained by the ECG reference device."
8. Sample Size for the Training Set
The document does not explicitly state the sample size used for the training set. It provides "Bench Testing Subject Demographics" with "Subjects (Unique): 711" and "Number of Sessions: 1,413". While these subjects and sessions were used for "Non-clinical tests," it's not explicitly stated that this dataset was used for training the algorithm. It likely represents a larger dataset used for internal development, validation, and potentially training, but the text doesn't provide a distinct "training set size."
9. How the Ground Truth for the Training Set Was Established
The document does not explicitly detail how the ground truth for the training set was established. However, given the nature of the device and the testing described, it can be inferred that ground truth for any training data would also have been established using reference medical devices (like ECG, pulse oximeters, etc.) to obtain accurate heart rate measurements, similar to how the test set ground truth was established. The "Device Description" mentions "The IVC App software uses proprietary software algorithms to extract a raw video signal through remote plethysmography (rPPG) by detecting subtle color variations in the microvasculature around a patient's face that occur with each cardiac cycle due to changes in blood volume to measure PR," implying the training would involve establishing relationships between video signals and actual pulse rates from such reference devices.
§ 870.2785 Software for optical camera-based measurement of pulse rate, heart rate, breathing rate, and/or respiratory rate.
(a)
Identification. The device uses software algorithms to analyze video signal and estimate pulse rate, heart rate, breathing rate, and/or respiratory rate. This device is not intended to independently direct therapy.(b)
Classification. Class II (special controls). The special controls for this device are:(1) A software description and the results of verification and validation testing based on a comprehensive hazard analysis and risk assessment must include:
(i) A full characterization of the software technical parameters, including algorithms;
(ii) If required image acquisition hardware is not included with the device, full specifications of the hardware requirements and testing to demonstrate the specified hardware ensures adequate data for validated and accurate measurements;
(iii) A description of the expected impact of all applicable sensor acquisition hardware characteristics and associated hardware specifications;
(iv) A description of all mitigations for user error or failure of any subsystem components (including signal detection, signal analysis, data display, and storage) on output accuracy; and
(v) Software documentation must include a cybersecurity vulnerability and management process to assure software functionality.
(2) Clinical data must be provided. This assessment must fulfill the following:
(i) The clinical data must be representative of the intended use population for the device. Any selection criteria or sample limitations must be fully described and justified.
(ii) The assessment must demonstrate output consistency using the expected range of data sources and data quality encountered in the intended use population and environment.
(iii) The assessment must compare device output with a clinically accurate patient-contacting relevant comparator device in an accurate and reproducible manner.
(3) A human factors and usability engineering assessment must be provided that evaluates the risk of improper measurement.
(4) Labeling must include:
(i) A description of what the device measures and outputs to the user;
(ii) Warnings identifying sensor acquisition factors or subject conditions or characteristics (garment types/textures, motion, etc.) that may impact measurement results;
(iii) Guidance for interpretation of the measurements, including a statement that the output is adjunctive to other physical vital sign parameters and patient information;
(iv) The expected performance of the device for all intended use populations and environments; and
(v) Robust instructions to ensure correct system setup.