(293 days)
The Gili Pro BioSensor (Gili BioSensor System) includes an optical module that is intended to capture motion-vibration signals from an illuminated surface for assessment of physiological information. Such information, captured during spot-measurement, includes:
- Heart rate ●
- Respiratory rate .
The device is indicated for use by or under the supervision of healthcare professionals for adult patients in a hospital, outpatient, or other medical care settings, or for clinical research purposes.
The device should be used while the subject is seated upright either in a chair or in a bed. The information stored on the system may be reviewed by qualified persons.
The Gili Pro BioSensor is an optical system consisting of a sensing unit and a mobile unit with a preinstalled software application. The optical sensing unit is an aluminum enclosure which houses a lithium ion battery, illuminating optics (laser projector and laser pointer), digital image sensor, range meter, and firmware to facilitate data processing. The illuminating optics are based on eye-safe lasers which are compliant with Class I laser product accessible emission limits. The sensing unit is connected via a USB cable to a mobile unit on which the mobile application is installed.
The system illuminates the subject via a low-powered near infra-red (NIR at ~780 nm) light beam while an image sensor module captures the back reflected light pattern by the light sensor. The laser pointer illuminates in the visible spectrum (~650 nm) to facilitate proper positioning of the sensor relative to the subject. Changes in the reflected light pattern are coupled with motions of the illuminated surface, which are affected by heart and breathing motions. Analysis of these patterns through the software application correlate with heart and respiratory rates, as part of vital signs assessment. The heart and respiratory rate values are displayed on the user interface of the mobile unit.
Here's a detailed breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:
Acceptance Criteria and Device Performance
| Parameter | Acceptance Criteria (Pre-specified) | Reported Device Performance (Clinical Study) |
|---|---|---|
| Heart Rate | (b) (4) (for non-arrhythmia patients) | Intercept of (b) (4) with a (b) (4) confidence interval of (b) (4) (for non-arrhythmia patients) |
| Respiratory Rate | (b) (4) BrPM (for general population) | Intercept of (b) (4) with a (b) (4) confidence interval of (b) (4) (for general population) |
| Heart Rate (Broader population including arrhythmias) | (b) (4) bpm | Intercept of (b) (4) with a (b) (4) confidence interval of (b) (4) |
Note: The specific numerical values for the acceptance criteria and confidence intervals are redacted in the provided document (indicated by "(b) (4)"). However, the document states that the device met these pre-specified criteria.
Study Details for Clinical Validation:
-
Sample Size Used for the Test Set and Data Provenance:
- Sample Size: 120 subjects in the main, pivotal study. (An additional 10 subjects were in a pilot phase).
- Data Provenance: The document does not specify the country of origin for the data. It indicates a "clinical study protocol and results" were provided by "ContinUse Biometrics Ltd. HaBarzel 32B Tel-Aviv, Israel," which suggests the study may have taken place in Israel, but this is not explicitly stated for the data collection itself. The study was prospective in nature, designed as a "two-phase trial."
-
Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:
- Heart Rate Ground Truth: ECG (Electrocardiography) was used as the gold standard for determining heart rate and the presence of arrhythmia. This does not inherently involve human "experts" establishing ground truth in the same way an image interpretation might, but rather relies on objective physiological measurement.
- Respiratory Rate Ground Truth: "Clinician over-scored capnography." This implies that clinicians (experts) were involved in interpreting or reviewing capnography data to establish ground truth. The specific number or qualifications of these clinicians are not provided.
-
Adjudication Method for the Test Set:
- The document does not explicitly describe an adjudication method for the test set, such as a 2+1 or 3+1 consensus process. For heart rate, the ground truth was derived directly from ECG. For respiratory rate, "clinician over-scored capnography" was used, which suggests expert review, but the adjudication process (e.g., if multiple clinicians disagreed) is not detailed.
-
Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- The document does not mention an MRMC comparative effectiveness study involving human readers. The study focuses on the standalone performance of the Gili Pro BioSensor against reference devices. There is no information about human readers improving with or without AI assistance.
-
Standalone (Algorithm Only) Performance:
- Yes, a standalone performance assessment was done. The entire clinical study described is dedicated to evaluating the algorithm's performance (via the Gili Pro BioSensor system) against gold-standard reference devices (ECG for HR, capnography for RR) without human interpretation of the Gili device's raw optical data being part of the primary outcome. The heart and respiratory rate values are "displayed on the user interface of the mobile unit," implying the algorithm generates these values autonomously.
-
Type of Ground Truth Used:
- Heart Rate: Gold standard reference ECG (objective physiological measurement).
- Respiratory Rate: Clinician over-scored capnography (a combination of objective physiological measurement and expert interpretation/scoring).
-
Sample Size for the Training Set:
- The document does not provide information about the sample size used for the training set. The clinical study described is explicitly for validation (effectiveness) of the device performance.
-
How the Ground Truth for the Training Set Was Established:
- As no information on a specific training set with ground truth is provided, this cannot be answered from the given text. The description focuses on the clinical validation study. It's common for development and training data to be separate from the robust clinical validation study.
§ 870.2786 Hardware and software for optical camera-based measurement of pulse rate, heart rate, breathing rate, and/or respiratory rate.
(a)
Identification. The device uses an optical sensor system and software algorithms to obtain and analyze video signal and estimate pulse rate, heart rate, breathing rate, and/or respiratory rates. 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) 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
(iii) Software documentation must include a cybersecurity vulnerability and management process to assure software functionality.
(2) Performance testing must demonstrate the safety of any illuminating optics.
(3) 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.
(4) A human factors and usability engineering assessment must be provided that evaluates the risk of improper measurement.
(5) 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.