(176 days)
The Biobeat Platform-2 is a wireless noninvasive remote monitoring system intended for use by healthcare professionals for spot check collection of physiological data in home and healthcare settings. This can include, functional oxygen saturation of arterial hemoglobin (%SpO2), pulse rate, blood pressure, respiration rate (RRp), hemodynamic parameters (stroke volume, cardiac output), and body temperature.
The Biobeat Platform-2 tracks changes in blood pressure based on Pulse Wave Transit Time (PWTT) which is obtained utilizing pulse measurements from the integrated SpO2 sensor, following a calibration process using an FDA-cleared oscillometric blood pressure monitor.
The Biobeat Platform-2 is intended for spot-checking and tracking changes of adult patients in hospitals, clinics, long-term care, and at home. The data from the Biobeat Platform-2 are intended for use by healthcare professionals as an aid to diagnosis and treatment. The device is not intended for use on critical care patients.
The Biobeat Platform-2 includes a sensor device that is attached to the patient's chest to collect physiological data for later review by their healthcare provider. The device consists of a light source (LEDs), thermistors and sensor array on the backside of the device. The LEDs transmit light into the subject's skin and part of this light is reflected from the tissue and detected by a photo-diode. This allows measurement of arterial oxygenation, pulse rate, change in blood pressure, stroke volume, cardiac output, and respiration rate. Body temperature is measured by the thermistors. Data is transmitted to a gateway via Bluetooth and then uploaded to the cloud. From the cloud, data is transmitted and presented in a web application for review by a healthcare professional. The device does not contain any alarms.
Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:
Acceptance Criteria and Device Performance
The document doesn't explicitly list "acceptance criteria" in a separate table with specific numerical targets for each parameter. However, it states the device aims for equivalent performance to its predicate devices and provides accuracy statements for certain physiological parameters. For the new parameters (Stroke Volume (SV) and Cardiac Output (CO)), the acceptance criterion is implicitly demonstrated by the Bland-Altman analysis showing acceptable Limits of Agreement (LOA) against a reference method.
Here's an attempt to structure the information into a table, inferring the acceptance criteria from the performance data and comparisons to predicate devices:
Table of Acceptance Criteria and Reported Device Performance
| Parameter / Metric | Acceptance Criteria (Implicitly from Predicate Comparison or Performance Data) | Reported Device Performance | Study that Proves Device Meets Acceptance Criteria |
|---|---|---|---|
| Functional Oxygen Saturation (%SpO2) | Accuracy (Arms): ±2% | Not explicitly re-tested for Biobeat Platform-2, relied on K212153. | K212153 (Primary Predicate Device study data) |
| Pulse Rate (PR/HR) | Accuracy (Arms): ±3% | Not explicitly re-tested for Biobeat Platform-2, relied on K212153. | K212153 (Primary Predicate Device study data) |
| Blood Pressure (BP) | Accuracy: ±5 mmHg | Not explicitly re-tested for Biobeat Platform-2, relied on K212153. | K212153 (Primary Predicate Device study data) |
| Respiration Rate (RRp) | No specific accuracy stated, but "measured by analyzing cyclic variations in the photoplethysmogram due to respiration." | Not explicitly re-tested for Biobeat Platform-2, relied on K212153. | K212153 (Primary Predicate Device study data) |
| Body Temperature | No specific accuracy stated. | Not explicitly re-tested for Biobeat Platform-2, relied on K212153. | K212153 (Primary Predicate Device study data) |
| Cardiac Output (CO) | Bland-Altman LOA to reference method (Fick, TD) within 30%. | Bland-Altman analysis showed LOA to the Fick method and TD within 30%. | Clinical Validation Data (90 patients, 80/77/82 included in final analysis) |
| Stroke Volume (SV) | Implicitly covered by Cardiac Output (CO) validation, as it's a hemodynamic parameter measured through the same new algorithm. | Implicitly covered by CO validation. | Clinical Validation Data (90 patients, 80/77/82 included in final analysis) |
| Software Validation | Per FDA guidance, General Principles of Software Validation; Final Guidance for Industry and FDA Staff (January 11, 2002) | "The new software elements have been documented and validated per FDA guidance." | Software validation per FDA guidance |
Study Details for New Features (Stroke Volume & Cardiac Output)
1. Sample sizes used for the test set and the data provenance:
* Sample Size:
* 90 patients recruited.
* 80 patients included in the final analysis comparing PPG device and Fick method.
* 77 patients included in the final analysis comparing TD with Fick method.
* 82 patients included in the final analysis comparing PPG with TD.
* Data Provenance:
* Country of Origin: Not explicitly stated, but the company address is in Petah Tikva, Israel. Based on the Clinical Validation Data section, it seems to be from a clinical site where patients underwent right heart catheterization.
* Retrospective or Prospective: The study states, "Comparison was performed retrospectively, after completion of the measurement phase." However, subjects were "recruited" and "simultaneously attached" to devices, which suggests prospective data collection followed by retrospective analysis. The description indicates a prospective collection design for the "test set."
2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
* This information is not provided in the text. The ground truth was established by objective medical methods (indirect Fick method and thermodilution), not subjective expert assessment.
3. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
* None. The ground truth was established by objective reference measurements (Fick method and thermodilution, and a comparison between PPG and TD), not by human expert adjudication of images or data.
4. 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. This was not an MRMC study. The study focused on the accuracy of the device's measurements against established clinical reference methods, not on human reader performance with or without AI assistance. The device output is physiological data for healthcare professionals to aid diagnosis and treatment, not an AI interpretation for a human reader to validate.
5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
* Yes. The clinical validation data presents the performance of the Biobeat device's algorithm (PPG device) in measuring cardiac output and comparing it to the reference methods (Fick and Thermodilution). This is a standalone algorithm performance evaluation.
6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
* Objective Clinical Reference Standards:
* Indirect Fick method
* Thermodilution (TD)
* These are considered "gold standard" or highly accurate methods for measuring cardiac output in a clinical setting.
7. The sample size for the training set:
* This information is not provided in the text. The document describes clinical validation for the test set, but not the training of the algorithms. It only states that a "new algorithm, derived from the existing photoplethysmogram, was added for measuring stroke volume and cardiac output."
8. How the ground truth for the training set was established:
* This information is not provided in the text. Given the new algorithm for SV/CO was "derived from the existing photoplethysmogram," it's possible it was developed using internal data and/or existing physiological models. The document focuses on the validation of this algorithm.
§ 870.2700 Oximeter.
(a)
Identification. An oximeter is a device used to transmit radiation at a known wavelength(s) through blood and to measure the blood oxygen saturation based on the amount of reflected or scattered radiation. It may be used alone or in conjunction with a fiberoptic oximeter catheter.(b)
Classification. Class II (performance standards).