(262 days)
The Biovitals Analytic Engine (BA Engine) is intended to be used with continuous biometric data from already cleared sensors measuring heart rate, respiratory rate, and activity in ambulatory patients being monitored in a healthcare facility or at home, during periods of minimal activity. The device learns the correlation between multiple vital signs during the patient's daily activity and builds an individualized biometric signature which is dynamically updated based on incoming data. The device computes a time series Biovitals Index (BI), which reflects changes in the patient's measured vital signs from their measured baseline, which is derived from the individualized biometric signature of the patient.
The BA Engine is a cloud-based software engine, intended to be an adjunct to and is not intended to replace vital signs monitoring. The BI is intended for daily intermittent, retrospective review by a qualified practitioner. The BA Engine is intended to provide additional information for use during routine patient monitoring. The BI is not intended for making clinical decisions regarding patient treatment or for diagnostic purposes.
The device is intended for an adult population.
Biovitals Analytics Engine consists of:
- An automated proprietary algorithm to analyze data and generate Biovitals Index.
- A cloud-based database to store the input, intermedium output and the final output
- A web application programming interface (API) which handle the continuous physiology data.
- A web application programming interface (API) query the databases and get output.
- A web dashboard to render the BA Engine output in a continuous graph format, which can help intended users to monitor a patient's Biovitals Index.
Biovitals Analytics Engine works in the following sequence:
- Accept input data via secure API;
- Analyze the input data using Biovitals Analytics Engine proprietary algorithm, which generate Biovitals Index:
- Personal physiology signature data base initialization (at the early stage on the algorithm when the engine learns the patients and builds the personal baseline)
- Biovitals Index calculation
- Biovitals Analytics engine generates the Biovitals Index which is a time series scalar value from 0 to 1.
- The output of BA Engine is stored in a cloud-based database.
- The output API queries the databases and gets the output, and the output shall be reviewed by the qualified practitioner via a dashboard.
The Biovitals Analytics Engine (BA Engine) computes a time series Biovitals Index (BI) that reflects changes in a patient's vital signs from their measured baseline. The device's performance was evaluated through clinical testing to show its correlation with changes in the relationship among vital sign parameters as assessed by a panel of physicians.
Here's a breakdown of the requested information:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Correlation with changes in vital sign parameters (PPA) | The Biovitals Index (BI) was correlated to the changes in relationship among vital sign parameters, with a lower bound of the 95% confidence interval of the positive percent agreement (PPA) greater than 0.7. |
| Within-subject variability for BI categories | Low (BI ≤ 0.3): 0.11 |
| Moderate (0.3 0.7): 0.17 |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: 50 subjects.
- Data Provenance: The subjects were patients presenting at an Emergency Department and were deemed appropriate for home monitoring. The document does not specify the country of origin, but given the FDA review, it is likely from the US, or data collected in a manner suitable for US regulatory submission. The study appears to be prospective as it describes patients presenting at an ED and being monitored.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications
- Number of Experts: A panel of three physicians.
- Qualifications: The document only states "a panel of three physicians" and does not provide specific qualifications (e.g., years of experience, sub-specialty).
4. Adjudication Method for the Test Set
- The document states that the performance was compared "against a panel of three physicians evaluating the changes in the relationship among the patients' vital sign parameters." This implies a consensus or majority opinion (e.g., 2+1, where at least two physicians agree). However, the specific adjudication method (e.g., 2+1, 3+1, none) is not explicitly stated.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done
- No, a formal MRMC comparative effectiveness study was not explicitly described for evaluating how human readers improve with AI vs. without AI assistance. The study described focuses on the standalone performance of the BI in correlating with physician assessments of vital sign changes, rather than comparing human reader performance with and without AI assistance. The device is intended as an "adjunct" for "daily intermittent, retrospective review," suggesting it provides additional information to a practitioner, which could imply human-in-the-loop, but the study design does not directly evaluate this human improvement.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
- Yes, a standalone performance evaluation of the algorithm was conducted. The study evaluated the Biovitals Index (BI) directly against the assessment of a panel of physicians. The PPA (Positive Percent Agreement) of the BI itself was measured against the physician panel's assessment, indicating a standalone performance evaluation.
7. The Type of Ground Truth Used
- The ground truth used was expert consensus / clinical assessment from a panel of three physicians. They evaluated the "changes in the relationship among the patients' vital sign parameters."
8. The Sample Size for the Training Set
- The document does not specify the sample size used for the training set. It only describes the methodology for establishing the personalized baseline: "The baseline is initially established using data from the first 24 hours and updated periodically as new data is received." And for the within-subject variability calculation: "The expected within-subject variability was computed using data from a clinical study involving 50 emergency department patients that were deemed appropriate for home monitoring." This suggests the 50 patients mentioned for the test set might also be involved in data used for variability computation, but it doesn't describe the training set for the core algorithm that generates the BI.
9. How the Ground Truth for the Training Set Was Established
- The document does not explicitly describe how ground truth (or the equivalent "gold standard") for the training set was established. Instead, it explains how the BA Engine "learns the correlation between multiple vital signs during the patient's daily activity and builds an individualized biometric signature which is dynamically updated based on incoming data." This is described as a personalized, dynamic baseline for each patient, rather than a pre-established, universal ground truth from a large training dataset. The algorithm "learns" from the individual patient's own physiological data to establish their personal baseline.
§ 870.2300 Cardiac monitor (including cardiotachometer and rate alarm).
(a)
Identification. A cardiac monitor (including cardiotachometer and rate alarm) is a device used to measure the heart rate from an analog signal produced by an electrocardiograph, vectorcardiograph, or blood pressure monitor. This device may sound an alarm when the heart rate falls outside preset upper and lower limits.(b)
Classification. Class II (performance standards).