(29 days)
The Oxehealth Vital Signs device is intended for noninvasive spot measurement of pulse rate and estimated breathing rate (chest wall movements) when the subject is still. It is software assessing video footage from a fixed-installation solution for use within single occupancy rooms within hospitals, general care and secured environments with professional healthcare oversight and where a framework exists which mandates periodic checks by a trained professional to ensure subject safety.
The Oxehealth system is intended for use by appropriately trained staff with a duty of care, and should not be used by untrained users.
The Oxehealth Vital Signs device is indicated for use on humans 18 years of age or older who do not require critical care or continuous vital signs monitoring.
The device is not intended to be the sole method of checking the physical health of a subject.
The modified Oxehealth Vital Signs device uses custom-designed software to read data collected using off-the-shelf cameras. Data collected in this manner can be used to act as a non-contact monitor of pulse and breathing rates for individuals aged 18 and older in single-subject room environments. Video is collected through video cameras installed in each room. When run through proprietary software- controlled algorithms, the software will allow a user to make spot checks for pulse and breathing rates of the individual in the room. Validation testing has demonstrated that the algorithms show pulse and breathing rates that are statistically non-inferior when compared to conventional methods and technology that determine pulse and breathing rates.
The provided document is a 510(k) summary for the Oxehealth Vital Signs device, specifically for a modification to a previously cleared version. The core of the submission revolves around demonstrating substantial equivalence to the predicate device, meaning the new modification does not raise new questions of safety or effectiveness.
Therefore, the study proving the device meets acceptance criteria largely refers to the studies performed for the original predicate device (Oxehealth Vital Signs version 1.30.0, classified in DEN200019), as the modifications discussed in this 510(k) submission do not affect the fundamental principles of operation or performance in measuring pulse rate and estimated breathing rate.
Here's a breakdown of the information requested, based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
The document explicitly states the performance criteria that were established for the predicate device and are considered unchanged for the modified device.
| Performance Metric | Acceptance Criteria (from predicate) | Reported Device Performance (from predicate, considered applicable) |
|---|---|---|
| Pulse Rate | 50 to 130 beats per minute | Accuracy uses the RMSE criterion |
| Pulse Rate Accuracy | ± 3 beats per minute (RMSE criterion) | May be reduced when the subject has a pulse rate greater than 110 beats per minute. |
| Pulse Rate Measurement Window | 9 seconds | 9 second measurement window |
| Estimated Breathing Rate (chest wall movements) | 8 to 31 breaths per minute | Accuracy uses the RMSE criterion |
| Estimated Breathing Rate Accuracy | ± 2 breaths per minute (RMSE criterion) | - |
| Estimated Breathing Rate Measurement Window | 30 seconds | 30 second measurement window |
| General | Statistically non-inferior when compared to conventional methods and technology that determine pulse and breathing rates. | Validated through testing (details not in this document, but referred to from DEN200019) |
Note: The document explicitly states "No change" for performance regarding the modified device compared to the predicate, implying that the acceptance criteria and the performance demonstrated by the predicate are carried over.
2. Sample Size Used for the Test Set and Data Provenance
The document refers to the clinical evidence provided and reviewed in the original DEN200019 submission. It states: "As that clinical evidence is still applicable now, no new clinical evidence is required".
Therefore, the specific sample sizes and data provenance for the test set are not detailed in this 510(k) summary, but would be found in the documentation for DEN200019. The summary only confirms that such data was provided for the predicate device and is considered sufficient for the modified device.
3. Number of Experts Used to Establish Ground Truth and Qualifications
The document does not provide details about the number and qualifications of experts directly for this 510(k) summary. This information would have been part of the original DEN200019 submission, where the clinical evidence was initially reviewed.
4. Adjudication Method for the Test Set
The document does not provide details about the adjudication method used for the test set. This information would have been part of the original DEN200019 submission.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
The document does not mention an MRMC comparative effectiveness study where human readers improve with AI vs. without AI assistance. The device's function is explained as "software assessing video footage from a fixed-installation solution for use within single occupancy rooms" to produce "spot check measurements." It's generally intended as a non-contact monitor, not as an AI-assistance tool for human interpretation in the sense of a diagnostic imaging study. The focus is on the device's ability to provide accurate measurements directly, not on enhancing human interpretation of complex data.
The validation testing demonstrated that "the algorithms show pulse and breathing rates that are statistically non-inferior when compared to conventional methods and technology that determine pulse and breathing rates." This implies a comparison against ground truth measurements, not a human-AI team performance study.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
Yes, based on the description, the "Performance Data" section indicates that "As the modified Oxehealth Vital Signs device is solely software, performance testing is demonstrated through software validation." The prior validation (from DEN200019) compared the device's output to "clinically accurate patient-contacting relevant comparator device." This strongly suggests a standalone performance evaluation where the algorithm's output is directly compared to a reference standard, without human intervention in the measurement process.
7. The Type of Ground Truth Used
The document states: "The assessment must compare device output with a clinically accurate patient-contacting relevant comparator device in an accurate and reproducible manner."
This indicates that the ground truth was established using measurements from "clinically accurate patient-contacting relevant comparator device(s)". This would imply standard, validated medical devices (e.g., pulse oximeters, capnographs, or other physiological monitoring equipment) used as the reference standard for pulse and breathing rates.
8. The Sample Size for the Training Set
The document does not provide details on the training set sample size. The focus of this 510(k) is on the substantial equivalence of a modified device to a predicate device, and it states that the modifications "do not affect the algorithm or the functionality of the software." This implies that the core algorithm, which would have been trained based on a training set, remains unchanged from the predicate version. Information on the training set would have been part of the initial submission for the predicate device (DEN200019).
9. How the Ground Truth for the Training Set Was Established
Similar to point 8, the document does not provide details on how ground truth for the training set was established. This information would have been part of the original DEN200019 submission. The current submission reiterates that the original clinical evidence, which included comparison to "clinically accurate patient-contacting relevant comparator device," is still applicable.
§ 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.