The FH Vitals SDK is designed to measure the pulse rate based on the given facial video stream. It is intended for non-invasive spot measurements of pulse rate when the subject is still. This SDK is not intended for use in patients with known or suspected heart arrhythmias.

While the SDK can be used for general healthcare, it is not designed to treat patients. The pulse rate measurement results provided by the FH Vitals SDK should complement, but not replace, the user's usual professional medical care and/or medication. If abnormalities are detected during the measurement with the FH Vitals SDK, users are advised to consult a medical professional.

The FH Vitals SDK is indicated for use in humans 18 years of age or older who do not require critical care or continuous vital signs monitoring. This software should not be the primary or sole method for assessing an individual's health.

Device Description

FH vitals SDK is a video-based, non-contact pulse rate measurement software with a face recognition function designed to measure and real-time display the pulse rate of adults. This system uses cameras to detect the user's face and obtains the continuous face image data, with signal processing and algorithm to compute the pulse rate. The software is intended to be installed on commercial mobile devices/laptops/computers equipped with cameras. It can be deployed on Android, iOS platform and Windows platforms.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study details for the FaceHeart Vitals Software Development Kit (FH vitals SDK):

1. Table of Acceptance Criteria and Reported Device Performance:

Acceptance Criteria (Performance)	Reported Device Performance (FH vitals SDK)
Pulse Rate Measurement Range	50-180 bpm
Performance (Error Level)	±3 bpm

The document notes that the predicate device had a pulse rate measurement range of 50-130 bpm and the same performance error level of ±3 bpm. The FH vitals SDK can measure a wider range of pulse rates.

2. Sample Size Used for the Test Set and Data Provenance:

Sample Size: 527 participants.
Data Provenance: The document does not explicitly state the country of origin. It indicates it was a "clinical study," which implies it was prospective data collection.

3. Number of Experts Used to Establish Ground Truth and Qualifications:

The document does not specify the number of experts used or their qualifications for establishing the ground truth.

4. Adjudication Method for the Test Set:

The document does not specify an adjudication method. It implies a direct comparison to the reference device.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

A multi-reader multi-case (MRMC) comparative effectiveness study was not conducted or reported. The study compares the stand-alone performance of the FH Vitals SDK to a reference device.

6. Stand-Alone Performance (Algorithm Only without Human-in-the-Loop Performance):

Yes, a standalone performance study was done. The clinical study compares the FH Vitals SDK's pulse rate measurements against a reference device (Philips MX100 ECG) without human assistance being part of the measurement process.

7. Type of Ground Truth Used:

The ground truth used was established by a clinically accurate patient-contacting relevant comparator device, specifically the Philips MX100 ECG.

8. Sample Size for the Training Set:

The document does not provide information on the sample size used for the training set. It mentions "Software documentation included a description of algorithm training and validation data," but does not give specific numbers for the training set itself.

9. How the Ground Truth for the Training Set Was Established:

The document does not explicitly state how the ground truth for the training set was established. It generally refers to "algorithm training and validation data" but doesn't detail the method for labeling or establishing truth for that data.

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services seal on the left and the FDA acronym along with the full name of the agency on the right. The seal features a stylized depiction of a human figure, while the FDA part includes the acronym in a blue square and the words "U.S. FOOD & DRUG ADMINISTRATION" in blue.

September 1, 2023

FaceHeart Corp. Morris Chung AVP PO Box 309, Ugland House Grand Cayman, KY1-1104 Cayman Islands

Re: K223622

Trade/Device Name: FaceHeart Vitals Software Development Kit (FH vitals SDK) Regulation Number: 21 CFR 870.2785 Regulation Name: Software for optical camera-based measurement of pulse rate, heart rate, breathing rate, and/or respiratory rate Regulatory Class: Class II Product Code: QME Dated: July 29, 2023 Received: July 31, 2023

Dear Morris Chung:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

{1}------------------------------------------------

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely.

Jennifer W. Shih -S

Jennifer Kozen Assistant Director Division of Cardiac Electrophysiology, Diagnostics and Monitoring Devices Office of Cardiovascular Devices Office of Product Evaluation and Ouality Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Indications for Use

Form Approved: OMB No. 0910-0120 Expiration Date: 06/30/2023 See PRA Statement below.

Submission Number (if known)

K223622

Device Name

FaceHeart Vitals Software Development Kit (FH vitals SDK)

ndications for Use (Describe)

Type of Use (Select one or both, as applicable)

Prescription Use (Part 21 CFR 801 Subpart D)

Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{3}------------------------------------------------

| FaceHeart

510(k) Summary

[This summary is submitted according to the requirements of 21 CFR 807.92]

1. Submitter's Name, Address and Date prepared:

Applicant	FaceHeart CorporationPO Box 309, Ugland House, Grand Cayman, KY1-1104,Cayman Islands.
Correspondent	Name: Morris ChungAddress: Rm.1003, 10F., Jan Qi Biomedical Engineering Building,No.75, Bo'ai St., East Dist., Hsinchu City 300,Taiwan (R.O.C.)Phone: +886-3-6591088Email: ml.chung@faceheart.com
Date Prepared	August 31, 2023

2. Device Names and Classifications

Proposed Device

Name of ProposedDevice	FH vitals SDK
Common Name:	Pulse Rate Measuring Software
Regulation Number	21 CFR 870.2785
Regulation Name	Software for optical camera-based measurement of pulse rate, heart rate,breathing rate, and/or respiratory rate
Regulatory Class	Class II
Product Code	QME
Review Panel	Cardiovascular

Predicate Device

PredicateManufacturer	Oxehealth Limited
---------------------------	-------------------

{4}------------------------------------------------

Heart

Predicate TradeName	Oxehealth Vital Signs
Predicate 510 (k)	K211906

3. Device Description:

It is the responsibility of the device manufacturer to integrate FH vitals SDK correctly and to obtain the necessary regulatory approval/clearance for the final device integrating FH vitals SDK. It is also the responsibility of the device manufacturer to ensure that their device or software application has the correct regulatory approvals and meets the required standards for their intended use. Any regulatory clearance and tests FH vitals SDK has do not apply to a device or software integrating FH vitals SDK. These processes and tests should be repeated at the system level.

4. Indications for Use:

{5}------------------------------------------------

e Heart

are detected during the measurement with the FH Vitals SDK, users are advised to consult a medical professional.

5. Technological Characteristics:

Similar to the predicate device, the FH vitals SDK is a software-only product that measures pulse rate through an optical camera-based mechanism.

This software intended to run on standard PCs, laptops, and mobile devices, analyzing video streams captured by compatible available video cameras to compute pulse rate.

This software is intended to analyze video collected by compatible cameras in stationary conditions. Users are instructed to keep the camera stationary (e.g., by using a stand or another suitable support). When integrating this software for use with camera signals from devices with accelerometers (e.g., smartphones), the manufacturer is instructed to use accelerometer data to only use this software with video collected when the camera is stationary.

6. Comparison with the Predicate Device (Substantial Equivalence):

	Subject Device	Predicate Device	Comparison
510(k) Number	K223622	K211906
Device Name	FH vitals SDK	Oxehealth Vital Signs
Common Name	Pulse Rate Measuring Software	Vital Signs
Manufacturer	FaceHeart Corp.	Oxehealth Ltd
Indications forUse	The FH Vitals SDK is designed to measure the pulse ratebased on the given facial video stream. It is intended for non-invasive spot measurements of pulse rate when the subject isstill. This SDK is not intended for use in patients withknown or suspected heart arrhythmias.While the SDK can be used for general healthcare, it is notdesigned to treat patients. The pulse rate measurementresults provided by the FH Vitals SDK should complement,but not replace, the user's usual professional medical careand/or medication. If abnormalities are detected during themeasurement with the FH Vitals SDK, users are advised toconsult a medical professional.The FH Vitals SDK is indicated for use in humans 18 years ofage or older who do not require critical care or continuous vitalsigns monitoring. This software should not be the primaryor sole method for assessing an individual's health.	Non-invasive spot checkmeasurements of pulse rateand breathing rate (chestwall movements).The Oxehealth Vital Signsdevice is intended fornoninvasive spotmeasurements of pulse rateand estimated breathingrate (chest wallmovements) when thesubject is still. It is softwareassessing video footagefrom a fixed-installationsolution for use withinsingle occupancy roomswithin hospitals, generalcare, and securedenvironments withprofessional healthcareoversight and where aframework exists whichmandates periodic checksby a trained professional toensure subject safety.The Oxehealth system isintended for use byappropriately trained staffwith a duty of care andshould not be used byuntrained users.The Oxehealth Vital Signsdevice is indicated for useon humans 18 years of agefor older who do not requirecritical care or continuousvital signs monitoring.The device is not intendedto be the sole method ofchecking the physicalhealth of a subject.	Similar.FaceHeart'sindications area subset of theOxeHealthVital Signsindications
Component	Software Only	Software Only	Same
Patient Type	Adults not requiring critical care	Adults not requiringcritical care	Same
UseEnvironment	Light source: above 300 Lux (Depends on camera)Measuring distance: 0.5-1.5m (Depends on camera)	In the presence of sourcesof flashing or variable light,including other NearInfrared illumination.	Different

Table 1. Substantial Equivalent (SE) Comparison Summary

{6}------------------------------------------------

F | Face Heart

{7}------------------------------------------------

F | Face Heart

Pulse RateMeasurementRange		50-180 bpm					50-130 bpm	Similar: FHvitals SDK canmeasure awider range ofpulse rate
Performance(Error Level)		±3 bpm					±3 bpm	Same
MeasurementWindow		1 min					9 seconds	Different
CompatibilitywithHardware-computing		The pulse rate measurement feature of FH Vitals SDK is asoftware product that exclusively supports the following threeoperating systems:• Windows 10• Android 12• iOS 12					Standard, off the shelfcomputers and mobiletablets, specified andinstalled by Oxehealth, andvalidated duringinstallation.Installation will be carriedout by an Oxehealthapproved installer,according to installationinstructions andverification proceduresprovided by Oxehealth.	Different
Compatibilitywith Hardware-Camera andAccessories	Item	C920 +Laptop	iPhone13 Pro	iPhone13 ProMax	SamsungS22Ultra	SamsungS22+	Standard, off the shelfmachine vision camera andinfrared illuminators, exactspecification determined byOxehealth and validatedduring installation	Different
	Camera FOV	78°	77°	80°	80°
	CameraSensor Size	1/3"	1/3.6"		1/2.82"	1/3.24"
	CameraApertureSize	F2.0	F2.2		F2.2	F2.2
	Streaming	VGA @ 30fps
	CPU	Intel i7-1165G7	A15		1 x Cortex X23 x Cortex A7104 x Cortex A510
	GPU	Intel IrisXeGraphics			Adreno 730
	OS	Windows10	iOS 12		Android 12
	OutputRange	Heart Rate: 50~180 bpm
	Output Time	1 min
	MemoryRequirement	500 MB and above
	OperatingRestriction		• Required to stay steady during measurement.• Support minor movement (speak or nodslightly)
	ApplicableEnvironment		• Illumination: above 300 lux• Measuring distance: 0.5-1.5m
Software	Error Level	within±3 bpm				C++/Java/Objective-C++	C++ and Node.js; use of3rd party libraries	Different

{8}------------------------------------------------

FaceHeart

7. Clinical Performance Data

FH vitals SDK was verified and validated in accordance with the special controls for optical camera-based measurement of pulse rate, heart rate, breathing rate, and/or respiratory rate (21 CFR 870.2785-Reclassification Order of DEN200019). The testing demonstrated that the device performed according to its specifications and that the technological and performance criteria were comparable to the predicate device.

Performance data is demonstrated by 1000-CSR-02-V2.0 clinical studies Report. The performance of the FH vitals SDK was tested in a clinical study of 527 participants, age 18 and older. Study demographic characteristics are summarized in Table 2.

Sample size	N=527
Gender	Females: 314 subjects Males: 213 subjects
Age Group	18-39: 213 subjects 40-59: 184 subjects Above 60:
BMI	0-18.5: 29 subjects 18.5-24.9: 270 subjects 25-29.9: 149 subjects 30+: 79 subjects
Makeup	With: 44 subjects Without: 483 subjects
Glasses	With: 183 subjects Without: 344 subjects
Facial hair	With: 48 subjects Without: 419 subjects
Skin typeaccording toFitzpatrick Scale	Types I and II: The number of subjects was 34 Types III and IV: The number of subjects was 410 Types V and VI: The number of subjects was 83
Facial Shapes	Heart: 28 subjects Oblong: 169 subjects Oval: 58 subjects Round: 232 subjects Square: 40 subjects

Table 2. Clinical Validation Study subject demographic

{9}------------------------------------------------

aceHeart

Disease History	Arrhythmia: 55 subjects Coronary Artery Disease (CAD): 90 subjects Heart Failure (HF): 23 subjects Hypertension: 125 subjects Other CVDs> 21 subjects
-----------------	-------------------------------------------------------------------------------------------------------------------------------------------------------

The data showed that compared with Philips MX100 ECG, the pulse rate deviation of FH Vitals SDK installed on laptops with C920, iPhone 13 Pro, iPhone 13 Pro Max, Samsung S22 Ultra, and Samsung S22+ were within +3bpm, accounting for about 90.3, 95.4%, 95.4%, 93.7%, and 94.3% in 527 subjects, respectively. On average, about 93.8% of the 527 subjects.

8. Non-Clinical Software Testing:

Our software underwent comprehensive non-clinical testing, as detailed in the "Full System Testing" report. Importantly, these tests were conducted on a system that integrates with our device and represents the final configuration. This testing approach encompassed both functionality tests and system performance tests.

. Device Compatibility:

The software's compatibility was verified on specific devices, ensuring that the final application functions correctly. The tested devices are as follows:

. Laptop (Asus Zenbook UX435EAL) with C920
. iPhone 13 Pro
iPhone 13 Pro Max
. Samsung S22+
Samsung S22

. Motion Impact on Performance Decay

According to our internal test, under the scenario of doing exercise or performing large movement, the mean absolute error of pulse rate measurement can range from 11.77 bpm to 42.06 bpm. Such error range indicates that motion has significant impact on the precision of pulse rate measurement.

{10}------------------------------------------------

FaceHeart

. Software Functionality:

The software is designed to track only one face, even in scenarios where multiple faces are present within the image frames. All warning messages were also validated to ensure they are triggered appropriately.

Scenario	Software Response
There are multiple faces in camera view.	The software tracks only one face during the measurement.
Use a finger to cover the camera.	Warning message: Missing Face.
Use a hand to cover the face.	Warning message: Missing Face.
Turn off lights in the room to make the face unrecognizable.	Warning message: Missing Face.
Enlarge the camera focus to have a blurred face which is unrecognizable.	Warning message: Missing Face.
Wear a hat to block a large portion of the face.	Warning message: Missing Face.
Wear a facial mask.	Warning message: Missing Face.
Make the face outside Rectangle.	Warning message: Bad Face Position.
Make the face-camera distance larger than 1.5M.	Warning message: Bad Face Position.
Nod slightly.	Warning message: Motion.
Shake the head slightly.	Warning message: Motion.
Move back and forth.	Warning message: Motion.
Stand up suddenly.	Warning message: Motion.
Shake the camera.	Warning message: Motion.
Low camera frame rate.	Warning message: Low Frame Rate.

. System Performance Metrics:

For each device, the following performance metrics were observed:

Device	Memory (MB)	CPU (%)	Average Image FrameProcessing Time:Time Cost (ms/frame)
C920 with Asus Zenbook UX435EAL	155	10	4.09
iPhone 13 Pro	58.5	43	3.58
iPhone 13 Pro Max	46.3	40	3.91
Samsung S22+	187	10	9.79
Samsung S22 Ultra	225	10	8.71

It's worth noting that the image processing speed of the software exceeds the frame rate of the camera, indicating that device performance meets real-time requirements.

{11}------------------------------------------------

1 FaceHeart

9. Consideration of Special Controls Guidance

In combination with the general controls of the FD&C Act, the software for optical camerabased measurement of pulse rate, heart rate, breathing rate, and/or respiratory rate (products submitted under 21 CFR 870.2785-Reclassification Order of DEN200019) is subject to the following special controls:

Special controls	Evidence of compliance
(1) A software description and the results of verification andvalidation testing based on a comprehensive hazard analysisand risk assessment must include:(i)A full characterization of the software technicalparameters, including algorithms;(ii)If required image acquisition hardware is not includedwith the device, full specifications of the hardwarerequirements and testing to demonstrate the specifiedhardware ensures adequate data for validated andaccurate measurements.(iii)A description of the expected impact of all applicablesensor acquisition hardware characteristics andassociated hardware specifications;(iv)A description of all mitigations for user error orfailure of any subsystem components (including signaldetection, signal analysis, data display, and storage) onoutput accuracy; and(v)Software documentation must include a cybersecurityvulnerability and management process to assure softwarefunctionality.	Softwaredocumentation includeda description ofalgorithm training andvalidation data, adiscussion of thespecifications ofcompatible hardware andthe impact of thesespecifications on thedevice, and testing of allmitigations for user error.Software documentationalso includedcybersecurity testing anda vulnerability analysis.
(2) Clinical data must be provided. This assessment mustfulfill the following:(i)The clinical data must be representative of the intendeduse population for the device. Any selection criteria orsample limitations must be fully described and justified.(ii)The assessment must demonstrate output consistencyusing the expected range of data sources and data qualityencountered in the intended use population andenvironment.(iii)The assessment must compare device output with aclinically accurate patient-contacting relevant comparatordevice in an accurate and reproducible manner.	Clinical validation studyis provided in Section 7above.
(3) A human factors and usability engineering assessmentmust be provided that evaluates the risk of impropermeasurement.	A Use-Related-Risk-Analysis was conductedand A Human FactorsValidation Study wasconducted with 15 healthcare providers and 15patients that showed
	minimal user errors, closecalls, or use difficulties.
(4) Labeling must include:(i) A description of what the device measures and outputsto the user;(ii) Warnings identifying sensor acquisition factors orsubject conditions or characteristics (garmenttypes/textures, motion, etc.) that may impactmeasurement results;(iii) Guidance for interpretation of the measurements,including a statement that the output is adjunctive toother physical vital sign parameters and patientinformation;(iv) The expected performance of the device for allintended use populations and environments; and(v) Robust instructions to ensure correct system setup.In addition, this is a prescription device and must comply with21 CFR 801.109.	Labeling requirementsare incorporated in theuser manuals.

{12}------------------------------------------------

Heart

10. Conclusion

In conclusion, the FH Vitals SDK shares a similar intended use to that of the already cleared predicate device, with its function encapsulating a subset of the features provided by the Oxehealth systems. Moreover, the proposed device aligns closely in technological characteristics and operational principles with the predicate device. The distinctions that do exist between the two devices do not introduce additional concerns regarding safety or performance. Consequently, we posit that the FH Vitals SDK is substantially equivalent to the predicate device.

Regulation Number and Section

§ 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.