The Samsung ECG app with IHRN is an over-the-counter (OTC) software-only, mobile medical application operating on a compatible Samsung Galaxy Watch and Phone for informational use only in adults 22 years and older. The app analyzes pulse rate data to identify episodes of irregular heart rhythms suggestive of atrial fibrillation (AFib) and provides a notification suggesting the user record an ECG to analyze the heart rhythm. The Irregular Heart Rhythm Notification Feature is not intended to provide a notification on every episode of irregular rhythm suggestive of AFib and the absence of a notification is not intended to indicate no disease process is present; rather the feature is intended to opportunistically acquire pulse rate data when the user is still and analyze the data when determined sufficient toward surfacing a notification.

Following this prompt, or based on the user's own initiative, the app is intended to create, record, store, transfer, and display a single channel ECG, similar to a Lead I ECG. Classifiable traces are labeled by the app as sinus rhythm. AFib. high heart rate (non-AFib), or AFib with high heart rate with the intention of aiding heart rhythm identification.

The app is not intended for users with other known arrhythmias, and it is not intended to replace traditional methods of diagnosis or treatment. Users should not interpret or take clinical action based on the device output without consultation of a qualified healthcare professional.

Device Description

The Samsung ECG App v1.3 is a software as a medical device (SaMD) that consists of a pair of mobile medical apps: one app on a compatible Samsung wearable and the other on a compatible Samsung phone, both general-purpose computing platforms.

When enabled, the wearable application of the SaMD uses a wearable photoplethysmography (PPG) sensor to background monitor cardiac signals from the user. The application examines beat-to-beat intervals and generates an irregular rhythm notification indicative of atrial fibrillation (AFib). Upon receiving an irregular rhythm notification or at their discretion, the user can record a single-lead ECG using the same wearable. The wearable application then calculates the average heart rate from the ECG recording and produces a rhythm classification. The wearable application also securely transmits the data to the ECG phone application on the paired phone. The phone application shows a time-stamped irregular rhythm notification history with heart rate information; ECG measurement history; and generates a PDF file of the ECG signal, which the user can share with their healthcare provider.

AI/ML Overview

Acceptance Criteria and Device Performance for Samsung ECG App v1.3

1. Acceptance Criteria and Reported Device Performance

Parameter	Acceptance Criteria (Reference Device: Apple ECG 2.0 App K201525)	Reported Device Performance (Samsung ECG App v1.3)
Heart Rate 50-150 BPM
AFib Sensitivity	98.5% (95% CI 97.3%, 99.6%)	96.0% (95% CI 94.0%, 97.8%)
Sinus Rhythm Specificity	99.3% (95% CI 98.4%, 100%)	98.7% (95% CI 94.0%, 97.8%)
Heart Rate 100-150 BPM
AFib Sensitivity	90.7% (95% CI 86.7%, 94.6%)	93.6% (95% CI 88.5%, 97.5%)
Sinus Rhythm Specificity	83% (95% CI 77.8%, 88%)	96.3% (95% CI 93.5%, 98.9%)
Visually Interpretable Waveforms	Not explicitly stated for reference device, but implied by "sufficient" signal quality	98.7% of cases
Accuracy of Key Intervals (RR, PR, QRS) and R-wave amplitude	Not explicitly stated for reference device, but implied by "sufficient" signal quality	Accurately measured when compared against standard Lead I ECG

Note: The reported performance for Samsung ECG App v1.3's "Sinus rhythm (HR 50-150 BPM)" and "AFib (HR 50-150 BPM)" is presented with the same 95% CI: (94.0%, 97.8%). This might be a transcription error in the document, as specificity and sensitivity for different conditions would typically have distinct confidence intervals. Assuming independent calculations, these values are presented as they appear in the source.

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

Sample Size: 1,013 subjects. These subjects contributed to 453 AFib recordings (heart rate 50 to 150 BPM) and 691 Sinus rhythm recordings (heart rate 50 to 150 BPM) for the primary endpoint analysis.
Data Provenance: The study was a multi-center study, implying data from multiple locations, likely within the US given the FDA submission context and the racial demographics provided (predominantly Caucasian). The study was likely prospective as it involved recruiting subjects and collecting data for validation.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications

The document does not explicitly state the "number of experts" or their specific "qualifications" used to establish the ground truth for the test set. It mentions "Clinical Validation showing comparable clinical performance...compared to the reference device" and that the "ECG function accurately classified...compared against the standard Lead I ECG," implying that comparison was made to physician-adjudicated or expertly interpreted ECGs, but the details of the ground truth establishment are not provided.

4. Adjudication Method for the Test Set

The document does not explicitly state the adjudication method used for establishing the ground truth for the test set.

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

There is no mention of a Multi Reader Multi Case (MRMC) comparative effectiveness study being done, or any effect size of how much human readers improve with AI vs without AI assistance. The study focuses on the standalone performance of the device's ECG rhythm classification compared to a reference device.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

Yes, a standalone study was conducted. The "Clinical Validation" section details the performance of the "ECG rhythm classification of the Samsung ECG App v1.3" in terms of sensitivity and specificity against a clinical ground truth, without explicit human-in-the-loop interaction for the classification task itself. The device "accurately classified" recordings.

7. Type of Ground Truth Used

The ground truth used was clinical diagnosis based on "446 subjects diagnosed with AFib, 536 subjects without AFib, and 31 subjects diagnosed with another type of irregular rhythm." The performance was evaluated by comparing the device's classifications against "standard Lead I ECG" interpretation, implying expert consensus (from qualified healthcare professionals interpreting the standard ECGs) or clinical diagnosis as the ground truth.

8. Sample Size for the Training Set

The document does not specify the sample size for the training set. It focuses on the validation study.

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

The document does not provide information on how the ground truth for the training set was established.

Summary

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

Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

August 2, 2024

Samsung Electronics Co., Ltd % Matthew Wiggins Sr. Director of Digital Health Commercialization Samsung Research America Inc. 665 Clyde Avenue Mountain View, California 94043

Re: K240909

Trade/Device Name: Samsung ECG App v 1.3 (ECG) Regulation Number: 21 CFR 870.2345 Regulation Name: Electrocardiograph Software For Over-The-Counter Use Regulatory Class: Class II Product Code: QDA, QDB Dated: July 3, 2024 Received: July 3, 2024

Dear Matthew Wiggins:

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 (the 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 available 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.

Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device"

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

(https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).

Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30. Design controls; 21 CFR 820.90. Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review. the OS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).

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 Part 803) for devices or postmarketing safety reporting (21 CFR Part 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 Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 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.

Kimberly Crowley

For: Jennifer Shih Kozen Assistant Director DHT2A: Division of Cardiac Electrophysiology, Diagnostics, and Monitoring Devices OHT2: Office of Cardiovascular Devices

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

Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

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

Indications for Use

Submission Number (if known)

K240909

Device Name

Samsung ECG App v 1.3 (ECG)

Indications 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."

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

K240909 - Samsung ECG App v1.3

Applicant Information
Manufacturer:	Samsung Electronics Co., Ltd129, Samsung-ro, Yeongtong-gu, Suwon-si, Gyeonggi-do 16677, Korea
Contact Person:	Matthew Wiggins, Ph.D.Samsung Research America665 Clyde Avenue, Mountain View, CA 940431-650-770-5804m.wiggins@samsung.com
Date Prepared:	July 3rd, 2024
Device Information
Trade/Device Name:	Samsung ECG App v1.3
Classification:	QDA - Electrocardiograph software for over-the-counter use (21 CFR 870.2345) QDB - Photoplethysmograph Analysis Software For Over-The-Counter Use (21 CFR 870.2790)
Predicate Device:	Primary: Samsung ECG Monitor App with Irregular Heart Rhythm Notification Feature (K230292)
Reference Device	Apple ECG 2.0 App (K201525)

Device Description

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

Intended Use/Indications for Use

The subject device's indications for use include the new classifiable ECG rhythms, High heart rate and Atrial fibrillation with high heart rate, while maintaining its background AFib monitoring and on-demand ECG classification intended uses. The updated indications for use are provided below.

The Samsung ECG with IHRN 2.0 is an over-the-counter (OTC) software-only, mobile medical application operating on a compatible Samsung Galaxy Watch and Phone for informational use only in adults 22 years and older. The app analvzes pulse rate data to identify episodes of irregular heart rhvthms suggestive of atrial fibrillation (AFib) and provides a notification suggesting the user record an ECG to analyze the heart rhythm. The Irregular Heart Rhythm Notification feature is not intended to provide a notification on every episode of irregular rhythm suggestive of AFib and the absence of a notification is not intended to indicate no disease process is present; rather the feature is intended to opportunistically acquire pulse rate data when the user is still and analyze the data when determined sufficient toward surfacing a notification.

Following this prompt, or based on the user's own initiative, the app is intended to create, record, store, transfer, and display a single channel ECG, similar to a Lead I ECG. Classifiable traces are labeled by the app as sinus rhythm, AFib, high heart rate (non-AFib), or AFib with high heart rate with the intention of aiding heart rhythm identification.

Comparison of Technological Characteristics

The ECG function of the subject device is substantially equivalent to the predicate and reference devices. Using the dry electrodes on the Galaxy Watch wearable, the user can record an on-demand ECG recording, similar to Lead I ECG, without requiring a physician visit. This function enables users to easily and more frequently record their ECG, and consult with their qualified healthcare provider. The updates to the ECG function primarily consist of expansion of classifiable ECG heart rates up to 150 beats per minutes, consistent with the reference Apple ECG 2.0 App (K201525).

The IHRN function of the subject device, including user workflow, sensor and algorithm function, and device output remains substantially equivalent to the predicate device, where it uses Photoplethysmograph (PPG) technology to extract rhythm information and notify the user when consistent tachograms are classified as a rhythm suggestive of Atrial Fibrillation.

A more detailed comparison between the subject device, the predicate device (Samsung ECG Monitor App with IHRN Feature, K230292), and the reference device (Apple's ECG 2.0 App, K201525) is provided in Table 1.

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

	Table 1. Technological Comparison of Subject Device, Predicate Device, and Reference Device
--	---------------------------------------------------------------------------------------------	--	--	--	--	--	--	--

	Subject Device:Samsung ECG App v1.3	Predicate Device:Samsung ECG Monitor App with IHRNFeature (K230292)	Reference Device:ECG 2.0 App (K201525)	Differences and Discussion
Key PlatformSensor (ECG)	Lead I Electrocardiogram (ECG) acquiredfrom the dorsal side of the wrist to theopposing hand's finger, which is placed onthe watch body.	Lead I Electrocardiogram (ECG) acquiredfrom the dorsal side of the wrist to theopposing hand's finger which is placed onthe watch body.	A single channelelectrocardiogram (ECG) similarto a Lead I ECG. Taken fromelectrodes on the back of thewatch on one had to the digitalcrown where the finger is placed	Identical to the Predicate Device.
Key PlatformSensor (IHRN)	Green wavelength PPG on the back side ofthe watch for contact with the dorsal side ofthe wrist.	Green wavelength PPG on the back side ofthe watch for contact with the dorsal side ofthe wrist.	N/A	Identical to the Predicate Device.
Platform(s)	• Samsung Galaxy Watch5 wearablerunning Wear OS version 4.0.• Galaxy phones with Android 9 (Pie).	• Samsung Galaxy Watch4 wearable orlater running Wear OS version 4.0.• Samsung Galaxy phones with Android 9(Pie) and beyond	• Apple Watch Series 4 withwatch OS 7.0 or later• Apple iPhone 6s with iOS 14 orlater	Substantially equivalent to thePredicate Device.
User Interface	• Wearable screen for initiating ECGrecording, viewing signal during acquisition(user engagement feature, not diagnosticquality), delivering rhythm classification,and capturing user reported symptoms• Phone screen for viewing and sharing ECGrecoding results and PDF report includingrecorded ECG and algorithmic rhythmclassification• Phone screen for onboarding and educationmaterials	• Wearable screen for initiating ECGrecording, viewing signal duringacquisition (user engagement feature, notdiagnostic quality), delivering rhythmclassification, and capturing user reportedsymptoms.• Phone screen for viewing and sharingECG recoding results and PDF reportincluding recorded ECG and algorithmicrhythm classification• Phone screen for onboarding andeducation materials	• Apple watch screen for initiatingspot checks, viewing signalduring acquisition (userengagement feature, notdiagnostic quality), and deliveringrhythm classification andcapturing symptoms• Phone screen for viewing andsharing ECG spot check results,viewing historic data and PDFreport including recorded ECGand algorithmic rhythmclassification	Substantially equivalent to thePredicate Device for ECG andIHRN function.
RhythmClassificationResults	• ECG Lead I Rhythm Classification forSinus rhythm, Atrial fibrillation, Atrialfibrillation with high heart rate, Highheart rate (non-AF), Inconclusive (inc.heart rate out of range), or Poorrecording• ECG signal quality assessment forsufficient for analysis• Average heart rate	• ECG Lead I Rhythm Classification forSinus rhythm, Atrial fibrillation,Inconclusive (heart rate out of range),or Poor recording (poor signal quality)• ECG signal quality assessment forsufficient for analysis• Average heart rate	• ECG Lead I RhythmClassification for Sinus Rhythm,Atrial Fibrillation, High heartrate, Inconclusive, PoorRecording• Heart Rate High/Low Indicator	Substantially equivalent to theReference Device.Due to expanded heart rate rangein the subject device, newclassifications for high heart rate(≥100 BPM and ≤ 150 BPM) arecreated [high heart rate (non-AFib), and AFib with high heartrate].
	Subject Device:Samsung ECG App v1.3	Predicate Device:Samsung ECG Monitor App with IHRNFeature (K230292)	Reference Device:ECG 2.0 App (K201525)	Differences and Discussion
ECG RhythmClassificationPerformance	HR 50-150 BPM• Sinus rhythm■ Specificity: 98.7% (95% CI 94.0%,97.8%)• Atrial Fibrillation■ Sensitivity: 96.0% (95% CI 94.0%,97.8%)HR 100-150 BPM• Sinus rhythm■ Specificity: 96.3% (95% CI 93.5%,98.9%)• Atrial fibrillation■ Sensitivity: 93.6% (95% CI 88.5%,97.5%)	• Sinus rhythm (HR 50-100 BPM)■ Specificity: 100% (95% CI 100%,100%)• Atrial fibrillation (HR 50-120 BPM)■ Sensitivity: 98.1% (95% CI 96.3%,99.9%)Note: ECG performance was establishedin K201168 and maintained in K230292 asthe ECG capability is equivalent betweendevices.	HR 50-150 BPM• Sinus Rhythm■ Specificity: 99.3% (95%CI 98.4%, 100%)• Atrial Fibrillation■ Sensitivity: 98.5% (95% CI97.3%, 99.6%)HR 100-150 BPM• Sinus Rhythm■ Specificity: 83% (95% CI77.8%, 88%)• Atrial Fibrillation■ Sensitivity: 90.7% (95% CI86.7%, 94.6%)	AF sensitivity and SR specificitywith all heart rate and high heartrate is substantially equivalent tothe Reference Device's pointestimate level and lowerconfidence bound performance.The IHRN function's performancehas not changed from the PredicateDevice.

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

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

Performance Data

The following clinical, usability, and bench testing were conducted, showing that the updated ECG function of the subject SaMD meets predetermined acceptance criteria to demonstrate safety, effectiveness, and substantial equivalent to the reference Apple ECG 2.0 App. No new safety issues were found during this testing.

Clinical Validation showing comparable clinical performance in terms of: ●
- Subject-level ECG classification accuracy, measured by sensitivity and specificity, for all o classifiable heart rates (50-150 beats per minute) and high heart rate (100-150 beats per minute)
- ECG signal quality sufficiency o
Human Factors Validation
IEC 60601-2-47 ECG Database Testing
Heart Rate Accuracy Bench Testing
Artifact Detection Bench Testing
Software Verification Testing
Labeling Verification Testing ●

In addition, testing was performed on the commercial platform, showing it meets all necessary specifications to safely and effectively host the subject SaMD. This included the following:

ECG Signal Quality, Sampling Rate, Operating Conditions, and Lead Detection Bench Testing ●
Platform Interface Software Testing (Android and WearOS) ●
Platform Interface Hardware Testing
- General safety tests: Electrical safety, electromagnetic compatibility, radio frequency o emissions, material safety for skin contact, thermal safety for skin contact tests
- Device robustness tests: Resistance to electrostatic discharge, water ingress and breakage o tests

As the IHRN function of the subject device has not been functionally changed since the predicate device clearance as Samsung ECG Monitor App with IHRN Feature (K230292), clinical, human factors, and PPG confounder testing were not repeated.

Clinical Study

Our clinical validation testing results indicate that the ECG rhythm classification of the Samsung ECG App v1.3 has comparable classification accuracy compared to the reference device. Classification accuracy is measured in sensitivity and specificity.

The updated ECG function was validated in a multi-center study with 1.013 subjects who were 22 years old or older. The subject demographics is summarized in Table 2 below. The study enrolled 446 subjects diagnosed with AFib, 536 subjects without AFib, and 31 subjects diagnosed with another type of irregular rhythm. These enrolled subjects contributed to 453 AFib recordings (heart rate 50 to 150 BPM) and 691 Sinus rhythm recordings (heart rate 50 to 150 BPM) for the primary endpoint analysis.

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

Parameter	Description	Percentage
Age	Mean	57.6
Age	Standard Deviation	18.3
Gender	Female	46.1%
Gender	Male	53.9%
Ethnic Group	Hispanic or Latino	6.4%
Ethnic Group	Non-Hispanic or Latino	93.6%
Race	American Indian or Alaska Native	0.4%
Race	Asian	2.2%
Race	Black or African American	8%
Race	Pacific Islander	0.2%
Race	Caucasian	87.7%
Race	Other	1.5%

Table 2. Clinical Validation Testing Subject Demographics

The ECG function accurately classified 435 out of the 453 AFib recordings with a sensitivity of 96.0% and classified 682 out of the 691 Sinus rhythm recordings with a specificity of 98.7%. There were no clinically meaningful difference in classification performance for age and gender demographic groups. The ECG App version 1.3 also produced visually interpretable waveforms in 98.7% of the cases. Furthermore, the key intervals (RR, PR, QRS) and R-wave amplitude of the waveforms were accurately measured when compared against the standard Lead I ECG.

Conclusion

The subject device and combined predicate and reference devices have intended use, the same key technological characteristics, and the same signal-acquisition capabilities. In clinical testing, the Samsung's updated ECG function demonstrated that it has comparable ECG rhythm classification accuracy performance as the Apple ECG 2.0 App. Therefore, Samsung ECG v1.3 is substantially equivalent to the Samsung ECG Monitor App with IHRN Feature (K230292) and the Apple ECG 2.0 App (K201525).

Regulation Number and Section

§ 870.2345 Electrocardiograph software for over-the-counter use.

(a)
Identification. An electrocardiograph software device for over-the-counter use creates, analyzes, and displays electrocardiograph data and can provide information for identifying cardiac arrhythmias. This device is not intended to provide a diagnosis.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Clinical performance testing under anticipated conditions of use must demonstrate the following:
(i) The ability to obtain an electrocardiograph of sufficient quality for display and analysis; and
(ii) The performance characteristics of the detection algorithm as reported by sensitivity and either specificity or positive predictive value.
(2) Software verification, validation, and hazard analysis must be performed. Documentation must include a characterization of the technical specifications of the software, including the detection algorithm and its inputs and outputs.
(3) Non-clinical performance testing must validate detection algorithm performance using a previously adjudicated data set.
(4) Human factors and usability testing must demonstrate the following:
(i) The user can correctly use the device based solely on reading the device labeling; and
(ii) The user can correctly interpret the device output and understand when to seek medical care.
(5) Labeling must include:
(i) Hardware platform and operating system requirements;
(ii) Situations in which the device may not operate at an expected performance level;
(iii) A summary of the clinical performance testing conducted with the device;
(iv) A description of what the device measures and outputs to the user; and
(v) Guidance on interpretation of any results.