(152 days)
The Withings Scan Monitor 2.0 is intended to record, store and transfer lead II and lead-III of a twochannel electrocardiogram (ECG). In addition, it calculates and displays leads I, aVF, aVL. The Withings Scan Monitor 2.0 also displays ECG rhythms and detects the presence of atrial fibrillation (when the monitor is prescribed or used under care of a physician).
The Withings Scan Monitor 2.0 is intended for use by healthcare professionals, patients with known or suspected heart conditions and health-conscious individuals.
The Withings Scan Monitor 2.0 is intended for adult patients in hospitals, clinics, long-term care facilities, and homes.
The Withings Scan Monitor 2.0 is a connected smart scale with a retractable handle, with Bluetooth and Wi-Fi capabilities that connects to a companion mobile application. The Withings Scan Monitor 2.0 is intended to create, record, store, transfer and display lead-III of a two-channel electrocardiogram (ECG).
When a user stands on the scale and holds the handle attached to it, a 30 second ECG recording begins. The Withings Scan Monitor 2.0 software analyzes data collected by the electrical sensors present on the scale to generate lead-III simultaneously and derive lead-I and leads aVR, aVF and aVL, calculate heart rate, and provide a rhythm classification to the user that is displayed on the scale. The companion application is intended to display, store, manage and share data.
The Withings Scan Monitor 2.0 classifies ECG signals as follows:
- Normal Sinus Rhythm
- Atrial Fibrillation
- Inconclusive
- Noise - Inconclusive
Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:
1. A table of acceptance criteria and the reported device performance
The document defines acceptance criteria primarily through the clinical study results and comparison to the predicate device.
| Acceptance Criteria | Reported Device Performance (Withings Scan Monitor 2.0) |
|---|---|
| AF detection sensitivity (all outputs) | 0.73 [95% CI lower bound: 0.639] |
| AF detection specificity (all outputs) | 0.955 [95% CI lower bound: 0.914] |
| AF detection sensitivity (AF/NSR only) | 0.989 [95% CI lower bound: 0.928] |
| AF detection specificity (AF/NSR only) | 0.994 [95% CI lower bound: 0.968] |
| Visibility accuracy of P-waves, QRS complexes, T-waves | Above 0.992 |
| Polarity accuracy of P-waves | 0.986 |
| Polarity accuracy of QRS complex | 0.948 |
| Polarity accuracy of T-waves | 0.911 |
| Standard deviation of difference in PR interval duration (vs 12-lead ECG) | < 20 ms |
| Standard deviation of difference in QRS width (vs 12-lead ECG) | < 20 ms |
| Standard deviation of difference in QT interval duration (vs 12-lead ECG) | 30.3 ms |
| Mean difference in heart rate (vs 12-lead ECG) | -0.96 bpm |
| Standard deviation of difference in heart rate (vs 12-lead ECG) | 3.81 bpm (below acceptable threshold of 10%) |
| Ability to classify heart rhythms | Successfully classified into Sinus Rhythm, Atrial Fibrillation, Inconclusive, or Noise. |
| Clinical equivalence of 6-lead ECG to standard 12-lead ECG | Demonstrated through P-wave, QRS, T-wave visibility and polarity accuracy, and duration differences of PR, QRS, QT intervals, and heart rate. |
| Equivalent performance to predicate device (Scan Monitor) in AF detection | Deemed equivalent despite minor sensitivity differences, as both meet confidence interval criteria and difference is not statistically significant. |
2. Sample size used for the test set and the data provenance
- Test Set 1: 137 participants
- Test Set 2: 262 participants
- Clinical Study Test Set (Validation): 274 patients (40 excluded from analysis, resulting in 234 analyzed patients for the confusion matrix).
- Data Provenance:
- Algorithm Test Data Sets (1 & 2): Not explicitly stated if retrospective or prospective, or country of origin, however, they are summarized with demographic characteristics.
- Clinical Study: Prospective, cross-sectional, diagnostic, multicentric, open-label study. No specific country mentioned, but typical for regulatory submissions, it would be a clinical site (or sites) adhering to relevant regulations.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Number of experts: Not explicitly stated as a specific count, but the document mentions that a "12-lead Reference ECG signals reviewed by cardiologists" was used as ground truth. This implies an expert review process by qualified cardiologists.
- Qualifications of experts: "Cardiologists." No further details on years of experience or sub-specialty are provided.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- The document states "12-lead Reference ECG signals reviewed by cardiologists" was used as the ground truth. It does not explicitly mention a specific adjudication method like 2+1 or 3+1. It suggests a single expert review or an implicit consensus process among cardiologists without detailing the mechanism.
5. 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, a multi-reader multi-case (MRMC) comparative effectiveness study evaluating human readers with AI assistance versus without AI assistance was not explicitly described in the provided text. The study primarily focuses on the standalone performance of the device's rhythm classification algorithm against expert-labeled 12-lead ECGs.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Yes, a standalone performance evaluation of the algorithm was done. The clinical study directly assesses the performance of the "rhythm classification algorithm ECG-SW1 running on the subject device Withings Scan Monitor 2.0" against the cardiologist-reviewed 12-lead ECGs. The confusion matrix and sensitivity/specificity calculations are for the device's algorithm output.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- The ground truth for the clinical study was established by expert review of 12-lead reference ECG signals by cardiologists.
8. The sample size for the training set
- The document states, "Publicly available datasets were utilized for the training datasets consist of several smaller datasets." It does not specify the exact sample size or number of ECG recordings used for the training set.
9. How the ground truth for the training set was established
- The ground truth for the training set was established using "Publicly available datasets." The specific methods for how the ground truth was originally established for these publicly available datasets are not detailed in this document. It implicitly relies on the quality and labeling of those common, openly accessible datasets.
{0}------------------------------------------------
Image /page/0/Picture/0 description: The image shows 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, with the letters "FDA" in a blue square. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
August 23, 2023
Withings Khushboo Surendran Regulatory Affairs Manager 2 rue Maurice Hartmann Issy-Les-Moulineaux, Ile-De-France 92130 France
Re: K230812
Trade/Device Name: Withings Scan Monitor 2.0 Regulation Number: 21 CFR 870.2340 Regulation Name: Electrocardiograph Regulatory Class: Class II Product Code: DPS, DXH Dated: July 21, 2023 Received: July 24, 2023
Dear Khushboo Surendran:
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.
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
{1}------------------------------------------------
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 (OS) 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 mediation-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 Shih Kozen Assistant Director Division of Cardiac Electrophysiology, Diagnostics and Monitoring Devices Office of Cardiovascular Devices Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
5. Indications for Use
DEPARTMENT OF HEALTH AND HUMAN SERVICES Food and Drug Administration Indications for Use
Form Approved: OMB No. 0910-0120 Expiration Date: June 30, 2023 See PRA Statement on last page
510(k) Number (if known)
Device Name
Withings Scan Monitor 2.0
Indications for Use (Describe)
The Withings Scan Monitor 2.0 is intended to record, store and transfer lead II and lead-III of a twochannel electrocardiogram (ECG). In addition, it calculates and displays leads I, aVF, aVL. The Withings Scan Monitor 2.0 also displays ECG rhythms and detects the presence of atrial fibrillation (when the monitor is prescribed or used under care of a physician).
The Withings Scan Monitor 2.0 is intended for use by healthcare professionals, patients with known or suspected heart conditions and health-conscious individuals.
The Withings Scan Monitor 2.0 is intended for adult patients in hospitals, clinics, long-term care facilities, and homes.
| Type of Use (Select one or both, as applicable) | ||||
|---|---|---|---|---|
| Prescription Use (Part 21 CFR 801 Subpart D)Subpart C) | >> Over-The-Counter Use (21 CFR 801 | |||
| 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. qov
{3}------------------------------------------------
510(k) Summary
1. Submitter
| Applicant: | Withings2 Rue Maurice HartmannIssy-Les-MoulineauxFrance 92130 |
|---|---|
| Submission Correspondent: | Khushboo SurendranRegulatory Affairs ManagerPhone: 857-233-2681Email: khushboo.surendran@withings.com |
| Date Prepared: | March 23, 2023 |
| 2. Subject device Information |
| Device Name: | Withings Scan Monitor 2.0 |
|---|---|
| Regulation name: | Electrocardiograph |
| Regulation number: | 21 CFR 870.2340 |
| Regulatory Class: | Class II |
| Product Code: | DPS, DXH |
| 510(k) review panel: | Cardiovascular |
3. Predicate device Information
| Predicate Manufacturer: | Withings |
|---|---|
| Predicate device name: | Scan Monitor |
| Predicate 510(k) number: | K201456 |
4. Description of the device
The Withings Scan Monitor 2.0 is a connected smart scale with a retractable handle, with Bluetooth and Wi-Fi capabilities that connects to a companion mobile application. The Withings Scan Monitor 2.0 is intended to create, record, store, transfer and display lead-III of a two-channel electrocardiogram (ECG).
When a user stands on the scale and holds the handle attached to it, a 30 second ECG recording begins. The Withings Scan Monitor 2.0 software analyzes data collected by the electrical sensors present on the scale to generate lead-III simultaneously and derive lead-I and leads aVR, aVF and aVL, calculate heart rate, and provide a rhythm classification to the user that is displayed on the scale. The companion application is intended to display, store, manage and share data.
The Withings Scan Monitor 2.0 classifies ECG signals as follows:
{4}------------------------------------------------
- Normal Sinus Rhythm ●
- Atrial Fibrillation ●
- Inconclusive
- . Noise - Inconclusive
5. Indications for Use/Intended Use:
The Withings Scan Monitor 2.0 is intended to record, store and transfer lead II of a two-channel electrocardiogram (ECG). In addition, it calculates and displays leads I, aVR, aVF, aVL.The Withings Scan Monitor 2.0 also displays ECG rhythms and detects the presence of atrial fibrillation (when the monitor is prescribed or used under care of a physician).
The Withings Scan Monitor 2.0 is intended for use by healthcare professionals, patients with known or suspected heart conditions and health-conscious individuals.
The Withings Scan Monitor 2.0 is intended for adult patients in hospitals, clinics, long-term care facilities, and homes.
| Characteristics | Subject device: WithingsScan Monitor 2.0 | Predicate device: ScanMonitor | Comparison to predicatedevice |
|---|---|---|---|
| DeviceName | Withings Scan Monitor 2.0 | Scan Monitor | NA |
| Number ofleads | 6-Lead | 1-Lead | Substantially equivalent. Theonly minor difference is thatthe subject device recordslead II and lead-III of atwo-channel electrocardiogram(ECG) and calculates lead I,whereas the predicate deviceanalyzes a single-channelECG and displays only lead IECG. Both devices use ECGLead I for rhythmclassification assessment.Lead II, lead III, aVR, aVF andaVL are for informationpurposes only and arevalidated in the clinical studyagainst the gold standard (12lead ECG). |
| Manufacturer | Withings | Withings | Identical |
| 510(k) | K230812 | K201456 | NA |
| RegulationNumber | 21 CFR 870.234021 CFR 870.2920 | 21 CFR 870.234021 CFR 870.292021 CFR 870.2700 | Identical, except for theregulation for oximeter whichdoes not apply to the subjectdevice |
| Class | II | II | Identical |
| 510(k)ReviewPanel | Cardiovascular | Cardiovascular | Identical |
| DeviceClass/Name | ElectrocardiographTransmitters and Receivers,Electrocardiograph,Telephone | ElectrocardiographTransmitters and Receivers,Electrocardiograph, TelephoneOximeter | Identical, except that thepredicate device can alsomeasure oxygen saturation ofarterial hemoglobin (%SpO2) |
| and therefore is also anoximeter | |||
| ProductCode | DPS, DXH | DPS, DXH, DQA | Identical, except that thepredicate device can alsomeasure oxygen saturation ofarterial hemoglobin (%SpO2)and therefore has anadditional product code (DQA) |
| Prescription/ OTC | Prescription and OTC | Prescription and OTC | Identical for the ECGacquisition and the atrialfibrillation detectionfunctionalities as Scan Monitorand Withings Scan Monitor2.0. |
| Intendeduse andIndicationsfor Use | The Withings Scan Monitor2.0 is intended to record,store and transfer lead II andlead-III of a two-channelelectrocardiogram (ECG). Inaddition, it calculates anddisplays leads I, aVR, aVF,aVL.The Withings Scan Monitor2.0 also displays ECGrhythms and detects thepresence of atrial fibrillation(when the monitor isprescribed or used under careof a physician).The Withings Scan Monitor2.0 is intended for use byhealthcare professionals,patients with known orsuspected heart conditionsand health-consciousindividuals.The Withings Scan Monitor2.0 is intended for adultpatients in hospitals, clinics,long-term care facilities, andhomes. | Scan Monitor is intended torecord, store and transfersingle-channelelectrocardiogram (ECG)rhythms.The Scan Monitor also displaysECG rhythms and detects thepresence of atrial fibrillation(when the monitor is prescribedor used under the care of aphysician).The Scan Monitor is intendedfor use by healthcareprofessionals, patients withknown or suspected heartconditions and health-consciousindividuals.The Scan Monitor is alsoindicated for use in measuringand displaying functionaloxygen saturation of arterialhemoglobin (%SpO2).The Scan Monitor is intendedfor adult patients in hospitals,clinics, long-term care facilities,and homes. | Substantially equivalent, Thepredicate device also allowsfor the measurement ofoxygen saturation of arterialhemoglobin (%SpO2) with thepredicate device. Both devicesrecord, store and displayECGs. |
| Intendedpopulation | Adults with known orsuspected heart conditionsand health-consciousindividuals | Adults with known or suspectedheart conditions andhealth-conscious individuals | Identical |
| EnvironmentUse | Hospitals, clinics, long termcare and home use | Hospitals, clinics, long-termcare and home use | Identical |
| TechnologicalCharacteristic | Subject device: WithingsScan Monitor 2.0 | Predicate device: ScanMonitor | Comparison to predicate device |
| Hardware Interface | Body Scan (scale) | Scan Watch (watch) | Substantially equivalent. Please refer tothe bench testing and clinical study reportthat demonstrate substantially equivalentperformance. Therefore, differences inhardware interface are substantiallyequivalent. |
| Principles ofOperation | User completes the circuitwith skin contact andhardware collects andtransmits electrical potentialsto the microcontroller unit toconvert and display ECGwaveform. After acquisition,the Withings Scan Monitor2.0 uses the ECG waveformsfrom the Withings BodyScan, and the Withings ScanMonitor 2.0 algorithmsprocess and classify thesignal and display theclassification to the user. | User completes the circuitwith skin contact andhardware collects andtransmits electrical potentialsto the microcontroller unit toconvert and display ECGwaveform. After acquisition,the Scan Monitor uses theECG waveforms from theWithings Scan Watch, and theWithings Scan Monitor 2.0algorithms process andclassify the signal and displaythe classification to the user. | Identical |
| Anatomicalsites | Fingers and feet. | Left hand fingers to right wristor vice versa | Substantially equivalent. The first maindifference between the two devices is thesite of ECG measurement. Please referto the bench testing results that show thatthe subject device has lower RMSEdistribution with a 12-lead ECG devicethan that of the predicate device andshow that ECG waveforms of thepredicate and subject devices areequivalent in terms of visibility of P-wave,T-wave, QRS complex visibility andpolarity and durations. Therefore theanatomical site differences do not raiseany issue of effectiveness in terms ofECG signal quality and also atrialfibrillation detection. |
| Acquisitionposition | Standing up on the device | Seated with arms rested on atable | Substantially equivalent. Please refer tothe bench testing results that show thatthe subject device has lower RMSEdistribution with a 12-lead ECG devicethan that of the predicate device andsubject devices are equivalent in terms ofvisibility of P-wave, T-wave, QRScomplex visibility and polarity anddurations. Therefore the acquisition sitedifference does not raise any issue ofeffectiveness in terms of ECG signalquality and also atrial fibrillation detection. |
| Number of ECGmeasuringelectrodes | Three ECG measuringelectrodes | Two ECG measuringelectrodes | Substantially equivalent. The secondmain difference between the two devicesis the number and function of the ECGelectrodes, resulting in the differentnumber of leads. The subject device hasthree (3) ECG measuring electrodes thatcome in contact with left fingers, rightfingers, left foot, whereas the predicatehas two (2) ECG measuring electrodesthat come in contact with the wrist. |
| Number offeedbackelectrodes | Two (2) feedback electrodes | One (1) feedback electrodes | Substantially equivalent. The subjectdevice has two (2) feedback electrodeson the sole of the right foot serving as afeedback mechanism to eliminateenvironmental electromagneticinterference, whereas the predicate hasone reference electrode that comes incontact with the fingers to eliminateenvironmental electromagneticinterference by a similar feedbackmechanism. |
| ECG acquisitionduration | 30 seconds | 30 seconds | Identical |
| Resolution | 16 bits | 16 bits | Identical |
| Sampling Rate | 500Hz | 300Hz | Substantially equivalent. The subjectdevice has a higher sampling frequencythat does not affect the performance ofthe ECG acquisition |
| Data storage | 8 Mbytes | 8 Mbytes | Identical |
| Analog FilterBandwidth | 0.033Hz - 200Hz | 0.34 Hz - 52 Hz | Substantially equivalent. The subjectdevice has a wider detection bandwidththat does not affect the performance ofthe ECG-SW1 AFib detection as theEquivalence between Withings ScanMonitor 2.0 and Withings Scan MonitorECG Waveforms report concludes |
| ECGClassificationResults | Normal Sinus RhythmAtrial FibrillationInconclusiveNoise | Normal Sinus RhythmAtrial FibrillationInconclusiveNoise | Identical |
| Location of signalprocessing | In the device | In the device | Identical |
| Firmwarealgorithm | ECG-SW1 algorithm | ECG-SW1 algorithm | Identical |
| Power Supply:BatteryBattery Life(typical) | Rechargeable Lithium-ionbattery | Rechargeable Lithium-ionbattery | Identical |
| Degree ofprotection | Type BF- Applied parts | Type BF- Applied parts | Identical |
| Standards | IEC 60601-1IEC 60601-1-2IEC 60601-2-47ANSI/AAMI EC57 | IEC 60601-1IEC 60601-1-2IEC 60601-2-47ANSI/AAMI EC57 | Identical |
| AAMI TIR69:2017/(R2020)ANSI IEEE C63.27-2017FCC testing per part 15 | AAMI TIR69:2017/(R2020)ANSI IEEE C63.27-2017FCC testing per part 15 | ||
| Display format | LCD screen320 x 240 pixels | OLED screen116 x 80 pixels | Substantially equivalent, no impact on thedisplay. Bigger screen on the subjectdevice for the 6-lead display |
| Physical Specs:Dimensions Weight | 372 x 446 x 45 mm4.4 kg | 240 x 38.4 x 13.2 mm0.058 kg | Substantially equivalent. The subjectdevice is bigger than the predicate deviceallowing it to have bigger electrodes andtherefore more reliable ECG signalacquisitions. |
| Environmental:Operating TempStorage | Operating: +5°C to 35°CStorage: -10°C to 50°C | Operating: +5°C to 40°CStorage: -20°C to 70°C | Substantially equivalent |
| Communications,Companion MobileApplication | Setup in BLEScale used via WIFI and BLE | Setup in BLEWatch used via BLE | Substantially equivalent |
6. Comparison to the Predicate
{5}------------------------------------------------
Table 6-1: High-level comparison between the subject device (Withings Scan Monitor 2.0) and previously cleared device (Scan Monitor) for intended use, and indications of use.
Both devices are intended to record, store and transfer electrocardiogram (ECG) and display ECG rhythms and detect the presence of atrial fibrillation.
Both devices have a similar intended population, i.e. healthcare professionals, patients with known or suspected heart conditions, health-conscious individuals and adults.
Both devices are intended for adult patients in hospitals, clinics, long-term care facilities, and homes.
{6}------------------------------------------------
Both devices consist of the combination of the electromechanical assembly (Scan Watch for the predicate device and Body Scan for the subject device) and the related software brick included in the Health Mate companion app. For the ECG feature, both devices are intended to be used when prescribed or used under the care of a physician.
{7}------------------------------------------------
{8}------------------------------------------------
Table 6-2: High-level comparison between the subject device (Withings Scan Monitor 2.0) and previously cleared device (Scan Monitor) for technological characteristics.
At a high level, the subject device records a two channel ECG utilizing three electrodes on the smart scale that can then be transferred and displayed to the user or healthcare professional on the companion mobile application. Similarly, the predicate device records a single channel ECG using three electrodes on the smart watch and displays the results on a companion mobile application.
The subject device has the same intended use and indications for use as the predicate device including the intended use population and intended use environment. Both devices are intended to record, store and transfer electrocardiogram (ECG) and display ECG rhythms and detect the presence of atrial fibrillation. Minor differences in the number of leads is intended to provide additional information but does not affect the substantial equivalence of the device and does not alter the intended clinical application.
The fundamental technology of using stainless steel electrodes to measure ECG and detect atrial fibrillation is the same for the subject device and the predicate device. The minor technical differences do not raise different questions of safety and effectiveness because the non clinical testing, usability testing and clinical testing demonstrate equivalent device performance as the predicate device.
7. Summary of Performance Testing
Non Clinical Testing
All necessary performance testings were conducted on the subject device to support a determination of substantial equivalence to the predicate device. This testing included testing to the following standards:
- IEC 60601-1:2005, ANSI AAMI ES60601-1:2005/A2:2021 Medical Electrical Equipment . - Part 1: General Requirements For Basic Safety And Essential Performance,
- IEC 60601-1-2:2014 Medical Electrical Equipment Part 1-2: General Requirements For . Basic Safety And Essential Performance - Collateral Standard: Electromagnetic Compatibility Requirements And Tests, and
{9}------------------------------------------------
- IEC 60601-2-47:2012 Medical Electrical Equipment Part 2-47: Particular Requirements ● For The Basic Safety And Essential Performance Of Ambulatory Electrocardiographic Systems.
- IEC 60601-1-11: Medical electrical equipment Part 1-11: General requirements for ● basic safety and essential performance - Collateral Standard: Requirements for medical electrical equipment and medical electrical systems used in the home healthcare environment.
- ANSI/AAMI EC57: Testing and reporting performance results of cardiac rhythm and ● ST-segment measurement algorithms.
- . AAMI TIR69:2017/(R2020) - Technical Information Report Risk management of radio-frequency, wireless coexistence for medical devices and systems
- ANSI IEEE C63.27-2017 American National Standard for Evaluation of Wireless ● Coexistence
- FCC testing per part 15
The device was tested for cytotoxicity, sensitization, irritation and intracutaneous irritation as per according to "Biological evaluation of medical devices- Part 1: Evaluation and testing within a risk management process", 2020.
Software verification and validation was performed per FDA guidance for the Content of Premarket Submissions for Software Contained in Medical Devices". The software for Withings Scan Monitor 2.0 is considered to have a "moderate" level of concern.
Human Factors Testing
Human Factors Validation testing was performed on the Withing Scan Monitor 2.0 to demonstrate substantial equivalence for the intended users, uses and use environments. Testing was conducted per FDA guidance "Applying Human Factors and Usability Engineering to Medical Devices". The Human Factor Validation study was performed in the U.S. with US participants and was conducted with 2 user groups:
-
- Adult lay users of ages 22-64 vears, and
-
- Elderly lay users of ages 65+ years
Both user groups included participants who are a mix of lay users with and without AFib. The validation protocol included simulated use scenarios, critical knowledge task questions, and interview questions to collective and subjective data to help determine potential root causes of any use errors and difficulties related to the user interface.
Users demonstrated a very good level of understanding and usage of the product. Overall users were able to record the ECG measurements, interpret the results and understand when it is appropriate to seek medical help. They were also able to answer simple and more complex questions around the contraindications and warnings of the product.
Algorithm Testing
Three distinct sets of data were used to design the algorithm. Each dataset is used in one of the usual three stages of a robust Machine Learning algorithm development: training, testing, and validation of the final ("locked") algorithm. In order to prevent any data leak or overfitting, there is no overlap between these three datasets. In particular, the data used for validation is independent from any training or testing since the recordings come from separate, independent sources: devices, patients, ECG reviewers and centers were all different.
{10}------------------------------------------------
Publicly available datasets were utilized for the training datasets consist of several smaller datasets. A summary of the demographic characteristics of the test data set is provided in the table below:
| Test Data Set 1 (n=137) | Test Data Set 2 (n=262) | ||||
|---|---|---|---|---|---|
| DemographicCharacteristics | DemographicCharacteristics | ||||
| Age | Age | ||||
| 66.6 +/- 13.5 | 68.2 +/- 14.8 | ||||
| Sex | Sex | ||||
| (N) | (%) | (N) | (%) | ||
| Male | 81 | 59 | Male | 160 | 61 |
| Female | 56 | 41 | Female | 102 | 39 |
| BMI (kg/m²) | BMI (kg/m²) | ||||
| 27.8 +/- 5.9 | 27.5 +/- 5.7 | ||||
| Height (cm) | Height (cm) | ||||
| 169.1 +/- 10.1 | 169.2 +/- 9.2 | ||||
| Weight (kg) | Weight (kg) | ||||
| 81.3 +/- 20.7 | 78.9 +/- 17.6 | ||||
| Cardiovascular Risk Factors | Cardiovascular Risk Factors | ||||
| Hypertension | Hypertension | ||||
| 59/137 (43%) | 135/262 (52%) | ||||
| Dyslipidemia | Dyslipidemia | ||||
| 29/137 (21%) | 90/262 (34%) | ||||
| Overweight or Obesity | Overweight or Obesity | ||||
| 75/137 (55%) | 111/262 (42%) | ||||
| Diabetes | Diabetes | ||||
| 16/137 (22%) | 57/262 (22%) |
Table 6-3: Demographic Characteristics of the ECG-SW1 algorithm test data set.
{11}------------------------------------------------
Clinical Study
The clinical study was a prospective, cross-sectional, diagnostic, multicentric open-label study with the anticipated total number of subjects that were planned to be recruited to meet the target was 250 patients of which 125 subjects with a known diagnosis of AF and 125 subjects with a known diagnosis of SR. The purpose of the study was to validate a rhythm classification algorithm ECG-SW1 running on the subject device Withings Scan Monitor 2.0 (WBSSM2) and its ability to detect and classify heart rhythms into one of four categories (sinus rhythm (SR), atrial fibrillation (AF), inconclusive or noise) using a six-lead ECG strip and to validate the Withings Scan Monitor 2.0 (WBSSM2) ability to generate a 6-lead electrocardiogram (ECG) that is clinically equivalent to a standard 12-lead ECG. 274 patients were included in the present study. 40 patients had to be excluded from the data analysis. Withings Scan Monitor 2.0 (WBSSM2) classified as "noise" 7.7% of the valid ECG records (25/321). Of the remaining signals (at rest + after effort), excluding other arrhythmias, Withings Scan Monitor 2.0 (WBSSM2) reached a sensitivity of 0.99 with a 95% confidence interval of [0.93, 1.0] and a specificity of 0.99 with a 95% confidence interval of [0.97, 1.0]. Withings Scan Monitor 2.0 (WBSSM2) accuracies computed on the visibility of all ECG waves (P-waves, QRS complexes and T-waves) was above 0.992. Polarity accuracy was 0.986 for P-waves, 0.948 for QRS complex, and 0.911 for T-waves. The standard deviation of the differences of duration of PR interval and QRS width between the signals of Withings Scan Monitor 2.0 (WBSSM2) and the 12-lead gold standard ECG device was < 20 ms, that is less than half the length of the smallest graduation on a standard paper ECG trace. The standard deviation of differences of duration of QT intervals was 30.3ms. Finally, the mean difference between heart rate measured by Withings Scan Monitor 2.0 (WBSSM2) and heart rate measured on the 12-lead ECG was -0.96 bpm with a 3.81 bpm standard deviation ("noise" ECGs excluded). The standard deviation of 3.81 bpm, being below the acceptable threshold for heart rate measurements error of 10%.
The table below presents the full confusion matrix for the subject device performance including all 4 outputs.
| Withings Clinical Study(321 participants) | 12-lead Reference ECG signals reviewed by cardiologists | |||||
|---|---|---|---|---|---|---|
| NormalSinusRhythm | AtrialFibrillation | Inconclusive | Noise | TOTAL | ||
| 6-leadWithings ScanMonitor 2.0 | Normal SinusRhythm | 170 | 1 | 9 | 5 | 185 |
| AtrialFibrillation | 1 | 74 | 0 | 2 | 77 | |
| Inconclusive | 4 | 8 | 21 | 1 | 34 | |
| Noise -Inconclusive | 3 | 18 | 2 | 2 | 25 | |
| TOTAL | 178 | 101 | 32 | 10 | 321 |
Table 6-4: Confusion matrix for Withings Scan Monitor 2.0 Vs 12-lead Reference ECG classification reviewed by cardiologists
Performance Comparison to predicate device
The table below provides the performance for the Withings Scan Monitor 2.0 compared to the
{12}------------------------------------------------
predicate device (Withings Scan Monitor).
| Atrial Fibrillation /Normal Sinus Rhythm | Withings Scan Monitor 2.0 | Withings Scan Monitor |
|---|---|---|
| Sensitivity [95% confidence interval lowerbound] | 0.73 [0.639] | 0.77 [0.675] |
| Specificity [95% confidence interval lowerbound] | 0.955 [0.914] | 0.965 [0.912] |
| Sensitivity AF/NSR only [95% confidence intervallower bound] ("Inconclusive" and "noise" excluded.) | 0.989 [0.928] | 0.963 [0.894] |
| Specificity AF/NSR only [95% confidence intervallower bound] ("Inconclusive" and "noise" excluded.) | 0.994 [0.968] | 1.000 [0.967] |
Table 6-5: Performance for the Withings Scan Monitor 2.0 compared to the predicate device
The sensitivity of Withings Scan Monitor was estimated to be 77% (lower bound 95%C1-67.5%) whereas the sensitivity of the Withings Scan Monitor 2.0 was 73.3% (lower bound 95%Cl=63.9%). Although there are differences in sensitivities between the two devices, both devices have equivalent performance because both devices use the same algorithm and meet the confidence intervals criteria and the difference in terms of sensitivity is not statistically significant.
8. Conclusion
The Withings Scan Monitor 2.0 has similar intended use and technological characteristics as the predicate device. Differences in technological characteristics were assessed through performance testing to show that the differences do not raise different questions of safety and effectiveness compared to the predicate device. Software verification and validation, Non-clinical testing, human factors and clinical study data demonstrate that the Withings Scan Monitor 2.0 is substantially equivalent to the predicate device.
§ 870.2340 Electrocardiograph.
(a)
Identification. An electrocardiograph is a device used to process the electrical signal transmitted through two or more electrocardiograph electrodes and to produce a visual display of the electrical signal produced by the heart.(b)
Classification. Class II (performance standards).