(152 days)
Not Found
Yes
The device description explicitly states that the algorithm employs "features-based machine learning based on a convolutional neural network (CNN)" and later mentions "The algorithm includes a machine learning component that consists of a convolutional network".
No.
The device is described as a "mobile medical application" that detects loss of pulse and alerts the user and emergency services. Its intended use explicitly states: "Loss of Pulse Detection is not intended to replace traditional methods of diagnosis, treatment, or monitoring." This indicates that it is not intended to provide treatment, which is a key characteristic of a therapeutic device.
Yes
The device identifies loss of pulse events by analyzing pulse data from wrist-worn products, which is a form of diagnosis. The "Intended Use" section explicitly states its purpose is to "identify loss of pulse events" and the "Device Description" confirms its use for "detection of loss of pulse." Although it mentions it "is not intended to replace traditional methods of diagnosis," its primary function is to detect and alert users to a potential medical condition, thereby performing a diagnostic-like function.
Yes
The device is explicitly described as "software-only" and "SaMD" (Software as a Medical Device) in the intended use and device description sections. While it relies on data from compatible consumer wrist-worn products with sensors, the device itself is the software component that analyzes this data and provides alerts.
Based on the provided information, this device is not an IVD (In Vitro Diagnostic).
Here's why:
- IVD Definition: In Vitro Diagnostics are devices used to examine specimens taken from the human body, such as blood, urine, or tissue, to provide information for diagnosis, monitoring, or screening.
- Device Function: The Loss of Pulse Detection device analyzes pulse data collected by photoplethysmography (PPG) and accelerometer sensors from a wrist-worn device. It does not analyze specimens taken from the body.
- Intended Use: The intended use is to identify loss of pulse events and provide alerts, and potentially initiate a call to emergency services. This is based on physiological data collected externally, not on the analysis of in vitro samples.
Therefore, while it is a medical device (specifically, a Software as a Medical Device - SaMD), it does not fit the definition of an In Vitro Diagnostic.
No
The provided text does not contain any explicit statement that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device. The 'Control Plan Authorized (PCCP) and relevant text' section explicitly states 'Not Found'.
Intended Use / Indications for Use
Loss of Pulse Detection is a software-only mobile medical application that is intended to be used with compatible consumer wrist-worn products to analyze pulse data to identify loss of pulse events and provide audio, visual, and haptic alerts to the user.
If the user remains unresponsive to these alerts, Loss of Pulse Detection will attempt to prompt a call to emergency services through the user's connected compatible hardware, such as a smartphone or smartwatch.
Loss of Pulse Detection is intended for over-the-counter (OTC) use. It is not intended to provide a notification on every loss of pulse event and the absence of an alert is not intended to indicate that no such event has occurred; rather the Loss of Pulse Detection is intended to opportunistically surface an alert of possible loss of pulsatility when sufficient data are available for analysis.
These data are only captured when the user is still. Loss of Pulse Detection is not intended to replace traditional methods of diagnosis, treatment, or monitoring.
Loss of Pulse Detection has not been tested for and is not intended for use in people under 22 years of age. It is also not intended for use in individuals previously diagnosed with a high risk for sudden cardiac death such as those with coronary artery disease, cardiomyopathy and/or unexplained syncope/fainting.
Product codes
SDY
Device Description
The Loss of Pulse detection SaMD is intended to be used for the detection of loss of pulse using photoplethysmography (PPG) and accelerometer sensors present in a wrist worn consumer wearable device. Upon detection of loss of pulse, when the smartwatch is worn, the feature will prompt haptic and audio alerts and notifications to the user and prompt the user's compatible hardware to call emergency services if the user is unresponsive to the notifications and alerts. This is an opt-in feature and will be off bv default.
The Loss of Pulse detection SaMD comprises a software component that resides on the compatible consumer wearable device (from here on referenced as a "smartwatch") and a user facing mobile application that resides on general purpose compatible consumer mobile devices such as a smartphone (from here on referenced as "Smartphone"). The software component on the smartwatch analyzes pulse data collected by photoplethysmography (PPG) and accelerometry sensors from qualified smartwatch, using an algorithm employing digital signal processing (DSP) and features-based machine learning based on a convolutional neural network (CNN) to detect possible loss of pulse events.
Mentions image processing
Not Found
Mentions AI, DNN, or ML
The Loss of Pulse Detection algorithm identifies potential loss of pulse events. The algorithm includes a machine learning component that consists of a convolutional network, which analyzes data from photoplethysmography (PPG) and accelerometer sensors.
Input Imaging Modality
Photoplethysmography (PPG)
Anatomical Site
Wrist-worn consumer wearable with PPG sensors.
Indicated Patient Age Range
Loss of Pulse Detection has not been tested for and is not intended for use in people under 22 years of age.
Intended User / Care Setting
Intended for over-the-counter (OTC) use. Use environment is Home/General Use.
Description of the training set, sample size, data source, and annotation protocol
The Loss of Pulse Detection algorithm was developed on a dataset consisting of over one hundred thousand hours of free-living data across hundreds of participants who experienced no loss of pulse events and 99 participants who experienced simulated loss of pulse events induced by an arterial occlusion model. The dataset used for model development was split at the participant level into training, validation, and held-out test sets. The Loss of Pulse Detection algorithm was trained on the training split and evaluated on the validation set.
Description of the test set, sample size, data source, and annotation protocol
When algorithm development was complete, the algorithm was locked and the algorithm was evaluated on the held-out test set. The training, validation, and test splits used for development included data from diverse participants with varied age, sex, BMI, and skin tone.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Algorithm Development:
The Loss of Pulse Detection algorithm was developed and evaluated on training, validation, and held-out test sets from a dataset of over one hundred thousand hours of free-living data across hundreds of participants with no loss of pulse events and 99 participants with simulated loss of pulse events.
Bench Testing/Non-Clinical Testing:
Bench testing included product signal acquisition testing, aggressor testing for known challenge conditions potentially impacting the quality of PPG signal acquisition, and accuracy assessment of the inputs to the Loss of Pulse Detection that were derived from the wrist-worn products. Qualification testing was repeated for all qualified wrist-wearable products. The algorithm was tested to ensure it accepted and rejected data correctly and could correctly analyze input data. Software documentation level is "Basic Documentation".
Human Factors Testing Summary:
A Human Factors Validation Study was performed using a simulated version of the Loss of Pulse Detection within the Pixel watch mobile app. 19 users were recruited from the general population, with the goal of recruiting at least 15 intended users (16 intended and 3 unintended users participated). Participants performed various tasks in representative, naturalistic use scenarios, including setup, onboarding, responding to escalation, triggering emergency response services, and passive feature use. A knowledge task was also performed to evaluate critical tasks. The study documented use errors, moderator assistance, close calls, and difficulties. The human factors testing found that the loss of pulse detection feature was safe and effective for the intended users, uses, and use environments.
Real World Evidence Summary:
Real-world evidence indicates users are able to respond to haptic, audio, and visual feedback and de-escalate based solely on reading the device labeling. A sample of data shows that users clear >98% of notifications from the pre-phone call gates in real-world free-living conditions. On average, 1 phone call was placed by Loss of Pulse Detection in 75 person-years of real-world use.
Clinical Testing Summary:
Two clinical studies were conducted to validate the Loss of Pulse Detection (LPD) software.
- Study 1: 135 participants (racially and ethnically diverse, diverse sex and age).
- Sensitivity: 69.3% (95% CI: 64.3%-74.1%)
- Specificity: 99.965% (95% CI 99.804, 99.999) on a day-level from 131 evaluable participants.
- Study 2: 21 participants (racially and ethnically diverse, diverse sex and age).
- Sensitivity after adjusting for performance after a simulated collapse: 64.5% (95% CI: 55.7% to 74.2%).
- A total of 5 adverse events were reported across both studies, none related to the LPD software; most were anticipated risks like skin irritation from wearing the device.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Sensitivity: 69.3% (95% C1: 64.3%–74.1%) across 135 users.
Sensitivity (adjusted for simulated collapse): 64.5% (95% CI: 55.7% to 74.2%).
Specificity: 99.965% (95% CI 99.804, 99.999) (day-level, from 131 evaluable participants).
Predicate Device(s): If the device was cleared using the 510(k) pathway, identify the Predicate Device(s) K/DEN number used to claim substantial equivalence and list them here in a comma separated list exactly as they appear in the text. List the primary predicate first in the list.
Fitbit Irregular Rhythm Notifications (K212372)
Reference Device(s): Identify the Reference Device(s) K/DEN number and list them here in a comma separated list exactly as they appear in the text.
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 870.2790 Photoplethysmograph analysis software for over-the-counter use.
(a)
Identification. A photoplethysmograph analysis software device for over-the-counter use analyzes photoplethysmograph data and provides information for identifying irregular heart rhythms. 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 must demonstrate the performance characteristics of the detection algorithm under anticipated conditions of use.
(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 demonstrate the ability of the device to detect adequate photoplethysmograph signal quality.
(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.
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 logo on the left and the FDA logo on the right. The FDA logo features the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG ADMINISTRATION" in blue text.
February 25, 2025
Fitbit Dinesh Puppala Regulatory Affairs Lead 215 Fremont Street San Francisco, California 94105
Re: K242967
Trade/Device Name: Loss of Pulse Detection Regulation Number: 21 CFR 870.2790 Regulation Name: Photoplethysmograph Analysis Software For Over-The-Counter Use Regulatory Class: Class II Product Code: SDY Dated: September 25, 2024 Received: September 26, 2024
Dear Dinesh Puppala:
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.
1
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" (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 QS 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.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-device-advicecomprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
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-regulatory
2
assistance/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 Quality Center for Devices and Radiological Health
Enclosure
3
Indications for Use
Form Approved: OMB No. 0910-0120 Expiration Date: 07/31/2026 See PRA Statement below.
Submission Number (if known)
Device Name
Loss of Pulse Detection
Indications for Use (Describe)
Loss of Pulse Detection is a software-only mobile medical application that is intended to be used with compatible consumer wrist-worn products to analyze pulse data to identify loss of pulse events and provide audio, visual, and haptic alerts to the user.
If the user remains unresponsive to these alerts, Loss of Pulse Detection will attempt to prompt a call to emergency services through the user's connected compatible hardware, such as a smartphone or smartwatch.
Loss of Pulse Detection is intended for over-the-counter (OTC) use. It is not intended to provide a notification on every loss of pulse event and the absence of an alert is not intended to indicate that no such event has occurred; rather the Loss of Pulse Detection is intended to opportunistically surface an alert of possible loss of pulsatility when sufficient data are available for analysis.
These data are only captured when the user is still. Loss of Pulse Detection is not intended to replace traditional methods of diagnosis, treatment, or monitoring.
Loss of Pulse Detection has not been tested for and is not intended for use in people under 22 years of age. It is also not intended for use in individuals previously diagnosed with a high risk for sudden cardiac death such as those with coronary artery disease, cardiomyopathy and/or unexplained syncope/fainting.
Type of Use (Select one or both, as applicable)
Prescription Use (Part 21 CFR 801 Subpart D)
X 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
Image /page/4/Picture/0 description: The image shows the Fitbit logo. The logo consists of a stylized letter 'f' made up of a collection of dots on the left, followed by the word 'fitbit' in a sans-serif font. The word 'fitbit' is written in lowercase letters, and there is a registered trademark symbol to the right of the word.
510(K) Summary
-
- Submitter Information: Fitbit LLC
215 Fremont Street. San Francisco, CA 94105 Contact Person: Dinesh Puppala Regulatory Affairs Lead Phone: (650)-267-1263 Email: puppalad(@google.com Date Prepared: Feb 19, 2025
- Submitter Information: Fitbit LLC
-
- Subject Device Information Name of Device: Loss of Pulse Detection Common or Usual Name: Loss of Pulse Detection Classification Name: Photoplethysmograph Analysis Software For Over-The-Counter Use Regulatory Class: Class II Product Code: SDY - 21 CFR 870.2790
-
- Predicate Device Fitbit Irregular Rhythm Notifications (K212372)
4. Indications for Use
Loss of Pulse Detection is a software-only mobile medical application that is intended to be used with compatible consumer wrist-worn products to analyze pulse data to identify loss of pulse events and provide audio, visual, and haptic alerts to the user.
If the user remains unresponsive to these alerts. Loss of Pulse Detection will attempt to prompt a call to emergency services through the user's connected compatible hardware, such as a smartphone or smartwatch.
Loss of Pulse Detection is intended for over-the-counter (OTC) use. It is not intended to provide a notification on every loss of pulse event and the absence of an alert is not intended to indicate that no such event has occurred; rather the Loss of Pulse Detection is intended to opportunistically surface an alert of possible loss of pulsatility when sufficient data are available for analysis.
These data are only captured when the user is still. Loss of Pulse Detection is not intended to replace traditional methods of diagnosis, treatment, or monitoring.
Loss of Pulse Detection has not been tested for and is not intended for use in people under 22 years of age. It is also not intended for use in individuals previously diagnosed with a high risk for sudden cardiac death such as those with coronary artery disease, cardiomyopathy and/or unexplained syncope/fainting.
Confidential
5
Image /page/5/Picture/0 description: The image shows the Fitbit logo. The logo consists of a stylized "f" made up of small circles on the left and the word "fitbit" in a sans-serif font on the right. The logo is black and white.
Device Description న.
Intended Use
Photoplethysmograph analysis software for over-the-counter use. A photoplethysmograph analysis software device for over-the-counter use analyzes photoplethysmograph data and provides information for identifying loss of pulse. This device is not intended to provide a diagnosis.
Technological Characteristics
The Loss of Pulse detection SaMD is intended to be used for the detection of loss of pulse using photoplethysmography (PPG) and accelerometer sensors present in a wrist worn consumer wearable device. Upon detection of loss of pulse, when the smartwatch is worn, the feature will prompt haptic and audio alerts and notifications to the user and prompt the user's compatible hardware to call emergency services if the user is unresponsive to the notifications and alerts. This is an opt-in feature and will be off bv default.
The Loss of Pulse detection SaMD comprises a software component that resides on the compatible consumer wearable device (from here on referenced as a "smartwatch") and a user facing mobile application that resides on general purpose compatible consumer mobile devices such as a smartphone (from here on referenced as "Smartphone"). The software component on the smartwatch analyzes pulse data collected by photoplethysmography (PPG) and accelerometry sensors from qualified smartwatch, using an algorithm employing digital signal processing (DSP) and features-based machine learning based on a convolutional neural network (CNN) to detect possible loss of pulse events.
| | Subject Device
Loss of Pulse Detection
K242967 | Predicate Device
Fitbit Irregular Rhythm
Notification
K212372 | Equivalence
Discussion |
|----------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Intended Use | Photoplethysmograph
analysis software for
over-the-counter use. A
photoplethysmograph analysis
software device for
over-the-counter use analyzes
photoplethysmograph data
and provides information for
identifying loss of pulse. This
device is not intended to
provide a diagnosis. | Photoplethysmograph analysis
software for over-the-counter
use. A photoplethysmograph
analysis software device for
over-the-counter use analyzes
photoplethysmograph data
and provides information for
identifying irregular heart
rhythms. This device is not
intended to provide a
diagnosis. | Same |
| Indications for
Use | Loss of Pulse Detection is a
software-only mobile medical
application that is intended to be
used with compatible consumer
wrist-worn products to analyze
pulse data to identify loss of
pulse events and provide a
notification to the user.
If the user remains unresponsive
to these alerts, Loss of Pulse
Detection will attempt to prompt
a call to emergency services
through the user's connected
compatible hardware, such as a
smartphone or smartwatch.
Loss of Pulse Detection is
intended for over-the-counter
(OTC) use. It is not intended to
provide a notification on every
loss of pulse event and the
absence of a notification is not
intended to indicate no disease
process is present; rather the
Loss of Pulse Detection is
intended to opportunistically
surface a notification of possible | The Fitbit Irregular Rhythm
Notifications is a software-only
mobile medical application that
is intended to be used with
compatible consumer wrist-worn
products to analyze pulse rate
data to identify episodes of
irregular heart rhythms
suggestive of atrial fibrillation
(AFib) and provide a notification
to the user.
The Fitbit Irregular Rhythm
Notifications is intended for
over-the-counter (OTC) use. It 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 Fitbit Irregular
Rhythm Notifications is intended
to opportunistically surface a
notification of possible AFib
when sufficient data are available
for analysis.
These data are only captured | Similar
Both devices are software-only
mobile medical applications
intended for use with
compatible consumer
wrist-worn products. They both
utilize PPG analysis software to
identify potential irregular heart
rhythms, analyze pulse data,
and provide notifications to the
user if an irregular heart rhythm
is detected. Neither device is
intended to provide a diagnosis
or monitor the outcome of their
alerts. Additionally, both
devices are intended for users
over 22 years old and are not
intended for individuals with
pre-existing cardiac conditions. |
| | pulselessness when sufficient
data are available for analysis.
These data are only captured
when the user is still. Loss of
Pulse Detection is not intended
to replace traditional methods of
diagnosis or treatment.
Loss of Pulse Detection has not
been tested for and is not
intended for use in people under
22 years of age. It is also not
intended for use in individuals | when the user is still. Along with
the user's risk factors, the Fitbit
Irregular Rhythm Notifications
can be used to supplement the
decision for AFib screening. The
Fitbit Irregular Rhythm
Notifications is not intended to
replace traditional methods of
diagnosis or treatment.
The Fitbit Irregular Rhythm
Notifications has not been tested
for and is not intended for use in
people under 22 years of age. It
is also not intended for use in
individuals previously diagnosed
with AFib. | |
| | previously diagnosed with a high
risk for sudden cardiac death
such as those with coronary
artery disease, cardiomyopathy
and/or unexplained
syncope/fainting. | | |
| Use Environment | Home/General Use | Home/General Use | Same
Both are intended for home
use. |
| Anatomical Site | Wrist-worn consumer wearable
with PPG sensors. | Wrist-worn consumer wearable
with PPG sensors. | Same
Both use consumer grade
wrist-worn devices to gather
signals from PPG sensors. |
| User interface | Mobile application run within
the Pixel watch consumer app. | Mobile application run within
the Fitbit consumer app | Same
Both devices include a mobile
application component that is
run within a consumer
application on the user's
mobile device (smartphone).
This mobile application serves
the purpose of the User
Interface for both devices. |
| Use Method | Collects and analyzes pulse data
during periods that meet input | Collects and analyzes
tachograms (based on pulse data)
during periods of stillness or
sleep using input from PPG
sensors. | Similar
Both devices analyze sensor
data from the PPG sensor and
only analyze data that meet
input signal quality
requirements. Stillness is part
of both devices' input signal
quality requirements. Both
devices limit the analysis
window to time periods
relevant to the irregular heart
rhythm being detected. The
use of the term "tachogram"
by the predicate device refers
to subsets of the PPG sensor
data cropped to approximate
individual R-R intervals, and
does not meaningfully alter
the use method, as both the |
| | | | subject and predicate devices
use signal processing
algorithms to analyze PPG
sensor data.
Both devices are passive
background screening tools
and users cannot initiate
readings.
Both devices opportunistically
surface a notification to the
user. |
| Limiting Factors | Motion, hand, and finger
movements during pulseless
period; tattoos on the wrist;
inadequate blood flow.
Does not continuously monitor
for signs of loss of pulse
A lack of notification does not
indicate an absence of an
underlying loss of pulse | Motion, hand and finger
movements, dark tattoos on the
wrist, inadequate blood flow.
Does not continuously monitor
for signs of AFib.
A lack of notification does not
indicate an absence of AFib. | Same
Both devices have similar
limiting factors.
Both devices are not intended
for continuous monitoring.
A lack of notification does not
indicate an absence of an
irregular rhythm for both
devices. |
| Compatible
devices | Consumer wrist-worn products
with PPG sensors (e.g.,
smartwatch) that have been
qualified for use with the Loss of
Pulse Detection feature | Consumer wrist-worn products
with PPG
sensors (e.g., smartwatch or
fitness tracker) that have been
qualified for use
with Fitbit Irregular Heart
Rhythm Notifications | Same
Both devices are compatible
with qualified wrist worn
products with PPG sensors
that have been qualified for
use with the respective feature.
The subject device is
compatible with a subset of
consumer wrist-worn products
on which the predicate is
qualified (i.e., smartwatches). |
| Principles of
Operation | Pulse rate data is gathered from a
consumer wrist-worn device.
The algorithm analyzes the data
and classifies it as having signs
of an irregular heart rhythm, loss
of pulse, or no signs thereof.
When signs of loss of pulse are
detected, a notification is
surfaced to the user. | Pulse rate data gathered from a
consumer wrist-worn device is
uploaded to a server. The
algorithm analyzes the data and
classifies it as having signs of
AFib or no signs of AFib. When
signs of AFib are detected a
notification is surfaced to the
user through the mobile | Similar
Both devices have the same
basic principle of operation,
with nonmaterial differences
stemming from the particular
irregular pulse rhythm that is
intended to be detected. Both
devices analyze pulse data |
| | | application. | from consumer wrist-worn
devices. Apparent differences
such as algorithmic analysis
on the watch in the subject
device and the server on the
predicate have no material
impact on safety or
effectiveness. Both devices
opportunistically surface
notifications to the user if an
irregular pulse rhythm is
detected. |
Summary of Substantial Equivalence
6
Image /page/6/Picture/0 description: The image shows the Fitbit logo. The logo consists of a stylized, geometric shape made up of small circles on the left, followed by the word "fitbit" in a sans-serif font. The wordmark is in lowercase letters, and there is a registered trademark symbol to the right of the "t".
7
Image /page/7/Picture/0 description: The image shows the Fitbit logo. The logo consists of a stylized, geometric pattern of dots on the left, followed by the word "fitbit" in a sans-serif font. A registered trademark symbol is located to the right of the word "fitbit".
8
9
6. Performance Data
Testing verifying the performance requirements of the subject device was conducted and is included in this premarket notification, the results of which support substantial equivalence. A summary of the testing is included below:
Algorithm Development
The Loss of Pulse Detection algorithm identifies potential loss of pulse events. The algorithm includes a machine learning component that consists of a convolutional network, which analyzes data from photoplethysmography (PPG) and accelerometer sensors. The algorithm was developed on a dataset consisting of over one hundred thousand hours of free-living data across hundreds of participants who experienced no loss of pulse events and 99 participants who experienced simulated loss of pulse events induced by an arterial occlusion model. The dataset used for model development was split at the participant level into training, validation, and held-out test sets The Loss of Pulse Detection algorithm was trained on the training split and evaluated on the validation set. When algorithm development was complete, the algorithm was locked and the algorithm was evaluated on the held-out test set. The training, validation, and test splits used for development included data from diverse participants with varied age, sex, BMI, and skin tone.
Bench Testing/Non-Clinical Testing
The Loss of Pulse Detection utilizes signals derived from compatible consumer grade wrist-worn products. The wrist-worn products were qualified for use with the software to ensure that the data provided could meet signal attribute and quality requirements necessary for heart rhythm analysis and detect adequate PPG signal quality. Bench testing included product signal acquisition testing, aggressor testing for known challenge conditions potentially impacting the quality of PPG signal acquisition, and accuracy assessment of the inputs to the Loss of Pulse Detection that were derived from the wrist-worn products. Qualification testing was repeated for all qualified wrist-wearable products. The algorithm was tested to ensure that it accepted and rejected data correctly and that it can correctly analyze the input data.
10
Image /page/10/Picture/0 description: The image shows the Fitbit logo. The logo consists of a stylized "fitbit" text in a sans-serif font, with a small registered trademark symbol to the right of the "t". To the left of the text is a geometric design made up of several small circles arranged in a pattern resembling a stylized star or snowflake.
The Loss of Pulse Detection presents a "Basic Documentation" Software Documentation Level based on the risks of device software function in the context of the device's intended use as defined in FDA's Guidance for the Content of Premarket Submissions for Device Software Functions (June 14, 2023) (Guidance Document). Testing of the mobile application demonstrates that the Loss of Pulse Detection feature adequately performs all the necessary functionalities including education/onboarding and generating user notifications when pulselessness is identified.
Human Factors Testing Summary
A Human Factors Validation Study was designed to evaluate the critical and noncritical tasks associated with the use of the device. The Human Factors Validation Study was performed using a simulated version of the Loss of Pulse Detection within the Pixel watch mobile app, representative of the final app. 19 users were recruited from the general population for the study, with the goal of recruiting at least 15 intended users. During the test session, each participant performed various tasks within representative, naturalistic use scenarios. These tasks included setup and onboarding to an initial check-in, responding to an escalation, triggering emergency response services, and passive feature use. The first evaluation activity (setup and onboarding) included a self-selection component where participants indicated whether or not they are an intended Loss of Pulse Detection application user, resulting in 16 intended and 3 unintended users. Participants also performed a knowledge task to evaluate critical tasks that could not be evaluated during the simulated use scenarios.
During each evaluation activity, use errors, instances of moderator assistance, close calls, and difficulties were documented. Open-ended questions were used to collect participants' subjective assessments of the root cause(s) associated with any such event and to collect participants' feedback on the product's use-safety. Data was consolidated and analyzed with a focus on events with the potential for serious harm (critical tasks). The human factors testing found that the loss of pulse detection feature was safe and effective for the intended users, uses, and use environments.
Real World Evidence Summary
Real-world evidence (RWE) indicates users are able to respond to haptic, audio, and visual feedback and de-escalate based solely on reading the device labeling. A sample of data from RWE shows that users clear >98% of notifications from the pre-phone call gates in real-world free-living conditions. There was, on average, 1 phone call placed by Loss of Pulse Detection in 75 person-years of real-world use.
Clinical Testing Summary
The Loss of Pulse Detection (LPD) software, intended for use with wrist-worn devices, was clinically validated in a study. The study aimed to evaluate the software's ability to detect loss of pulse events and initiate an emergency call.
A total of 135 participants were enrolled in one clinical study and 21 participants in another clinical study. The participants included a racially and ethnically diverse population, including adults of diverse sex and age. The results from the clinical validation study showed a sensitivity of 69.3% (95% C1: 64.3%
74.1%)
Confidential
11
Image /page/11/Picture/0 description: The image shows the Fitbit logo. The logo consists of a stylized "fitbit" text in a sans-serif font, with a small registered trademark symbol to the right. To the left of the text is a geometric pattern made up of 13 circles of varying sizes, arranged in a diamond shape.
across 135 users and a sensitivity of 64.5% (95% CI: 55.7% to 74.2%) after adjusting for performance after a simulated collapse. The specificity was analyzed using evaluable data from 131 participants from the first study. It showed a day-level specificity of 99.965% (95% CI 99.804, 99.999). A total of 5 adverse events were reported. No adverse events reported were related to the LPD software. Most adverse events were identified as possible anticipated risks in the study protocol, namely skin irritation from wearing a consumer wrist-worn device. Demographic characteristics of the study population are summarized in the table below.
| | Clinical validation study
(pulseless and pulsatile) | Clinical validation study
(pulseless) |
|------------------------------------|--------------------------------------------------------|------------------------------------------|
| N | 135 | 21 |
| Age | | |
|