The Body Temperature Software (BTS) App is a software-only mobile medical application intended for over-the-counter (OTC) use with compatible mobile computing platforms that includes a general purpose infrared sensor for the intermittent determination of human body temperature on people of all ages.

Device Description

The Body Temperature Software (BTS) is a mobile medical application available to its intended users via their mobile device. The Body Temperature Software (BTS) collects and analyzes temperature data obtained via the infrared sensor built into the smartphone to approximate the user's rectal temperature which is then displayed on the application's user interface. The Body Temperature Software (BTS) is a pre-installed application on the Pixel 8 Pro with Android 14 operating system release or higher.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study information for the Body Temperature Software (BTS), based on the provided text:

Acceptance Criteria and Device Performance

Acceptance Criteria	Reported Device Performance
Clinical accuracy criteria in conformance with ISO 80601-2-56:2017 (for clinical bias and Limits of Agreement).	Clinical Bias: +0.04°C (calculated using the mean of three comparator device readings).Limits of Agreement (LOA): Lower LOA: -0.94°C (-1.09°C, -0.78°C 95% CI); Upper LOA: 1.02°C (0.85°C, 1.18°C 95% CI).Accuracy Range: Within the stated temperature range of 36°C and 40°C.
Bench Testing (Non-clinical performance testing): Demonstrate the ability of the device to detect adequate signal quality under anticipated conditions of use. Testing must evaluate: - The laboratory accuracy of the device across the intended output range under the intended operating conditions. - The impact of confounding factors on device accuracy.	Range Check Flag: Correctly captures distance and gates forehead temperature measurement signals within a specified range.
	Infrared Sensor Internal (Ambient) Temperature (TA) Check Flag: Sufficiently and correctly measures internal and sensor window temperature and gates forehead temperature within a specified range.
	Robustness to External Aggressors: Variations in inputs due to motion artifacts, environment, and wear condition/position do not significantly affect algorithm performance.
	Fitzpatrick/Monk Level Performance: Infrared sensor signal quality does not vary significantly across various skin tones, and skin tone emissivity does not impact algorithm performance.
	Hardware Equivalency: Variations of hardware and software components on compatible Pixel mobile devices have no significant effect on signal quality.
	Skin Temperature Range Check: Filtered maximum forehead temperature is in the range of 30°C to 40°C.
	Body Temperature Check: Calculated maximum temperature is in the range of 34.5°C to 43°C.
	Window & Sensor Temperature Differences Check: Sensor-to-sensor window temperature difference is ≤ 2°C.
Software verification, validation, and hazard analysis	The Body Temperature Software has a Moderate Level of Concern (LOC). Appropriate documentation was provided to support the validation of the software for a Moderate LOC in accordance with FDA's 2005 guidance.
Usability and Human Factors	Usability testing demonstrated that the Body Temperature Software (BTS) is safe and effective for the intended users, uses, and use environments.

Study Details

Sample size used for the test set and the data provenance:
- Clinical Study Test Set:
  - Sample Size: 145 racially and ethnically diverse subjects were enrolled, 144 completed the study.
    - 37 newborns and infants (0 to < 2 years)
    - 36 children (2 to < 12 years)
    - 37 adolescents and transitional adolescents (12 to < 18 years)
    - 35 adults (≥ 22 years)
  - Data Provenance: Prospective, single-arm, multi-center observational study. The country of origin is not explicitly stated.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The document describes comparison against a "legally marketed comparator device" (clinical thermometer), not against expert clinical assessment for ground truth. Therefore, the concept of "experts establishing ground truth" in the diagnostic sense is not directly applicable here. The comparator device serves as the reference standard.
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- The document implies a direct comparison method where three readings from the BTS device were compared against three readings from the comparator device for each participant. It does not mention an "adjudication" process in the sense of multiple experts reviewing and resolving discrepancies for the ground truth.
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 was not conducted. This device is a standalone measurement tool, not an AI-assisted diagnostic aid for human readers.
If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, the primary clinical study evaluates the standalone performance of the Body Temperature Software (BTS) by comparing its output directly to a legally marketed comparator device. The device itself is "software-only" and collects data via the smartphone's infrared sensor to produce a temperature reading.
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The ground truth for the clinical study was established by a legally marketed comparator device (clinical thermometer) in conformance with ISO 80601-2-56:2017 standards for body temperature measurement. This essentially serves as a "reference standard" rather than a subjective expert consensus or objective pathology.
The sample size for the training set:
- The document does not specify a sample size for the training set. It focuses on the clinical validation study and bench testing.
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, as details about the algorithm's development or training data are not included in this regulatory summary.

Summary

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

DE NOVO CLASSIFICATION REQUEST FOR BODY TEMPERATURE SOFTWARE (BTS)

REGULATORY INFORMATION

FDA identifies this generic type of device as:

Body temperature sensing software. Body temperature sensing software is a software device used for the determination of human body temperature by means of analyzing input sensor data.

NEW REGULATION NUMBER: 21 CFR 880.2915

CLASSIFICATION: Class II

PRODUCT CODE: QZA

BACKGROUND

DEVICE NAME: Body Temperature Software (BTS)

SUBMISSION NUMBER: DEN230050

DATE DE NOVO RECEIVED: July 17, 2023

CONTACT: Fitbit LLC 199 Fremont Street San Francisco, CA 94105

INDICATIONS FOR USE

LIMITATIONS

The feature has not been tested for and is not intended to be used to measure the body temperature of a premature baby (defined as less than or equal to 37 calendar weeks gestational age at birth).

Use of the BTS App is not intended to diagnose or monitor a serious medical condition or disease and is not a substitute for a consultation with a healthcare professional. Don't interpret or take clinical action based on the device output without consulting a qualified healthcare professional.

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

This device CANNOT detect illnesses.

This device DOES NOT replace the advice of your healthcare provider.

This device should be operated by persons over 18 years of age.

DO NOT use this device to measure body temperature when exposed to the following conditions:

. Excessive motion (e.g., operating machinery, walking), and/or
Direct sun or near radiant heat sources (e.g., heaters). .

DO NOT use this device to measure body temperature when the smartphone is visibly damaged, or has sensors or ports obstructed. Reference manufacturer instructions for maintenance.

DO NOT use this device to measure body temperature when the external environmental temperature is outside of 15°C - 35°C (59°F - 95°F).

DO NOT use this device to measure body temperature if you suspect hypothermia.

PLEASE REFER TO THE LABELING FOR A MORE COMPLETE LIST OF WARNINGS, PRECAUTIONS AND CONTRAINDICATIONS.

DEVICE DESCRIPTION

Software	Body Temperature Software (BTS)
Hardware	Pixel 8 Pro (Android 14 operating system release or higher)
Intended Users	All users over the age of 18
Intended Patient Population	General population excluding premature/preterm infants

Users must opt-in and go through an onboarding process prior to use of the Body Temperature Software (BTS) application. The Body Temperature Software (BTS) onboarding process consists of a pop-up screen requiring user acknowledgement of the intended use, patient population, and user population followed by a video walkthrough demonstrating the kev steps necessary to obtain a temperature measurement. These steps include (1) identifying the sensor on the back of the phone, (2) removal of accessories that cover the forehead and temple, (3) place the sensor as close to the center of the forehead without touching, and (4) conducting the measurement sweep from the center of the forehead to the temple within four (4) seconds. The hardware platform provides audible, visual, and tactile feedback in addition to voice assist during these steps. The

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

audible, visual, and tactile feedback are intended to communicate the process steps (e.g., appropriate distance to forehead, counting of seconds of the forehead sweep) related to obtaining a temperature measurement during the forehead sweep. The voice assist is intended to provide audio guidance supplementary to the existing feedback.

After the four (4) second forehead sweep, the temperature data is then used as an input into the Body Temperature Software (BTS) algorithm to convert the measured skin temperature data into a body temperature value representative of an approximation of rectal temperature results are able to be stored in the mobile application for seven (7) days. This information includes the time and date of the measurement, age range associated with the temperature guidance if enabled, and the temperature result.

Within the Body Temperature Software (BTS) mobile application, a user may enable the Temperature Guide that informs users whether their temperature measurement indicates a normal, elevated, or high temperature based on medical literature. The results of this functionality are based on the age range chosen prior to taking a measurement. The age ranges include 0-3 months. 3-36 months, 3+ years.

The application performs a series of checks prior to launching the application, during the measurement sweep, and during the processing of the signal to ensure that the temperature data collected is valid for processing. Using this valid collected data, the algorithm processes the sensor data collected during the sweep and displays a measurement to the user that approximates rectal temperature.

To enable the mobile application to obtain a temperature measurement, the systems check, proximity detection, and infrared sensor checks must pass. If the signal quality checks are deemed acceptable, following additional proximity and internal infrared sensor ambient temperature checks, additional signal quality checks are performed upon signal ingestion to the algorithm and again at subsequent points throughout the algorithm analysis to verify that the signal received by the sensor is accurate and reliable.

If these checks fail, error messages are intended to inform the user when the collected signal is not of sufficient quality. The potential error messages include 'Sensor out of range', 'Unable to start measurement', 'Measurement failed', 'Temperature sensor is too warm/too cool', and 'Temperature sensor unavailable'.

In addition to the signal quality checks implemented within the Body Temperature Software (BTS) process flow to obtain an accurate temperature measurement, pre-specified requirements for the hardware platform (e.g., operating system, processor speed, memory, etc.), sensor (e.g., sensor type, sensitivity, accuracy, etc.), and signal quality (e.g., maximum forehead temperature, infrared sensor internal temperature, estimated body temperature, sensor to sensor window difference, proximity, system check) must be met.

SUMMARY OF NONCLINICAL/BENCH STUDIES

SOFTWARE

The Body Temperature Software has a Moderate Level of Concern (LOC). Appropriate documentation was provided to support the validation of the software for a Moderate LOC in

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

accordance with FDA's 2005 guidance titled, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices."

PERFORMANCE TESTING - BENCH

The Body Temperature Software (BTS) was subjected to a series of bench tests to assess its functional performance under nominal conditions and conditions exposing the device to factors that may impact signal quality. These tests were performed in conformance with ISO 80601-2-56:2017 Medical electrical equipment - Part2-56: Particular requirements for basic safety and essential performance of clinical thermometers for body temperature measurement using the final version of the device or a version of the device that was sufficiently representative of the final version of the device. The bench testing summarized in the table below was performed to demonstrate acceptable performance of the device for its intended use.

Test	Description
Range Check Flag	Demonstrate that the range enable flag correctly capturesdistance and gates forehead temperature measurementsignals when within a specified range from the user'sforehead.
Infrared Sensor Internal(Ambient) Temperature (TA)Check Flag	Demonstrate that internal temperature of the infrared sensorcan sufficiently and correctly measure the internaltemperature and sensor window temperature and gatesforehead temperature within a specified range.
Robustness to ExternalAggressors	Demonstrate that variations in the inputs due to a variety ofcommon and/or expected behavioral and physiologicalconditions do not affect the performance of the algorithmsignificantly. These conditions include motion artifacts,environment, and wear condition/position of the device.
Fitzpatrick/Monk LevelPerformance	Demonstrate that the infrared sensor signal quality does notvary significantly across various skin tones, and skin toneemissivity does not impact algorithm performance.
Hardware Equivalency	Demonstrate that variations of the hardware and softwarecomponents found on compatible Pixel mobile devices haveno significant effect on the signal quality of the dataprovided as inputs for the algorithm.
Skin Temperature RangeCheck	Demonstrate that the filtered maximum foreheadtemperature must be in the range of 30°C to 40°C, which isinclusive of the human body temperature range.
Body Temperature Check	Demonstrate that the calculated maximum temperature mustbe in the range of 34.5°C to 43°C which is inclusive of thehuman body core temperature range.

Performance/Input Signal Testing (Bench) Summary

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

Test	Description
Window & SensorTemperature DifferencesCheck	Demonstrate that the sensor-to-sensor window temperaturedifference is $\leq$ 2°C.

SUMMARY OF CLINICAL INFORMATION

Clinical Study

The Sponsor provided data from a clinical study as well as literature to support the clinical accuracy of the Body Temperature Software (BTS). This study used data collected from a subset of participants enrolled in a prospective. single-arm, multi-center observational study conducted to demonstrate the Body Temperature Software (BTS) produces temperature measurements within the specified clinical accuracy criteria when compared to a legally marketed comparator device in conformance with ISO 80601-2-56:2017 Medical electrical equipment - Part2-56: Particular requirements for basic safety and essential performance of clinical thermometers for body temperature measurement.

A total of 145 racially and ethnically diverse subjects were enrolled in the clinical study, including 37 newborns and infants (0 to < 2 years), 36 children (2 to < 12 years), 37 adolescents and transitional adolescents (12 to < 18 years), and 35 adults (≥ 22 years). A total of 144 subjects completed the study. The statistical analyses used the data collected in its entirety as well as age and race subgroup analyses.

Each subject's body temperature measurements were obtained using the Body Temperature Software (BTS) and comparator device. A total of six (6) temperature measurements were obtained on each participant, three (3) with the Body Temperature Software (BTS) and three (3) with the comparator device. The primary endpoint was to determine the clinical bias, including the Limits of Agreement (LOA), between the Body Temperature Software (BTS) and comparator device.

Overall. the clinical bias was within the established acceptance criteria and supports use of the device in the intended patient population. The clinical bias for the entire patient population was +0.04°C when calculated using the mean of the three (3) comparator device readings. The associated upper and lower LOAs were -0.94°C (-1.09°C. -0.78°C 95% CI) and 1.02°C (0.85°C. 1.18°C 95% CI), respectively. The accuracy of the subject device was determined to be within the stated temperature range of 36℃ and 40℃.

Human Factors and Usability Study

The Sponsor provided a Human Factors and Usability study which included a total of 31 participants from the following two user groups for the Body Temperature Software (BTS):

. 16 lay people at least 18 years of age who use Android smartphones.
15 lay caregivers at least 18 years of age who use an Android smartphone and provide . care for another individual.

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

All participants used the Body Temperature Software (BTS) mobile application which included videos and instructions embedded in the application's software interface. Apart from the initial onboarding video that is played prior to taking a first temperature reading, no additional training was provided to the study participants.

Overall, usability testing demonstrated that the Body Temperature Software (BTS) is safe and effective for the intended users, uses, and use environments.

LABELING

The labeling for the device satisfies the requirements of 21 CFR 801.109. The labeling consists of adequate Instructions for Use, an onboarding sequence, and pop-up messages in the user interface. The Instructions for Use include the indications for use, a description of the device. cautions, warnings and limitations, information regarding the temperature guidance functionality, operating instructions, troubleshooting, overview of the clinical study, and device performance specifications.

Please see the Limitations section above for important warnings and precautions presented in the device labeling.

RISKS TO HEALTH

The table below identifies the risks to health that may be associated with use of body temperature sensing software and the measures necessary to mitigate these risks.

Risk to Health	Mitigation Measures
Inaccurate device output leadingto patient receiving incompleteor delayed treatment/diagnosis	Clinical performance testingNon-clinical performance testingSoftware verification, validation, and hazard analysisLabeling
Poor signal quality resulting infailure to detect elevated bodytemperature	Non-clinical performance testingSoftware verification, validation, and hazard analysisLabeling

Identified Risks to Health and Mitigation Measures

SPECIAL CONTROLS

In combination with the general controls of the FD&C Act. the body temperature sensing software is subject to the following special controls:

For devices where the output temperature is calculated by adjusting the signal from the (1) input sensor, clinical performance testing must demonstrate the accuracy of the device under anticipated conditions of use.
(2) Non-clinical performance testing must demonstrate the ability of the device to detect adequate signal quality under anticipated conditions of use. Testing must evaluate:
- (i) The laboratory accuracy of the device across the intended output range under the intended operating conditions: and
- (ii) The impact of confounding factors on device accuracy.

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

(3) Software verification, validation, and hazard analysis must be performed. Documentation must include a characterization of the technical specifications of the software, including the application algorithm and its inputs and outputs.
(4) Labeling must include:
- (i) Compatible hardware platform(s) and operating system requirements:
- Situations in which the device may not operate at an expected performance level; (ii)
- A summary of the clinical performance testing conducted with the device, (iii) including a description of the reference body site:
- Established device performance specifications: and (iv)
- Information on interpretation of results. (v)

BENEFIT/RISK DETERMINATION

The Body Temperature Software (BTS) is intended to approximate rectal temperature. The device demonstrated a laboratory accuracy of ±0.3℃ and met clinical accuracy requirements of ISO 80601-2-56 for the intended patient population. The device is not intended to diagnose users or patients with a condition or illness, but it provides an accessible tool to monitor body temperature.

The probable benefits of the Body Temperature Software (BTS) are that the device is easily accessible, convenient to use, is comparable to other legally marketed non-contact infrared thermometers and demonstrates favorable clinical performance in regard to clinical bias. The device is available on a mobile platform that is easy to navigate, clean, and disinfect as needed. The temperature is provided after a quick four (4) second temperature sweep across the forehead and these results are able to be saved up to seven (7) days for personal or clinical reasons.

The risks for the Body Temperature Software (BTS) include inaccurate device outputs leading to patients receiving incomplete or delayed treatment/diagnosis and poor signal quality resulting in failure to detect elevated body temperature. Non-clinical testing, under the conditions of use and conditions that may impact signal quality, is required to: 1) ensure that the device is provided with sufficient temperature data from the infrared sensor, and 2) characterize the likelihood of inaccurate outputs. Labeling is also required to help the user interpret the results they receive. Here, the labeling specifically states the conditions for use and that the device is not intended to replace a healthcare professional's opinion.

The Body Temperature Software (BTS) does include some additional considerations that may impact signal quality that are not present in currently marketed non-contact infrared thermometers (i.e., confounding factors). Some of these confounding factors have been assessed through performance testing and demonstrated the accuracy specification is not impacted. For those not tested and those found to impact accuracy through bench testing, the labeling and user interface of the device (available through the application) warns users of these environments and factors. In such cases, the Body Temperature Software (BTS) would return an error that the measurement failed, or a condition has not been met such that a temperature reading could not be provided.

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

Overall, the benefit of an easily accessible thermometer outweighs the risks of inaccurate results and failure to detect elevated body temperature as a result of poor signal quality given the mitigations employed including the special controls in combination with the general controls. There is a reasonable assurance of safety and effectiveness for the device when used as intended. A majority of the risks associated with the BTS app are consistent with risks that exist for currently marketed non-contact infrared thermometers.

Patient Perspectives

This submission did not include specific information on patient perspectives for this device.

Benefit/Risk Conclusion

In conclusion, given the available information above, the data support that for the Body Temperature Software (BTS), the probable benefits outweigh the probable risks. The device provides benefits, and the risks can be mitigated by the use of general controls and the identified special controls.

CONCLUSION

The De Novo request for the Body Temperature Software (BTS) is granted and the device is classified under the following:

Product Code: QZA Device Type: Body temperature sensing software Class: II Regulation: 21 CFR 880.2915

Regulation Number and Section

N/A