Search Results
Found 6 results
510(k) Data Aggregation
(152 days)
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.
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 by 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.
The document provides the following information regarding the acceptance criteria and the study that proves the device meets the acceptance criteria for the Loss of Pulse Detection (LPD) software:
1. Table of Acceptance Criteria and Reported Device Performance
While explicit "acceptance criteria" are not presented in a formal table with specific thresholds, the document details the performance metrics achieved in the clinical validation study. The performance is primarily evaluated based on sensitivity and specificity.
| Performance Metric | Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|---|
| Sensitivity (Loss of Pulse Events) | Sufficiently high to detect true loss of pulse events. | 69.3% (95% CI: 64.3% - 74.1%) across 135 users |
| Sensitivity (Adjusted for Simulated Collapse) | Maintained sensitivity after simulated collapse. | 64.5% (95% CI: 55.7% - 74.2%) |
| Specificity (Absence of Loss of Pulse Events) | Sufficiently high to minimize false positives. | 99.965% (95% CI 99.804, 99.999) (day-level) |
| Alert De-escalation (Real-World) | Users able to respond and de-escalate. | >98% of notifications cleared from pre-phone call gates. |
| Emergency Calls (Real-World) | Few false emergency calls. | 1 phone call placed per 75 person-years of use. |
2. Sample Sizes and Data Provenance
-
Test Set (Clinical Validation Studies):
- Primary Study: 135 participants for sensitivity evaluation (pulseless and pulsatile data).
- Secondary Study: 21 participants for sensitivity evaluation (pulseless data).
- Specificity Evaluation: 131 evaluable participants from the first study.
- Data Provenance: The document states participants were from a "racially and ethnically diverse population, including adults of diverse sex and age." It does not specify the country of origin, nor explicitly state if it was retrospective or prospective, though clinical validation studies are generally prospective. The phrase "simulated loss of pulse events induced by an arterial occlusion model" suggests a controlled, prospective clinical study.
-
Training and Validation Sets (Algorithm Development):
- Training/Validation/Development Datasets: Over one hundred thousand hours of free-living data (from hundreds of participants who experienced no loss of pulse events) and data from 99 participants who experienced simulated loss of pulse events induced by an arterial occlusion model.
- Data Provenance: The document states "The training, validation, and test splits used for development included data from diverse participants with varied age, sex, BMI, and skin tone." Again, country of origin is not specified. The data comprised both "free-living data" (suggesting retrospective real-world data) and "simulated loss of pulse events" (suggesting prospective controlled data).
3. Number of Experts and Qualifications for Ground Truth
The document does not explicitly state the number of experts used to establish ground truth or their specific qualifications (e.g., "radiologist with 10 years of experience"). For the clinical validation study where simulated loss of pulse was induced, it implies that the ground truth for "loss of pulse" was established directly through the experimental protocol (arterial occlusion model) rather than by expert review of physiological signals post-hoc. For "no loss of pulse" data, the ground truth is inherently the absence of such an event in free-living data of healthy individuals.
4. Adjudication Method for the Test Set
The document does not specify an adjudication method (e.g., 2+1, 3+1) for the test set. Given that the ground truth for simulated loss of pulse was established by an induced event, and for pulsatile data by its natural occurrence, a separate adjudication method using human experts on the collected data is not described as part of the primary ground truth establishment.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
An MRMC comparative effectiveness study was not explicitly mentioned or detailed. The study described focuses on the standalone performance of the algorithm and its ability to trigger an emergency call workflow, rather than comparing human reader performance with and without AI assistance. The "Real World Evidence Summary" indicates that human users interact with the device's alerts, but it does not quantify human improvement due to AI assistance in a comparative MRMC framework.
6. Standalone (Algorithm-Only) Performance
Yes, standalone performance was done. The reported sensitivity and specificity values (69.3% and 99.965%) represent the performance of the Loss of Pulse Detection algorithm. The clinical validation study was designed to evaluate the software's ability to detect loss of pulse events.
7. Type of Ground Truth Used
- For Loss of Pulse Events: Ground truth was established through simulated loss of pulse events induced by an arterial occlusion model. This is a physiological, objective method.
- For Absence of Loss of Pulse: Ground truth for pulsatile data was established by the absence of induced events in control participants and "free-living data across hundreds of participants who experienced no loss of pulse events." This relies on the natural state of healthy individuals.
8. Sample Size for the Training Set
The training set was part of a larger dataset used for algorithm development, which consisted of:
- "Over one hundred thousand hours of free-living data across hundreds of participants who experienced no loss of pulse events."
- Data from "99 participants who experienced simulated loss of pulse events induced by an arterial occlusion model."
The document states this dataset was split at the participant level into training, validation, and held-out test sets. The exact number of participants or hours specifically in the training set is not separately quantified, but it is a substantial portion of the entire development dataset.
9. How Ground Truth for the Training Set was Established
The ground truth for the training set was established in the same manner as for the test set:
- For loss of pulse events, it was based on simulated events induced by an arterial occlusion model.
- For the absence of loss of pulse, it was based on free-living data from participants who did not experience such events, implying a ground truth established by the absence of a known medical condition/event.
Ask a specific question about this device
(66 days)
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.
The Body Temperature Software ("BTS") mobile application ("App"), is a Software as a Medical Device (SaMD) that leverages an infrared sensor from qualified compatible general computing platforms (i.e. Google Pixel Smartphone) to provide on-demand body temperature measurements. The BTS App is based on well understood infrared measurement technology. The app leverages consumer general purpose computing platforms to collect the inputs for measurement.
The BTS App is intended to be operated by users above 18 years of age and can be used to measure body temperature for themselves or other individuals. To collect the input temperature data, the user is guided to conduct a non-contact forehead sweep starting at the center of the forehead and ending at the temple, thereby passing over the temporal artery, which corresponds to the highest temperature point on the forehead. This temperature data is then used as an input into the BTS App to convert the measured skin temperature data into a body temperature value. Before and during this measurement process, the BTS App performs a series of signal quality checks to ensure the validity of the temperature data collected. Additionally, to aid users with the interpretation of their measurements, the BTS App also has the option to present users with a color-coded temperature quide to indicate if the measurement falls within normal limits or indicative of an elevated state based on wellrecognized body temperature ranges for the specified age of the individual being measured.
The BTS App collects the temporal artery temperature, which is processed using a polynomial function to approximate a rectal temperature.
Here's a breakdown of the acceptance criteria and study information for the Body Temperature Software (BTS) based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Laboratory Accuracy | ±0.5°F (±0.3°C) |
| Measurement Range | 94.1°F-109.4°F (34.5°C-43°C) |
2. Sample Size Used for the Test Set and Data Provenance
The document does not explicitly state the sample size used for the test set or the data provenance (e.g., country of origin, retrospective or prospective). It mentions "Validation Testing" and "Laboratory accuracy testing," implying a test set was used, but details are omitted in this summary.
3. Number of Experts and Qualifications for Ground Truth Establishment
Not applicable. The document describes laboratory accuracy testing based on a "reference body rectal site" and adherence to ISO standards, not expert-established ground truth.
4. Adjudication Method for the Test Set
Not applicable. The reported testing focuses on device accuracy against a physical reference (rectal temperature) in a laboratory setting, not subjective expert judgment requiring adjudication.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. The document focuses on the device's standalone performance and its equivalence to a predicate device, not on human reader improvement with or without AI assistance.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
Yes, a standalone (algorithm only) performance study was conducted. The "Laboratory Accuracy" data, demonstrating ±0.3°C accuracy, directly reflects the algorithm's performance in determining body temperature from IR sensor input. The device description explicitly states it's a "Software as a Medical Device (SaMD)" that processes sensor data.
7. Type of Ground Truth Used
The ground truth used for the accuracy assessment was a reference body rectal site. The BTS app "processes the sensor data collected during the sweep and determines the body temperature" and "The displayed temperature is that of the temporal artery which is processed using a polynomial function to approximate a rectal temperature."
8. Sample Size for the Training Set
The document does not specify the sample size for the training set. It mentions the "BTS App is based on well understood infrared measurement technology" and "The BTS App collects the temporal artery temperature, which is processed using a polynomial function to approximate a rectal temperature," suggesting the algorithm was developed and trained prior to this specific premarket notification, but details regarding its training are not provided in this summary.
9. How the Ground Truth for the Training Set Was Established
The document does not detail how the ground truth for the training set was established. It primarily focuses on the device's performance validation against a predicate and ISO standards. Given the use of a "polynomial function to approximate a rectal temperature," it's highly likely that the model was trained using paired temporal artery temperature readings and corresponding rectal temperature measurements as ground truth, but the specifics of this process are not included in this submission summary.
Ask a specific question about this device
(151 days)
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.
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.
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.
- Sample Size: 145 racially and ethnically diverse subjects were enrolled, 144 completed the study.
- Clinical Study Test Set:
-
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.
Ask a specific question about this device
(252 days)
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 when the user's still. Along with the user's risk factors, the Fitbit irreqular Rhythm Notifications can be used to supplement the decision for AFib screening. The Fitbit Irregular Rhythm Notfications is not intended to replace traditional methods of diagnosis or treatment.
The Fitbit Irregular Rhythm Notifications has not been tested for use in people under 22 years of age. It is also not intended for use in individuals previously diagnosed with AFib.
The Fitbit Irreqular Rhythm Notifications consists of an algorithm that classifies pulse rate data, and a mobile application run within the Fitbit app that serves as the user interface (UI) and device display.
The Fitbit Irregular Rhythm Notifications leverages pulse rate data collected from compatible commercially available, general purpose wrist-worn products (e.g., smartwatch or fithess tracker). Photoplethysmograph (PPG) sensors consist of light-emitting diodes (LED) and photodiodes that detect changes in blood flow of a user's vasculature at any given moment. When the heart beats, it sends a pressure wave through the vasculature causing a blood flow increase. By monitoring the fluctuations the consumer wrist-worn products can measure pulse rate data. When the user is still the sensor detects when individual pulses reach the periphery (i.e., wrist) and measures beat-to-beat intervals.
If the analyzed data are consistent with signs of atrial fibrillation, a notification indicating that a heart rhythm showing signs suggestive of AFib will be displayed to the user. The Fitbit Irregular Rhythm Notifications will only surface a notification of a heart rhythm showing signs of AFib once in a 24-hour period.
The Fitbit Irregular Rhythm Notifications mobile app functions within the Fitbit consumer application and is run on a compatible, user-provided general purpose mobile computing product (e.g., smartphone or tablet). The Fitbit Irregular Rhythm Notifications mobile app serves as the display/user interface for the Fitbit Irregular Rhythm Notifications.
Acceptance Criteria and Device Performance for Fitbit Irregular Rhythm Notifications
1. Table of Acceptance Criteria and Reported Device Performance
The provided document focuses on the substantial equivalence to a predicate device rather than explicitly stating acceptance criteria as a numerical target. However, it details the performance metrics demonstrated by the clinical study to support this equivalence. The key performance metric reported is the Positive Predictive Value (PPV) for AFib detection.
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Clinical performance supportive of substantial equivalence to predicate device. | Positive Predictive Value (PPV) of 98.2% (97.5% LCB: 96.4%) in subjects with a positive algorithm detection. |
2. Sample Size and Data Provenance
- Test Set Sample Size: 225 subjects received a positive algorithm detection and wore an ECG patch for comparison.
- Data Provenance: The study recruited subjects from Fitbit's U.S. user population. The data is prospective, as users consented and were instructed to perform specific actions (schedule a telehealth visit, wear an ECG patch) following algorithm detection.
3. Number of Experts and Qualifications for Ground Truth
The document states that "Data gathered from the ECG patch was analyzed by medical professionals to determine whether signs of AFib were present." It does not specify the exact number of experts or their detailed qualifications (e.g., "radiologist with 10 years of experience").
4. Adjudication Method for the Test Set
The document does not explicitly describe an adjudication method like 2+1 or 3+1. It states that "data gathered from the ECG patch was analyzed by medical professionals to determine whether signs of AFib were present," implying a single assessment or a consensus process not detailed.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No Multi-Reader Multi-Case (MRMC) comparative effectiveness study was mentioned. The study focused on the standalone algorithm's performance against ECG ground truth, not on how human readers improve with or without AI assistance.
6. Standalone (Algorithm Only) Performance
Yes, a standalone performance study was conducted. The clinical study evaluated the Fitbit Irregular Rhythm Notifications algorithm's ability to identify irregular heart rhythms suggestive of AFib. The reported PPV of 98.2% is a measure of this standalone algorithmic performance.
7. Type of Ground Truth Used
The ground truth used for the test set was ECG patch data analyzed by medical professionals. This is a direct measure of cardiac electrical activity, considered a gold standard for AFib diagnosis.
8. Sample Size for the Training Set
The document does not specify the sample size for the training set. It mentions that the clinical study "recruited subjects from Fitbit's U.S. user population, inviting them to participate in a study. Upon consent, users had their PPG data analyzed for signs consistent with AFib by the algorithm." This describes part of the clinical validation, but not the training process or the data used for it.
9. How Ground Truth for the Training Set Was Established
The document does not provide details on how the ground truth for the training set was established. It only describes the ground truth establishment for the clinical validation test set (ECG patch data analyzed by medical professionals).
Ask a specific question about this device
(156 days)
The Fitbit ECG App is a software-only mobile medical application intended for use with Fitbit wrist wearable devices to create, record, store, transfer, and display a single channel electrocardiogram (ECG) qualitatively similar to a Lead I ECG. The Fitbit ECG App determines the presence of atrial fibrillation (AFib) or sinus rhythm on a classifiable waveform. The AFib detection feature is not recommended for users with other known arrhythmias.
The Fitbit ECG App is intended for over-the-counter (OTC) use. The ECG data displayed by the Fitbit ECG App is intended for informational use only. The user is not interpret or take clinical action based on the device output without consultation of a qualified healthcare professional. The ECG waveform is meant to supplement rhythm classification for the purposes of discriminating AFib from normal sinus rhythm and not intended to replace traditional methods of diagnosis or treatment. The Fitbit ECG App is not intended for use by people under 22 years old.
The Fitbit ECG App is a software-only medical device used to create, record, display, store and analyze a single channel ECG. The Fitbit ECG App consists of a Device application ("Device app") on a consumer Fitbit wrist-worn product and a mobile application tile ("mobile app") on Fitbit's consumer mobile application. The Device app uses data from electrical sensors on a consumer Fitbit wrist-worn product to create and record an ECG. The algorithm on the Device app analyzes a 30 second recording of the ECG and provides results to the user. Users are able to view their past results as well as a pdf report of the waveform similar to a Lead I ECG on the mobile app.
Below is the information regarding the Fitbit ECG App's acceptance criteria and the study that proves it, based on the provided document:
1. Table of acceptance criteria and the reported device performance
| Category | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| AFib Detection (Sensitivity) | Not explicitly stated in the provided text as a numerical criterion, but implicitly expected to be high for AFib detection. The predicate device's performance often forms the basis for substantial equivalence. | 98.7% for AFib detection |
| AFib Detection (Specificity) | Not explicitly stated in the provided text as a numerical criterion, but implicitly expected to be high for ruling out AFib. The predicate device's performance often forms the basis for substantial equivalence. | 100% for AFib detection |
| ECG Waveform Morphological Equivalence to Lead I | ECG waveform "qualitatively similar to a Lead I ECG" and expected to meet specific morphological equivalence criteria. | 95.0% of AF and SR tracings deemed morphologically equivalent to Lead I of a 12-Lead ECG waveform. |
2. Sample size used for the test set and the data provenance
- Sample Size: 475 subjects.
- Data Provenance: Subjects were recruited across 9 US sites. This indicates prospective data collection from the United States.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Number of Experts: For subjects with a known history of AFib, a "single qualified physician" performed the screening and assigned them to the AFib cohort. The document doesn't specify how many experts reviewed the 12-lead ECGs for the ground truth of AFib or Sinus Rhythm (NSR) for all 475 subjects, beyond the single physician for the AFib cohort screening. For the overall study, it implies a 12-lead ECG was the reference, which would typically be interpreted by qualified cardiologists or electrophysiologists.
- Qualifications of Experts: For AFib screening, the expert was referred to as a "single qualified physician." Specific qualifications like "radiologist with 10 years of experience" are not provided.
4. Adjudication method for the test set
The document does not explicitly state an adjudication method (e.g., 2+1, 3+1). It mentions that subjects with a known history of AFib were screened by a "single qualified physician." For the simultaneous 12-lead ECG, it implies a clinical standard interpretation which often involves adjudicated reads, but this is not detailed in the provided text.
5. If a Multi-Reader, Multi-Case (MRMC) comparative effectiveness study was done
No, a Multi-Reader, Multi-Case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance was not reported in this document. The study focuses on evaluating the standalone performance of the Fitbit ECG App against a clinical standard (12-lead ECG).
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, a standalone performance study was done. The document states: "The Fitbit ECG App software algorithm was able to detect AF with the sensitivity and specificity of 98.7% and 100%, respectively." This indicates a direct evaluation of the algorithm's performance.
7. The type of ground truth used
The ground truth was established using a simultaneous 30-second 12-lead ECG. This is a clinical gold standard for rhythm analysis.
8. The sample size for the training set
The document does not provide the sample size for the training set. It only details the clinical testing conducted for validation/evaluation of the device.
9. How the ground truth for the training set was established
The document does not provide information on how the ground truth for the training set was established, as it focuses on the validation study.
Ask a specific question about this device
(164 days)
The ARIA WiFi Smart Scale is a body analyzer that measures body weight and uses bioelectrical impedance analysis (BIA) technology to estimate body fat percentage in generally healthy individuals 10 years of age or older. It is intended for home use only.
ARIA is a body weight scale and a body fat analyzer that operates by using a low, safe, battery-generated electrical current through the body (using a bioelectrical impedance analysis technique) to provide body fat and body weight information. After the user registers their scale, the scale automatically recognizes the subject based on body weight and body fat readings. ARIA contains a WiFi module (802.11 module) that allows it to connect to the Internet in the user's home. The module provides a complementary interface to the Fitbit website. Body weight and body fat measurements are independent of internet communication after initial product registration.
The ARIA scale automatically measures body weight and body fat composition. The scale recognizes the user based on previous weight readings, and can accept up to eight (8) different users. The 16 most recent readings are kept in memory on the scale and readings are also transmitted to the user's optional fitbit.com personal account for trending. If users have similar weight, the proper identity can be selected by tapping the scale.
Here's a breakdown of the acceptance criteria and study information for the Fitbit ARIA WiFi Smart Scale, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The acceptance criteria for the ARIA WiFi Smart Scale are established not through explicit numerical thresholds but by demonstrating substantial equivalence to a predicate device (Withings Smart Body Scale K121971) and showing that its body fat measurements are not statistically different from the predicate, with variation within an acceptable range.
| Feature/Metric | Acceptance Criteria (Implied from Predicate/Study) | Reported Device Performance |
|---|---|---|
| Substantial Equivalence | Demonstrates equivalence in technology, intended use, classification, product code, indication for use, device description, analysis method, operating parameters, number of electrodes, power source, IP connectivity, and measured parameters to the predicate device (Withings WBS01 Smart Body Scale K121971). | The ARIA WiFi Smart Scale is listed as substantially equivalent to the Withings Smart Body Scale (K121971) across all listed features. Differences noted (e.g., age range, specific power source type, minor IP connectivity details) are presented as not impacting substantial equivalence. |
| Body Fat Measurement | Body fat composition (%) measurements should not be statistically different (p>0.05) from the predicate device, and body fat measurements should vary by < 8% from one another when compared to the predicate device. | "Results of this study lead to the conclusion that the measurements from ARIA were not statistically different from the predicate device (p>0.05) and body fat measurements varied by <8% from one another." |
| Safety and EMC | Compliance with IEC 60601-1 (medical electrical equipment safety) and IEC 60601-1-2 (electromagnetic compatibility). | "The ARIA WiFi Smart Scale has been tested according to IEC 60601-1, IEC 60601-1-2 and was found to meet all requirements." |
| Reliability & Human Factors | Meet specified criteria as per internal testing. | "Performance data (reliability testing and human factors testing) also support that the ARIA device meet its specified criteria." (Specific criteria not detailed in the summary). |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: 50 subjects (25 male and 25 female).
- Data Provenance: The study was a "small comparative clinical study" comparing the ARIA WiFi Smart Scale to the predicate device. The text does not specify the country of origin but implies it was conducted by the manufacturer or a contracted clinical research organization. The study design strongly suggests it was prospective as it involved collecting new data for direct comparison between the two devices.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
The study does not establish an independent "ground truth" against which the device performance is measured in the classical sense (e.g., DEXA or underwater weighing). Instead, the performance of the ARIA device is compared directly against the predicate device (Withings Smart Body Scale K121971) as the reference. Therefore, there were no experts used to establish a separate ground truth for the test set. The predicate device's measurements serve as the comparator.
4. Adjudication Method for the Test Set
Not applicable. This was a direct comparison study between a new device and a predicate device. There was no complex labeling or interpretation by multiple human readers requiring adjudication. The study involved objective measurements of body fat percentage from both devices.
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, an MRMC comparative effectiveness study was not done. This device (Fitbit ARIA WiFi Smart Scale) is a standalone measurement device for body weight and body fat, not an AI-assisted diagnostic tool that aids human readers. The study performed was a direct comparison of its measurement accuracy against a predicate device.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Yes, a standalone performance study was done. The clinical performance testing compared the ARIA WiFi Smart Scale's measurements of body fat composition directly against the measurements from the predicate device. This is a standalone comparison as it assesses the device's output independently. The device's primary function is to measure and display these values, which are then transmitted to a user's account for tracking, but the core performance evaluation focuses on the accuracy of these direct measurements.
7. The Type of Ground Truth Used
The "ground truth" for the clinical performance study was the measurements obtained from the predicate device (Withings Smart Body Scale K121971). The study aimed to demonstrate that the ARIA device's measurements were not statistically different from those of the legally marketed predicate device. While BIA is an estimation method itself, for the purpose of demonstrating substantial equivalence, the predicate device's output serves as the comparative reference.
8. The Sample Size for the Training Set
The document does not mention a training set or any machine learning/AI model that would require a distinct training set. The ARIA WiFi Smart Scale uses Bioelectrical Impedance Analysis (BIA) technology, which is a well-established method, not typically relying on a separately described "training set" in the context of regulatory submissions for this type of device. The description focuses on its sensor technology and comparison to a predicate.
9. How the Ground Truth for the Training Set Was Established
As no training set is mentioned or implied for a machine learning model, this question is not applicable. The device relies on physical principles of bioelectrical impedance.
Ask a specific question about this device
Page 1 of 1