Search Results

The WHOOP ECG Feature is a software-only mobile medical application intended for use with the WHOOP Strap to create, record, store, transfer, and display a single-channel electrocardiogram (ECG) qualitatively similar to a Lead I ECG. The WHOOP ECG Feature determines the presence of atrial fibrillation (AFib), normal sinus rhythm, low heart rate (≤ 50 beats per minute [bpm]), and high heart rate (≥ 100 bpm) on a classifiable waveform. The WHOOP ECG Feature is not recommended for users with other known arrhythmias.

The WHOOP ECG Feature is intended for over-the-counter (OTC) use. The ECG data displayed by the ECG Feature are intended for informational use only. The user is not intended to interpret or take clinical action based on the device output without the 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 is not intended to replace traditional methods of diagnosis or treatment.

The WHOOP ECG Feature is intended for use by adults 22 years of age and older.

The WHOOP ECG Feature is a software-only medical mobile application integrated into the consumer (non-device) WHOOP System. It consists of three medical device modules: ECG Strap Module, ECG Phone Module, and ECG Cloud Module.

The feature is designed to create, record, store, transfer, and display a single-channel electrocardiogram (ECG), qualitatively similar to a Lead I ECG. It analyzes ECG recordings collected via the ECG electrodes on the WHOOP Strap.

The ECG Strap Module firmware is integrated within the WHOOP Strap's firmware. The ECG Strap Module firmware contains the FDA-cleared B-Secur HeartKey Software Library (K200884) which is used to provide classification for a 30-second ECG spot check recording into corresponding WHOOP ECG Feature outputs: Normal Sinus Rhythm; AFib; Low Heart Rate; High Heart Rate; Inconclusive; and Unsuccessful Reading. Users must opt in and complete onboarding through the ECG Phone Module within the WHOOP Mobile Application before accessing the ECG Feature.

The ECG Cloud Module processes requests for ECG report generation. Users can download ECG reports in PDF format to their mobile device or share them via applications such as email or messaging.

The WHOOP ECG Feature is not intended to replace traditional diagnostic or treatment methods.

The provided FDA 510(k) clearance letter for the WHOOP ECG Feature offers details regarding its acceptance criteria and the study conducted to prove it meets those criteria. Here's a structured breakdown of the information:

Acceptance Criteria and Reported Device Performance

1. Table of Acceptance Criteria and Reported Device Performance

• Probability of AFib result for true AFib: 87.47%
• Probability of SR result for true SR: 96.59% |
  | Morphology Assessment | Acceptable similarity of waveform morphology to reference ECG. | Comprehensive visual assessment demonstrated acceptable signal quality. Quantitative assessment compared key features (PR interval, QRS duration, R-wave amplitude, RR interval) with 12-lead reference. | Supported by clinical validation; differences do not raise new safety/effectiveness questions. |
  | User Comprehension/Human Factors | Users can correctly use the device, interpret output, and understand when to seek medical care. Users can adequately self-select if the device is intended for them. | Results were positive, demonstrating correct device use, output interpretation, and understanding of when to seek medical care. Testing with 51 participants confirmed adequate user self-selection. | Special Control (4) under 21 CFR 870.2345 addressed. Supports OTC use. |
  | Signal Acquisition Reliability | Reliable acquisition of ECG signals suitable for analysis and display. | Testing on commercial WHOOP system confirmed ability to reliably acquire ECG signals. | Supported by IEC 60601-2-47:2012 compliance. |
  | Database Testing | Compliance with special controls under 21 CFR 870.2345(3) using adjudicated dataset. | Conducted as per ANSI/AAMI EC57:2012(R2020). (Specific performance metrics not detailed, but compliance stated). | |
  | Software Verification | Compliance with FDA guidance for software functions. | Completed as recommended by "Guidance for Industry and FDA Staff Content of Premarket Submissions for Device Software Functions (issued June 14, 2023)." Includes cybersecurity, labeling, and management plan. | Device is a "basic level device" in terms of software. |
  | Electromagnetic Compatibility (EMC) & Electrical Safety | Compliance with relevant standards. | Meets specifications based on IEC 62368-1: 2018, EN 301-489 series, FCC 47 CFR Part 15 Subpart B:2024. | Confirms electrical safety and absence of electromagnetic interference issues. |

Study Information

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

• Test Set Sample Size: Approximately 540 subjects.
  • 255 enrolled in the AFib cohort.
  • 285 enrolled in the normal sinus rhythm cohort.
• Data Provenance: The document does not explicitly state the country of origin. It describes the study as a "clinical trial," which typically implies prospective data collection. There is no mention of it being retrospective.

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

• Number of Experts: One "cardiologist" was used for rhythm classification.
• Qualifications of Experts: The ground truth was established by "a cardiologist." Specific experience (e.g., 10 years of experience) is not detailed in the provided text.

4. Adjudication Method for the Test Set

• The document states that rhythm classification of a 12-lead ECG by "a cardiologist" was compared to the device's classification. This implies a single expert established the ground truth. There is no mention of a multi-reader adjudication method (e.g., 2+1 or 3+1).

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly stated as being done within the context of human readers improving with AI vs. without AI assistance. The study described focuses on the device's standalone performance compared to a cardiologist's interpretation of a 12-lead ECG.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done

• Yes, the primary clinical validation described was a standalone (algorithm only) performance assessment. The study "compared to the rhythm classification of a simultaneously collected ECG from the WHOOP feature" against the 12-lead ECG interpreted by a cardiologist. The reported sensitivity, specificity, and inconclusive rates are metrics of the algorithm's performance.

7. The Type of Ground Truth Used

• Expert Consensus (single expert): The primary ground truth for rhythm classification (AFib/Sinus Rhythm) was established by a "cardiologist" interpreting a 12-lead ECG. This is a form of expert interpretation as ground truth.
• Reference Device Comparison: For waveform morphology, a "12-lead reference system" and "12-lead reference ECG" were used for comparison, implying a gold standard for electrical activity measurement.

8. The Sample Size for the Training Set

• The document does not provide information regarding the sample size of the training set used for the WHOOP ECG Feature algorithm.

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. It only mentions that the WHOOP ECG Feature integrates the FDA-cleared B-Secur HeartKey Software Library (K200884), which would have had its own training and validation data. The specific methods for establishing ground truth for the WHOOP ECG Feature's training data are not detailed.

Ask a specific question about this device