(205 days)
The Garmin ECG app is a software-only, mobile medical application intended for use with compatible Garmin smartwatches to create, record, store, transfer, and display a single-channel electrocardiograph similar to a Lead I ECG. The ECG app determines the presence of atrial fibrillation (AFib) or sinus rhythm (SR) on a classifiable waveform. The ECG app is not recommended for users with other known arrhythmias.
The ECG app is intended for over-the-counter (OTC) use. The ECG data displayed by the ECG app is intended for informational use only. The user is not intended to 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 SR, and it is not intended to replace traditional methods of diagnosis or treatment.
The ECG app is not intended for use by people under 22 years old.
The Garmin ECG App (ECG App) is a software-only, mobile medical application that has two components: (1) the Watch ECG App for compatible Garmin smartwatches ("Watch" or "Watches"), and (2) the Smartphone ECG App included within Garmin's consumer health and fitness application ecosystem, Garmin Connect allows users to store, manage, and share their respective health and fitness data.
The ECG App is intended to create, record, store, transfer, and display a single lead ECG signal similar to a Lead | ECG. The Watch ECG App acquires and analyzes the single lead ECG signal from electrodes built into each Watch and detects the presence of atrial fibrillation (AFib) or normal sinus rhythm (SR) in the adult wearer of the Watch ECG App then calculates the average heart rate and displays that value, along with the rhythm classification result, to the user on the Watch screen. The user may annotate the result by choosing from a provided list of symptoms.
Optionally, and only when directed by the user, the Watch ECG App can securely transmit the result to the Smartphone ECG App for the purposes of storing and viewing a history of ECG App results. The user may also export ECG App results as a PDF for easy sharing.
The Garmin ECG App is a software-only, mobile medical application intended for use with compatible Garmin smartwatches to detect the presence of atrial fibrillation (AFib) or sinus rhythm (SR) from a single-channel electrocardiograph (similar to Lead I ECG).
Here's a breakdown of the acceptance criteria and the study that proves the device meets them:
1. Acceptance Criteria and Reported Device Performance
The acceptance criteria for the Garmin ECG App's clinical performance were based on its ability to accurately detect AFib and sinus rhythms. The reported device performance is presented in the table below:
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Atrial Fibrillation Sensitivity | 99.5% |
| Sinus Rhythm Specificity | 100% |
| AFib Detection (including inconclusive recordings) | 86.5% |
| Sinus Rhythm Detection (including inconclusive recordings) | 91.1% |
2. Sample Size and Data Provenance
- Test Set Sample Size: Approximately 590 subjects.
- Data Provenance: The document does not explicitly state the country of origin or whether the study was retrospective or prospective. However, it describes a "clinical study," which typically implies a prospective design.
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: Not explicitly stated, but the ground truth for the test set was established by "board-certified cardiologists."
- Qualifications of Experts: Board-certified cardiologists.
4. Adjudication Method for the Test Set
The adjudication method is not explicitly detailed beyond stating that "12-Lead ECG rhythm classifications performed by board-certified cardiologists" were used as the comparison for the ECG app's classifications. It implies that these expert classifications served as the gold standard for comparison.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
There is no mention of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study being conducted to assess how much human readers improve with AI vs. without AI assistance. The study focuses on the standalone performance of the Garmin ECG App compared to expert-classified 12-Lead ECGs.
6. Standalone Performance (Algorithm Only)
Yes, a standalone performance study (algorithm only without human-in-the-loop performance) was done. The reported sensitivities and specificities (99.5% AFib sensitivity, 100% SR specificity for classifiable waveforms, and 86.5% AFib detection, 91.1% SR detection overall) are for the device's algorithmic classification.
7. Type of Ground Truth Used
The ground truth used was expert consensus based on 12-Lead ECG rhythm classifications performed by board-certified cardiologists.
8. Sample Size for the Training Set
The document does not explicitly state the sample size used for the training set for the ECG app's algorithm. The provided information specifically refers to the clinical validation study (test set).
9. How Ground Truth for the Training Set Was Established
The document does not explicitly describe how the ground truth for the training set was established. It mentions that "Garmin conducted database testing using a previously adjudicated dataset as per ANSI/AAMI EC57:2012" under "Non-Clinical Testing." While this indicates the use of adjudicated data for some form of testing, it doesn't specify if this was the training dataset or how that adjudication was performed (e.g., expert review, specific criteria).
§ 870.2345 Electrocardiograph software for over-the-counter use.
(a)
Identification. An electrocardiograph software device for over-the-counter use creates, analyzes, and displays electrocardiograph data and can provide information for identifying cardiac arrhythmias. 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 under anticipated conditions of use must demonstrate the following:
(i) The ability to obtain an electrocardiograph of sufficient quality for display and analysis; and
(ii) The performance characteristics of the detection algorithm as reported by sensitivity and either specificity or positive predictive value.
(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 validate detection algorithm performance using a previously adjudicated data set.
(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.