(89 days)
The Samsung ECG Monitor Application with Irregular Heart Rhythm Notification is an over-the-counter (OTC) softwareonly, mobile medical application operating on a compatible Samsung Galaxy Watch and Phone for informational use only in adults 22 years and older. The app analyzes pulse rate data to identify episodes of irregular heart rhythms suggestive of atrial fibrillation (AFib) and provides a notification suggesting the user record an ECG to analyze the heart rhythm. The Irregular Heart Rhythm Notification Feature 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 feature is intended to opportunistically acquire pulse rate data when the data when determined sufficient toward surfacing a notification.
Following this prompt, or based on the user's own initiative, the app is intended to create, record, store, transfer, and display a single-channel ECG. similar to a Lead I ECG. Classifiable traces are labeled by the app as either AFib or sinus rhythm with the intention of aiding heart rhythm identification.
The app is not intended for users with other known arrhythmias, and it is not intended to replace traditional methods of diagnosis or treatment. Users should not interpret or take clinical action based on the device of the of a qualified healthcare professional.
The Samsung ECG Monitor App with Irregular Heart Rhythm Notification (IHRN) Feature is a software as a medical device (SaMD) that consists of a pair of mobile medical apps: one app on a compatible Samsung wearable and the other on a compatible Samsung phone, both general-purpose computing platforms.
When enabled, the wearable application of the SaMD uses a wearable photoplethysmography (PPG) sensor to background monitor bio-photonic signals from the user. The application examines beat-to-beat intervals and generates an irregular rhythm notification indicative of atrial fibrillation (AFib). Upon receiving an irregular rhythm notification or at their discretion, the user can record a single-lead ECG using the same wearable. The wearable application then calculates the average heart rate from the ECG recording and produces a rhythm classification. The wearable application also securely transmits the data to the ECG phone application on the paired phone device. The phone application shows a time-stamped irregular rhythm notification history with heart rate information; ECG measurement history; and generates a PDF file of the ECG signal, which the user can share with their healthcare provider.
Here's a breakdown of the acceptance criteria and the study details for the Samsung ECG Monitor Application with Irregular Heart Rhythm Notification Feature, based on the provided text:
Acceptance Criteria and Device Performance
| Acceptance Criteria (Targeted Performance) | Reported Device Performance (Samsung IHRN Feature) |
|---|---|
| Subject Level: | |
| Sensitivity (for irregular rhythm notification) | 68.0% (C.I. 60.5 - 75.5) |
| Specificity (for irregular rhythm notification) | 98.8% (C.I. 98.0 - 99.6) |
| Tachogram Level: | |
| Positive Predictive Value (PPV) | 95.7% (C.I. 94.7 - 96.7) |
| ECG Function (inherited from K201168): | |
| Atrial Fibrillation Sensitivity | 98.1% |
| Sinus Rhythm Specificity | 100% |
The document states that Samsung's algorithm performance for the IHRN function is substantially equivalent to the predicate device (Apple IRN Feature DEN180042) at both subject and tachogram levels, indicating these reported values met the acceptance criteria. For the ECG function, the device inherited the performance from the previously cleared Samsung ECG Monitor App (K201168) and thus the reported values were assumed to meet their prior acceptance criteria.
Study Details
2. Sample size used for the test set and the data provenance:
-
IHRN Clinical Validation (PPG-based notification):
- Analyzable Dataset for primary and secondary endpoints: 810 subjects (from 888 enrolled).
- Tachogram-level assessment: 98 subjects with AFib episodes (over an hour) and 101 subjects with less than an hour of AFib or no AFib were randomly selected from the cardiologist-reviewed subjects. Up to 25 positive tachograms with reference ECG data were randomly selected from these subjects.
- Data Provenance: The document does not explicitly state the country of origin, but it is a clinical study. The phrasing "All recruited subjects were at risk for AFib and had experienced symptoms..." suggests prospective data collection.
-
ECG Function (on-demand):
- No new clinical, human factors, or ECG database tests were conducted as the function was unchanged from the K201168 clearance. Therefore, a new test set was not used for this specific clearance.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- IHRN Clinical Validation:
- Subject-level ground truth: "clinician-adjudicated and cardiologist-reviewed patch ECG data." The exact number of clinicians/cardiologists for this overarching adjudication is not specified, but it implies multiple experts.
- Tachogram-level ground truth: "Two board-certified cardiologists reviewed each reference ECG for annotation with a third cardiologist serving as tie-breaker."
- Qualifications: "Board-certified cardiologists."
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Tachogram-level ground truth: 2+1 (Two board-certified cardiologists reviewed, with a third serving as a tie-breaker).
- Subject-level ground truth: Not explicitly stated as a specific numerical method (e.g., 2+1), but referred to as "clinician-adjudicated and cardiologist-reviewed," implying a consensus or expert-driven process.
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 MRMC comparative effectiveness study involving human readers with and without AI assistance was mentioned or conducted. The study evaluated the device's performance (IHRN feature) against a clinical ground truth, not the improvement of human readers using the device.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, the clinical validation study for the Irregular Heart Rhythm Notification (IHRN) feature primarily assesses the standalone performance of the PPG-based algorithm in identifying irregular rhythms and generating notifications. The "subject-level irregular rhythm notification accuracy" and "tachogram-level positive predictive value" are metrics of the algorithm's performance without direct human interpretation being part of the primary output.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- IHRN Clinical Validation: Expert consensus using reference ECG patch data reviewed and adjudicated by clinicians and board-certified cardiologists.
8. The sample size for the training set:
- The document does not specify the sample size for the training set. It focuses on the validation study.
9. How the ground truth for the training set was established:
- The document does not specify how the ground truth for the training set (if any) was established. It only details the ground truth establishment for the test/validation set.
§ 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.