(249 days)
The B-Secur HeartKey Software Library is intended to be used by medical device manufacturers in medical devices to assess a single lead ECG spot checks from adult patients. The product allows the processing and extraction of beats from an ECG signal to provide a heart rate reading and ECG rhythm analysis. The library will classify a 30 second ECG spot check recording as normal sinus rhythm, atrial fibrillation, bradycardia, and tachycardia, unreadable or inconclusive.
The library is intended to be integrated into other device software. All interpretations must be reviewed by a medical professional for clinical decision making, and the user of the device should not make changes to their medication without consulting a physician.
The library is not intended for use in life supporting or sustaining systems, or cardiac alarm systems.
The B-Secur HeartKey Software Library is an "object library". An object library is a collection of callable functions that have been compiled into native machine code of the computer on which they will execute. The HeartKey Software Library includes a basic application for viewing and analyzing electrocardiogram (ECG) data. The source code for the library is not available and cannot be modified by the end user.
The B-Secur HeartKey Software Library provides ECG signal processing and QRS detection for a single lead ECG 30s spot check. System input lead is configurable based on the application, but the typical application is arrhythmia screening from a Lead I stainless steel dry electrode device capable of carrying out periodic spot checks.
The software library is designed to accept a digital ECG stream and produce several metrics.
Acceptance Criteria and Study Details for B-Secur HeartKey Software Library (K200884)
The B-Secur HeartKey Software Library is intended for medical device manufacturers to assess single-lead ECG spot checks from adult patients. It processes ECG signals to provide heart rate and classify ECG rhythms as normal sinus rhythm, atrial fibrillation, bradycardia, tachycardia, unreadable, or inconclusive.
1. Acceptance Criteria and Reported Device Performance
The document does not explicitly state numerical acceptance criteria. However, it indicates that the algorithm's performance was assessed to ensure it "performs to its specifications and meets its intended use, which is substantially equivalent to that of the predicate device."
The study compared the HeartKey Software Library's performance against its specifications and those implied by its equivalence to the predicate device. The performance focused on:
- Heart Rate Validation
- Tachycardia and Bradycardia Validation
- Atrial Fibrillation Validation
- Arrhythmia Detection Validation
While specific numerical performance metrics for the HeartKey Software Library are not provided, the document states: "The results of the testing demonstrate that the HeartKey® Software Library performs to its specifications and meets its intended use, which is substantially equivalent to that of the predicate device."
2. Sample Size and Data Provenance for Test Set
The document states that algorithm performance testing was assessed using:
- ECG databases from ANSI/AAMI EC57:2012: This standard outlines requirements for ambulatory electrocardiographs. These are likely established, publicly available databases.
- B-Secur proprietary datasets: The specifics of these datasets are not detailed, so information on their country of origin or whether they are retrospective or prospective is not available in this document.
The exact sample size used for the test set is not explicitly mentioned.
3. Number and Qualifications of Experts for Ground Truth
The document does not specify the "number of experts" used to establish ground truth for the test set or their "qualifications." It generally refers to using "ECG databases from ANSI/AAMI EC57:2012 and other proprietary datasets," which would typically have expert-derived ground truth.
4. Adjudication Method for Test Set
The document does not describe any specific adjudication method (e.g., 2+1, 3+1) for establishing the ground truth of the test set.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No Multi-Reader Multi-Case (MRMC) comparative effectiveness study is mentioned in the provided text. The submission focuses on the standalone performance of the algorithm and its equivalence to a predicate, not on human-in-the-loop performance improvement.
6. Standalone Performance (Algorithm Only) Study
Yes, a standalone performance study was conducted. The document states: "Non-clinical testing was conducted to assess algorithm performance and to verify that the HeartKey® Software Library performs as intended including Heart Rate Validation, Tachycardia and Bradycardia Validation, Atrial Fibrillation Validation and Arrhythmia Detection Validation." This indicates that the algorithm's performance was evaluated inherently, without human intervention in the interpretation process.
7. Type of Ground Truth Used
The ground truth for the performance assessment was derived from "ECG databases from ANSI/AAMI EC57:2012 and other proprietary datasets." While not explicitly stated, such databases typically involve expert consensus or board-certified cardiologist interpretations to establish the definitive rhythm classifications and heart rate measurements.
8. Sample Size for Training Set
The document does not explicitly state the sample size used for the training set. It only mentions the databases used for performance testing.
9. How Ground Truth for Training Set Was Established
The document does not explicitly detail how the ground truth for the training set was established. However, given that performance testing used "ECG databases from ANSI/AAMI EC57:2012 and other proprietary datasets," it is reasonable to infer that similar methods (likely expert consensus or interpretations from cardiologists) would have been used for any training data derived from these or similar sources.
§ 870.2340 Electrocardiograph.
(a)
Identification. An electrocardiograph is a device used to process the electrical signal transmitted through two or more electrocardiograph electrodes and to produce a visual display of the electrical signal produced by the heart.(b)
Classification. Class II (performance standards).