(139 days)
The Automatic Arrhythmia Detection Software Library is intended for use by qualified medical professionals for assessing historic ambulatory ECG data. The product allows downloading and analyzing data recorded in compatible format by Holter or Event monitoring devices. The Automatic Arrhythmia Detection Software Library provides ECG signal processing and analysis on a beat by beat basis, QRS and Ventricular Ectopic Beat detection, and QRS feature extraction.
The product can be integrated into computerized ECG monitoring devices. In this case the medical device manufacturer will identify the indication for use depending on the application of their device.
The Monebo Automatic Arrhythmia Detection Software Library is an "object library". An object library is a collection of callable functions that have been complied (or assembled) into machine code or IDL code of the computer on which they execute. The Automatic Arrhythmia Detection Software Library consists of a basic application for viewing, analyzing and annotating ECG data and callable object library built on the Microsoft .Net framework. An application software program can be written to invoke some or all of the functions in an object library.
The Monebo Automatic Arrhythmia Detection Software Library provides ECG signal processing, QRS detection, QRS feature extraction, and ventricular ectopic beat detection for up to 12 leads of captured ECG data.
Monebo will compile the Automatic Arrhythmia Detection Software Library specified by an ECG analysis device manufacturer. An object library will be created and delivered to the device manufacturer, who can then integrate it into application software for their ECG analysis. The device manufacturer will be required to submit a 510k with the specific requirements for that device.
Here's an analysis of the acceptance criteria and study data for the Monebo Automatic Arrhythmia Detection Software Library, Version 1:
1. Table of Acceptance Criteria and Reported Device Performance:
The document does not explicitly state "acceptance criteria" in terms of specific thresholds the device needed to meet to be considered effective. However, the performance metrics observed in the bench tests are presented, and by comparing these to industry standards or expectations for such devices, we can infer what might have been considered "acceptable." Given the device received 510(k) clearance, the reported performance was deemed sufficient by the FDA for substantial equivalence.
| Metric (Implied Acceptance Criteria) | Reported Performance (AHA Database) | Reported Performance (MIT-BIH Database) | Reported Performance (NST Database) |
|---|---|---|---|
| QRS Sensitivity (Se) | 99.56% | 99.45% | 91.56% |
| QRS Positive Predictivity (+P) | 99.9% | 99.45% | 85.66% |
| VEB Sensitivity (Se) | 82.49% | 87.03% | 81.79% |
| VEB Positive Predictivity (+P) | 95.65% | 87.76% | 53.19% |
Explanation of Metrics:
- QRS Se (Sensitivity): The percentage of actual QRS complexes correctly identified by the software.
- QRS +P (Positive Predictivity): The percentage of QRS detections made by the software that were actually QRS complexes.
- VEB Se (Ventricular Ectopic Beat Sensitivity): The percentage of actual Ventricular Ectopic Beats correctly identified by the software.
- VEB +P (Ventricular Ectopic Beat Positive Predictivity): The percentage of Ventricular Ectopic Beat detections made by the software that were actually Ventricular Ectopic Beats.
2. Sample Size Used for the Test Set and Data Provenance:
- Sample Size: The document refers to "AHA and MIT-BIH databases" and an "NST database." These are well-known, publicly available databases of ECG recordings, often used for benchmarking arrhythmia detection algorithms. The specific number of recordings or patients from each database used for testing is not explicitly stated in this summary.
- Data Provenance:
- Country of Origin: Not specified for the AHA and MIT-BIH databases, but they are recognized international standards. The NST database's origin is also not specified.
- Retrospective or Prospective: These databases typically consist of retrospective ECG recordings collected over time for research and testing purposes.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:
The document does not provide information on the number or qualifications of experts used to establish the ground truth for the AHA, MIT-BIH, or NST databases. However, it's widely known that these databases were meticulously annotated by multiple cardiologists and electrophysiologists using established criteria to create the "gold standard" annotations.
4. Adjudication Method for the Test Set:
The document does not explicitly state the adjudication method used for the creation of the ground truth in the AHA, MIT-BIH, or NST databases. However, for such widely accepted benchmark databases, a rigorous consensus-based adjudication process involving multiple experts is standard practice to establish the ground truth.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:
No, the provided document does not describe a Multi-Reader Multi-Case (MRMC) comparative effectiveness study. The study presented is a standalone performance evaluation of the algorithm against existing, expert-annotated databases. Therefore, there is no effect size reported for human readers improving with AI vs. without AI assistance.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done:
Yes, a standalone performance study was done. The "Test Results" section explicitly states "The bench test results of the software using AHA and MIT-BIH databases are show in the table below." This indicates that the algorithm's performance was evaluated purely on its own, without a human in the loop, against the ground truth annotations in these databases.
7. The Type of Ground Truth Used:
The type of ground truth used was expert consensus annotations. The AHA and MIT-BIH databases, in particular, are renowned for having their ECG recordings meticulously annotated by multiple expert cardiologists and electrophysiologists, creating a "gold standard" for various cardiac events, including QRS complexes and ventricular ectopic beats.
8. The Sample Size for the Training Set:
The document does not provide any information regarding the sample size used for the training set for the Monebo Automatic Arrhythmia Detection Software Library. It only discusses the test results on the specified databases.
9. How the Ground Truth for the Training Set was Established:
Since the document does not mention the training set or its sample size, it also does not provide information on how the ground truth for the training set was established.
§ 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).