(227 days)
The Automatic Analysis and Interpretation Software Library is intended for use by qualified medical professionals for the assessment of arrhythmias using historic ambulatory ECG data. The product supports downloading and analyzing data recorded in compatible formats from any device used for the arrhythmia diagnostics such as Hotter, Event Monitor, 12 lead ambulatory or resting ECG devices, or other similar devices when assessment of the rhythm is necessary. The Automatic Analysis and Interpretation Software Library can also be electronically interfaced, and perform analysis with data transferred from other computer based ECG systems, such as an ECG management system. The Automatic Analysis and Interpretation Software Library provides ECG signal processing and analysis on a beat by beat basis, QRS and Ventricular Ectopic Beat detection, QRS feature extraction, interval measurement, heart rate measurement, and rhythm analysis for up to sixteen(16) leads of captured data. The library is not for use in life supporting or sustaining systems or ECG monitoring and Alarm devices. 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 Automated ECG Analysis and Interpretation 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 Monebo Automated ECG Analysis and Interpretation Software Library consists of a basic application for viewing, analyzing and annotating ECG data, and a 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 Automated ECG Analysis and Interpretation Software Library provides ECG signal processing, QRS detection and measurement of duration, QRS feature extraction, classification of Normal and Ventricular Ectopic beats, heart rate measurement, measurement of PR and QT intervals, and rhythm interpretation for up to 16 leads of captured ECG data. The library can be accessed through an Application Program Interface (API) as a callable function. This allows the library to be used as an accessory to an ECG management application or as a stand-alone product. Monebo will compile the Monebo Automated ECG Analysis and Interpretation Software Library specified by an ECG 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.
Here's a summary of the acceptance criteria and study details for the Monebo Automated ECG Analysis and Interpretation Software Library, based on the provided document:
1. Acceptance Criteria and Reported Device Performance
The acceptance criteria are implicitly defined by the results achieved in comparison to established benchmarks (AHA, MIT-BIH, CSE databases) for QRS detection, ventricular ectopic beat (VEB) detection, heart rate, and various arrhythmia statements. The document doesn't explicitly state pass/fail thresholds for each metric but reports the device's performance against these recognized standards.
Bench Test Results (per ANSI/AAMI EC 57):
| Summary results of AHA and MIT testing | QRS Se | QRS +P | VEB Se | VEB +P |
|---|---|---|---|---|
| AHA | 99.56 | 99.9 | 82.49 | 95.65 |
| MIT-BIH | 99.45 | 99.45 | 87.03 | 87.76 |
| NST | 91.56 | 85.66 | 81.79 | 53.19 |
Bench Test Results (per IEC 60601-2-51 for CSE Database):
The table provided for the CSE database is incomplete and contains corrupted text, making it impossible to extract specific criteria and performance values for measurement accuracy (mean difference and standard deviation).
Arrhythmia Detection Accuracy (Overall MIT DB):
| Sensitivity | Specificity | Positive Predictive Accuracy | Negative Predictive Accuracy | |
|---|---|---|---|---|
| Arrhythmia Detection (MIT DB) | 96 | 97 | 73 | 97 |
Accuracy of Specific Arrhythmia Statements (MIT DB):
| Arrhythmias | Sensitivity | Specificity | Positive Predictive Accuracy | Negative Predictive Accuracy |
|---|---|---|---|---|
| Normal sinus rhythm | 100 | 100 | 95 | 100 |
| PVC | 100 | 100 | 86 | 100 |
| APC | 96 | 66 | 70 | 66 |
| Atrial Fibrillation | 100 | 100 | 77 | 100 |
| Ventricular Tachycardia | 75 | 89 | 60 | 89 |
| Bradycardia | Insufficient data | 96 | Insufficient data | 96 |
| Tachycardia | Insufficient data | 100 | Insufficient data | 100 |
| AV block | 57 | 87 | 26 | 87 |
| BBB | 77 | 88 | 25 | 88 |
| Ventricular Trigeminy | 50 | 84 | 100 | 84 |
| Ventricular Bigeminy | 81 | 93 | 81 | 93 |
| AIVR | 100 | 100 | 15 | 100 |
| Pause | Insufficient data | Insufficient data | Insufficient data | Insufficient data |
(CU DB - Ventricular Flutter):
| Arrhythmias | Sensitivity | Specificity | Positive Predictive Accuracy | Negative Predictive Accuracy |
|---|---|---|---|---|
| Ventricular Flutter* | 100 | 94 | * | * |
| *Positive Predictive and Negative Predictive Accuracy cannot be calculated because all records contain VF. |
Rhythm Accuracy (250 Annotated ECG Strips):
| Rhythm | Sensitivity | Positive Predictivity | Specificity | False Positive Rate | Negative Predictivity |
|---|---|---|---|---|---|
| Normal sinus rhythm | 91.18 | 100.00 | 100.00 | 0.00 | 96.81 |
| Atrial fibrillation | 90.91 | 80.00 | 95.15 | 4.85 | 98.00 |
| Nodal rhythm | 76.47 | 46.43 | 93.56 | 6.44 | 98.20 |
| SVTA | 100.00 | 61.90 | 92.86 | 7.14 | 100.00 |
| Ventricular tachycardia | 100.00 | 85.71 | 99.59 | 0.41 | 100.00 |
| BBB | 82.14 | 79.31 | 97.30 | 2.73 | 97.74 |
| 1st degree AV block | 88.46 | 74.19 | 96.43 | 3.57 | 98.63 |
| 2nd degree AV block (Mobitz 1) | 96.77 | 100.00 | 100.00 | 0.00 | 99.55 |
| 2nd degree AV block (Mobitz 2) | 100.00 | 100.00 | 100.00 | 0.00 | 100.00 |
| Complete AV block | 96.77 | 100.00 | 100.00 | 0.00 | 99.55 |
| Idioventricular rhythm | 72.73 | 88.89 | 99.58 | 0.42 | 98.76 |
| Sinus bradycardia | 91.67 | 100.00 | 100.00 | 0.00 | 98.62 |
| Sinus tachycardia | 77.78 | 100.00 | 100.00 | 0.00 | 98.31 |
| APC | 77.50 | 65.26 | 80.59 | 19.41 | 88.39 |
| PVC | 89.55 | 73.17 | 87.98 | 12.02 | 95.83 |
| Pause | 96.88 | 73.81 | 94.95 | 5.05 | 99.52 |
| Overall Performance | 90.23 | 82.19 | 96.42 | 3.58 | 98.23 |
2. Sample Size Used for the Test Set and Data Provenance
The document indicates the following for test sets:
- AHA, MIT-BIH, NST (likely part of MIT-BIH): Standard databases used for benchmarking. The specific number of records/patients from these databases is not provided, but these are well-known, publicly available, and diverse datasets.
- Provenance: These are international, publicly available retrospective databases.
- CSE Database: Standard database used for benchmarking.
- Provenance: This is an international, publicly available retrospective database.
- MIT DB Arrhythmia Statements: Specific sections provide sensitivity, specificity, and predictive values for various arrhythmias using the MIT-BIH database.
- Provenance: International, publicly available retrospective database.
- 250 Annotated ECG Strips: Used for detailed rhythm classification metrics.
- Provenance: "renorded by various event recorders". The country of origin is not specified, nor is whether it's retrospective or prospective, but it implies a collection of real-world patient data.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
- The document does not specify the number or qualifications of experts used to establish the ground truth for any of the databases (AHA, MIT-BIH, CSE, or the 250 ECG strips). It relies on the pre-established annotations of these benchmark databases, which are generally considered expert-annotated.
4. Adjudication Method for the Test Set
- The document does not specify any adjudication method (e.g., 2+1, 3+1, none) for the test sets. It relies on the existing annotations within the standard databases.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No MRMC comparative effectiveness study is mentioned in the document. The study evaluates the standalone performance of the algorithm against established ground truths, not its impact on human reader performance.
6. Standalone (Algorithm Only) Performance Study
- Yes, a standalone performance study was done. The entire "Test Results" section (K062282, pg 2 and 3) details the performance of the "Monebo Automated ECG Analysis and Interpretation Software Library" in identifying QRS complexes, VEBs, and various arrhythmias against established benchmark databases (AHA, MIT-BIH, CSE) and a set of 250 annotated ECG strips. This directly measures the algorithm's performance without human intervention.
7. Type of Ground Truth Used
- The ground truth used for the studies appears to be expert consensus annotations as provided within the standard benchmark databases (AHA, MIT-BIH, CSE) and the "250 annotated ECG strips." These databases are conventionally annotated by electrophysiologists or cardiologists based on visual inspection and established diagnostic criteria. The document does not mention pathology or outcomes data as ground truth.
8. Sample Size for the Training Set
- The document does not specify the sample size or details about any training set used for the algorithm. The provided information focuses entirely on the validation and testing of the final algorithm's performance on external datasets.
9. How the Ground Truth for the Training Set Was Established
- Since no information about a training set is provided, there is no detail on how its ground truth 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).