(531 days)
Guava II is intended to be used by cardiologists, general practitioners, cardiac or ECG technicians, nurses, monitoring service technicians, and other cardiac related institutions or care givers to store, retrieve, communicate and report ECG and ECG data acquired from a variety of ECG sources including single and multilead ECG devices. Guava II is intended to be electronically interfaced, and perform analysis with data transferred from other computer based ECG systems. Guava II includes an algorithm that will analyze the 12 Lead ECG and produce measurements of the ECG recording as well as textual interpretation. The product also includes an automatic analysis and interpretation software library that 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 twelve (12) leads of historic ambulatory ECG data. The Guava II algorithm analysis can detect and classify arrhythmias and may be used to triage data, however, Guava II is not intended to offer independent diagnosis or provide medical alarms. Clinical judgment and experience are used to check and interpret the data as part of a diagnosis. Guava II is not for use in lifesupporting or sustaining systems or EGG monitoring devices. Guava II is intended for use in clinics, hospitals, physician's offices, or anywhere a medical doctor deems appropriate.
The Guava II is a medical device software with a formal Application Programming Interface (API). The API can be invoked from Host Applications to provide services for capturing, storing, retrieving, viewing, editing, and analyzing ECGs (1-, 2-, 3-Channel and 12-Lead) and other Biosignals. Guava II may also be licensed to 3rd party organizations interested in embedding the capabilities within their own products. When the Guava II is used in other medical products, manufacturers will identify the indications for use depending on the application of their device.
The Guava II is not a life-supporting or life-sustaining system. It is intended that competent human intervention be involved before any impact on health occurs. Clinical judgment and experience are used to check and interpret the data.
Here's an analysis of the acceptance criteria and study information for the Guava II device based on the provided 510(k) summary:
Acceptance Criteria and Reported Device Performance
The provided document does not explicitly list specific numerical acceptance criteria (e.g., sensitivity, specificity, accuracy targets) nor provide detailed quantitative performance metrics for the Guava II device's algorithm. Instead, the performance testing section broadly states:
- "The device complies with AAMI EC11 and AAMI EC38 standards."
- "Verification and validation activities related to the device modification were performed on the applicant device, and the predetermined acceptance criteria were met in all cases."
Without specific numerical criteria or results, a table of acceptance criteria and reported performance cannot be generated in the traditional sense of metrics like sensitivity or accuracy. The "acceptance criteria" here are defined by compliance with AAMI standards and the successful outcome of the V&V activities.
If we were to infer the "reported performance" based on the conclusion, it would be "substantially equivalent to the predicate devices" and that its functions are "identical in function" to the QRS Algorithm in the predicate device.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criterion | Reported Device Performance |
|---|---|
| Compliance with AAMI EC11 and AAMI EC38 standards | "The device complies with AAMI EC11 and AAMI EC38 standards." |
| Predetermined acceptance criteria for V&V activities | "Predetermined acceptance criteria were met in all cases." |
| QRS Algorithm Functionality | "identical in function to the QRS Algorithm embedded in GlobalCardio." |
2. Sample size used for the test set and the data provenance:
- Test Set Sample Size: Not specified in the provided document.
- Data Provenance: Not specified in the provided document.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not specified.
- Qualifications of Experts: Not specified.
- The Intended Use section states that "Clinical judgment and experience are used to check and interpret the data as part of a diagnosis," implying human expertise is involved in the clinical workflow, but this does not directly describe the establishment of a ground truth for a test set in a study.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not specified.
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 is mentioned. The study described focuses on the device's own performance and its equivalence to predicate devices, not on human reader improvement.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance assessment of the algorithm appears to have been conducted. The statement "The Guava II Louvain Data Processor performs automated ECG analysis and interpretation in the same manner as GlobalCardio. The two products use the identical machine code library (DLL) to perform the analysis, and testing demonstrates the QRS Algorithm embedded in the Guava II Louvain Data Processor is identical in function to the QRS Algorithm embedded in GlobalCardio" suggests a direct comparison of the algorithm's output.
- "Verification and validation activities related to the device modification were performed on the applicant device, and the predetermined acceptance criteria were met in all cases. The activities included scenario validations, algorithm confirmation testing, and device functional testing." This also points to standalone algorithm testing.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The document does not explicitly state the type of ground truth used for performance testing. However, given the context of ECG analysis and comparison to a predicate device, it is common for the ground truth to be established by expert cardiologist review/consensus of the ECG waveforms, or by comparison to the established accuracy of the predicate's algorithm (implying the predicate’s ground truth method was implicitly used). The closest hint is the reference to "Clinical judgment and experience are used to check and interpret the data."
8. The sample size for the training set:
- Not specified. The document primarily discusses performance testing and equivalence to predicate devices, not the development or training of the algorithm.
9. How the ground truth for the training set was established:
- Not specified. As no training set information is provided, no details on its ground truth establishment are available.
§ 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).