(139 days)
EK12 analyzes ten or more seconds of a previously acquired electrocardiogram (ECG) from physiological ECG signal recording devices for rhythm and measurements.
EK12 is used to create reports intended for use by a Qualified Medical Professional, including a trained ECG Technician operating within Independent Diagnosic Testing Facility (IDTF) requirements and performance standards for the review and assessment of an ECG.
EK12 is indicated for use on adults and pediatric patients older than 2 years. The device is intended for use in an IDTF or a professional medical facility, such as a hospital, clinic, or doctor's office.
The EK12 algorithm is a software only algorithm
The provided text is a 510(k) summary for the GE Medical Systems Information Technologies, Inc.'s EK12 Algorithm. While it discusses non-clinical tests and standards, it explicitly states that clinical studies were not required to support substantial equivalence, and thus, does not provide detailed information about a study proving the device meets acceptance criteria derived from clinical performance.
However, it does reference compliance with a voluntary standard, AAMI/ANSI EC57: 2012 – Testing And Reporting Performance Results Of Cardiac Rhythm and ST-Segment Measurement Algorithms. This standard likely defines acceptance criteria for rhythm and ST-segment measurement algorithms. Without the full standard, I can only infer the type of criteria.
Based on the information provided, here's what can be extracted:
1. Table of Acceptance Criteria and Reported Device Performance:
The document states: "The EK12 Algorithm program was designed and tested for compliance with applicable clauses of the following voluntary standard: AAMI/ANSI EC57: 2012 – Testing And Reporting Performance Results Of Cardiac Rhythm and St-Segment Measurement Algorithms."
Since no specific acceptance criteria or reported performance values are explicitly stated in this 510(k) summary, I cannot populate a table with the exact metrics. However, conceptually, the table would look like this if the data were available:
| Feature / Metric (as per AAMI/ANSI EC57) | Acceptance Criteria (from AAMI/ANSI EC57) | Reported Device Performance (EK12 Algorithm) | Result (Met/Not Met) |
|---|---|---|---|
| Rhythm Detection Accuracy | X% Sensitivity, Y% Specificity | N/A (data not provided) | N/A |
| ST-segment Measurement Accuracy (e.g., bias, precision) | Within +/- Z μV (or other unit) | N/A (data not provided) | N/A |
| Heart Rate Accuracy | Within +/- W bpm | N/A (data not provided) | N/A |
| Arrhythmia Classification Accuracy | Appropriate metrics for each arrhythmia | N/A (data not provided) | N/A |
| ... (other relevant metrics from AAMI/ANSI EC57) | ... | N/A (data not provided) | N/A |
2. Sample Size Used for the Test Set and Data Provenance:
The document does not explicitly state the sample size for a "test set" or its data provenance. It refers to "Software Verification Testing" and "Performance testing" but does not detail the datasets used for these. Given it's a non-clinical evaluation, it's possible simulated data or pre-existing standard datasets (e.g., MIT-BIH Arrhythmia Database, European ST-T Database) might have been used, but this is not mentioned.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:
This information is not provided. As per the document: "The subject of this premarket submission, EK12 Algorithm, did not require clinical studies to support substantial equivalence." Therefore, there's no mention of expert-adjudicated ground truth for a clinical test set. If the non-clinical performance testing involved expert annotation, it is not detailed here.
4. Adjudication Method for the Test Set:
Not applicable, as no clinical test set or expert ground truth establishment is described.
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, an MRMC comparative effectiveness study was not conducted or reported in this document. The device did not require clinical studies/data.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done:
Yes, the testing described appears to be for the standalone algorithm, as it refers to "Software Verification Testing" and "Performance testing" of the "EK12 Algorithm program" for compliance with a cardiac rhythm and ST-segment measurement standard. The intended use states that EK12 "is used to create reports intended for use by a Qualified Medical Professional" who performs review and assessment, indicating it's a decision support tool, but the testing itself would be for the algorithm's output.
7. The Type of Ground Truth Used:
The document does not specify the type of ground truth. Given compliance with AAMI/ANSI EC57, the standard typically defines methods for establishing ground truth, often relying on a combination of expert review (e.g., highly experienced cardiologists or electrophysiologists) of ECGs, sometimes corroborated with clinical outcomes or other diagnostic tests, for standardized databases. However, the specific method used for the EK12's performance testing is not detailed here.
8. The Sample Size for the Training Set:
The document does not provide the sample size for the training set. It only mentions the "EK12 Algorithm" as a software-only algorithm and its testing for compliance.
9. How the Ground Truth for the Training Set was Established:
The document does not provide information on how the ground truth for the training set was established.
§ 870.1025 Arrhythmia detector and alarm (including ST-segment measurement and alarm).
(a)
Identification. The arrhythmia detector and alarm device monitors an electrocardiogram and is designed to produce a visible or audible signal or alarm when atrial or ventricular arrhythmia, such as premature contraction or ventricular fibrillation, occurs.(b)
Classification. Class II (special controls). The guidance document entitled “Class II Special Controls Guidance Document: Arrhythmia Detector and Alarm” will serve as the special control. See § 870.1 for the availability of this guidance document.