(99 days)
The Midmark IQecg is indicated for use, under the supervision of a Physician, to obtain electrocardiograms from the adult and pediatric human body surface. The process of taking an electrocardiogram is non-invasive, painless, without direct risk to the patient and is reproducible.
The Midmark IQecg is a PC based 12-lead resting diagnostic electrocardiograph with interpretation and data storage capabilities. Together with the Midmark IQmanager software running on Microsoft Windows operating systems, the IQecg device can acquire 12-lead ECG (electrocardiogram) data, generate ECG measurement and interpretation results, provide review/edit functions to modify the measurement and interpretation results, store the ECG data and report in a database, archive the ECG reports for future reference and share the ECG reports with other physicians via network or email. The IQecg can also be connected to servers and electronic medical records.
The provided document is a 510(k) Pre-market Notification for the Midmark IQecg, a resting diagnostic electrocardiograph. It details the device description, technological comparison to a predicate device, intended use, and general performance testing. However, it does not contain detailed information regarding specific acceptance criteria, a comprehensive study proving the device meets those criteria, or the methodology typically associated with AI/ML device studies (e.g., ground truth establishment, sample sizes for training/test sets, expert adjudication, MRMC studies).
The document is a regulatory submission for a traditional medical device, not an AI/ML powered device, which would typically involve different types of performance testing and reporting for its interpretative algorithms. The "interpretation" provided by the IQecg is likely based on established, rule-based algorithms for ECG analysis, rather than a machine learning model.
Therefore, many of the requested data points (like sample sizes for test/training sets, detailed ground truth establishment, expert adjudication, MRMC studies, or standalone performance for an AI algorithm) are not explicitly available or applicable in this document.
1. Table of Acceptance Criteria and Reported Device Performance
The document states that "The Midmark IQecg was tested in accordance with requirements and procedures, and test results indicated that the device complies with the predetermined requirements." However, the specific acceptance criteria and detailed quantitative performance metrics are not provided in this summary. The comparison focuses on technological characteristics rather than clinical performance metrics or specific algorithm accuracy.
| Acceptance Criteria (Not Explicitly Stated in Document) | Reported Device Performance |
|---|---|
| Not provided in detail. General statement: "complies with the predetermined requirements." | Frequency response bandwidth: 0.05Hz - 150Hz |
| ECG signal sampling rate: 500 samples/second | |
| QTc Measurement: User selects up to 2 from 4 formulas (Hodges, Bazett, Framingham, Fridericia). Default is Hodges. | |
| "as safe and performs as effectively as the predicate device." |
2. Sample size used for the test set and the data provenance
- Sample Size for Test Set: Not specified.
- Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). The document mentions "Performance Testing" was conducted, but details are absent.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable/Not specified. For this type of traditional ECG device with established interpretation algorithms, ground truth for performance testing is typically based on standardized databases or reference ECG recordings with known arrhythmias/morphologies, rather than expert consensus on individual cases for algorithm validation as would be common for new AI/ML systems.
4. Adjudication method for the test set
Not applicable/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
Not applicable. This device predates the widespread use of sophisticated AI for ECG interpretation requiring such studies in regulatory submissions. The interpretation component is likely based on established, rule-based algorithms, not a novel AI model that would assist human readers in an MRMC study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The device is described as having "interpretation results." While the performance of this interpretation algorithm was likely assessed, the specifics of this "standalone" performance testing (e.g., metrics like sensitivity, specificity for various conditions) are not detailed in the provided summary. The comparison focuses on hardware specifications and QTc calculation methods, implying that the interpretation algorithm itself is substantially equivalent to the predicate.
7. The type of ground truth used
Not specified. For ECG interpretation algorithms, ground truth often comes from:
- Standardized ECG databases (e.g., MIT-BIH Arrhythmia Database).
- Clinically adjudicated ECGs (though details of adjudication would be needed).
- Correlation with other diagnostic tests or clinical outcomes.
Given this is a traditional ECG device, it's highly probable it relies on established benchmarks.
8. The sample size for the training set
Not applicable/Not specified. For traditional rule-based algorithms, there isn't a "training set" in the machine learning sense. If the interpretation component involved statistical models, the data used to develop them is not mentioned.
9. How the ground truth for the training set was established
Not applicable/Not specified, as it's not an AI/ML device with a training set.
§ 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).