Search Results

CardioConfirm is intended to be used by qualified clinicians to finalize cardiology reports for adult and pediatric patients. To aid the clinician's interpretation of resting ECGs, CardioConfirm supports the display and onscreen measurement of ECG waveforms. CardioConfirm also supports the algorithmic comparison of serial adult ECGs and allows the user to edit the automatic comparison statements.

CardioConfirm is intended to be controlled by a host application that manages user authentication, user permissions, and secure persistent storage of the tests.

CardioConfirm is a software component that is embedded into a host application (e.g. EMR) as a Dynamic Link Library (DLL) or launched as an executable application. CardioConfirm allows the user to display, edit and finalize diagnostic cardiology ECG, Stress and Holter reports. A Clinician can open a diaqnostic cardiology test from a workstation application and pass it to CardioConfirm as a DICOM object for viewing or editing. CardioConfirm is able to open and edit diagnostic cardiology ECG, Stress and Holter reports from Mortara Instrument, Inc. devices and offers an optional version which can edit diagnostic cardiology ECG, Stress and Holter reports from multiple diagnostic cardiology equipment vendors.

CardioConfirm allows the clinician the ability to view, measure, and compare previously acquired resting ECGs as well as perform visual and textual serial comparison of acquired ECGs. With visual serial comparison, the clinician can view current and previous ECG's simultaneously superimposed on the screen. Textual serial comparison allows the clinician to enter or edit text that describes the significant differences between the ECG's. For adult ECG's the initial text can be generated by the VERITAS SERIAL COMPARISON algorithm. The algorithm generates comparative statements automatically on the basis of the VERITAS INTERPRETATION statements originally made by the Mortara acquiring devices, measurements and the ECG waveforms. The clinician can edit the patient demographics, previous measurements and interpretations and the serial comparison statements, and then sign final ECG reports.

The clinician can also view and edit stress and Holter reports that includes editing patient demographics, summary statistics and physician conclusions. The clinician can electronically sign both stress and Holter final reports in CardioConfirm and print final reports or generate PDF copies to store in the host application. If a physician wants to amend a previously finalized report with additional information, CardioConfirm has an option to perform amendments to final reports and store the updated test in the host application.

CardioConfirm is available in two versions. The standard version is intended to be used with tests generated by Mortara equipment. The professional version is intended to be used with tests generated by any equipment that produces DICOM 12-lead ECG Waveform and Encapsulated PDF objects.

I will provide the information based on the text provided, which focuses on the regulatory submission and comparison to predicate devices, rather than a detailed study protocol for performance. The document primarily describes the device and asserts its substantial equivalence based on non-clinical data. It explicitly states that clinical data was not required.

Here's the breakdown of the information you requested, based on the provided text:

1. A table of acceptance criteria and the reported device performance

The provided text does not list specific numeric acceptance criteria for device performance or corresponding reported performance metrics in the format typically used for studies determining efficacy or accuracy (e.g., sensitivity, specificity, F1-score). Instead, it implicitly defines "performance" through a comparison of technological characteristics with predicate devices and emphasizes software verification and validation. The "reported device performance" is framed as performing "as intended" and demonstrating "substantial equivalence."

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document makes no mention of a "test set" in the context of clinical or performance data for the device. The "non-clinical data" and "software verification and validation" (Section 7) refer to engineering and software testing, not a dataset of patient cases used to evaluate the diagnostic or comparison algorithm's performance against human experts or ground truth. Therefore, sample size, data provenance, retrospective/prospective nature are not applicable or provided.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

Not applicable, as no clinical test set for evaluating diagnostic performance or algorithmic comparison accuracy is described in the provided text.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

Not applicable, as no clinical test set 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 MRMC study was done. The document explicitly states: "The subject of this premarket notification did not require clinical data to support substantial equivalence." (Section 7)

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

The document describes the device as providing "algorithmic comparison of serial adult ECGs" and mentions "The algorithm generates comparative statements automatically on the basis of the VERITAS INTERPRETATION statements originally made by the Mortara acquiring devices, measurements and the ECG waveforms." (Section 4). However, it does not provide performance metrics for this algorithm in a standalone capacity (e.g., sensitivity, specificity for identifying changes). It also states that users can "edit the automatic comparison statements" and "edit previously-signed interpretations," indicating that the device is intended for human-in-the-loop use. No standalone performance study as such is detailed.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

For the "VERITAS SERIAL COMPARISON algorithm" mentioned (which generates initial comparative statements), the ground truth for its development or internal validation is not explicitly stated. Given the context, it would likely be based on consensus interpretations by cardiologists or a similar expert review of ECG changes, but this is not specified in the document. For the overall device, the "ground truth" for its acceptance criteria revolved around demonstrating functional equivalence to existing devices and proper software engineering practices, rather than diagnostic accuracy against a clinical ground truth.

8. The sample size for the training set

The document does not mention a "training set" in the context of a machine learning or AI model that would typically require one for statistical performance evaluation. The "VERITAS SERIAL COMPARISON algorithm" implicitly refers to an algorithmic component, but details on its development data (training set) are not provided.

9. How the ground truth for the training set was established

Not applicable, as no "training set" is documented, nor is the establishment of its ground truth described.

Ask a specific question about this device