(90 days)
VISUALIZATION AND MEASUREMENT OF ECG BY TRAINED USED RECORDINGS TO BE MEDICAL CONDITION. MON | TORING CARDIAC IN THE OF STAFF
The Cardio Vision software is a program which runs on a personal computer and is used for the display and storage of Electrocardiogram recordings. The software receives an input signal containing the ECG data from an ECG receiving center. The receiving center is connected to the computer on which the Cardio Vision software is running via a serial port. The ECG receiving center receives the ECG signal from an ECG recording device either via direct connection or via telephone. The software interprets the digital signal and displays it on the screen in real time as a single or multiple lead ECG plot.
The received ECG signal can be stored on the disk and can be compared to previous ECG recordings for that patient. In addition, measurements can be performed on the ECG plot.
The provided text describes the Cardio Vision Software, an ECG display and storage program. Here's a breakdown of the acceptance criteria and study information:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criterion (Implicit) | Reported Device Performance |
|---|---|
| Data sampling and processing accuracy | "Comparison of the log file with the original signal verified that the data sampling and data processing modules function properly." |
| Data display accuracy and scaling | "Using the ECG display module to display data from prepared files verified that the data was displayed properly and in the correct scale." |
| Consistency and accuracy of ECG data processing and presentation | "The comparison of Cardio Vision Software printouts with simultaneous ECG strip chart output demonstrated that the Cardio Vision Software processes and presents ECG data consistently and accurately." |
| Substantial equivalence to predicate devices | "The safety and effectiveness of the Cardio Vision software are similar to that of its predicate devices. It is SHL's opinion that the Cardio Vision software is substantially equivalent to its legally marketed predicate devices in terms of safety and effectiveness." (This is a claim of equivalence, supported by the above bench and clinical data). |
2. Sample Size Used for the Test Set and Data Provenance
The document does not explicitly state a specific sample size for a "test set" in the context of clinical trials or an independent validation study. The "Bench Data" section refers to an "artificial signal" and "prepared files," which implies synthetic or pre-recorded data for testing specific functionalities. The "Clinical Data" section refers to "simultaneous ECG strip chart output," suggesting real patient data, but no further details on the number of patients, recordings, or their provenance (country, retrospective/prospective) are provided.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications
The document does not detail any expert review process for establishing ground truth for a test set. The validation primarily relies on comparison with "original signals" (for bench data) and "simultaneous ECG strip chart output" (for clinical data), implying these were considered the ground truth references. There is no mention of human experts directly annotating or establishing ground truth for the purpose of evaluating the device.
4. Adjudication Method for the Test Set
No adjudication method (e.g., 2+1, 3+1) is mentioned, as there is no indication of multiple independent expert reviewers establishing a ground truth that would require adjudication.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done. The document does not describe any study involving human readers with and without AI assistance, nor does it provide an effect size for such a comparison.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
Yes, the studies described are essentially standalone evaluations of the algorithm's performance.
- Bench Data: "An artificial signal was fed into the receiving center, and the resulting ECG data was displayed and written to a log file. Comparison of the log file with the original signal verified that the data sampling and data processing modules function properly." This is an algorithm-only test.
- Clinical Data: "The comparison of Cardio Vision Software printouts with simultaneous ECG strip chart output demonstrated that the Cardio Vision Software processes and presents ECG data consistently and accurately." This also evaluates the software's output against a reference without explicit human intervention in the interpretation of the software's output for evaluation purposes.
7. Type of Ground Truth Used
- Bench Data: The ground truth for the bench data was the "original artificial signal."
- Clinical Data: The ground truth for the clinical data was "simultaneous ECG strip chart output." This suggests the output from a traditional, established ECG recording method was used as the reference standard.
8. Sample Size for the Training Set
The document does not provide any information about a training set for the Cardio Vision Software. This suggests the software is primarily a display and storage tool, not an AI/ML-based diagnostic algorithm that learns from a training set. The descriptions focus on its functionality in processing and presenting data, rather than making automated interpretations or diagnoses.
9. How the Ground Truth for the Training Set Was Established
As no training set is mentioned or implied, the establishment of ground truth for a training set is not applicable to this device description.
§ 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).