Search Results

Horizon Cardiology™ ECG Management is a software application designed to import, display, store, analyze, distribute and manage information related to ECG procedures of adult and pediatric patients from external ECG devices.

Horizon Cardiology™ ECG Management allows analysis of resting ECGs and provides preliminary data for editing and confirmation by an over-reading physician. Horizon Cardiology ECG Management can also provide a serial comparison of resting ECG data to facilitate review of a patient's current ECG with previous ECGs of the same patient.

Horizon Cardiology™ ECG Management is intended to be used under the direct supervision of a licensed healthcare practitioner and by trained operators in a hospital or facility providing patient care. Horizon Cardiology ECG Management is not intended for real-time monitoring.

Horizon Cardiology™ ECG Management is a standard ECG management system for importing ECG waveform data, reviewing, performing measurements, diagnosis and comparison of ECG procedures and storing them for future review and management.

Horizon Cardiology™ ECG Management functions as a non-real time system. It receives ECG procedure files after the cessation of the ECG procedure, which can originate from any one of a variety of manufacturer's cardiographs, Stress ECG machines, Holter recording devices or Holter analysis and review stations. Horizon Cardiology™ ECG Management acquires the ECG waveforms through a network connection or via a diskette, and normalizes them to a common format. If the ECG cart has made an ECG procedure analysis, Horizon Cardiology™ ECG Management presents it and utilizes the Glasgow University Interpretive Algorithm to perform its own measurements, diagnosis and serial comparison without changing the raw waveform data.

Horizon Cardiology™ ECG Management acquires the Stress and Holter ECG files in PDF format through a network connection, modem or via a portable media (diskette, SD card, etc.) or wireless device and stores them in their original format without changing the file.

Horizon Cardiology™ ECG Management uses an intuitive interface, which provides tools to edit measurements and procedure diagnoses and enables the physician to seamlessly review numerous ECG procedures. Horizon Cardiology™ ECG Management complies with HL7 standards for export to the Hospital Information System (HIS) to provide billing information. Horizon Cardiology7™ ECG Management supports final ECG report distribution by printing, faxing, e-mailing and automatic export to other systems. The Horizon Cardiology™ ECG Management database complies with the requirements of HIPAA through robust password security, record access security and file allocation in a secure and managed server.

Horizon Cardiology™ ECG Management allows access to ECG records from web-enabled PC's throughout a network and enables authorized clinical users to access the system from remote locations.

The provided text describes McKesson Israel Ltd.'s Horizon Cardiology™ ECG Management system. It is a software application designed to import, display, store, analyze, distribute, and manage information related to ECG procedures. The analysis component uses the Glasgow University Interpretive Algorithm.

However, the provided document does not contain acceptance criteria for specific performance metrics (like sensitivity, specificity, accuracy, or reader improvement). It states that "Verification and validation testing was performed on Horizon Cardiology™ ECG Management to ensure it met all specifications. The device was further validated to ensure that it performs as intended. In all instances, Horizon Cardiology™ ECG Management functioned as intended and the results observed demonstrate substantial equivalence with the predicate devices."

This indicates that the study focused on demonstrating substantial equivalence to predicate devices (Medcon Ltd.'s Horizon Cardiology ECG (K061905) and GE Healthcare's GE MUSE® Cardiology Information System (K110132)). Substantial equivalence claims generally rely on demonstrating that the new device has the same intended use, similar technological characteristics, and principles of operation, and does not raise new issues of safety or effectiveness. This is often achieved through comparative analysis of features and functionality rather than rigorous statistical performance testing against predefined criteria for diagnostic accuracy.

Therefore, many of the requested details about acceptance criteria and specific study designs are not present in this 510(k) summary.

Here's a breakdown of what can be extracted and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size Used for the Test Set and Data Provenance

• Test Set Sample Size: Not specified.
• Data Provenance (country of origin, retrospective/prospective): Not specified.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

• Not specified. The document states the system "provides preliminary data for editing and confirmation by an over-reading physician," implying physician review but not detailing its role in establishing formal ground truth for validation.

4. Adjudication Method for the Test Set

• Not specified.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

• Was an MRMC study done? No, an MRMC study focused on comparing human readers with and without AI assistance is not described. The validation focuses on the system itself and its equivalence to predicate devices.
• Effect Size of Human Readers Improve with AI vs. without AI assistance: Not applicable, as no such study is described.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop) Performance Was Done

• Was a standalone study done? The document indicates that the device performs its own measurements, diagnosis, and serial comparison using the Glasgow University Interpretive Algorithm. It "provides preliminary data for editing and confirmation by an over-reading physician." This implies a standalone diagnostic output that is then subject to physician review. However, the document does not present specific performance metrics for this standalone output against a ground truth. The "performance data" section focuses on meeting specifications and substantial equivalence rather than diagnostic accuracy.

7. The Type of Ground Truth Used

• Type of Ground Truth: Not explicitly stated for performance evaluation. For the system's intended use, the "over-reading physician" is expected to confirm or edit the preliminary analysis, suggesting physician consensus or final readings as the de facto clinical ground truth. However, for the validation study, the specific method of establishing ground truth for performance metrics is absent.

8. The Sample Size for the Training Set

• Training Set Sample Size: Not applicable. The document describes a system that utilizes the Glasgow University Interpretive Algorithm, an established algorithm, rather than a de novo machine learning model trained on a specific dataset. Therefore, there isn't a "training set" in the context of training a novel AI algorithm.

9. How the Ground Truth for the Training Set Was Established

• How Ground Truth for Training Set was Established: Not applicable, as the device uses an established algorithm rather than a newly trained AI model.

Ask a specific question about this device