Search Results

The intended user is a medical device manufacturer who will integrate the ST/AR Library into a computerized cardiac monitoring device. The ST/AR Library integrator will ultimately identify the indications for use, depending on the nature of their device.

The analysis capabilities of the ST/AR Library are indicated for monitoring and detecting the following from up to 12 body surface ECG leads for adult, pediatric, or neonatal patients:

• QRS detection
• ventricular ectopic beat detection (non-paced only)
• rhythm call analysis, including asystole, bigeminy, couplets, irregular heart rate, pause or missed beat, VEB/minute, run, trigeminy, triplets, ventricular tachycardia
• ST segment level measurement (adult patients only)
• ventricular fibrillation detection

The Brentwood Real Time ST and Arrhythmia Analysis Software Library is an "object library'. An object library is a collection of callable functions that have been compiled (or assembled) into the native machine code of the computer on which they will execute. An application software program can be written to invoke some or all of the functions in an object library. The compiled (or assembled) application code can be "linked" to the called functions from an object library at the time the executable code image is built. An executable code image created in this manner will contain the application software code and all of the functions it invoked from the object library.

The Brentwood Real Time ST and Arrhythmia Analysis Software Library consists of a collection of ANSI Standard C (ISO/IEC 9899) callable functions. It provides real time ECG signal processing, QRS detection, QRS complex feature extraction, ventricular ectopic beat detection, ST level measurement, rhythm calls, and ventricular fibrillation detection capabilities for up to 12 leads of captured ECG lead data.

Brentwood will compile the Brentwood Real Time ST and Arrhythmia Analysis Software Library using the compiler specified by an ECG analysis device manufacturer. An object library will be created and delivered to the manufacturer, who can then integrate it into application software for their ECG analysis device(s).

Here's a breakdown of the acceptance criteria and study information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document states that performance testing was conducted in accordance with ANSI/AAMI EC57:1998. This standard defines the acceptance criteria for these types of measurements. While the specific numerical acceptance criteria for each metric (e.g., QRS detection sensitivity/specificity, heart rate accuracy, VEB detection accuracy) are not explicitly stated in the provided text, the document implies that the device met these criteria by stating "The following testing was performed in accordance with ANSI/AAMI EC57:1998 to evaluate the performance of the Brentwood Real Time ST and Arrhythmia Analysis Software Library." and subsequently receiving FDA clearance.

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

• Sample Size for Test Set: Not explicitly stated as a number of patients or recordings. However, the study used the following standard databases:
  • AHA (American Heart Association) database
  • MIT-BIH Arrhythmia Database
  • NST (noise stress test) database
  • CU (Creighton University) database (for ventricular fibrillation specifically)
  • ESC (European Society of Cardiology) database (for ST segment analysis specifically)
• Data Provenance: Retrospective, as standard, publicly available databases (AHA, MIT-BIH, NST, CU, ESC) were utilized. The country of origin of these databases is generally international, with MIT-BIH being U.S.-based.

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

• Number of Experts: Not specified in the provided text.
• Qualifications of Experts: Not specified in the provided text. However, for established standard databases like MIT-BIH and AHA, the ground truth annotations are typically performed by experienced cardiologists or electrophysiologists.

4. Adjudication Method for the Test Set

• Adjudication Method: Not specified in the provided text. For established standard databases, the ground truth may have been generated through consensus or a "gold standard" based on expert review.

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

• MRMC Study: No, an MRMC comparative effectiveness study was not performed. The testing focused on the standalone performance of the software library against established databases, not on comparing human readers with and without AI assistance.

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

• Standalone Performance: Yes, a standalone performance evaluation was done. The entire performance testing section describes the evaluation of the "Brentwood Real Time ST and Arrhythmia Analysis Software Library" against standardized databases, focusing solely on the algorithm's capabilities.

7. The Type of Ground Truth Used

• Type of Ground Truth: The ground truth was based on expert annotations and established reference points within the standard databases (AHA, MIT-BIH, NST, CU, ESC). This can be classified as expert consensus/annotation-based ground truth, as these databases are meticulously reviewed and annotated by specialists.

8. The Sample Size for the Training Set

• Sample Size for Training Set: Not specified in the provided text. The document describes a "software library" that provides functions, implying it might be a predefined algorithm or model rather than something that was "trained" in the modern machine learning sense using a specific training set. If it was trained, the details are not provided.

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

• Ground Truth for Training Set: Not specified. As mentioned above, it's unclear if a traditional "training set" with established ground truth was used in the modern machine learning context for this software library. If it was, the method for establishing ground truth is not provided.

Ask a specific question about this device