Search Results

The intended use of the CARTO™ 3 System is catheter-based cardiac electrophysiological (EP) procedures. The CARTO™ 3 System provides information about the electrical activity of the heart and about catheter location during the procedure. The system can be used on patients who are eligible for a conventional electrophysiological procedure. The system has no special contraindications.

The CARTO™ 3 EP Navigation System V8.4, is a catheter-based atrial and ventricular mapping system designed to acquire and analyze navigation catheter's location and intracardiac ECG signals and use this information to display 3D anatomical and electro anatomical maps of the human heart. The location information needed to create the cardiac maps and the local electrograms are acquired using specialized mapping catheters and reference devices. The CARTO™ 3 System uses two distinct types of location technology – magnetic sensor technology and Advanced Catheter Location (ACL) technology.

The CARTO™ 3 System V8.4 consists of the following hardware components:

• Patient Interface Unit (PIU)
• Workstation with Graphic User Interface (GUI)
• Wide-Screen monitors, keyboard, and mouse
• Intracardiac In Port
• Intracardiac Out Port
• Power Supply
• Patches Connection Box and Cables (PU)
• Pedal
• Location Pad (LP)
• Signal Processing Unit (SPU)

All hardware components of the CARTO™ 3 system V8.4 are the same as those found in the predicate device.

The provided FDA 510(k) clearance letter and summary for the CARTO™ 3 EP Navigation System V8.4 details two new AI-powered features: the CARTOSOUND™ REVEAL Module and the LA FAM Module.

Based on the provided document, here's a breakdown of the acceptance criteria and the study information:

1. Acceptance Criteria and Reported Device Performance

The document states that the testing verified and validated that the new features perform according to specifications and that existing features were not negatively affected. However, specific quantitative acceptance criteria (e.g., a specific accuracy percentage, Dice coefficient, etc.) for the AI algorithms in the CARTOSOUND™ REVEAL Module or LA FAM Module are not explicitly provided in the public document. The reported performance is that "All system features were found to perform according to specifications" and "All tests were successfully completed."

Given the lack of specific quantitative metrics in the provided document, I cannot create a table with specific numeric acceptance criteria and reported performance values. The closest information is:

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

• CARTOSOUND™ REVEAL Module:
  • Sample Size: Not explicitly stated as a number. The document mentions "Data for... validation of the DL algorithm was collected from a representative range of LA and LV chamber volumes and geographical locations, using a variety of ultrasound system settings, ULS scanners, and catheters."
  • Data Provenance: "geographical locations" implies diverse data sources, but specific countries are not mentioned. The data was collected from "CARTO™ 3 System cases with ultrasound information," suggesting it's retrospective clinical data gathered during past procedures where the CARTO™ 3 system was used.
• LA FAM Module:
  • Sample Size: Not explicitly stated as a number. The document mentions "Data for... validation of the DL algorithm consisted of CT and CARTO™ 3 System cases with FAM and was collected from a representative range of LA chamber volumes, geographical locations, and catheters."
  • Data Provenance: "geographical locations" implies diverse data sources, but specific countries are not mentioned. The data was collected from "CT and CARTO™ 3 System cases with FAM," suggesting it's a mix of retrospective clinical CT data and retrospective clinical data from past CARTO™ 3 procedures.

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

Not explicitly stated in the provided document. The document describes the "anatomical labeling and automatic contouring algorithms" as "developed and tested using CARTO™ 3 System cases with ultrasound information." For the 3D shell model, it was "developed and tested using CT and CARTO™ 3 System cases with FAM." However, the exact number, qualifications (e.g., cardiologist, electrophysiologist, radiologist, years of experience), and process of expert involvement in establishing ground truth for the test set are not detailed.

4. Adjudication Method for the Test Set

Not explicitly stated in the provided document. The document does not describe any specific multi-expert adjudication method (e.g., 2+1, 3+1, none) used for the test set ground truth.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No MRMC comparative effectiveness study involving human readers assisting with AI vs. without AI assistance was mentioned. The testing described focuses on the standalone performance of the AI modules and regression testing of the overall system.

6. Standalone Performance (Algorithm Only without Human-in-the-Loop)

Yes, standalone performance was implied for the AI algorithms. The description of CARTOSOUND™ REVEAL and LA FAM modules specifically mentions "locked AI algorithms" for "Automatic identification," "Automatic 2D contours creation," and "Automatic 3D sell creation." The "Retrospective Validation Tests" were performed on "clinical recorded data" to "validate the clinical functionality and quality of the introduced modules," suggesting an evaluation of these automated features.

7. Type of Ground Truth Used

• CARTOSOUND™ REVEAL Module:
  • For anatomical labeling and automatic contouring: Ground truth was derived from "CARTO™ 3 System cases with ultrasound information." This likely implies expert consensus or manual annotation by experts reviewing these clinical images.
  • For 3D shell model: Ground truth was derived from "CT and CARTO™ 3 System cases with FAM." This suggests CT imaging, potentially combined with expert manual segmentation or annotation from CARTO™ 3 FAM data.
• LA FAM Module:
  • Ground truth was derived from "CT and CARTO™ 3 System cases with FAM." This also suggests CT imaging, potentially combined with expert manual segmentation or annotation from CARTO™ 3 FAM data.

In both cases, while not explicitly stated, the generation of "ground truth" for a medical imaging task typically involves expert manual annotation or comparison to a gold standard imaging modality (like CT for anatomical structures).

8. Sample Size for the Training Set

• CARTOSOUND™ REVEAL Module: Not explicitly stated as a number. The document mentions "Data for training... of the DL algorithm was collected from a representative range of LA and LV chamber volumes and geographical locations, using a variety of ultrasound system settings, ULS scanners, and catheters."
• LA FAM Module: Not explicitly stated as a number. The document mentions "Data for training... of the DL algorithm consisted of CT and CARTO™ 3 System cases with FAM and was collected from a representative range of LA chamber volumes, geographical locations, and catheters."

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

• CARTOSOUND™ REVEAL Module:
  • For anatomical labeling and automatic contouring: "The anatomical labeling and automatic contouring algorithms were developed and tested using CARTO™ 3 System cases with ultrasound information." This implies expert annotation or labeling of cardiac structures and contours within these ultrasound images.
  • For 3D shell model: "The 3D shell model was developed and tested using CT and CARTO™ 3 System cases with FAM." This implies expert segmentation or model creation/validation based on CT images and CARTO™ 3 FAM data.
• LA FAM Module:
  • "Data for training... of the DL algorithm consisted of CT and CARTO™ 3 System cases with FAM." This indicates the ground truth for training was established through expert analysis and annotation of CT scans and CARTO™ 3 Fast Anatomical Maps (FAM).

Similar to the test set, the establishment of ground truth for training data in medical AI typically relies on manual work by qualified experts to delineate structures or confirm labels.

Ask a specific question about this device