(201 days)
TAVIPILOT is an intra-operative software which provides real-time fluoroscopy detection, tracking and marking of the Non-Coronary Cusp and the prosthetic valve, to allow optimal guidance for precise positioning of the prosthetic valve, according to the planning phase, for TAVI/TAVR (transcatheter aortic valve implantation/replacement) procedures. The guidance provided by TAVIPILOT is not intended to substitute the cardiac surgeon's or the interventional cardiologist's judgment and analysis of the patient's condition.
The device is only intended for adults (i.e., 21 years and older).
Contra-indications:
- Patients who have already undergone a TAVI/TAVR or SAVR (surgical aortic valve replacement)
- Patients diagnosed with aortic insufficiency
- Patients for whom the main access for the TAVI/TAVR catheter is not femoral
- Patients who have a non-tricuspid native valve
- Patients who have a permanent Pacemaker implant or temporary Pacemaker within 2 cm from the aortic root, other than the pacing guidewire
- Patients who have thoracic surgical implants
- Patients who are not adults
TAVIPILOT is an intra-operative software which provides real-time fluoroscopy detection, tracking and marking of the Non-coronary Cusp and the prosthetic valve, to allow optimal guidance for precise positioning of the prosthetic valve, according to the planning phase, for TAVI/TAVR (transcatheter aortic valve implantation/replacement) procedures.
The guidance provided by the TAVIPILOT is not intended to substitute the cardiac surgeon's or the interventional cardiologist's judgment and analysis of the patient's condition.
The TAVIPILOT software tool is intended to be used in combination with FDA cleared X-ray systems to assist cardiac surgeons and interventional cardiologists with the treatment of structural heart diseases using minimal invasive interventional techniques for which TAVI/TAVR is indicated.
In addition to conventional live fluoroscopy TAVIPILOT provides the user with tools to guide the procedure using a 2D projection of the aortic root-related landmarks and transcatheter aortic valve overlayed on the 2D X-ray image data from the FDA cleared X-ray systems.
During Live phase the SD offers anatomical detection and tracking of the aortic root-related landmarks and transcatheter aortic valve which is overlayed in 2D on the 2D fluoroscopy x-ray image data using trained AI/ML model.
TAVIPILOT does not change or influence the TAVI procedure.
The main operating principle of TAVIPILOT consists of the following SW workflow:
- Preparing for Live task
- Live Task
Here's a breakdown of the acceptance criteria and the study proving the device meets those criteria, based on the provided FDA 510(k) clearance letter for TAVIPILOT:
Acceptance Criteria and Device Performance Study for TAVIPILOT
The TAVIPILOT device, an intra-operative software utilizing AI/ML for real-time fluoroscopy detection, tracking, and marking of the Non-Coronary Cusp (NCC) and transcatheter aortic valve (TAV), was validated to demonstrate its performance and substantial equivalence to a predicate device.
1. Table of Acceptance Criteria and Reported Device Performance
| Parameter | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| NCC Detection, Tracking, and Marking Accuracy | NCC detected, tracked, and marked within ≤ 2 mm | NCC detected, tracked, and marked ≤ 2 mm in 100% of all patients tested with statistical significance. |
| TAV Detection, Tracking, and Marking Accuracy | TAV detected, tracked, and marked within ≤ 1 mm | TAV detected, tracked, and marked ≤ 1 mm in 100% of all patients tested with statistical significance. |
| Accuracy in Contrasted/Non-contrasted Images | Accuracy maintained in both contrasted and non-contrasted images. | Accuracy was obtained in both contrasted and non-contrasted images. |
| Comparison to Predicate Device (NCC) | Equivalent or better detection, tracking, and marking of the NCC compared to the predicate device. | TAVIPILOT has equivalent or better detection, tracking, and marking of the NCC compared to the predicate device in all patients. |
| Compatibility/Interoperability with C-arm X-ray Devices | Compatible and interoperable with FDA cleared GE, Philips, and Siemens C-arm X-ray devices meeting specified requirements. | TAVIPILOT was validated for compatibility and interoperability with FDA cleared C-arm X-ray devices (using data from GE, Philips, and Siemens devices) and confirmed compatible. |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: "a representative and statistically supported number of patients, representative of both EU and US TAVI populations, including gender and ethnicity considerations." (Specific number not provided, but stated to be statistically supported and representative).
- Data Provenance: The patients/data were "representative of both EU and US TAVI populations, including gender and ethnicity considerations." This implies retrospective or prospective acquisition from these regions. The document does not explicitly state if the data was retrospective or prospective.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: Not explicitly stated, but implies a collective of experts ("Ground truth was performed by board certified experts").
- Qualifications of Experts: "board certified experts with substantial experience with relevant clinical tasks, thus ensuring quality annotations."
4. Adjudication Method for the Test Set
The adjudication method is not explicitly mentioned. It only states that "Ground truth was performed by board certified experts." This could imply single-reader, multiple-reader consensus, or other methods, but no specific method like 2+1 or 3+1 is detailed.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- MRMC Study Done: No. The provided document details a standalone performance test of the algorithm's accuracy against ground truth, and a comparison to a predicate device but without human readers. The study focuses on the AI's direct detection, tracking, and marking performance rather than its impact on human reader performance.
- Effect Size of Human Readers Improvement: Not applicable, as no MRMC study with human-in-the-loop was reported.
6. Standalone (Algorithm Only) Performance Study
- Standalone Study Done: Yes. The "NCC and TAV detection, tracking and marking validation testing" and "Comparison to Predicate Device testing" sections describe the algorithm's performance directly against ground truth, independent of human readers. This represents a standalone (algorithm-only) performance evaluation.
7. Type of Ground Truth Used
- Type of Ground Truth: Expert Consensus. "Ground truth was performed by board certified experts with substantial experience with relevant clinical tasks, thus ensuring quality annotations."
8. Sample Size for the Training Set
The document does not provide information regarding the sample size used for the training set. It only mentions the use of "trained AI/ML model" and refers to the validation test set.
9. How the Ground Truth for the Training Set Was Established
The document does not explicitly state how the ground truth for the training set was established. It only refers to the training of the AI/ML model. However, given that "Ground truth was performed by board certified experts" for the test set, it is plausible that a similar method (expert annotation) was used for the training data, but this is not confirmed in the text.
§ 892.1650 Image-intensified fluoroscopic x-ray system.
(a)
Identification. An image-intensified fluoroscopic x-ray system is a device intended to visualize anatomical structures by converting a pattern of x-radiation into a visible image through electronic amplification. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II (special controls). An anthrogram tray or radiology dental tray intended for use with an image-intensified fluoroscopic x-ray system only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9. In addition, when intended as an accessory to the device described in paragraph (a) of this section, the fluoroscopic compression device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.