Search Results

The Intuitive Surgical Endoscopic Instrument Control System (da Vinci Xi Surgical System Model IS4000) is intended to assist in the accurate control of Intuitive Surgical Endoscopic Instruments including rigid endoscopes, blunt and sharp endoscopic dissectors, scalpels, forceps/pick-ups, needle holders, endoscopic retractors, electrocautery and accessories for endoscopic manipulation of tissue, including grasping, cutting, blunt and sharp dissection, approximation, ligation, electrocautery, suturing, and delivery and placement of microwave and cryogenic ablation probes and accessories, during urologic surgical procedures, general laparoscopic surgical procedures, gynecologic laparoscopic surgical procedures, general thoracoscopic surgical procedures and thoracoscopically- assisted cardiotomy procedures. The system can also be employed with adjunctive mediastinotomy to perform coronary anastomosis during cardiac revascularization. The system is indicated for adult and pediatric use. It is intended to be used by trained physicians in an operating room environment in accordance with the representative, specific procedures set forth in the Professional Instructions for Use.

The Intuitive Surgical Endoscopic Instrument Control System (da Vinci X Surgical System Model IS4200) is intended to assist in the accurate control of Intuitive Surgical Endoscopic Instruments including rigid endoscopes, blunt and sharp endoscopic dissectors, scalpels, forceps/pick-ups, needle holders, endoscopic retractors, electrocautery and accessories for endoscopic manipulation of tissue, including grasping, cutting, blunt and sharp dissection, approximation, ligation, electrocautery, suturing, and delivery and placement of microwave and cryogenic ablation probes and accessories, during urologic surgical procedures, general laparoscopic surgical procedures, gynecologic laparoscopic surgical procedures, general thoracoscopic surgical procedures and thoracoscopically-assisted cardiotomy procedures. The system can also be employed with adjunctive mediastinotomy to perform coronary anastomosis during cardiac revascularization. The system is indicated for adult and pediatric use. It is intended to be used by trained physicians in an operating room environment in accordance with the representative, specific procedures set forth in the Professional Instructions for Use.

This 510(k) is for a labeling modification only, to include "Ventral Hernia Repair" (VHR) procedures under the cleared "general laparoscopic surgical procedures" Indication for Use of the da Vinci Xi Surgical System, Model IS4000 and the da Vinci X Surgical System, Model IS4200. There are no changes to the technological characteristics of the cleared da Vinci Xi or X Surgical Systems (Models IS4000 and IS4200) proposed in this submission. The da Vinci Xi and X Surgical Systems, Models IS4000 and IS4200, are software-controlled, electro-mechanical systems designed for surgeons to perform minimally invasive surgery. The Model IS4000 and Model IS4200 Surgical Systems consist of a Surgeon Console, a Patient Side Cart (PSC), and a Vision Side Cart (VSC) and are used with an Endoscope, EndoWrist Instruments, and Accessories.

The provided document, K173585, describes the a 510(k) premarket notification for a labeling modification to include "Ventral Hernia Repair" (VHR) procedures under the cleared "general laparoscopic surgical procedures" Indication for Use of the da Vinci Xi Surgical System (Model IS4000) and the da Vinci X Surgical System (Model IS4200). The document does not describe the acceptance criteria and study proving a device's performance against acceptance criteria in the manner typically seen for AI/ML-enabled devices. Instead, it focuses on demonstrating the substantial equivalence of adding VHR procedures to the existing robotic surgical systems by comparing the outcomes of robotic-assisted VHR to traditional open and laparoscopic VHR.

Therefore, many of the specific questions about acceptance criteria for an AI/ML device's performance, sample sizes for test sets, establishment of ground truth by experts, MRMC studies, and standalone algorithm performance, as requested in the prompt, are not applicable or directly addressed by this document. This document is about a surgical system, not an AI/ML diagnostic or prognostic tool.

However, I can extract information related to the clinical study data used to support the labeling modification, which serves a similar purpose to a performance study for a new indication.

Here's the information as it relates to the provided document:

1. A table of acceptance criteria and the reported device performance:

The document doesn't define explicit numerical "acceptance criteria" in the way one would for an AI/ML device (e.g., "sensitivity must be >X%"). Instead, it demonstrates comparability and, in some cases, superiority of the robotic-assisted VHR to existing surgical methods across several clinical outcomes and measures. The "acceptance" for this 510(k) is based on demonstrating substantial equivalence and safety and effectiveness for the new indication compared to existing methods.

The tables provided (Tables 1, 2, 3, and 4a) present the "reported device performance" in terms of clinical outcomes for robotic-assisted VHR procedures compared to open and laparoscopic VHR. Below is a summary of the key findings, which serve as the "performance" data used to support the new indication.

Summary of Device Performance (Robotic-Assisted VHR vs. Comparators)

Note: The document explicitly states that longer operative times for robotic-assisted cases were "not associated with increases in the complication, readmission, reoperation or mortality rates." This addresses a potential negative finding.

2. Sample sizes used for the test set and the data provenance:

• Test Set (Clinical Data): Real-world evidence (RWE) from the AHSQC registry database.
  • Non-Complex VHR Procedures:
    • Robotic-Assisted vs. Open: Propensity score matched cohorts of N=871 for each group.
    • Robotic-Assisted vs. Laparoscopic: Propensity score matched cohorts of N=615 for each group.
    • Data Provenance: The registry data for these procedures occurred between July 7, 2013, and January 1, 2017. The document does not specify the country of origin, but AHSQC (America's Hernia Society Quality Collaborative) suggests it is primarily from the United States. The data is retrospective as it's from a registry of past procedures.
  • Complex VHR Procedures:
    • Robotic-Assisted vs. Open: Propensity score matched cohorts of N=297 for each group.
    • Robotic-Assisted vs. Laparoscopic: Unmatched data from the AHSQC Registry Database (Robotic-Assisted N=305, Laparoscopic N=27) and a summary of published literature of laparoscopic VHR (N=3-53 per study).
    • Data Provenance: Similar to non-complex, July 7, 2013, and January 1, 2017, primarily United States, retrospective.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

This is not applicable in the context of this document. The "ground truth" for the performance data is derived directly from clinical outcomes recorded in a surgical registry (AHSQC) and published clinical literature. These are factual clinical occurrences (e.g., length of stay, complications, readmissions, mortality) rather than subjective interpretations by experts, as would be the case for image-based diagnostic AI/ML.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

Not applicable. As noted above, the data are clinical outcomes from a registry, not expert-labeled data requiring adjudication.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

Not applicable. This is not an AI-assisted diagnostic or interpretation device that would involve human "readers." The "device" (da Vinci Xi/X Surgical System) is a surgical tool. The study compares surgical approaches (robotic, open, laparoscopic), not the performance of human readers with or without AI assistance.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

Not applicable. The da Vinci system is a human-controlled robotic surgical system; it does not operate "stand-alone" as an algorithm would. Performance is always human-in-the-loop (i.e., the surgeon uses the system).

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

The ground truth for the clinical performance data (test set) is Real-World Evidence (RWE) from a clinical registry (AHSQC). This constitutes outcomes data (e.g., length of stay, complication rates, readmission rates, recurrence rates, mortality rates) directly recorded from patient care. For certain comparisons (Complex VHR Robotic-Assisted vs. Laparoscopic), it also incorporates published literature on laparoscopic VHR outcomes.

8. The sample size for the training set:

The document does not describe a "training set" in the context of machine learning. The da Vinci Xi and X Surgical Systems are existing electromechanical systems; this submission is for an expanded indication. The "training" for the system itself has already occurred and is inherent in its design and previous clearances. The data used in this submission serves as clinical validation data for the expanded Indication for Use.

9. How the ground truth for the training set was established:

Not applicable, as there is no "training set" in the AI/ML sense described.

In summary, this 510(k) submission demonstrates the substantial equivalence and safety/effectiveness of adding a new surgical indication to an already cleared robotic surgical system, not the performance of a new AI/ML device against specific quantitative acceptance criteria. The "study" here is a retrospective analysis of clinical outcomes from a large surgical registry and published literature.

Ask a specific question about this device