Search Results

The Maestro System is intended to hold and position laparoscopes and laparoscopic instruments during laparoscopic surgical procedures.

The Moon Maestro System is a 2-arm system which utilizes software and hardware to provide support to surgeons for manipulating and maintaining instrument position. Motors compensate for gravitational force applied to laparoscopic instruments, while surgeon control is not affected. Conventional laparoscopic tools are exclusively controlled and maneuvered by the surgeon, who grasps the handle of the surgical laparoscopic instrument and moves it freely until the instrument is brought to the desired position. Once surgeon hand force is removed, the Maestro system reverts to maintenance of the specified tool position and instrument tip location.
This 510(k) is being is being submitted to implement 5G and WiFi capability to the previously cleared Maestro System (K242323). This modification is intended for data offload; only Telemetry and Event logs will be sent over 5G or WiFi. A PCCP is also implemented for the ScoPilot feature.

Here's a summary of the acceptance criteria and the study details for the Maestro System, based on the provided FDA 510(k) clearance letter. It's important to note that the document is focused on a modification to an already cleared device and a Predetermined Change Control Plan (PCCP), so some of the detailed information often found in initial submissions might be less explicit here.

Acceptance Criteria and Reported Device Performance

The document describes various performance tests without explicitly listing pass/fail acceptance criteria values. However, it indicates compliance with recognized standards and that validation activities were performed to pre-defined performance requirements for the ScoPilot feature. For the purpose of this summary, I'll extract the performance aspects mentioned.

Study Details

The primary study mentioned in this document relates to the validation of the ScoPilot ML model and the non-clinical bench studies for the overall system.

1. Sample size used for the test set and the data provenance:

   • ML Model Validation (ScoPilot): An "independent testing dataset containing videos" was used. The specific number of videos or cases is not provided in this document.
   • Data Provenance: The document does not specify the country of origin or whether the data was retrospective or prospective. It only mentions using data "including brands unseen during training/tuning."

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

   • This information is not provided in the document for the ScoPilot ML model validation.

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

   • This information is not provided in the document.

4. 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:

   • A MRMC study or any study comparing human readers with and without AI assistance is not mentioned in this document. The device (Maestro System) is an instrument holder and positioner, and the ScoPilot feature assists in instrument tracking and positioning, not in diagnostic interpretation where MRMC studies are common.

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

   • Yes, performance testing for the ScoPilot ML model was done in a standalone manner, with the model being "trained and tuned" and then verified against "predefined performance requirements" on an "independent testing dataset." The performance metrics used were "lower bound of the 95%CI for AP and AR (Average Precision and Average Recall likely)."

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

   • For the ScoPilot ML model, the ground truth establishment method is not explicitly detailed. It would likely involve manual annotation of instrument tips and surgical tools within the video frames by qualified personnel to create the labels against which the algorithm's detection and tracking are evaluated.

7. The sample size for the training set:

   • This information is not provided in the document. The text mentions the ML model was "trained and tuned through a K-fold cross-tuning process."

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

   • This information is not explicitly detailed in the document, but it would align with the method used for the test set (likely manual annotation of surgical tools in video data). The PCCP mentions "Modification retraining the ML model with the addition of newly acquired data enables it to detect surgical instrument classes already claimed, and an increased variety of other brands in the video feed more accurately" and adding "surgical cautery hooks to the ML model class hooks as another surgical instrument class." This implies a process of labeling or annotating new data for these specific elements.

Ask a specific question about this device