Search Results

The HYDROS Robotic System is indicated for the resection and removal of prostate tissue in males suffering from lower urinary tract symptoms (LUTS) due to benign prostatic hyperplasia.

The HYDROS Robotic System has three components – the HYDROS Robotic System, HYDROS TRUS Probe, and HYDROS Handpiece.

1. HYDROS Robotic System
   The HYDROS Robotic System, consists of the following nine components:

• HYDROS Tower
• Touchscreen Interfaces - Monitor that supports the Tower Monitor (Tmon) and Surgeon Monitor (Smon)
• HYDROS Software
• HYDROS Operating System
• Embedded Software
• Motorpack
• Handpiece Arm
• TRUS Probe Arm
• Foot Pedal

The HYDROS Robotic System is provided non-sterile, and no sterilization is required prior to each use. The Tower, Foot Pedal, Roll Stand, Articulating Arms, and Motorpack are reprocessed per instructions provided with the device after each use. The HYDROS Robotic System does not come in contact with the patients during the procedure.

2. HYDROS TRUS Probe
   The HYDROS TRUS Probe is a biplane transrectal ultrasound probe that is used in the conjunction with the HYDROS Robotic System and HYDROS Handpiece to provide ultrasound imaging to deliver the AQUABLATION procedure. The HYDROS TRUS Probe is re-usable and provided non-sterile. It is reprocessed prior to each use as per the instructions provided in the IFU.

3. HYDROS Handpiece
   The HYDROS Handpiece is the single-use sterile surgical device introduced to the surgical site within the prostate through the urethra to visualize, resect and remove prostatic tissue. The HYDROS Handpiece is integrated with a digital CMOS Scope and is terminally sterilized by EtO.

The provided document is a 510(k) Clearance Letter and 510(k) Summary for the HYDROS Robotic System. This type of FDA submission focuses on demonstrating substantial equivalence to a predicate device, rather than providing detailed clinical study results and acceptance criteria for specific AI/ML components as one might find in a De Novo or PMA submission.

Therefore, the document does not contain all the requested information for the acceptance criteria and the study proving the device meets those criteria, particularly for the AI/ML aspects. It only states that the AI/ML component "Passes" FDA guidance.

However, based on the information provided, here's what can be extracted and inferred:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state acceptance criteria in quantitative terms for the AI/ML features. Instead, it indicates that the AI/ML component passed relevant FDA guidance.

Limitations: The document does not provide specific performance metrics (e.g., accuracy, sensitivity, specificity, or localization error thresholds) as acceptance criteria for the FirstAssist AI™ feature, nor does it present quantitative results. The "Pass" indicates general compliance with regulatory expectations for a 510(k) AI/ML submission.

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

The document does not specify the sample size used for the test set or the data provenance (e.g., country of origin, retrospective/prospective) for the AI/ML components. It only mentions "non-clinical performance data" and "simulated use testing and cadaver testing" for overall system validation, but these don't specifically refer to the AI/ML test set.

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

The document does not provide information on the number of experts used to establish ground truth or their qualifications for the AI/ML test set.

4. Adjudication Method for the Test Set

The document does not specify any adjudication method used for the test set, particularly for the AI/ML component.

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

The document does not mention a Multi-Reader Multi-Case (MRMC) comparative effectiveness study. It also does not provide any effect size for human readers improving with AI assistance. The AI feature ("FirstAssist AI™") is described as "optional" assistance during the PLAN step for displaying nozzle position, prostate capsule boundary, and placing landmarks, implying it's a tool for surgeons rather than a primary diagnostic AI.

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

The document implicitly suggests a standalone component analysis for the AI/ML feature by stating it "provides the handpiece nozzle position and the prostate capsule boundary" and "will place the 4 landmarks." However, detailed standalone performance metrics (e.g., how accurate the AI's landmark placement is without human correction, or the performance of the AI in identifying boundaries) are not provided. The description focuses on its function as an assistive tool, implying human review and adjustment.

7. The Type of Ground Truth Used

The document does not explicitly state the type of ground truth used for the AI/ML component. Given the nature of prostate anatomy and procedural planning in a surgical context, it could involve expert anatomical annotation on imaging data, but this is not specified.

8. The Sample Size for the Training Set

The document does not provide the sample size used for the training set of the AI/ML model.

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

The document does not describe how the ground truth for the training set was established for the AI/ML model.

Summary of AI/ML Specifics from the Document:

• Feature Name: FirstAssist AI™ (previously Assisted Planning)
• Functionality:
  • Transverse view: Provides handpiece nozzle position and prostate capsule boundary.
  • Sagittal view: Places 4 landmarks (treatment start (TS), bladder neck (BN), mid-prostate (MP), and treatment end (TE)).
• User Interaction: The surgeon has the option to adjust the landmarks as needed.
• Change from Predicate: The subject device has an "updated AI model for the same functionality of landmark identification."
• Regulatory Status: "Passes" FDA Guidance for AI/ML.

In conclusion, while the document confirms the HYDROS Robotic System has an AI/ML component ("FirstAssist AI™") and was cleared based on non-clinical performance and equivalence to a predicate, it lacks the detailed quantitative acceptance criteria and study particulars for the AI/ML model itself that would typically be found in a more comprehensive clinical validation report. The "Pass" for AI/ML indicates compliance with the regulatory requirements pertinent to a 510(k) submission, which often rely on demonstration of similar performance to a predicate or adherence to recognized performance standards rather than extensive de novo clinical studies specifically for the AI component's accuracy.

Ask a specific question about this device