Search Results

The Acessa Guidance System is indicated for enhancing the ultrasonic image of the Acessa Handpiece and for predicting its future path on a computer monitor screen which also shows the image of a B-scan (or similar display) of a medical ultrasound imaging system. The device is intended as an optional accessory for use during the Acessa System procedure.

The Acessa Guidance System consists of the following components: Guidance Controller (Model Number 5100), Guidance Ultrasound Transducer Sleeve (Model Number 5500), Guidance Field Generator (Model Number 5200), Guidance Handpiece Cable (Model Number 5400), and Power Cord (Model Number 4110). The Acessa Guidance System uses electromagnetic tracking technology to track the positions of the Guidance Ultrasound Transducer Sleeve and the Guidance Handpiece shaft and draws virtual representations of them in their spatial relationship, so that a physician can predict the Guidance Handpiece shaft's future path in relation to the features in the ultrasound slice. The Acessa Guidance System is considered an optional accessory to procedures where ultrasound is currently used for visualization, such as the Acessa System procedure.

The Acessa Guidance System includes the following performance testing:

1. Table of Acceptance Criteria and Reported Device Performance:

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

• The document does not specify sample sizes for any of the listed performance tests.
• The provenance of the data (e.g., country of origin, retrospective or prospective) is not provided for any of the tests.

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

• This information is not provided in the document. The tests described are primarily engineering, biocompatibility, and simulated environment tests, rather than clinical studies requiring expert ground truth for interpretation of patient data.

4. Adjudication Method for the Test Set:

• This information is not applicable as the provided testing is not a clinical study involving human reader interpretation requiring adjudication.

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

• No, an MRMC comparative effectiveness study was not conducted or described in this document. The device is a guidance system, and the testing focuses on its engineering and functional performance rather than its impact on human reader performance in a diagnostic context.

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

• The document describes performance testing that largely functions as "standalone" performance for the device's components (electrical, safety, biocompatibility, mechanical). The "system worse-case accuracy comparison testing in a simulated clinical environment" evaluates the algorithm's accuracy in a controlled setting without explicit mention of human-in-the-loop performance influencing the measurement. However, the device is an "optional accessory" for use during a procedure and is meant to enhance ultrasonic images and predict tool paths, implying human interaction during its intended use. Therefore, while some tests are algorithmic/system performance, it's not a standalone diagnostic algorithm.

7. The Type of Ground Truth Used:

• Electrical and Safety Testing: Ground truth is established by the specified international standards (e.g., ANSI/AAMI ES 60601-1).
• Biocompatibility Testing: Ground truth is established by the specified international standards (e.g., ISO 10993 series).
• Mechanical (Guidance Sleeve end cap tensile testing): Ground truth would be engineered specifications or established industry standards for material strength.
• Accuracy (System worse-case accuracy comparison): Ground truth would be defined reference points or known positional values within the simulated clinical environment.
• Software Validation: Ground truth would be the software requirements specifications and expected functional behavior.

8. The Sample Size for the Training Set:

• The document does not mention a "training set" in the context of machine learning or AI models. The software is noted to be from the manufacturer of the predicate device and based on their cleared device, implying reuse or adaptation of existing software rather than a de novo development requiring a distinct training phase.

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

• This information is not applicable as no training set for an AI model is described.

Ask a specific question about this device

The Acessa System is indicated for use in percutaneous, laparoscopic coagulation and ablation of soft tissue, including treatment of symptomatic uterine fibroids under laparoscopic ultrasound guidance.

The Acessa System includes the following system components: Generator (Model Number 1000): Provides RF energy to the Handpiece through the Handpiece Cable. Handpiece (Model Number 2000): Consisting of a disposable handle with a trocar-pointed shaft and 7 deployable needle electrodes. For use only disposable electrosurgical devices provided by Halt Medical, Inc. Handpiece Cable (Model Number 4200): Connects Handpiece to the Generator. This extension cable is provided with the Generator. Pads (Model Number 3000): A disposable set of 2 units, providing the return path for the RF energy applied by the Handpiece. Use only the Pads provided by Halt Medical, Inc. Pad Cable (Model Number 4300): Connects the Pads to the Generator. This extension cable is provided with the RF Generator. Power Cord (Model Number 4110): A medical grade power cord that provides AC power to the Generator. The Power cord is provided with the Generator. Foot Pedal (Model Number 4100): Pneumatic foot pedal with tubing used to turn RF energy on and off. The Foot Pedal with tubing is provided with the Generator. The Acessa System is designed to deliver up to 200 W of RF power at 460 kHz in three operational modes: Temperature Control, Manual Control and Coagulation Mode. A touch screen with a graphical user interface (GUI) enables selection of operational parameters such as the mode of operation, the ablation time, the target temperature, and the power delivery level. With the Handpiece placed in the tissue to be ablated and its electrodes deployed, RF power can be turned on. The system parameters are continuously monitored and displayed on the Generator. If the measured parameters are outside the acceptable limits, the RF energy delivery automatically stops and a message appears on the graphical user interface. RF energy during an ablation or coagulation can also be stopped at any time by the user by pressing the foot pedal. NOTE: The Acessa System must be used under laparoscopic ultrasound guidance. Laparoscopic ultrasound equipment is not included with the Acessa System.

The provided document describes the Acessa System, a device for laparoscopic coagulation and ablation of soft tissue, specifically for symptomatic uterine fibroids. Here's a breakdown of the acceptance criteria and the studies conducted:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" in a tabulated format with specific thresholds. Instead, it describes various performance testing and clinical study outcomes that demonstrate the device's safety and effectiveness. Based on the provided information, the closest approximation of acceptance criteria and reported performance is:

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

The document details three main clinical studies that serve as the "test set" for the device's performance:

• Peri-hysterectomy feasibility study:
  • Sample Size: Not explicitly stated, but implies a small cohort of patients undergoing hysterectomy where the Acessa System was used.
  • Data Provenance: Not explicitly stated, but likely prospective and from a clinical setting where hysterectomies were being performed.
• Prospective, non-randomized, longitudinal Phase II studies:
  • Sample Size: A total of 69 subjects (implied from the phrase "sixty-five subjects (94.2%)" and "sixty-one subjects (88.4%)" which point to a denominator around 69).
  • Data Provenance: Prospective, non-randomized, conducted at "two separate centers," likely in the US (not explicitly stated country, but common for IDE trials).
• Device pivotal (Phase III) study:
  • Sample Size: 137 women with symptomatic fibroids.
  • Data Provenance: Prospective, conducted at 11 centers in the United States (9 centers) and Latin America (2 centers).

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

The document does not describe a ground truth established by a specific number of experts for image interpretation or diagnosis in the traditional sense of AI studies. Instead, the "ground truth" for the clinical effectiveness studies was derived from:

• Patient-reported outcomes: Validated questionnaires (UFS-QOL, EQ-5D), menstrual pad counts, patient surveys on satisfaction and symptom effectiveness, and self-reported return to normal activities.
• Clinical measurements: Uterine volume, fibroid volume (assessed by contrast-enhanced MRI).
• Pathology reports: From the peri-hysterectomy study, correlated with ablation zones.
• Adverse event reporting: By investigators.
• Investigators: 13 investigators participated in the pivotal study. Their specific qualifications (e.g., number of years of experience) are not detailed but they are presumed to be qualified clinicians (e.g., gynecologists) experienced in treating uterine fibroids.

4. Adjudication Method for the Test Set

The document does not mention an explicit adjudication method (like 2+1 or 3+1 consensus) for establishing a "ground truth" for the test set. The clinical trial data relies on patient reporting, objective clinical measurements, and investigator reporting of adverse events and outcomes based on standard clinical practice.

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

No. The Acessa System is a therapeutic device (for ablation), not a diagnostic device that involves "human readers" interpreting images. Therefore, an MRMC study comparing human readers with and without AI assistance is not applicable to this device.

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

No. The Acessa System is a physical medical device (generator, handpiece, etc.) used by a physician during a laparoscopic procedure. It is not an algorithm or AI system that operates in a standalone capacity without human interaction for its primary function. While it has internal software for control and monitoring, its performance is inherently tied to human use and guidance.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

The ground truth for evaluating the Acessa System's performance was primarily a combination of:

• Clinical Outcomes Data:
  • Patient-reported outcomes: From validated questionnaires (Uterine Fibroid Symptom Quality of Life (UFS-QOL), EuroQol 5 Dimensions (EQ-5D)), patient satisfaction surveys, symptom severity scales, and menstrual pad counts.
  • Objective clinical measurements: Reduction in uterine and fibroid volume (via contrast-enhanced MRI), reduction in menstrual blood loss, and reintervention rates.
  • Adverse event reporting: Clinical events reported by investigators and medical staff.
• Pathology: In the peri-hysterectomy feasibility study, pathology reports of ablation zones were correlated with procedure documentation.
• Device specifications: For electrical, mechanical, and software performance.

8. The Sample Size for the Training Set

The document does not describe a "training set" in the context of an AI/machine learning model. The studies described are clinical trials and engineering validations for a physical medical device. The "training" in this context would be the development and iterative testing of the device during its engineering phase, which is not quantified by a patient sample size but by laboratory and bench testing efforts.

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

Since there is no "training set" in the AI/ML sense, this question is not directly applicable. For the device development itself, "ground truth" for design and engineering was established through:

• Internal specifications and standards: Adherence to regulatory standards (EN/IEC 60601-1, EN/IEC 60601-1-2, EN/IEC 60601-2-2, ISO 10993).
• Bench testing: To qualify and quantify mechanical and functional properties, ablation output, and safety features.
• Animal studies: To demonstrate performance as intended and per specifications prior to human trials.

Ask a specific question about this device