Search Results

VLFT10GEN: The Valleylab FT10 energy platform is a high frequency electrosurgical generator intended for use with monopolar and bipolar accessories for cutting and coagulating tissue. When used with compatible sealing devices, it is indicated for sealing vessels up to and including 7mm thick tissue (tissue bundles), and lymphatics. When used with compatible ablation devices it is indicated for cardiac tissue ablation. The generator can also be used with compatible resectoscopes for endoscopically controlled removal or coagulation of tissue using 0.9% NaCl solution as the irrigation medium. The tissue fusion function has not been shown to be effective for tubal sterilization or tubal coagulation for sterilization procedures.

Valleylab ™FT10 Electrosurgical Generator (VLFT10FXGEN): The VLFT10FXGEN is a high frequency electrosurgical generator intended for use with monopolar and bipolar accessories for cutting and coagulating tissue.

Valleylab ™FT10 Vessel Sealing Generator (VLFT10LSGEN): The VLFT10LSGEN is a high frequency electrosurgical generator. When used with compatible sealing devices, it is indicated for sealing vessels up to and including 7 mm, tissue bundles, and lymphatics.

Valleylab™ FT10 Energy Platform (VLFT10GEN): The Valleylab™ FT10 Energy Platform is a high frequency electrosurgical generator intended for use with monopolar and bipolar accessories for cutting and coagulating tissue. The generator provides radio frequency (RF) energy for monopolar and bipolar surgical applications, tissue-fusion, and vessel-sealing applications (LigaSure/vessel sealing function) and cardiac applications. It is a combination of a full-featured general surgery electrosurgical unit and a bipolar vessel sealing system. The monopolar and bipolar sections, including the LigaSure/Bipolar section of the system, are isolated outputs that provide the appropriate power for cutting, desiccating, and fulgurating tissue during monopolar and bipolar surgery.

Valleylab™ FT10 Electrosurgical Generator (VLFT10FXGEN): The Valleylab™ FT10 Electrosurgical Generator is a high frequency electrosurgical only version of the VLFT10GEN Energy Platform. It is intended for use with monopolar and bipolar accessories for cutting and coagulating tissue.

Valleylab™ FT10 Vessel Sealing Generator (VLFT10LSGEN): The Valleylab™ FT10 Vessel Sealing Generator is the vessel sealing only version of the VLFT10GEN Energy Platform. It is a high frequency electrosurgical generator. When used with compatible sealing devices, it is indicated for sealing vessels up to and including 7 mm, tissue bundles, and lymphatics.

The provided text is a 510(k) summary for a medical device, the Valleylab™ FT10 Energy Platform Software Version 5.0. It describes the device, its intended use, a comparison to a predicate device, and performance data. However, this document does not contain details about a study evaluating a device based on AI/ML. Instead, it describes an electrosurgical generator and highlights performance data related to electrical safety, EMC, software verification/validation, and mechanical testing.

Therefore, I cannot extract information pertaining to:

1. A table of acceptance criteria and the reported device performance regarding AI/ML performance metrics (e.g., sensitivity, specificity, AUC). The document refers to "acceptance criteria" for engineering and safety tests, not for AI performance.
2. Sample sizes used for the test set and the data provenance for AI/ML evaluation.
3. Number of experts used to establish the ground truth for an AI/ML test set and their qualifications.
4. Adjudication method for an AI/ML test set.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done for AI assistance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done for an AI/ML algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.) for AI/ML.
8. The sample size for the training set for an AI/ML algorithm.
9. How the ground truth for the training set was established for an AI/ML algorithm.

The document explicitly states: "This premarket submission did not rely on the assessment of clinical performance data to demonstrate substantial equivalence." This means that no clinical studies (which would typically involve human readers for an MRMC study or large datasets for standalone AI performance) were conducted or included in this 510(k) submission. The "Software verification and validation testing" mentioned is general software quality assurance, not specific to AI/ML model performance.

In summary, the provided text does not contain the information requested about AI/ML device performance and testing.

Ask a specific question about this device

The CUSA® Clarity Ultrasonic Surgical Aspirator System is indicated for use in surgical procedures where fragmentation, emulsification and aspiration of soft and hard (e.g. bone) tissue is desirable.

The CUSA Clarity Ultrasonic Surgical Aspirator is indicated for use in:
Plastic and Reconstructive surgery, Orthopedic Surgery, Gynecological Surgery and Thoracic Surgery and the following specific uses:
Neurosurgery - including removal of primary and secondary malignant and benign brain and spinal tumors, including but not limited to meningiomas and gliomas
Gastrointestinal and Affiliated Organ Surgery - including removal of benign or malignant tumors or other unwanted tissue, including hepatic parenchyma, in open or laparoscopic procedures, hepatic resection, tumor resection, lobectomy or trisegmentectomy, or removal of tissue during liver allotransplantation and donor hepatectomy
Urological surgery- including removal of renal parenchyma during nephrectomy or partial nephrectomy
General Surgery - including removal of benign or malignant tumors or other unwanted soft or hard tissue in open or minimally invasive general surgical procedures
Laparoscopic Surgery - including removal of hepatic parenchyma in laparoscopic hepatic resection, lobectomy or trisegmentectomy, in laparoscopic donor hepatectomy or laparoscopic cholecystectomy or laparoscopic pancreatic jejunostomy, or pancreatectomy, or laparoscopic appendectomy, laparoscopic colon resection or laparoscopic partial gastrectomy

The device within the scope of this premarket notification is the optional CUSA® Electrosurgery Module (CEM) accessory that is intended to be used with the 23 kHz components of the CUSA® Clarity Ultrasonic Surgical Aspirator System.

The purpose of this submission is to modify the CEM nosecone accessory currently offered with CUSA Clarity to allow for connection with additional electrosurgical generators, to continue to provide electrosurgical capabilities to the user. The additional electrosurgical generators that the modified CEM Nosecone may be used with include the Medtronic FT10 (K191601), Medtronic FX8 (K181389), Erbe VIO 300D (K083452), and Erbe VIO 3 (K190823). Compatibility with the Medtronic Force FX (K143161) will be maintained as well.

The CUSA Clarity 23kHz Expanded CEM Nosecone has the same intended use and technological characteristics as the predicate CUSA Clarity 23 kHz CEM Nosecone (K190180). The subject CEM nosecone will continue to allow the surgeon to apply immediate electrosurgical coagulation to bleeding tissue at the surgical site, with the same handpiece assembly that is removing unwanted tissue.

The provided text describes the CUSA Clarity Ultrasonic Surgical Aspirator System, specifically focusing on a modified CEM nosecone accessory for the 23 kHz components. This submission is a 510(k) premarket notification claiming substantial equivalence to a predicate device.

Here's an analysis of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present acceptance criteria in a quantitative table format with corresponding device performance values. Instead, it describes various non-clinical tests undertaken to ensure the safety and efficacy of the device and its substantial equivalence to the predicate.

The reported device performance is broadly stated as:

• "Testing was determined successful and supports the conclusion that all product specifications and design inputs have been met."
• "The results of the non-clinical testing indicate that the intended use of the device, fundamental scientific technology, and performance of the CUSA Clarity 23 kHz Expanded CEM Nosecone is substantially equivalent to the predicate device."

Therefore, a table of quantitative acceptance criteria and specific reported device performance cannot be generated from the provided text. The information indicates that all tests were passed and specifications met, implying the device performed within acceptable limits.

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

The document describes non-clinical testing but does not specify a "test set" in terms of subject or patient data. The tests are focused on device characteristics rather than clinical outcomes with a patient population.

• Sample size for test set: Not applicable in the context of device performance testing described. The tests are on the device itself (e.g., handpiece life, functionality, mechanical properties).
• Data provenance: Not applicable in the context of patient data. The provenance is from internal testing conducted by Integra LifeSciences Corporation. There is no mention of country of origin for data related to clinical or patient studies, as none were performed. The tests are prospective as they were conducted as part of the submission process.

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

• Number of experts: Not applicable. The "ground truth" for the non-clinical tests is established by engineering specifications, recognized standards (FDA guidance documents, ISO standards for biocompatibility, EMC, and electrical safety), and comparison to the predicate device's established performance.
• Qualifications of experts: Not specified as a separate set of experts for ground truth. However, the development and testing would have been overseen by Integra LifeSciences Corporation's engineering and regulatory teams.

4. Adjudication Method for the Test Set

• Adjudication method: Not applicable. The testing described is objective device performance (e.g., sterilization, biocompatibility, electrical safety, mechanical, thermal effects). Success or failure is determined by meeting predefined engineering specifications and regulatory standards, not by an adjudication process between human experts on a specific outcome.

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

• MRMC study: No. The document explicitly states: "No clinical studies were performed or required as all conducted performance tests appropriately support a determination of substantial equivalence compared with the predicate device."
• Effect size of human readers with/without AI assistance: Not applicable, as no MRMC study or study involving human readers with or without AI assistance was conducted. The device is a surgical aspirator system, not an AI diagnostic tool.

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

• Standalone study: Not applicable. The CUSA Clarity Ultrasonic Surgical Aspirator System is a physical medical device, not an algorithm. Therefore, "standalone" performance in the context of an algorithm is not relevant.

7. The Type of Ground Truth Used

The "ground truth" for the device's acceptable performance is based on:

• Established engineering specifications and design inputs: Ensuring the device functions as intended.
• Compliance with FDA guidance documents and recognized standards: Such as those for sterilization, biocompatibility, EMC, electrical safety, thermal effects, and capacitive coupling.
• Substantial equivalence to the legally marketed predicate device (CUSA® Clarity Ultrasonic Surgical Aspirator System K190180): This implies that the predicate's established safety and effectiveness profile serves as a benchmark for the new component.

8. The Sample Size for the Training Set

• Sample size for training set: Not applicable. This device is not an AI/ML algorithm that requires a training set. The performance is assessed through traditional engineering and regulatory compliance testing.

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

• How ground truth for training set was established: Not applicable, as there is no training set for this type of device.

Ask a specific question about this device

The Hominis Surgical System is an endoscopic instrument control system that is intended to assist in the accurate control of the Hominis Arms during single site, natural orifice laparoscopic-assisted transvaginal benign surgical procedures listed below. The Hominis Surgical System is indicated for use in adult patients. It is intended to be used by trained physicians in an operating room environment.

The representative uses of the Hominis Surgical System are indicated for the following benign procedures:

• Total Benign Hysterectomy with Salpingo-Oophorectomy ●
• Total Benign Hysterectomy with Salpingectomy ●
• Total Benign Hysterectomy ●
• Salpingectomy
• Oophorectomy
• Adnexectomy
• Ovarian cyst removal ●

The Hominis Surgical System (see Figure 1) is a mountable electromechanical surgical system for transluminal approaches used in single-site benign hysterectomy and salpingo-oophorectomy surgical procedures through a transvaginal access point. The system consists of two (2) Hominis Arms, a Hominis Control Console, a Hominis Motor Units Assembly, and Hominis Surgical System Accessories (Hominis Sterile Drape, GYN Trocar Kit, Hominis System Cables, and Bed Fixation Kit). During clinical use, surgeons operate the Hominis Arms from the Hominis Control Console with a compatible and FDA-cleared third-party standard laparoscope (transumbilical) and visual guidance system.

The Hominis Surgical System is a robotic surgical system designed to assist in transvaginal laparoscopic-assisted benign surgical procedures. The acceptance criteria and the study proving the device meets these criteria are detailed through a combination of non-clinical bench testing, animal and cadaver studies, human factors testing, and a pre-market clinical study.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are primarily derived from the "NON-CLINICAL PERFORMANCE TESTING - BENCH" section. These tests demonstrate the system's mechanical, electrical, and thermal performance, as well as its interaction with tissue. All reported results for these bench tests were marked as "Pass".

Table: Acceptance Criteria and Reported Device Performance (Bench Tests)

Clinical Study Acceptance Criteria (Effectiveness & Safety):

The clinical assessment of safety and effectiveness was established if the clinical endpoints met or were more favorable than study endpoints obtained from existing clinical studies in a literature review.

Effectiveness Results:

• Conversion rate (i.e. conversion to laparotomy, laparoscopy, other): None (Acceptance: Met or more favorable than literature review)
• Procedure completion: 100% (Acceptance: Met or more favorable than literature review)
• Ports used in addition to vaginal and umbilical port): None (Acceptance: Met or more favorable than literature review)
• Average Operative Time (range) [minutes]: 57.07 (24-88) (Acceptance: More favorable than traditional vaginal hysterectomy; comparable/favorable to robotically-assisted abdominal hysterectomy per literature review)
• Average length of hospital stay (range) [days]: 3.2 (2-8) (Acceptance: More favorable than traditional vaginal hysterectomy; comparable/favorable to robotically-assisted abdominal hysterectomy per literature review)
• Re-admission rate [%]: 0 (Acceptance: More favorable/comparable to literature review)
• Re-operation rate [%]: 0 (Acceptance: More favorable/comparable to literature review)

Safety Results:

• Intra-operative Adverse Events (AEs) and Serious Adverse Events (SAEs) [%]: 0 (Acceptance: More favorable than traditional vaginal hysterectomy and robotically-assisted abdominal hysterectomy per literature review)
• Bladder injury [# of patients]: 0 (Acceptance: More favorable/comparable to literature review)
• Rectal injury [# of patients]: 0 (Acceptance: More favorable/comparable to literature review)
• Transfusion rate: 0 (Acceptance: More favorable/comparable to literature review)
• Mortality [%]: 0 (Acceptance: More favorable/comparable to literature review)
• Cuff dehiscence rate: 0 (Acceptance: More favorable/comparable to literature review)
• Vaginal cuff healing: 23% (7 of 30 subjects) had relatively delayed healing (9-14.5 weeks). All healed. (Acceptance: Within normal range for recovery, deemed acceptable)

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

The primary test set for demonstrating clinical safety and effectiveness was the pre-market clinical study.

• Sample Size (Clinical Study): 30 subjects
• Data Provenance: Multi-center, prospective study. The specific countries are not explicitly stated for the primary clinical study, but the "Investigators Background" mentions surgeons from Rambam hospital (Haifa, Israel) and Imelda hospital (Bonheiden, Belgium). So, the data is from Israel and Belgium, collected prospectively.

Additional test sets were used for non-clinical and human factors testing:

• Animal Study: 5 ewe models. (GLP Ewe Study)
• Cadaver Study: 5 female cadavers.
• Human Factors Study: 71 users in total (50 surgeons, 21 OR staff). This included 24 US surgeons and 16 US OR staff. The study was conducted in a simulated OR setting.

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

For the Clinical Study:

• The clinical study involved investigators, specifically surgeons, performing the procedures and assessing outcomes. The "Investigators Background" section notes that all surgeons (total of (b)(4) from Rambam hospital and (b)(4) from Imelda hospital) underwent a device-specific training program.
• Qualifications of Experts: The surgeons' experience in robotic surgery ranged from 0 to 10 years, with three surgeons having no independent robotic experience. Experience in vaginal hysterectomies ranged from no experience to 80 procedures; (b)(4) were novice users (no prior vaginal hysterectomies) and (b)(4) performed (b)(4) or less. Experience in laparoscopic hysterectomies ranged from no experience to (b)(4) procedures; (b)(4) were novice users (no prior laparoscopic hysterectomies) and (b)(4) performed (b)(4) or less.
• The study endpoints (e.g., complications, operative time, conversion rate) were clinically assessed by these participating surgeons and likely other medical staff as part of their standard clinical practice and protocol adherence.

For the Human Factors Study:

• The study involved 71 users (50 surgeons, 21 OR staff).
• Qualifications of Experts: Surgeon participants had 0-40 years of clinical experience and 0-10 years of robotic surgical experience. US OR staff had 1-23 years of clinical experience and 0-10 years of robotic experience. These individuals acted as their own "ground truth" for usability by attempting the critical tasks.

4. Adjudication Method for the Test Set

For the Clinical Study:

• The document does not explicitly detail an independent adjudication method for clinical outcomes. The reported results appear to be direct observations and measurements from the participating sites and investigators.
• "All procedures were successfully completed, including safely and successfully performing transvaginal access with the GYN Trocar Kit. No device-related complications or adverse events occurred..."

For the Human Factors Study:

• For each critical task, "the expected and incorrect responses were pre-defined based on sub-tasks and risks associated with that critical task."
• "Task success criteria looked at expected and incorrect responses, and completion of the task safely and effectively..."
• "Each critical task was evaluated for successful completion and a test case for the critical tasks passes if all participants eventually provided the correct response."
• Ratings of "difficult" and "close call" were "analyzed for possible root-cause but were considered to be a pass." Any potential use problem observed was assessed for root cause and possible outcomes.
• This suggests an implicit adjudication based on the pre-defined success/failure criteria, rather than an explicit multi-reader adjudication panel.

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 MRMC or AI assistance study was conducted. The Hominis Surgical System is an electromechanical surgical system, not an AI-assisted diagnostic or assistive tool in the traditional sense that "improves" human readers. It is a tool for performing surgery.

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

• Not applicable. The Hominis Surgical System is a human-controlled electromechanical surgical system. Its function is to assist a human surgeon in performing procedures; it is not designed to operate autonomously. The bench tests and animal/cadaver studies evaluate the system's performance, but always in the context of being operated by a user.

7. The Type of Ground Truth Used

• Bench Tests: Engineering specifications, physical measurements, and established quality control standards for mechanical, electrical, and thermal properties. Simulated use scenarios.
• Animal and Cadaver Studies: Direct observation of surgical task performance, procedure completion, hemostasis, thermal spread, and system safety by trained surgeons. Histopathological evaluation for tissue effects.
• Human Factors Study: Pre-defined "expected and incorrect responses" for critical tasks, observed performance by representative users, and expert assessment of safety and effectiveness based on task completion and identification of use errors.
• Clinical Study: Clinical outcomes (e.g., presence/absence of complications, operative time, blood loss, length of stay, conversion rates) as observed and recorded by the surgical teams and follow-up medical staff. The comparison was made against literature review data from conventional procedures, effectively using an aggregated historical control as a ground truth for comparative effectiveness.

8. The Sample Size for the Training Set

• The document does not describe a "training set" in the context of machine learning model development. This device is a robotic system, not an AI algorithm that learns from data in that manner.
• However, for the device use training program, all users (surgeons and OR Staff) in the clinical study and human factors study underwent this training. The human factors study involved 71 users (50 surgeons, 21 OR staff) who received a "condensed training program." This training program itself is subject to iterative improvement based on collected data.

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

• Since there isn't a "training set" for an AI model, this question is interpreted in the context of the device use training program.
• The "ground truth" for the effectiveness of the training program is established through human factors validation testing. This testing identified "critical tasks" (tasks that, if performed incorrectly, could cause serious harm). The training program was designed to ensure users could safely and effectively perform these critical tasks.
• Establishment method: The critical tasks themselves were identified during the risk analysis process (UFMEA - Use Failure Mode Effects Analysis). The training was developed to mitigate these use-related risks. User competency after training was assessed by evaluating performance on these critical tasks during the human factors study. "All users met pre-specified success criteria before moving towards clinical cases." The human factors study verified that "all of the identified critical tasks were completed across the different user types within the surgical team, and that all test cases met their acceptance criteria...by all users." This demonstrated the effectiveness of the training in enabling safe usage. The training effectiveness will also be continuously monitored via post-market surveillance.

Ask a specific question about this device

The Cardioblate Gemini-s surgical ablation device is intended to ablate cardiac tissue during cardiac surgery using radiofrequency (RF) energy. The system is indicated for use, under direct or endoscopic visualization, in surgical procedures, including minimally invasive surgical procedures.

The Cardioblate Gemini-s surgical ablation device (Model 49351) is a hand-held, single-use, bipolar, radio-frequency (RF) ablation device for use in cardiac surgery. It has a saline irrigation system to deliver fluid at the contact point between the tissue and electrode to cool the tissue during RF energy delivery. This device is intended for intermittent operation.

The proposed Cardioblate Gemini-s device is intended for use with the Valleylab™ FT10 Energy Platform (VLFT10GEN) with software version 3.0.0 or higher.

The devices are provided sterile and nonpyrogenic, are disposable, and are for single use only. They are sterilized using ethylene oxide.

The Cardioblate Gemini-s is a bipolar electrode device that transmits radio frequency energy, generated by an external generator, between the two electrodes. The device has dual linear electrodes, 6.3 cm in length, with integral fluid delivery to the electrodes. The Gemini-s device is port accessible, intended for open or closed chest procedures to ablate tissue through resistive heating due to radiofrequency energy passing through tissue. The device is designed to reproduce the Cox-Maze lesion pattern by creating linear transmural lesions in both atria of the heart during cardiac procedures.

The Gemini-s surgical ablation device has a flexible neck design that provides the physician with the ability to access various anatomies utilizing a neck curve through the full range from 0 to 180-degree configuration.

Once the electrodes are correctly positioned, the parallel jaws lock by squeezing the handle. The electrodes have full contact with the tissue and the locking mechanism must be fully engaged to ensure accurate transmurality readings. Simultaneous with the actuation of the trigger and jaw closure is the opening of the (normally closed) fluid path to start the flow of saline. The device automatically shuts off the saline when the jaws are open and when the device is not in use.

The provided document is a 510(k) summary for the Medtronic Cardioblate Gemini-s Surgical Ablation Device. This document focuses on demonstrating substantial equivalence to a predicate device, rather than proving the device meets specific performance acceptance criteria for an AI/ML-enabled diagnostic device.

Therefore, the information required to answer your specific questions about acceptance criteria, study design, ground truth establishment, sample sizes for training/test sets, expert adjudication, and MRMC studies is not present in this document. This submission is for an electrosurgical device, not an AI software.

However, I can extract and structure the information that is available regarding performance testing to show what kind of "acceptance criteria" and "study" were relevant for this type of device based on its nature.

Based on the provided Medtronic 510(k) Summary for the Cardioblate Gemini-s Surgical Ablation Device (K200514), here's what can be inferred about its "acceptance criteria" and "study" for regulatory approval:

Core Principle for Approval: The primary "acceptance criterion" for this Class II device, as outlined in the 510(k) process, is demonstrating substantial equivalence to a legally marketed predicate device (K121767 Cardioblate Gemini-s Surgical Ablation Device, Model 49260). This means the device must perform as safely and effectively as the predicate, and any differences must not raise new questions of safety or effectiveness.

1. Table of Acceptance Criteria and Reported Device Performance (Inferred)

Since this is a substantial equivalence submission for an electrosurgical device, the "acceptance criteria" are not reported as quantitative metrics like sensitivity/specificity for a diagnostic AI. Instead, they are related to compliance with relevant standards and demonstrating comparable performance to the predicate.

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

• Sample Size: Not explicitly stated as a number of "cases" or "patients" in the context of an AI test set. For the benchtop lesion verification, the "sample size" would likely refer to the number of ablation attempts or tissue samples tested. This number is not provided.
• Data Provenance: The studies were non-clinical performance tests (mechanical, electrical, EMC, benchtop lesion verification, usability). They were not based on patient data in the sense of retrospective or prospective clinical studies. The "data" comes from engineering and benchtop laboratory testing.

3. Number of Experts and Qualifications for Ground Truth:

• Not Applicable: This type of submission relies on engineering and laboratory testing against established standards and predicate device performance, not expert human image interpretation to establish ground truth for an AI algorithm. Therefore, there's no mention of experts or their qualifications for ground truth establishment in this context.

4. Adjudication Method for the Test Set:

• Not Applicable: There is no "test set" in the sense of a dataset requiring human adjudication for ground truth for an AI algorithm.

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

• No: An MRMC study is relevant for evaluating the impact of an AI algorithm on human reader performance. This device is an electrosurgical tool, not an AI diagnostic, so an MRMC study was not performed or necessary.

6. If a Standalone (Algorithm Only) Performance Study was Done:

• Not Applicable: This is an electrosurgical device, not an AI algorithm. The performance studies evaluate the physical device's specifications and capabilities.

7. The Type of Ground Truth Used:

• Engineering Standards and Predicate Performance: The "ground truth" for this device's performance is compliance with established international standards (IEC 60601 series) for medical electrical equipment, and demonstrably equivalent performance to the predicate device in terms of mechanical function, electrical safety, EMC, and the ability to create lesions in a soft tissue model.

8. The Sample Size for the Training Set:

• Not Applicable: This is not an AI/ML device, so there is no "training set."

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

• Not Applicable: As there is no training set for an AI/ML model, this question does not apply.

In summary: The provided document is a 510(k) submission for a physical medical device (an electrosurgical ablation device) seeking clearance based on substantial equivalence to a predicate. The "acceptance criteria" and "studies" described primarily involve engineering and benchtop testing to demonstrate compliance with standards and comparable performance to the existing predicate device, rather than the rigorous clinical validation methodology (including AI-specific elements like ground truth establishment, expert adjudication, and MRMC studies) that would be required for an AI/ML software as a medical device (SaMD).

Ask a specific question about this device