Search Results

The Senhance Surgical System is intended to assist in the accurate control of laparoscopic instruments for visualization and endoscopic manipulation of tissue including grasping, cutting, blunt and sharp dissection, approximation, ligation, electrocautery, suturing, mobilization, and retraction. The Senhance Surgical System is intended for use in general laparoscopic surgical procedures, laparoscopic gynecological surgery, and laparoscopic urological surgery. The system is indicated for adult and pediatric use. It is intended for use by trained physicians in an operating room environment in accordance with the instructions for use.

Use of the device is limited to patients two (2) years of age and older and a weight equal to or above 10kg, who are suitable to be subjected to a conventional endoscopic technique.

The Senhance Surgical System is a multi-arm, console-based robotic system that allows a surgical team to perform laparoscopic surgery in the abdomen and pelvis in a manner similar to a manual laparoscopic approach. Each robotic arm can hold either a laparoscopic surgical instrument or an endoscope to facilitate a surgeon remotely operating the instrument from the cockpit.

More specifically, the Senhance Surgical System consists of: a surgeon console (cockpit), which provides remote manipulators or handles to allow the surgeon to maneuver the surgical instruments and a video monitor to display the endoscopic signal; manipulator arms, which hold and maneuver the instruments and endoscope based on inputs from the surgeon; Intelligent Surgical Unit (ISU), which is the system communication hub, connecting the cockpit and manipulator arms; and instruments, which manipulate the tissue of interest.

In addition, force feedback provides an optional tactile sensory input to the surgeon control handles to give a sense of tissue elasticity. An eye tracking feature provides the surgeon an optional method to control the endoscope from the cockpit, rather than using the surgeon control handles. The ISU allows for three additional methods of camera control, in addition to the optional eye tracking method.

Here's a breakdown of the acceptance criteria and study details based on the provided text for the Senhance Surgical System:

Acceptance Criteria and Device Performance

The provided document does not explicitly state numerical acceptance criteria for the expanded indication. Instead, it demonstrates that the Senhance Surgical System's performance for urological procedures is comparable or superior to existing alternative surgical techniques (robotic, laparoscopic, and open surgery) based on several clinical outcome metrics derived from a Systematic Literature Review (SLR) and real-world evidence from the TRUST registry.

The core acceptance is that the device, with its expanded indications for use, "does not raise different questions of safety or effectiveness or alter the fundamental therapeutic use of the system" compared to the predicate devices. The performance data presented in Table 18 supports this claim by showing favorable or similar outcomes.

Table 1: Acceptance Criteria (Implied Comparability) and Reported Device Performance

Note on Acceptance Criteria: The document focuses on demonstrating substantial equivalence by showing that the Senhance System's performance for urological procedures is safe and effective and comparable to established methods, rather than setting specific numerical thresholds as "acceptance criteria." The favorable comparison against SLR data serves as the "proof" of meeting this implied standard.

Study Details

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

   • Test Set Sample Size: 416 urology cases performed using the Senhance system.
   • Data Provenance: Retrospective clinical data review from the TRUST registry. "TRUST" is a prospective, multi-center patient registry primarily for European clinical centers. For this study, sites additionally retrospectively enrolled previously treated patients (after obtaining informed consent) and entered retrospective data. The data collection for the TRUST registry is stated to be still ongoing. The study collected data from December 2017 to August 2023.

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

   • The document does not explicitly state the number of experts or their qualifications for establishing the ground truth of the TRUST registry data. The data originates from clinical centers participating in the TRUST registry, implying that surgical outcomes and patient data were recorded by the healthcare professionals (surgeons, nurses, etc.) at those centers as part of their routine clinical practice and study participation.

3. Adjudication Method for the Test Set:

   • The document does not specify an adjudication method (e.g., 2+1, 3+1) for the clinical data collected in the TRUST registry. The data appears to be collected directly from clinical records and reported outcomes within the registry structure.

4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

   • No, an MRMC comparative effectiveness study was not performed as described. The study compared the device's performance (Senhance System) to the performance of other surgical techniques (Robotic, Laparoscopy, Open) based on aggregated data from a registry and a systematic literature review. It did not involve multiple human readers assessing cases with and without AI assistance to measure reader improvement.

5. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:

   • Yes, in essence. The entire evaluation focuses on the performance of the "Senhance Surgical System" itself, which is a robotic-assisted surgical system. While a human surgeon is "in the loop" operating the system, the performance metrics (e.g., surgical complications, blood loss, operative time) are attributed to the system's use rather than analyzing the human-machine interaction for "improvement." The clinical data demonstrates the system's performance in isolation from a specific human reader improvement claim. The device is assisting the surgeon, so the performance reported is inherently "with assistance," but there isn't a comparison of human performance without the Senhance system to human performance with the Senhance system in a controlled observation experiment of the surgeon's performance. Instead, it compares the overall patient outcomes when using the system versus other surgical approaches.

6. Type of Ground Truth Used:

   • Clinical Outcomes Data: The ground truth for the test set (TRUST registry) is based on real-world clinical outcomes data and patient records from surgical procedures. This includes metrics like Length of Stay, Surgical Complications, Estimated Blood Loss, Readmission Rates, Reoperation Rates, Mortality, and Postoperative Complications.
   • Expert Consensus (Implicit in SLR): For the comparative data from the Systematic Literature Review, the "ground truth" for the aggregated averages comes from peer-reviewed research publications, where clinical outcomes are established and reported by the medical community.

7. Sample Size for the Training Set:

   • The document does not describe a "training set" in the context of an AI-driven imaging or diagnostic algorithm. The Senhance Surgical System is a robotic-assisted surgical system, and its development and validation would involve engineering verification and validation, bench testing, and clinical studies rather than an AI training/test split of data in the typical sense. The "Performance Data" section mentions "Extensive bench testing was conducted on the previously cleared Senhance system," but does not specify a separate training set.

8. How the Ground Truth for the Training Set Was Established:

   • As there is no "training set" described in the context of AI specific to this submission, this question is not directly applicable. The underlying engineering, functional, and safety validations for the robotic surgical system would have established its operational capabilities and safety through various testing methodologies, often guided by industry standards and expert engineering principles.

Ask a specific question about this device

The Senhance Surgical System is intended to assist in the accurate control of laparoscopic instruments for visualization and endoscopic manipulation of tissue including grasping, cutting, blunt and sharp dissection, approximation, ligation, electrocautery, suturing, mobilization, and retraction. The Senhance Surgical System is intended for use in general laparoscopic surgical procedures and laparoscopic gynecological surgery. The system is indicated for adult and pediatric use. It is intended for use by trained physicians in an operating room environment in accordance with the instructions for use.

Use of the device is limited to patients two (2) years of age and older and a weight equal to or above 10kg, who are suitable to be subjected to a conventional endoscopic technique.

The Senhance Surgical System is a multi-arm, console-based robotic system that allows a surgical team to perform laparoscopic surgery in the abdomen and pelvis in a manner similar to a manual laparoscopic approach. Each robotic arm can hold either a laparoscopic surgical instrument or an endoscope to facilitate a surgeon remotely operating the instrument from the cockpit.

More specifically, the Senhance Surgical System consists of: a surgeon console (cockpit), which provides remote manipulators or handles to allow the surgeon to maneuver the surgical instruments and a video monitor to display the endoscopic signal; manipulator arms, which hold and maneuver the instruments and endoscope based on inputs from the surgeon: Intelligent Surgical Unit (ISU), which is the system communication hub, connecting the cockpit and manipulator arms; and instruments, which manipulate the tissue of interest.

In addition, force feedback provides an optional tactile sensory input to the surgeon control handles to give a sense of tissue elasticity. An eye tracking feature provides the surgeon an optional method to control the endoscope from the cockpit, rather than using the surgeon control handles. The ISU allows for three additional methods of camera control, in addition to the optional eye tracking method.

The purpose of this submission is to expand the indications for use to include pediatric patients, two (2) years of age and older and a weight equal to or above 10kg.

This document describes the regulatory submission for the Senhance Surgical System to expand its indications for use to include pediatric patients. The core of the information addresses the acceptance criteria and the study proving the device meets these criteria as adapted for the new pediatric indication.

Here's a breakdown of the requested information based on the provided text:

Acceptance Criteria and Device Performance

The provided text does not explicitly state pre-defined acceptance criteria in terms of numerical thresholds for performance metrics. Instead, the study aimed to demonstrate that the Senhance System's performance for pediatric use is "as safe and effective as its predicate" and "comparable" to existing surgical techniques (robotic, laparoscopic, and open surgery) based on a set of clinical endpoints.

The "acceptance criteria" can be inferred as showing non-inferiority or comparability to established techniques across these clinical endpoints.

Table of Acceptance Criteria (Inferred Comparability) and Reported Device Performance

Conclusion from data: "Operative times and complication rates were comparable between the retrospective clinical data with the Senhance system and the systematic literature review."

Study Details

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

   • Test Set (Retrospective Clinical Data): 32 pediatric patients.
   • Data Provenance: The data was collected from "real-world evidence" on the Senhance Surgical System for the pediatric population. It appears to be retrospective clinical data collected from a hospital (or hospitals) where the Senhance system was used. The specific country of origin is not explicitly stated, but the inclusion criteria for the literature review specify "US or EU study" to reduce variation in surgical method, which might suggest a similar geographic focus for the clinical data. The study states it was a "retrospective clinical data review."

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

   • The document describes a retrospective clinical data review and a systematic literature review. It does not mention experts establishing "ground truth" for a test set in the context of an AI device's performance evaluation against expert readings. The "ground truth" here is the real-world clinical outcomes as recorded in patient charts (for the 32 patients) and reported in peer-reviewed literature. Therefore, no specific number of experts or their qualifications for establishing ground truth for a test set (in the typical AI validation sense) are provided.

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

   • Not applicable in this context. This study is an evaluation of clinical outcomes based on real-world data and literature comparison, not an AI performance study requiring human adjudication of AI outputs.

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:

   • No, an MRMC study was not done. This study is not evaluating the improvement of human readers with AI assistance. It's evaluating the clinical safety and effectiveness of a robotic surgical system for a new patient population.

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

   • No. The Senhance Surgical System is a human-controlled robotic system; its "performance" is inherently tied to the surgeon's use of the device. This study evaluates the clinical outcomes of procedures performed with the device, not a standalone AI algorithm.

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

   • The "ground truth" for the 32 pediatric cases was clinical outcomes data (e.g., intra-operative complications, post-operative complications, conversion rates, length of stay, blood loss, etc.) as recorded in patient records.
   • For the comparative data, the ground truth was derived from peer-reviewed research publications (literature review) reporting clinical outcomes for alternative surgical techniques.

7. The sample size for the training set:

   • Not applicable. This is not an AI algorithm development study that requires a training set. The device (Senhance Surgical System) itself is already developed, and this submission is for an expanded indication for use.

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

   • Not applicable, as no training set for an AI algorithm was used in this evaluation.

Ask a specific question about this device

The Senhance® Surgical System is intended to assist in the accurate control of laparoscopic instruments for visualization and endoscopic manipulation of tissue including grasping, cutting, blunt and sharp dissection, approximation, ligation, electrocautery, suturing, mobilization and retraction. The Senhance Surgical System is intended for use in general laparoscopic surgical procedures and laparoscopic gynecological surgery. The system is indicated for adult use. It is intended for use by trained physicians in an operating room environment in accordance with the Instructions for Use.

The Senhance Articulating platform (internally named Articulating Be4) is intended as an addition to the suite of adapters, couplers and instruments previously cleared for use with the Senhance Surgical System ("Senhance System") most recently cleared under K212054 which is being used as the predicate. This submission requests clearance for one (1) new Articulating Adapter and two (2) Articulating Couplers to be used with the existing articulating instruments.

The provided text describes the acceptance criteria for the Senhance Articulating Platform, an addition to the Senhance Surgical System, and summarizes various studies conducted to demonstrate its substantial equivalence to a predicate device (Senhance Surgical System K212054).

Here's a breakdown of the requested information based on the text:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't explicitly present a formal "acceptance criteria" table with specific pass/fail metrics. Instead, it describes performance testing categories and their summaries, demonstrating that the device met expectations or performed as intended. The overarching acceptance criterion for this 510(k) submission is to demonstrate substantial equivalence to the predicate device, meaning it is as safe and effective and performs similarly.

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

• Sample Size for Test Set: The document does not specify a numerical sample size for any of the individual tests. It uses terms like "comprehensive set of testing," "single-center," and "surgical teams."
• Data Provenance: The document generally indicates prospective assessment through various forms of testing (bench, validation, usability). It doesn't specify the country of origin, but given it's an FDA submission for a US company (Asensus Surgical, Inc. in Durham, NC), it's highly likely the data was generated in the United States.

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

• The document mentions "users who represented the intended primary user population" for the "Design Validation" and "surgical teams" for "Usability Testing." However, it does not specify the number of experts or their qualifications (e.g., "radiologist with 10 years of experience"). This is a common characteristic of device submissions focusing on mechanical function and usability rather than diagnostic accuracy.

4. Adjudication Method for the Test Set:

• The document states the design validation was "un-blinded, observational." It does not mention any explicit adjudication method like "2+1" or "3+1" for conflict resolution, as would be common in studies involving subjective assessment. Given the nature of the tests (mechanical performance, cleaning effectiveness, usability of surgical tools), direct adjudication as seen in image interpretation might not be applicable or described in this summary.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and its effect size:

• No, an MRMC comparative effectiveness study was not done. The document focuses on demonstrating the safety and effectiveness of the new articulating platform itself and its compatibility with the existing Senhance Surgical System, primarily through technical and simulated-use testing. It does not evaluate the improvement of human readers (surgical teams) with or without AI assistance, as this is a surgical system, not a diagnostic AI tool.

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

• This question is not applicable in the context of the Senhance Articulating Platform. This device is a component of a robotic surgical system that assists human surgeons; it is not a standalone algorithm performing a task without human interaction (like image analysis AI). The "Software" testing confirmed the system's software reliability with the new components, but this is about the system's control functionality, not an AI algorithm performing a task in isolation.

7. Type of Ground Truth Used:

The ground truth or reference standard for this type of device (surgical instrument/platform) is primarily established by:

• Performance Specifications/Engineering Standards: For bench testing (e.g., "perform as intended after tests of mechanical integrity," "Sterility Assurance Level (SAL) of at least 10⁻⁶," compliance with IEC standards).
• Defined User Needs and Intended Uses: For design validation and usability testing (e.g., "according to defined user needs," "independently perform all critical tasks without use errors that would lead to harm").
• Established Reprocessing Protocols: For cleaning effectiveness.

There isn't a "pathology" or "outcomes data" ground truth in the typical diagnostic sense, as this isn't a diagnostic device.

8. Sample Size for the Training Set:

• The document does not mention a training set sample size. This is because the submission is for a hardware addition to a robotic surgical system, not a machine learning or AI model that requires a dedicated training set. The "Software" testing is about verifying the existing system's software functions correctly with the new components, not training a new algorithm.

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

• Not applicable, as there is no mention of a training set for an AI/ML model in this submission.

Ask a specific question about this device

The Senhance® Surgical System is intended to assist in the accurate control of laparoscopic instruments for visualization and endoscopic manipulation of tissue including grasping, cutting, blunt and sharp dissection, approximation, ligation, electrocautery, suturing, mobilization and retraction. The Senhance Surgical System is intended for use in general laparoscopic surgical procedures and laparoscopic gynecological surgery. The system is indicated for adult use. It is intended for use by trained physicians in an operating room environment in accordance with the Instructions for Use.

The Senhance® Surgical System (Senhance system) is a multi-arm, console-based robotic system that allows a surgical team to perform laparoscopic surgery in the abdomen and pelvis in a manner similar to a manual laparoscopic approach. The capital equipment of the Senhance system is comprised of the following three main subsystems which are powered separately and connected by means of communications cables:

• Cockpit The station where the surgeon inputs information through hand and eye movements to direct the arms to move within the surgical field.
• Manipulator Arm(s) - Up to three mechanized instrument support arms that produce output movements based on the instruction from the cockpit or bedside assistant. Each robotic arm can hold either a laparoscopic surgical instrument or an endoscope to facilitate a surgeon remotely operating the instrument from the cockpit.
• Intelligent Surqical Unit (ISU) The ISU component, which is the communication hub that connects the cockpit inputs to the manipulator arms. The ISU contains a high-performance computer that enables the surgeon to control the endoscope using software features that apply image processing algorithms to the endoscope video signal.

The provided text describes a 510(k) premarket notification for the Senhance Surgical System. While it details the device, its intended use, and various tests performed, it does not contain the specific information required to complete the table of acceptance criteria and the detailed study information as requested.

The document states that "Software testing and a comprehensive set of performance testing were conducted to demonstrate that the modified device is as safe and effective, and thus substantially equivalent, to the predicate," and that "Functional performance tests utilizing well-established test methodology verified that the ISU features and Senhance system performed as intended." However, it does not provide the acceptance criteria themselves, nor the quantitative results of these tests. It also lacks details on the sample sizes, expert involvement, ground truth establishment, or specific study designs (like MRMC) for proving the device meets performance criteria related to AI/image processing features.

Therefore, I cannot fill out the requested table and answer many of the questions based on the provided text. The text broadly states that tests were done and requirements were met, but it does not give the specifics of those tests or their quantitative outcomes.

Here's what I can extract and what's missing:

Acceptance Criteria and Device Performance Table:

Study Details (Based on available information and what is missing):

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

   • Test Set Sample Size: NOT PROVIDED. The document mentions "Pre-Clinical Design Validation" was conducted in a "simulated patient model," but does not specify the sample size of "cases" or "simulated procedures."
   • Data Provenance (country of origin, retrospective/prospective): NOT PROVIDED. The study was a "single-center, un-blinded, observational, simulated use design validation evaluation." It doesn't specify if this involved retrospective data or prospective data collection from actual surgical procedures. The "simulated patient model" suggests synthetic or cadaveric data rather than clinical patient data.

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

   • Number of Experts: NOT PROVIDED. The evaluation was conducted "with users who represented the intended primary user population," implying surgeons, but the number and specific qualifications (e.g., years of experience, subspecialty) are not mentioned.
   • Qualifications of Experts: Users "represented the intended primary user population," which for the Senhance system are "trained physicians." Specific qualifications or years of experience are NOT PROVIDED.

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

   • Adjudication Method: NOT PROVIDED. The study is described as "observational," but no details on how discrepancies (if any) in assessments were resolved are given.

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:

   • MRMC Study: NOT PROVIDED/Unclear. The study describes a "single-center, un-blinded, observational, simulated use design validation evaluation." This does not suggest an MRMC comparative effectiveness study comparing human readers with and without AI assistance for specific diagnostic or performance metrics. The new features ("Follow Me," "Measurements," "Digital Tags," "Image Enhancement") are described as aids to the surgeon, but a comparative study on improved human performance is not detailed.
   • Effect Size: NOT PROVIDED. Since an MRMC study is not explicitly described, the effect size is also not given.

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

   • Standalone Performance: NOT PROVIDED. The document mentions "Functional performance tests utilizing well-established test methodology verified that the ISU features and Senhance system performed as intended." This might imply an evaluation of the algorithms' direct output (e.g., accuracy of 3D distance measurements), but it's not explicitly labeled as "standalone" and no quantitative results are provided. The "Image Characterization Verification" is a procedure for the system, which might have its own internal performance metrics.

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

   • Type of Ground Truth: NOT EXPLICITLY STATED for all features. For some features, like "Measurements," the ground truth would likely be precise physical measurements in the simulated environment. For others, like the efficacy of "Image Enhancement," it might be subjective user satisfaction or objective image quality metrics, but this is not detailed. The "Pre-Clinical Design Validation" assessed "all applicable user level requirements" in a "simulated patient model," implying that the "ground truth" was whatever the expected, correct performance was in that simulated environment.

7. The sample size for the training set:

   • Training Set Sample Size: NOT PROVIDED. The document describes software verification and validation, but provides no information on the training data for any machine learning components within the "new image processing features."

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

   • Training Set Ground Truth Establishment: NOT PROVIDED. As no training set details are given, how its ground truth was established is also not mentioned.

Summary of what the document does state:

• The device is a robotically-assisted surgical system (Senhance Surgical System) used for laparoscopic procedures.
• The 510(k) is for a modified device with new software features related to image processing and endoscope movement (Follow Me, Measurements, Digital Tags, Image Enhancement, Image Characterization).
• The software is considered a "major" level of concern.
• Performance testing, electrical safety/compatibility, and software verification/validation were conducted.
• A "Pre-Clinical Design Validation" was done at a single center, un-blinded, observational, in a simulated use environment with intended users.
• The conclusion is that the modified device is "as safe and effective" as the predicate and "does not raise any different questions of safety and effectiveness," supporting substantial equivalence.

Without access to the actual test reports or the full 510(k) submission, the detailed quantitative information for acceptance criteria and study results cannot be provided from this letter.

Ask a specific question about this device

The Senhance® Surgical System is intended to assist in the accurate control of laparoscopic instruments for visualization and endoscopic manipulation of tissue including grasping, cutting, blunt and sharp dissection, approximation, ligation, electrocautery, suturing, mobilization. The Senhance Surgical System is intended for use in general laparoscopic surgical procedures and laparoscopic gynecological surgery. The system is indicated for adult use. It is intended for use by trained physicians in an operating room environment in accordance with the instructions for use.

The Senhance Articulating platform is intended as an addition to the suite of instruments and adapters previously cleared for use with the Senhance® Surgical System ("Senhance system"). These instruments add degrees of freedom near the instrument end effector to allow for additional range of motion for the surgeon when performing laparoscopic tissue manipulations. Two articulating instruments are being added to the suite of instruments –Bipolar Atraumatic Grasper and Needle Driver. The instruments are single use and provided sterile to the end user. The instruments connect to a coupler which in turn connects to the articulating adapter which attaches to the Senhance Manipulator Arm.

The provided text, a 510(k) summary for the Senhance Surgical System, describes the device, its intended use, and substantial equivalence to predicate devices, supported by various performance tests. However, it does not contain the specific information required to complete a table of acceptance criteria and the detailed study results as requested in the prompt.

Specifically, the document does NOT include:

• A table of acceptance criteria with reported device performance (quantitative metrics are absent). The document mentions various performance tests (Biocompatibility, Reprocessing, Bench Testing, Electrical Safety, Software V&V, Pre-Clinical Design Validation, Usability Testing) but provides only qualitative statements about their success (e.g., "demonstrated that the patient-contacting portions... are non-toxic," "confirmed that the articulating instruments perform as intended," "Software verification and validation were successfully conducted," "All applicable user level requirements were assessed and found to be met," "The surgical teams were able to independently perform all critical tasks without use errors that would lead to harm"). It does not list specific numerical acceptance thresholds or the measured device performance against those thresholds.
• Sample sizes used for a "test set" in the context of AI/ML performance. While "Pre-Clinical Design Validation" involved a "simulated use design validation evaluation" with "users who represented the intended primary user population," and "Usability Testing" involved "surgical teams," these are not described as conventional "test sets" for evaluating an AI/ML algorithm's analytical performance (e.g., in terms of sensitivity/specificity).
• Data provenance (country of origin, retrospective/prospective).
• Number of experts or their qualifications for establishing ground truth.
• Adjudication method for a test set.
• Details on a Multi-Reader Multi-Case (MRMC) comparative effectiveness study, or effect size of human reader improvement with AI assistance. The device described is a surgical system with articulating instruments, not an AI software intended to assist human readers in, for example, diagnostic image interpretation.
• Details on a standalone (algorithm only) performance study. Again, this is a surgical system, not an AI algorithm evaluated in isolation.
• Type of ground truth used (expert consensus, pathology, outcomes data).
• Sample size for the training set.
• How ground truth for the training set was established.

Conclusion:

The provided document describes the regulatory submission for a surgical system, focusing on its substantial equivalence to a predicate device through various engineering and usability validations. It does not provide the specific type of information requested, which pertains more to the rigorous testing and validation of an Artificial Intelligence/Machine Learning (AI/ML) based medical device, particularly in a diagnostic or assistive interpretive role, where concepts like acceptance criteria for sensitivity/specificity, ground truth establishment by experts, and MRMC studies are common. The device described, the "Senhance Surgical System," is a robotically-assisted surgical tool with new articulating instruments, not an AI/ML diagnostic or predictive software.

Ask a specific question about this device