Search Results

The ELID (Endoscopic Less Invasive Decompression) system intended to provide lumbar decompression of the spine to treat various spinal condition(s) using minimally invasive techniques and instrumentation.

The ELID (Endoscopic Less Invasive Decompression) System consists of instrumentation intended to aid the user in completing steps necessary to perform lumbar decompression. Instruments include a bone needle, flat blade dilator, dilator tubes, and rongeurs. Instruments in the ELID (Endoscopic Less Invasive Decompression) System are supplied non-sterile, reusable, and manufactured from aluminum per ASTM B211, Nitinol per ASTM 2063, or stainless steel per ASTM A564.

The provided text is a U.S. FDA 510(k) Clearance Letter and a 510(k) Summary for the ELID (Endoscopic Less Invasive Decompression) System. While it describes the device, its indications for use, technological characteristics, and a list of performance tests conducted, it does not provide specific acceptance criteria or detailed study results that demonstrate the device meets those criteria.

The "Performance Data" section states that certain tests were conducted and their results "show that the strength of the ELID (Endoscopic Less Invasive Decompression) System is sufficient for its intended use and is substantially equivalent to legally marketed predicate devices." However, it does not quantify this performance, nor does it specify the acceptance criteria for each test.

Therefore, I cannot fulfill your request for:

• A table of acceptance criteria and the reported device performance. The document only lists the types of tests performed (Cleaning Validation, Sterilization Validation, Biocompatibility, Usability Testing, Particulate Analysis) but doesn't provide the detailed results or the specific quantitative acceptance thresholds for these tests.
• Sample sizes used for the test set and the data provenance. The document mentions "test modes" but does not detail the sample sizes for these tests or the origin of any data (e.g., human or ex-vivo samples, country of origin, retrospective/prospective).
• Number of experts and their qualifications for ground truth establishment. This type of information is typically relevant for AI/ML-based devices relying on expert annotations, which is not clearly indicated as a component of the ELID system described. The ELID system seems to be a set of physical surgical instruments.
• Adjudication method. Similar to the point above, this is generally for AI/ML performance evaluation against expert ground truth.
• MRMC comparative effectiveness study. This is typically for AI/ML devices assisting human readers/interpreters, which doesn't seem to be the primary function of the ELID system.
• Standalone performance. This again relates to AI/ML algorithms. The ELID system appears to be a set of manual surgical instruments.
• Type of ground truth used. For an AI/ML device, this could be expert consensus, pathology, or outcomes data. For the ELID system, ground truth would likely refer to engineering specifications and performance evaluations for mechanical properties, biocompatibility, etc. The document does not specify this in detail.
• Sample size for the training set. Not applicable, as this is a physical medical device, not an AI/ML algorithm requiring a training set.
• How the ground truth for the training set was established. Not applicable.

In summary, the provided document is a regulatory clearance letter acknowledging substantial equivalence based on a set of non-clinical performance tests, but it does not disclose the detailed quantitative acceptance criteria or the specific results of these tests, nor does it describe AI/ML related study methodologies like those you've requested. The "Performance Data" section only states that the results "show that the strength... is sufficient for its intended use and is substantially equivalent."

Ask a specific question about this device

The HydroCision SpineSite System is intended to be used as a single-use endoscopic video camera in a variety of endoscopic diagnostic and surgical procedures for spine applications. The device is also intended to be used as an accessory for microscopic surgery.

The HydroCision SpineSite System is comprised of (i) sterile disposable endoscope and (ii) reusable Video Processing Unit (VPU). The HydroCision SpineSite System provides illumination, image processing and digital documentation for endoscopic procedures. The HydroCision SpineSite System is not suitable for use in the MR environment.

The SpineSite Endoscope provides distal LED illumination via LEDs surrounding a high-resolution video sensor. The SpineSite Endoscope contains a working channel for the passage of micro instrumentation to the surgical site. The SpineSite Endoscope is provided sterile, via ethylene oxide sterilization.

The SpineSite Endoscope is designed to be connected to the SpineSite VPU via a proprietary edge card connector which provides power to the endoscope and supports video processing capability. The SpineSite VPU is powered via connection to an external wall outlet via a 12V power adapter.

The provided text is a 510(k) clearance letter and a 510(k) summary for the HydroCision SpineSite System. It details the device's indications for use, its components, and various non-clinical performance tests conducted to meet regulatory requirements. However, this document does not contain any information about a study proving the device meets specific acceptance criteria related to its performance in a clinical or AI-assisted context.

The "Performance Testing" section lists only non-clinical tests:

• Biocompatibility per ISO 10993-1
• Design verification/validation to mechanical and optical specifications
• Electrical, Mechanical and Thermal (EMT) safety testing per IEC 60601-1, IEC 60601-2-18
• Human Factors/ Usability per IEC 60601-1-6
• Electromagnetic compatibility testing per IEC 60601-1-2
• Software validation

The "Substantial Equivalence Summary" focuses on comparing the HydroCision SpineSite System to its predicate device (Arthrex Nanoscope System) on aspects like intended use, technological design, sterilization, electrical safety, materials, and technical features (optical resolution, field of view, depth of field, etc.). It states: "The safety and effectiveness of the HydroCision SpineSite System are adequately supported by the non-clinical performance data, substantial equivalence information, and comparison of design characteristics provided within this premarket notification."

Therefore, based solely on the provided text, I cannot answer the specific questions related to acceptance criteria and a study proving the device meets those criteria, particularly those concerning:

1. A table of acceptance criteria and reported device performance (in a clinical/AI context).
2. Sample size and data provenance for a test set.
3. Number and qualifications of experts for ground truth.
4. Adjudication method for the test set.
5. MRMC comparative effectiveness study (AI vs. human).
6. Standalone algorithm performance.
7. Type of ground truth used (expert consensus, pathology, outcomes data).
8. Sample size for the training set.
9. How ground truth for the training set was established.

The device described is an endoscopic video camera system, not an AI-powered diagnostic device, which is what the questions regarding "AI assistance," "effect size," "standalone algorithm performance," and "training set" typically refer to. The document suggests a traditional medical device clearance based on substantial equivalence and non-clinical performance testing for a physical device, not an AI/ML algorithm.

Ask a specific question about this device

Indications remain unchanged from pre-pandemic COVID-19 vaccines for use in individuals 6 months of age and older.

HPE 8570B 50 Ohm Programmable Step Attenuator, DC to 18 GHz

This FDA clearance letter for the Arthrex Spine Endoscope (K243602) does not contain information about the development and validation of an AI/ML device. Instead, it describes a traditional medical device submission for an endoscope.

The letter explicitly states on Page 6: "The Arthrex Spine Endoscope did not require animal testing or human clinical studies to support the determination of substantial equivalence." and "All verification activities were successfully completed to confirm the subject device meets product requirements and design specifications established for the device." This indicates that the clearance was based on non-clinical bench testing and comparison to a predicate device, typical for traditional medical devices, rather than a novel AI/ML algorithm requiring extensive clinical validation with ground truth, expert readers, and comparative effectiveness studies.

Therefore, I cannot extract the requested information about acceptance criteria and study proving an AI/ML device meets those criteria from this document. The document pertains to a physical endoscope, not an AI/ML system.

If you have a different document pertaining to an AI/ML medical device, please provide it, and I will do my best to extract the requested information.

Ask a specific question about this device

The VECTR - Video Endoscopic Carpal Tunnel Release System is in minimally invasive ligament or fascia release surgeries, such as:

· Carpal tunnel release in the wrist

· Cubital tunnel release in the elbow

The VECTR – Video Endoscopic Carpal Tunnel Release System is composed of a handpiece (5200-01) and a proprietary tablet (5200-90). The handpiece is an arthroscopic unit with an integrated surgical knife. It is intended for minimally invasive ligament or fascia release in endoscopic carpal tunnel release (ECTR) surgery. The proprietary tablet is a registered class I medical device that is commercially available.

The handpiece is a single-use disposable device that combines the traditional manual surgical knife with an arthroscope all in one. It is fully integrated into a single unit and consists of a functional tip (surgical knife), live-action camera, light, cannula, and cord to connect to the proprietary tablet. The surgical knife can be used to sever tendons, ligaments, or fascia in the joints or limbs and is able to be protracted or retracted via a slide switch on the side of the handpiece.

During procedures, surgeons will introduce the device through incisions made in the patient's wrist. Once inside, the camera and light are used to visualize the surgical environment on the proprietary tablet. Once the surgeon has maneuvered the device into the desired location, the blade can be actuated and the ligament can be cut. Once cut, the surgeon will withdraw the blade and remove the device.

The provided text does not contain information about acceptance criteria for the VECTR - Video Endoscopic Carpal Tunnel Release System, nor does it detail a study proving the device meets specific acceptance criteria in the manner requested. The document is a 510(k) summary for FDA clearance, which focuses on demonstrating substantial equivalence to a predicate device through non-clinical testing.

Therefore, I cannot populate the table or answer the specific questions about acceptance criteria performance, sample sizes, ground truth, expert qualifications, adjudication, or MRMC studies.

Here's an overview of the information that is available in the provided text, categorized as much as possible according to your request, but highlighting the absence of the specific details you're looking for:

1. Table of Acceptance Criteria and Reported Device Performance

• Not available in the provided text. The document describes a series of non-clinical tests conducted (sterility, package stability, shelf life, biocompatibility, EMC, electrical/mechanical/thermal safety, and bench testing) to support substantial equivalence. However, it does not specify quantitative acceptance criteria for each of these tests, nor does it present the results in a comparative table format against such criteria. It generally states that the device "performs the intended functions as designed" and "is substantially equivalent."

2. Sample size used for the test set and the data provenance

• Test Set Sample Size: Not specified for any of the non-clinical tests. The document mentions "nonclinical testing provided," "testing completed," or "testing referenced," but does not give numerical sample sizes for these tests.
• Data Provenance: The data described are from non-clinical tests performed by Rafael Medical Devices, LLC, and referenced standards. This indicates the testing was conducted in a controlled environment, likely by the manufacturer or contracted labs, rather than being derived from patient data (retrospective or prospective). The geographical origin of the testing is not specified beyond the company's location (Newark, NJ, USA).

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

• Not applicable. This information is relevant for studies involving human interpretation or clinical outcomes. The provided text details non-clinical laboratory testing.

4. Adjudication method for the test set

• Not applicable. Adjudication is typically associated with clinical studies or expert review of data where discrepancies might arise. The non-clinical tests described would follow standardized protocols without an adjudication process in this context.

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

• Not applicable. The VECTR system is a physical surgical device (handpiece with integrated camera and knife) and proprietary tablet, not an AI or software-based diagnostic tool. Therefore, an MRMC study comparing human readers with and without AI assistance is not relevant to this device.

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

• Not applicable. As noted above, the device is not an algorithm, but a surgical instrument with integrated video capabilities. The "standalone" performance here refers to the device itself performing its intended functions (e.g., blade deployment, video output, safety features), which was assessed through bench testing as described.

7. The type of ground truth used

• For the non-clinical tests, the "ground truth" would be established by the specifications and validated methodologies of the referenced standards (e.g., ISO, ASTM, ANSI, AAMI, USP). For example:
  • Sterility: Absence of viable microorganisms, confirmed by biological indicators and bioburden testing according to AAMI/ISO 11135, ISO 11138, ISO 11737.
  • Package Stability: Maintenance of seal integrity and protection against shipping hazards, evaluated against ASTM standards (D5276-19, D642-20, D999-08, D4728-17, D6344-04).
  • Biocompatibility: Absence of toxicological effects (cytotoxicity, sensitization, irritation, systemic toxicity, pyrogenicity) as defined by ISO 10993 series and USP .
  • EMC: Compliance with immunity and emission levels as per IEC 60601-1-2.
  • Electrical, Mechanical, Thermal Safety: Adherence to safety requirements outlined in ANSI/AAMI ES60601-1, ISO 14971, and IEC 60601-2-18.
  • Bench Testing (functionality): Device specifications for parameters like blade deployment, insertion force, blade height, sharpness, deflection, and video output, verified through direct measurement.

8. The sample size for the training set

• Not applicable. This device is a surgical instrument, not a machine learning model, 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 a machine learning model, this question is not relevant.

In summary, the provided document focuses on non-clinical testing to demonstrate substantial equivalence of a physical medical device. It does not contain the specific details regarding acceptance criteria, clinical study design, or AI performance metrics as requested.

Ask a specific question about this device

The MIDASVu is indicated for use in diagnostic and operative arthroscopic and endoscopic procedures to provide illumination and visualization of interior cavity joints and other body cavities through a natural or surgical opening.

MIDASVu is an advanced imaging system comprised of sterile, single-use scopes (0° and 30° viewing angle) and a reusable tablet. The scopes include camera and image capture features with LED light source. The distal tip of the scopes contains the camera, illumination, and imaging optics. The scopes are available in three lengths: 60mm, 90mm, and 120mm. The scopes and tablet work in concert as a system to acquire, display and record an intra-articular image as well as store images and video taken during the procedure.

The provided text is a 510(k) summary for the MIDASVu device. It primarily discusses the device's substantial equivalence to a predicate device based on non-clinical testing. It does not include information about acceptance criteria for an AI/ML-based device, nor does it detail a study proving such a device meets acceptance criteria. The MIDASVu is described as an "advanced imaging system" and an "arthroscope," which implies a hardware device for visualization, not an AI/ML diagnostic or assistive tool.

Therefore, the requested information regarding acceptance criteria, performance studies of an AI/ML device, sample sizes, expert ground truth, adjudication methods, MRMC studies, standalone performance, and training set details for an AI/ML device is not present in the provided document. The document focuses on demonstrating substantial equivalence to a predicate hardware device through non-clinical performance and safety testing (electrical safety, EMC, biocompatibility, software validation for functionality, and cybersecurity for the embedded software of the hardware device, not for an AI/ML component).

Ask a specific question about this device

The Vertos Medical mild Device Kit is a set of specialized surgical instruments intended to be used to perform lumbar decompressive procedures for the treatment of various spinal conditions.

The Vertos Medical mild Device Kit is a sterile, single-use device. The mild Device is composed of surgical tools consisting of one each of the following components: mild Initiator, mild Access Auger, mild Bone Rongeur, and mild Tissue Sculpter. The mild Initiator is pre-assembled for convenience and includes: the mild Trocar and Handle, mild Portal, mild Portal Grip, and mild Depth Guide. The mild Device Kit is utilized for tissue access, retraction, and resection within the lumbar spine via a minimally invasive posterior approach. The procedure is conducted percutaneously with the mild Tissue Sculpter and Bone Rongeur, placed through an introducer cannula, the mild Portal.

This document is a 510(k) Pre-market Notification for a medical device, specifically the Vertos mild Device Kit. It explicitly states that the device is a set of specialized surgical instruments and not an AI or software-driven diagnostic tool.

Therefore, the request for "acceptance criteria and the study that proves the device meets the acceptance criteria" in terms of AI/software performance metrics (like sensitivity, specificity, MRMC studies, ground truth establishment by experts, etc.) is not applicable to this submission.

The "Performance Tests" section (VII) outlines the types of testing conducted for this surgical instrument kit, which focus on mechanical performance, safety, and sterility.

Here's a breakdown of the information that is present, aligning with the actual content provided:

1. A table of acceptance criteria and the reported device performance:

The document doesn't provide a table with specific numerical acceptance criteria and reported performance values for each criterion. Instead, it states that the device "met all predetermined acceptance criteria" for various performance tests. The performance is described qualitatively:

The following criteria are NOT applicable or NOT detailed in the provided document, as it pertains to a surgical instrument kit, not an AI/software device:

• Sample sized used for the test set and the data provenance: Not applicable in the context of AI/software test sets. The cadaveric testing implies a "sample size" of cadavers, but the number is not specified.
• Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for a surgical instrument is its mechanical function and safety, not diagnostic accuracy.
• Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable.
• 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: Not applicable.
• If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable.
• The type of ground truth used (expert consensus, pathology, outcomes data, etc.): For this device, ground truth is established through engineering and biocompatibility standards, and cadaveric performance, not medical consensus reads or pathology.
• The sample size for the training set: Not applicable (no AI/software training set).
• How the ground truth for the training set was established: Not applicable (no AI/software training set).

Ask a specific question about this device

The Digital ClarusScope System and Digital NeuroPEN System are intended for accessing and visualizing the spinal nerve roots, foramina, intervertebral disc, and surrounding tissues of the spine during discectomy procedures, bone and osteophyte removal, and procedures associated with ruptured or herniated discs.

The Digital ClarusScope System and Digital NeuroPEN System are spinal endoscopes which provide a light source, camera, and HDMI output for visualization. Irrigation is provided for flushing during the procedure. The working channel facilitates the use of tools necessary for spinal procedures (Digital ClarusScope versions only). The Digital ClarusScope and Digital NeuroPEN are intended to be used with the non-sterile, reusable Clarus Digital Control Module with standard HDMI video output. The proximal end of the Digital ClarusScope and Digital NeuroPEN terminate in two fittings: the endoscope connector attaches to the Clarus Digital Control Module, which interfaces to a standard off-the-shelf HDMI video monitor which is not provided by Clarus and is not part of this 510(k) application; the other fitting is an irrigation extension tube with a female Luerlock connector.

The provided text is a 510(k) summary for the Clarus Medical Digital ClarusScope System and Digital NeuroPEN System. It describes the device, its intended use, and argues for its substantial equivalence to a predicate device. However, it does not contain information regarding specific performance acceptance criteria or detailed study results for proving the device meets these criteria. It lists various tests performed (e.g., performance testing, sterility, biocompatibility, electrical safety) but does not provide quantitative results, sample sizes, ground truth establishment, or details about expert involvement that would be needed to fill out the requested table and answer the study-related questions.

Therefore, I cannot populate the table or answer the specific questions about the study design as the information is not present in the provided document.

A 510(k) summary typically focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than providing a detailed report of clinical or non-clinical trials with specific performance metrics against pre-defined acceptance criteria. While it mentions system verification and validation through "performance testing," "simulated use test," etc., it does not disclose the details of these tests in a way that would allow for a comprehensive answer to your request.

Based on the provided text, I can only state that the information required to answer your questions is not available.

Ask a specific question about this device

The FMS VUE™ Fluid Management and Tissue Debridement System is intended to provide controlled fluid distention and suction, controlled cutting, shaving and abrading of bone and tissue for use in arthroscopic surgery of the shoulder, knee, ankle, elbow, wrist and hip joints.

The FMS VUE Fluid Management and Tissue Debridement System is an arthroscopic pump system designed to provide optimal visibility of the surgical field by computer-controlled fluid regulation of intra-articular pressure, and flow during arthroscopic procedures. The system integrates a tissue debridement for controlled cutting, burring, shaving and abrading of bone and soft tissue.
The FMS VUE Fluid Management and Tissue Debridement System consists of irrigation pump, which controls joint pressure, and the suction pump, which controls the flow of saline and waste from the joint.
The FMS VUE Fluid Management and Tissue Debridement System includes an integrated shaver console, intended to provide controlled cutting, burring, shaving and abrading of bone and soft tissue.
The FMS VUE Fluid Management and Tissue Debridement System is designed to work with the existing FMS VUE platform accessories including: foot pedal, remote hand control, shaver handpieces, FMS connect cable, tubing sets, blades, and burrs.
The FMS VUE Fluid Management and Tissue Debridement System contains updates in the hardware, which include replaced near obsolescence components and new real panel connectors.
The FMS VUE Fluid Management and Tissue Debridement System software modification includes an additional shaver oscillation profile algorithm.

The provided document is a 510(k) summary for the DePuy Mitek, Inc. FMS VUE™ Fluid Management and Tissue Debridement System, seeking substantial equivalence to a previously cleared predicate device (K130169). The submission highlights hardware updates and a software modification (an additional shaver oscillation profile algorithm).

Crucially, this document is for a medical device (arthroscopic pump and debridement system) and not an AI/ML powered device that would typically have the acceptance criteria and study information you're asking for related to AI model performance (e.g., sensitivity, specificity, MRMC studies, ground truth establishment by experts).

The "acceptance criteria" and "study that proves the device meets the acceptance criteria" in this context are related to the hardware and software changes for a physical medical device, demonstrating that the modified device remains as safe and effective as its predicate.

Therefore, many of the requested points in your prompt are not applicable to the information contained in this 510(k) summary. I will address the applicable points based on the document's content.

Acceptance Criteria and Device Performance (Non-AI/ML Context)

The acceptance criteria here are focused on demonstrating that the updated FMS VUE system maintains its functional performance, electrical safety, electromagnetic compatibility, and software integrity, proving it is substantially equivalent to the predicate device despite hardware and minor software changes.

Table of Acceptance Criteria and Reported Device Performance (as inferred from the document):

• Pressure Security Test (Low & High Pressure Fault Checks): Performed. Results not detailed but implied to be acceptable.
• DUO (Inflow/Outflow) Performance: Performed. Results not detailed but implied to be acceptable.
• SOLO (Inflow) Performance: Performed. Results not detailed but implied to be acceptable.
• RFID Capability Functional Testing with existing electrical accessories (Foot Pedal, Remote Hand Control, Shaver Handpieces, FMS Connect Cable): Performed. Results not detailed but implied to be acceptable.
• Backflow-Prevention Valve Testing (Dye Leak Testing): Performed. Results not detailed but implied to be acceptable.
• Microbial and Viral Ingress Testing: Performed. Results not detailed but implied to be acceptable.
  Overall: "Results of functional performance testing were compared to the predicate device and have demonstrated that the proposed device is suitable for its intended use." |
  | Software Verification & Validation | - Software verification and validation (V&V) testing was conducted. Documentation provided as per FDA guidance "Content of Premarket Submission for Device Software Functions" (Basic Documentation level).
• "The software development process for the subject FMS VUE Fluid Management and Tissue Debridement System software conforms to all clauses of IEC 62304 standard." (IEC 62304 is a standard for medical device software life cycle processes). |
  | Electrical Safety & EMC | - "The subject FMS VUE Fluid Management and Tissue Debridement System complies with the IEC 60601-1 standard for safety and the IEC 60601-1-2 standard for EMC." (These are international standards for medical electrical equipment safety and electromagnetic compatibility). |

Study Information (as applicable to this non-AI/ML medical device submission)

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

   • The document describes "functional performance testing" of the physical device. This doesn't involve "test sets" of patient data in the way an AI/ML model would. Instead, it refers to testing the physical device and its components (e.g., pressure transducers, pumps, software algorithms for fluid control, electrical safety tests).
   • The provenance of data is from laboratory testing and verification conducted by the manufacturer, DePuy Mitek, Inc. (a Johnson & Johnson company). It is implicitly prospective testing for the design verification and validation of the modified device. No specific patient data or geographic origin is relevant here.

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

   • This question is not applicable. "Ground truth" in the context of an AI/ML model's diagnostic or predictive performance is not relevant for the functional performance testing of a fluid management and tissue debridement system. The "ground truth" here is the engineering specifications and performance requirements established by the manufacturer, verified through standard test methods and adherence to regulatory standards (e.g., IEC 60601-1, IEC 62304).

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

   • This question is not applicable. Adjudication methods like 2+1 or 3+1 are used in clinical studies, particularly for establishing ground truth from multiple expert readers in imaging studies. This is a functional and safety verification of a physical device.

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:

   • This question is not applicable. The device is a physical arthroscopic fluid management and tissue debridement system, not an AI/ML-powered diagnostic or assistive tool for human readers. No MRMC study was performed or required. The document explicitly states: "No human clinical testing was conducted to determine the safety and effectiveness of the FMS VUE Fluid Management and Tissue Debridement System."

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

   • The device has an integrated shaver console with an "additional shaver oscillation profile algorithm." The software verification and validation would have tested this algorithm's performance within the system, which can be seen as a form of standalone testing for the algorithm's functional correctness. The document states: "Software verification and validation testing was conducted..." and "The software development process... conforms to all clauses of IEC 62304 standard." This implicitly covers testing of the algorithm without a human-in-the-loop, to ensure it performs as programmed.

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

   • This question is not applicable in the typical sense for AI/ML. The "ground truth" for the device's functional performance are the engineering specifications, validated test methods, and compliance with recognized industry standards (e.g., pressure output accuracy, flow rates, software logic, electrical safety limits).

7. The sample size for the training set:

   • This question is not applicable. This is not an AI/ML system that requires a "training set" of data in the manner of deep learning models. The software algorithms are likely rule-based or control-loop algorithms, not learned from large datasets.

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

   • This question is not applicable for the same reason as point 7.

Ask a specific question about this device

The Hawkeye Control Unit with Eyas Endoscope is intended for use in diagnostic and operative arthroscopic and endoscopic procedures to provide visualization and image capture of an interior body cavity through a surgical incision.

The E Surgical Hawkeye Control Unit with Eyas Endoscope is an arthroscope system, consisting of the Hawkeye Control Unit (Medical Tablet plus Console Box), and the Eyas Endoscope. The Medical Tablet is a touch panel computer for the system function control, endoscope image displays and operation data storage. The Eyas Endoscope is a hand-held, single-use device for accessing the interior of a joint to capture the real-time image of the target site through a small incision. The Console Box is an interface between the Medical Tablet and Eyas Endoscope. There are 10 models of Eyas Endoscope in this system; including 2 different directions of view (0° and 30°) in combination with 5 different working lengths. All these models must be used in conjunction with Hawkeye Control Unit to perform as intended. The E Surgical Hawkeye Control Unit with Eyas Endoscope is also capable recording and storing the images in the system for later review.

This document is a 510(k) Premarket Notification from the FDA regarding the "Hawkeye Control Unit with Eyas Endoscope." It details the device, its intended use, a comparison to a predicate device, and summaries of bench testing and compliance with standards.

However, the provided text does not contain information about studies proving the device meets acceptance criteria related to a comparative effectiveness study involving AI or human readers, nor does it provide details about ground truth establishment with experts, adjudication methods, or standalone AI performance.

The document focuses on demonstrating substantial equivalence to a predicate device (Trice medical mi-eye2, mi-eye 2 monitor (K162475)) through comparison of features, operating principles, technology, and compliance with various recognized standards (electrical safety, biocompatibility, sterilization, software lifecycle, packaging).

The "Bench Testing Summary" section describes various tests performed on the device components (Console Box, Medical Tablet, Eyas Endoscope, and their packaging) to verify their functionality and performance against specifications. These are typical engineering and quality assurance tests, not clinical performance studies for diagnostic accuracy or comparative effectiveness with human readers, especially not for an AI component.

Given the provided text, it's not possible to fully answer the request as it pertains to AI model acceptance criteria and validation studies. The device as described is an arthroscope system for visualization and image capture, not an AI-powered diagnostic tool.

Therefore, for the specific questions asked that relate to AI model validation, the answer is: This document does not contain the requested information about AI model acceptance criteria or validation studies, as the device described is an arthroscope system, not an AI-powered diagnostic or assistive tool.

If we interpret "acceptance criteria" in the context of this document as the criteria for demonstrating substantial equivalence for an arthroscope system, then the "reported device performance" is its adherence to technical specifications and relevant safety/performance standards, as summarized in the bench testing.

Here's what can be extracted based on the provided text, focusing on the device's technical acceptance and testing, not AI:

Acceptance Criteria and Device Performance (Based on Technical Specifications and Bench Testing)

The document implicitly defines acceptance criteria through its comparison to a predicate device and its demonstrated compliance with international standards. The performance is reported as meeting these standards and having features functionally equivalent to the predicate.

1. Table of acceptance criteria and the reported device performance (Interpreted as technical and functional equivalence):

Since the device is not an AI-powered diagnostic system, the following questions cannot be answered from the provided document:

2. Sample size used for the test set and the data provenance: Not applicable for an AI test set. The document describes bench testing on the device itself.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for an AI model is not established here.
4. Adjudication method for the test set: Not applicable.
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: Not applicable. This is not an AI-assisted device.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Not applicable.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable. The "ground truth" for this device's performance is its adherence to engineering specifications and international standards, demonstrated by bench testing.
8. The sample size for the training set: Not applicable, as this is not an AI algorithm.
9. How the ground truth for the training set was established: Not applicable.

In summary, this FDA 510(k) document indicates substantial equivalence for an arthroscope system based on standard engineering and performance tests, not on AI model validation.

Ask a specific question about this device

Kyphoplasty Balloon Catheter is intended to be used for the reduction of fixation of fractures and/or creation of a void in cancellous bone in the spine during balloon kyphoplasty (for use with cleared spinal polymethymethacrylate (PMMA) bone cements).

Kyphoplasty Balloon Catheter is an inflatable balloon catheter used in percutaneous kyphoplasty (PKP). The Balloon Catheter consists of an outer tube and core tube/rod, inflatable balloon located at the distal tip. The radiopaque markers located at the balloon tip to reflect the balloon position during positioning. The balloon catheter is supplied sterilized, single-use.

The provided text describes the 510(k) summary for the Kyphoplasty Balloon Catheter, focusing on its non-clinical testing to demonstrate substantial equivalence to a predicate device. It explicitly states that no clinical study was performed or included in the submission. Therefore, I cannot provide information on acceptance criteria and study proving device meets acceptance criteria related to a clinical study, human reader performance, or multi-reader multi-case studies, as there were none reported.

The information below is derived from the non-clinical (bench) testing section, which serves as the primary evidence for this device's acceptance.

Here's the breakdown based on the provided text for the non-clinical testing:

1. Table of Acceptance Criteria and Reported Device Performance (Non-Clinical Bench Testing)

The document primarily lists acceptance criteria for various bench tests. It states that "The test results show pass the requirements" for the performance tests, implying the device met these criteria, but specific reported values are not provided, except for the "Balloon Inflation Behavior" which includes a target range.

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

The document does not specify the sample size (number of devices) used for each bench test. The studies were non-clinical (bench tests) meaning they were conducted in a lab environment using the physical device. Data provenance refers to the origin of the data. For bench testing, this would typically be from the manufacturer's internal testing facilities (Jiangsu Changmei Medtech Co., Ltd.). The data is prospective in the sense that the testing was performed specifically for this 510(k) submission.

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

Not applicable. For non-clinical bench testing, "ground truth" is established by engineering specifications, validated test methods, and measurement against international standards (ISO, ASTM, USP). Experts involved would be engineers and quality control personnel, not medical practitioners.

4. Adjudication Method for the Test Set

Not applicable. Adjudication methods like 2+1 or 3+1 are used in clinical studies, typically for resolving disagreements among human readers or expert reviewers of clinical data. This document describes bench testing where measurements are objective and quantitative.

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, an MRMC study was not done. The document explicitly states: "No clinical study is included in this submission." This device is a physical medical device (balloon catheter), not an AI-assisted diagnostic tool.

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

Not applicable. This is a physical device, not an algorithm.

7. The Type of Ground Truth Used

For non-clinical bench tests, the "ground truth" is based on:

• Pre-defined engineering specifications and acceptance criteria.
• Measurements against established physical properties and performance metrics.
• Compliance with recognized international standards (e.g., ISO 10993 for biocompatibility, ISO 11135 for sterilization, ASTM F1980 for shelf-life, ISTA-2A for shipping).

8. The Sample Size for the Training Set

Not applicable. "Training set" refers to data used to train machine learning algorithms. This document describes a physical medical device and its non-clinical testing.

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

Not applicable for the same reason as above.

Ask a specific question about this device