Search Results

Visions® PV.014P RX Digital IVUS Catheter:

The Visions® PV.014P RX Digital IVUS Catheter is designed for use in the evaluation of vascular morphology in blood vessels of the coronary and peripheral vasculature by providing a cross-sectional image of such vessels. This device is not currently indicated for use in the cerebral vessels.

The Visions® PV.014P RX Digital IVUS Catheter is designed for use as an adjunct to conventional angiographic procedures to provide an image of the vessel lumen and wall structures.

Visions® PV .018 Digital IVUS Catheter:

The Visions® PV .018 Digital IVUS Catheter is designed for use in the evaluation of vascular morphology in blood vessels of the coronary and peripheral vasculature by providing a cross-sectional image of such vessels. This device is not currently indicated for use in cerebral vessels.

The Visions® PV .018 Digital IVUS Catheter is designed for use as an adjunct to conventional angiographic procedures to provide an image of the vessel lumen and wall structures.

The Visions® PV .014P RX Digital IVUS Catheter and the Visions® PV .018 PV .018 Digital IVUS Catheter are being bundled into one submission per FDA Guidance for Industry: Bundling Multiple Devices or Multiple Indications in a Single Submission, June 2007 (FDA-2003-D-0376), as the two catheters share the same indications for use, FDA classification product codes, and technological characteristics, and part of the same product line of catheters.

Visions® PV .014P RX Digital IVUS Catheter

The Visions® PV .014P RX Digital IVUS Catheter incorporates a cylindrical ultrasound transducer array located near the distal tip of the catheter. The array radiates acoustic energy into the surrounding tissue and detects the subsequent ultrasonic echoes. The information from the echoes is used to generate real-time images of the coronary or peripheral vessels.

The Visions® PV .014P RX Digital IVUS Catheter utilizes an internal lumen that allows the catheters to track over a 0.018" (0.46 mm) guide wire. The guide wire exits from the guide wire lumen approximately 31 cm proximal to the catheter tip. The PV .018 catheters are introduced either percutaneously or via surgical cut down into the vascular system.

The Visions® PV .014P RX Digital IVUS Catheter may only be used with Volcano imaging systems, such as the Volcano s5™, Volcano s5i™, Volcano CORE Mobile, and Volcano CORE imaging systems. The catheter will not operate if connected to any other imaging system.

Visions® PV .018 Digital IVUS Catheter

The Visions® PV .018 Digital IVUS Catheter incorporates a cylindrical ultrasound transducer array located near the distal tip of the catheter. The array radiates acoustic energy into the surrounding tissue and detects the subsequent ultrasonic echoes. The information from the echoes is used to generate real-time images of the coronary or peripheral vessels.

The Visions® PV .018 Digital IVUS Catheter utilizes an internal lumen that allows the catheters to track over a 0.018" (0.46 mm) guide wire. The guide wire exits from the guide wire lumen approximately 31 cm proximal to the catheter tip. The PV .018 catheters are introduced either percutaneously or via surgical cut down into the vascular system.

The Visions® PV .018 Digital IVUS Catheter may only be used with Volcano imaging systems, such as the Volcano s5™, Volcano s5i™, Volcano CORE Mobile, and Volcano CORE imaging systems. The catheter will not operate if connected to any other imaging system.

N/A

Ask a specific question about this device

The Visionary Optics Scleral Contact Lens for daily wear is indicated for use for the management of multiple ocular conditions, such as, degenerations that lead to an irregular corneal shape (e.g. keratoconus, keratoglobus, pellucid marginal degeneration, Salzman's Nodular Degeneration), dystrophies (e.g. Cogan's dystrophy, Granular Corneal Dystrophy, Lattice Corneal Dystrophy,), post-surgery (e.g. corneal transplant, LASIK, radial keratotomy), and corneal scarring from infection or trauma.

The Visionary Optics Scleral Contact Lens for daily wear is also indicated for therapeutic management of ocular surface disease including dry eye (e.g. ocular manifestations of Graft-versus-Host disease, Sjogren's syndrome, dry eye syndrome), limbal stem cell deficiency (e.g. Stevens-Johnson syndrome, chemical and thermal burns, radiation, filamentary keratitis), epidermal ocular disorders of the skin (e.g. atopy, ectodermal dysplasia), neurotrophic keratitis (e.g. Herpes simplex, Herpes zoster, Familial Dysautonomia), and corneal exposure (e.g. anatomic, paralytic) that might benefit from the presence of an expanded tear reservoir and protection against an adverse environment. When prescribed for therapeutic use for distorted cornea or ocular surface disease, the Visionary Optics Scleral Contact Lens may incidentally provide correction of refractive error in persons with myopia, astigmatism or presbyopia.

Eye care practitioners may prescribe the lenses for frequent/planned replacement wear, with cleaning, disinfection and scheduled replacement. When prescribed for frequent wear, the lens may be cleaned and disinfected using a chemical (not heat) lens care system.

The Visionary Optics Scleral Contact Lens (roflufocon D, roflufocon E, hexafocon A, hexafocon B, tisilfocon A, fluoroxyfocon A) for daily wear is a large diameter rigid gas permeable contact lens design that vaults over the cornea and rests on the conjunctiva overlying the sclera. The Visionary Optics Scleral Contact Lens is lathe cut from one of the following hydrophobic, FDA Group #3 fluoro-silicone acrylate materials: roflufocon D, roflufocon E, hexafocon A, hexafocon B, tisilfocon A, or fluoroxyfocon A.

The provided FDA 510(k) summary (K233325) for the Visionary Optics Scleral Contact Lens describes non-clinical and clinical studies conducted to support the substantial equivalence claim. However, it does not provide specific acceptance criteria or detailed study results in the format requested. The document primarily focuses on demonstrating equivalence to predicate devices rather than providing a standalone performance validation for a novel device with explicit performance metrics.

Therefore, much of the requested information regarding acceptance criteria, specific performance metrics, sample sizes for test sets, ground truth establishment, expert qualifications, adjudication methods, and MRMC studies is not available within the provided text.

Here's a breakdown of what can be extracted and what is not available:

1. Table of Acceptance Criteria and Reported Device Performance

Explanation: The document does not present specific numerical acceptance criteria (e.g., "X% accuracy," "Y precision"). Instead, for non-clinical studies, it states that manufacturing tolerances were met and bioburden was "within the established acceptance criteria of less than 100 CFU per lens." For clinical studies, the "acceptance criteria" appear to be implied by the outcome: no serious adverse events and stable/improved patient conditions.

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

• Test set sample size: 33 patients (63 total eyes).
• Data provenance: Not explicitly stated, but the study involved "Nine (9) independent practitioners," suggesting a multi-center, prospective clinical evaluation. The document does not specify the country of origin of the data.

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

• Number of experts: Nine (9) independent practitioners.
• Qualifications of experts: Not explicitly stated other than "independent practitioners." Their specific specializations (e.g., ophthalmologists, optometrists, or subspecialties) or years of experience are not provided.

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

• Adjudication method: Not described. The text states that "The practitioners reviewed all patients therapeutically managed... and reported the outcome of each patient." There is no mention of an adjudication process among these practitioners for establishing a unified ground truth.

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

• MRMC comparative effectiveness study: No, this document pertains to a medical device (scleral contact lens), not an AI-powered diagnostic or assistive tool. Therefore, an MRMC study related to AI assistance for human readers is not applicable and was not performed.

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

• Standalone performance: No, this device is a physical contact lens, not an algorithm. The clinical performance inherently involves human fitting and patient use.

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

• Type of ground truth: The "ground truth" for the clinical study appears to be the observed clinical outcome reported by the independent practitioners, specifically: "no serious or significant adverse reactions reported" and "for all patients, the ocular condition(s) and vision remained stable or improved." This is a form of outcomes data based on clinical observation and assessment by practitioners.

8. The sample size for the training set

• Training set sample size: Not applicable and not mentioned. This is a medical device, not a machine learning model. The "training" described in the context of this submission refers to the historical data and previous 510(k) clearances that establish the safety and effectiveness of the materials used in the lens.

9. How the ground truth for the training set was established

• Ground truth establishment for training set: Not applicable and not mentioned. As this is not an AI/ML device, the concept of a "training set ground truth" as you've framed it is not relevant. The safety and effectiveness of the materials (roflufocon D, roflufocon E, etc.) used in the device were established through "reference to previous 510(k) clearances" and "previous 510(k) clearances," implying that historical data and prior regulatory assessments for these materials served as the basis for their use in the current device.

Ask a specific question about this device

The Visionbody System is a device intended to stimulate healthy muscles in order to improve or facilitate muscle performance. It is to be used by adults only.

The Visionbody System is not intended to be used in conjunction with therapy or treatment of medical conditions of any kind. None of the training programs or operational parameters are designed or ailing muscles and its use on such muscles is contraindicated.

The Visionbody System's electrical impulses allow the triggering of action potentials on motoneurons of motor nerves (excitations). These excitations of motoneurons are transmitted to the muscle fibers via the motor endplate where they generated mechanical muscle fiber responses that correspond to muscle work. Depending on the parameters of the electrical impulses (pulse frequency, duration, duration of rest, total session duration), different types of muscle work can be imposed on the stimulated muscles.

The Visionbody System is a wireless electrical muscle stimulation device for health and fitness applications. The main components are the Visionbody Box, the Visionbody Software and the choice of a Visionbody garment, whether a Visionbody Powersuit, Visionbody PowerPants or Visionbody Power Vest, dependent on a user's personal choice and needs. The Visionbody Box delivers a safe low to mid frequency electrical current to the electrodes in a Visionbody garment. The Visionbody uses electrical muscle stimulation (EMS) and electrical muscle activation (EMA) technologies to provide a streamlined approach to a user's fitness goals, especially regarding body composition, strength and endurance. Underlying to both these technologies are safe electrical impulses, which stimulate muscle contractions equating to muscle workouts.

The provided text is a 510(k) Summary for the Visionbody system, a powered muscle stimulator. It details a comparison with a predicate device (Katalyst Training System Model 1) and two reference devices (FM-B2403A EMS and R-E1 EMS).

Here's a breakdown of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" in a quantitative manner as one might find for diagnostic performance (e.g., sensitivity, specificity thresholds). Instead, the acceptance criteria are implicitly demonstrated through compliance with various safety and performance standards and by showing substantial equivalence to a legally marketed predicate device.

The "reported device performance" is primarily the device's compliance with safety standards and its functional characteristics. The comparison table directly addresses this.

Summary of the study that proves the device meets the acceptance criteria:

The study is a non-clinical product evaluation intended to demonstrate safety and effectiveness for substantial equivalence. It is primarily a comparison of technical characteristics and compliance with recognized standards rather than a traditional clinical trial or performance study with a test set of data.

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

There is no mention of a "test set" in the context of human data or any specific patient or subject data being used for device performance evaluation in this document. The evaluation is based on non-clinical testing of the device itself against established engineering and safety standards, and a comparative analysis against predicate and reference devices' technical specifications.

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

Not applicable. As there is no human "test set" or diagnostic evaluation mentioned, there is no ground truth established by experts in that context. The "truth" here is compliance with technical specifications and safety standards.

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 device is a powered muscle stimulator, not an AI-powered diagnostic imaging system that would involve human readers or AI assistance in interpretation.

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

The term "standalone" typically refers to the performance of an AI algorithm independent of human input or review. While the Visionbody system has software, its purpose is to control electrical muscle stimulation, not to perform diagnostic or interpretative tasks where "standalone" performance metrics for AI would apply. The device's "standalone" performance would be its functional operation in stimulating muscles according to its programmed parameters, which was evaluated through performance testing.

The document states: "Software verification and validation testing were conducted on the Visionbody system and documentation was provided as recommended by FDA's Guidance... The software for this device was considered as a "moderate" level of concern, since a failure or latent flaw in the software would lead to a delayed delivery of appropriate medical care." This confirms standalone software testing was performed to ensure its functionality and safety.

7. The type of ground truth used

The ground truth used for this type of device (a powered muscle stimulator) is primarily:

• Compliance with recognized international standards: Electrical safety (IEC 60601-1, IEC 60601-2-10), Electromagnetic Compatibility (IEC 60601-1-2), Biocompatibility (ISO 10993 series), and Usability/Risk Management (IEC 62366).
• Manufacturer's own requirements and specifications: Performance testing verified the device against its own design requirements.
• Predicate device characteristics: Similarity to a legally marketed predicate device (Katalyst Training System Model 1) serves as a benchmark for substantial equivalence in safety and effectiveness.

8. The sample size for the training set

Not applicable. This is not an AI/machine learning device that requires a "training set" of data in the typical sense for model development. The software is for device control, not for learning or prediction based on data.

9. How the ground truth for the training set was established

Not applicable.

Ask a specific question about this device

The Visionary Optics Scleral Contact Lens for daily wear is indicated for use for the management of multiple ocular conditions, such as, degenerations that lead to an irregular corneal shape (e.g. keratoconus, keratoglobus, pellucid marginal degeneration, Salzmann's Nodular Degeneration), dystrophies (e.g. Cogan's dystrophy, Granular Corneal Dystrophy, Lattice Corneal Dystrophy,), post-surgery (e.g. corneal transplant, LASIK, radial keratotomy), and corneal scarring from infection or trauma.

The Visionary Optics Scleral Contact Lens for daily wear is also indicated for therapeutic management of ocular surface disease including dry eye (e.g. ocular manifestations of Graft-versus-Host disease, Sjogren's syndrome, dry eye syndrome), limbal stem cell deficiency (e.g. Stevens-Johnson syndrome, chemical and thermal burns, radiation, filamentary keratitis), epidermal ocular disorders of the skin (e.g. atopy, ectodermal dysplasia), neurotrophic keratitis (e.g. Herpes simplex. Herpes zoster, Familial Dysautonomia), and corneal exposure (e.g. anatomic, paralytic) that might benefit from the presence of an expanded tear reservoir and protection against an adverse environment. When prescribed for therapeutic use for distorted cornea or ocular surface disease, the Visionary Optics Scleral Contact Lens may incidentally provide correction of refractive error in persons with myopia, astigmatism or presbyopia.

Eye care practitioners may prescribe the lenses for frequent/planned replacement wear, with cleaning, disinfection and scheduled replacement. When prescribed for frequent wear, the lens may be cleaned and disinfected using a chemical (not heat) lens care system.

The Visionary Optics Scleral Contact Lens (roflufocon D, roflufocon E, hexafocon A, hexafocon B, tisilfocon A) for daily wear is a large diameter rigid gas permeable contact lens design that vaults over the cornea and rests on the conjunctiva overlying the sclera. The Visionary Optics Scleral Contact Lens is lathe cut from one of the following hydrophobic, FDA Group #3 fluorosilicone acrylate materials: roflufocon D, roflufocon E, hexafocon B, or tisilfocon A.

I am sorry, but the provided text does not contain the detailed information necessary to complete the requested table and study description regarding acceptance criteria and device performance. The document is a 510(k) summary for a contact lens, primarily focusing on its substantial equivalence to predicate devices rather than presenting a detailed study with specific acceptance criteria, sample sizes, expert qualifications, or adjudication methods for performance evaluation.

Here's a breakdown of why I cannot fulfill your request based on the provided text:

• No explicit Acceptance Criteria: The document mentions that lenses were manufactured to "established finished product specifications within the ANSI Z80.20 tolerance" for bench testing, and bioburden testing had an "established acceptance criteria of less than 100 CFU per lens." However, it does not provide a comprehensive table of acceptance criteria for the overall device performance as per your request (e.g., visual acuity, comfort, etc.).
• No detailed Device Performance Results: While it states that manufacturing verification testing demonstrated the ability to manufacture lenses "to a variety of prescribed parameters" and bioburden testing was "within the established acceptance criteria," it does not provide specific numerical results or a comparative performance table against a set of acceptance criteria.
• No information on Test Set Sample Size and Data Provenance: The document does not specify the sample size used for any performance testing, nor does it provide information about the country of origin or whether the data was retrospective or prospective.
• No information on Experts for Ground Truth: There is no mention of experts, their number, or qualifications used to establish ground truth for any testing described.
• No Adjudication Method: The document does not describe any adjudication methods used for a test set.
• No MRMC Comparative Effectiveness Study: The submission primarily relies on substantial equivalence to predicate devices and general claims of safety and effectiveness, not a multi-reader multi-case comparative effectiveness study with AI assistance.
• No Standalone Performance (AI-specific): This device is a contact lens, not an AI algorithm. Therefore, "standalone (i.e., algorithm only without human-in-the-loop performance)" is not applicable.
• No Ground Truth Type (for performance studies): Since detailed performance studies with ground truth are not presented, this information is not available. The "ground truth" for a contact lens would typically involve clinical measurements by optometrists/ophthalmologists, patient feedback, and objective physiological responses, but these are not quantified or described in the provided text.
• No Training Set Sample Size or Ground Truth Establishment for Training Set: As this is not an AI device, the concepts of training sets and their ground truth establishment are not applicable here.

The section under "VII. PERFORMANCE DATA" explicitly states:

• "Non-clinical testing to demonstrate the safety and effectiveness of contact lenses manufactured from roflufocon D, roflufocon E, hexafocon A, hexafocon B and tisilfocon A has been addressed by reference to previous 510(k) clearances."
• "Clinical testing to demonstrate the safety and effectiveness of contact lenses manufactured from roflufocon D, roflufocon E, hexafocon A, hexafocon B and tisilfocon A with the labeled indications for use has been addressed through previous 510(k) clearances."

This indicates that extensive new performance studies were not conducted for this specific 510(k) clearance, but rather reliance on prior clearances for similar materials and designs. The only specific tests mentioned are:

• Bench Testing: Manufacturing verification to ensure lenses meet ANSI Z80.20 tolerance for established finished product specifications. No specific results table or acceptance criteria other than "within the ANSI Z80.20 tolerance" are provided.
• Bioburden Testing: Demonstrated "colony forming units (CFU) per lens was within the established acceptance criteria of less than 100 CFU per lens."

Therefore, I cannot extract the level of detail you are requesting from this document.

Ask a specific question about this device

Vision 2, EVARVision, TrackVision 2 and HeartVision 2 software applications are intended to enable users to load 3D datasets and overlay and register in real time these 3D datasets with radioscopic or radiographic images of the same anatomy in order to support catheter/device guidance during interventional procedures.

Structures of interest and estimated dimensions can be overlaid on the radioscopic or radiographic images. Image processing can be applied to enhance the display of such images. This information is intended to assist the physician during interventional procedures.

The Stereo 3D option enables physicians to visualize and localize needles, points, and segments on a 3D model/space using a stereotactic reconstruction of radioscopic or radiographic images at a significantly lower dose than use of a full cone beam CT acquisition. This information is intended to assist the physician during interventional procedures.

Vision Applications are a group of software applications called Vision 2, EVARVision, TrackVision 2 and HeartVision 2 that share the same core functionalities to target different clinical procedures.

Vision Applications load 3D datasets previously acquired from an acquisition modality (CT, MR or CBCT) and prepared with Volume Viewer application [K041521]. They overlay and register in real-time these 3D datasets with the 2D X-ray live images acquired from the GE Interventional X-ray system [K181403] (called IGS X-ray system in the rest of the document) to help support localization and guidance of catheters / devices during interventional procedures, in conjunction with primary images, native live 2D X-ray images.

Vision Applications help physicians to perform interventional procedures by providing enhanced image quality and additional 3D information instead of 2D X-ray live images alone.

Vision Applications operate on GE's Advantage Workstation (AW) [K110834] platform and communicates with the IGS X-ray system [K181403] for receiving the live X-ray images.

The subject device, Vision Applications were developed from modifications to the primary predicate device Innova Vision Applications [K092639], including the addition of new optional feature "Digital Pen". The Digital Pen option is what triggered this 510k and was modified from the reference device, GE's IGS X-ray systems [K181403] under the name Stenosis Analysis. The Vision Applications include also Stereo 3D option feature [K152352, secondary predicate].

The primary features/functionalities of the Vision Applications are:

• . Digital Pen.
• Overlay of 2D/3D images.
• Reception and display of live 2D images and related information. ●
• Loading of 3D datasets.
• Review mode.
• Film/Sequence/photo store.
• . Display controls for Visualization of images: including Zoom/Roam, Rendering, Planning data display, Annotation display, Virtual Collimation, ECG Display, Calcification Visualization Enhancement, display adjustment tools.
• Automatic Registration: including A priori registration and Registration based on Augmented Calibration.
• Manual Registration.
• Bi-view registration.
• User Interface: control from AW and from Tableside.
• . 2D Modes.
• Send Angles: including EVAR Angles, Progress View/Bull's eye.
• . Stereo 3D.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on your provided text:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size for Test Set and Data Provenance

• Sample Size: The text states "a phantom with series of known dimension." It does not provide a specific numerical sample size for the test set.
• Data Provenance: The data was generated through "Engineering bench testing" using a "phantom." This indicates the data is prospective and simulated in a controlled environment, rather than from actual patient clinical data. The country of origin is not explicitly stated for this specific test, but the submitter is GE Medical Systems SCS, located in Buc, France.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: The document does not mention the use of experts to establish ground truth for this engineering bench testing. The ground truth for the dimension estimation was based on a "phantom with series of known dimension," implying a pre-defined, objective standard rather than expert consensus on images.

4. Adjudication Method for the Test Set

• Adjudication Method: Not applicable. The ground truth was based on a phantom with known dimensions, not on human interpretation requiring adjudication.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• MRMC Study: No, an MRMC comparative effectiveness study was not performed. The text explicitly states, "The subject of this premarket submission, Vision Applications, did not require clinical studies to support substantial equivalence."

6. Standalone (Algorithm Only) Performance Study

• Standalone Study: Yes, the testing described appears to be a standalone performance study of the "Digital Pen option" specifically focusing on its "dimension estimation accuracy." This was performed using "engineering bench testing" with a "phantom," meaning the algorithm's performance was evaluated against known physical dimensions without human-in-the-loop assistance during the measurement evaluation. The overall device, however, is intended to assist human operators.

7. Type of Ground Truth Used

• Type of Ground Truth: For the "Digital Pen option" dimension estimation testing, the ground truth was objective, pre-defined physical dimensions of a phantom ("a phantom with series of known dimension").

8. Sample Size for Training Set

• Sample Size: The document does not provide information about the sample size used for the training set. This is common for submissions if the device is a modification of a predicate and primarily relies on engineering changes and validation rather than a completely new AI model.

9. How Ground Truth for Training Set was Established

• How Ground Truth was Established: The document does not provide information on how ground truth was established for a training set. This suggests that the development likely leveraged existing algorithms or established principles from the predicate devices and the reference device's "Stenosis Analysis" functionality, rather than requiring a new, extensive labeled training dataset for novel AI model development.

Ask a specific question about this device

The Vision Monitor MonCvONE system is a non-invasive medical device used to generate photic stimulations and to register the responses including electrical responses generated by the retina and the visual nervous system in addition to psychophysical and pupillary responses. It displays digitized electroretinogram (ERG), visual evoked potential (VEP), sensory electro-oculogram (EOG), light and dark adapted perimetry thresholds, dark adaptometry, full field stimulus threshold (FST), photo aversion thresholds (PAT), pupillometry as curves, power spectra and topographic maps. These functions are controlled and interpreted by trained medical professionals.

Photopic stimuli are presented to the patient on a hemispherical cupola. Various modes are available for preferential stimulation of different visual functions. Electrophysiological data is recorded by up to 5 recording channels using conventional EEG electrodes (not provided with the device). Psychophysical responses are recorded with a press button and pupillometry responses recorded with an eye tracker.

During the period of time that the system is acquiring data (1-20 minutes), there is a real time display of the raw and processed data presented to the operator. Once the resulting individual responses are acquired, the signals are analyzed by software using algorithms for spatial filtering and artifact rejection. Data may be presented in a number of forms, including waves recorded at each of the points tested, color plots, or 3D topographical representation.

Here's an analysis of the provided text, outlining the acceptance criteria and the study details for the Vision Monitor-MonCvONE device:

Acceptance Criteria and Device Performance

Study Details

Based on the provided text, the submission describes non-clinical testing rather than a clinical study involving human patients to establish the device's performance against ground truth.

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

   • The document describes non-clinical bench testing including technical, functional, and compatibility tests. It does not mention a test set of patient data with a specific sample size. The testing focuses on the device's adherence to standards and its internal components' functionality.
   • Data provenance: Not applicable as no patient data test set is described.

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

   • Not applicable. The document describes engineering and safety testing against defined standards and specifications, not interpretation of medical data by experts to establish ground truth for a test set.

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

   • Not applicable. There is no mention of a test set requiring adjudication. The testing described is based on engineering principles and regulatory standards.

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. The document does not describe an MRMC study, nor does it indicate that the device involves AI for interpretation by human readers. The device generates and displays physiological data; "These functions are controlled and interpreted by trained medical professionals."

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

   • The document describes the device as a system that generates photic stimulations and registers responses, with software for analysis and display. However, it explicitly states, "These functions are controlled and interpreted by trained medical professionals." This indicates that the device is intended for use with human-in-the-loop interpretation, and no standalone (algorithm-only) performance claim or study is detailed. The described tests are about the device's performance in generating and recording data, and its software's functionality, not its diagnostic accuracy in an unsupervised manner.

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

   • The ground truth for the described testing is based on engineering specifications, regulatory standards (e.g., IEC 60601-1, ISO 14971), and functional requirements for generating, recording, and processing electrophysiological signals. There is no mention of a clinical ground truth (like pathology or expert consensus on patient cases) being used for the performance claims in this submission.

7. The sample size for the training set:

   • Not applicable. The device is a measurement and display system, not an AI or machine learning algorithm that requires a training set of data.

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

   • Not applicable, as there is no training set mentioned for this device.

Ask a specific question about this device

The VisionAir Patient-Specific Airway Stent is indicated for the treatment of adults ≥22 years of age with symptomatic stenosis of the airway. The silicone stent is intended for implantation into the airway by a physician using the recommended deployment system or an equivalent rigid bronchoscope and stent placement system that accepts the maximum stent diameter being placed. The stent is intended to be in the patient up to 12 months after initial placement.

The subject device, VisionAir Patient-Specific Airway Stent is comprised of a cloudbased software suite and the patient-specific airway stent. These two function together as a system to treat symptomatic stenosis of the airway per the indications for use. The implantable patient-specific airway stent is designed by a physician using a CT scan as a guide in the cloud-based software suite. The airway is segmented from the CT scan and used by the physician in designing a patient-specific stent. When design is complete, the stent is manufactured via silicone injection into a 3D-printed mold and delivered to the treating physician nonsterile, to be sterilized before use.

The implantable patient-specific airway stent includes the following general features:

• Deployed through a compatible rigid bronchoscope system
• Made of biocompatible, implant-grade silicone
• Steam sterilizable by the end user
• Anti-migration branched design
• Anti-migration studs on anterior surface of main branch
• Single-use

The cloud-based software suite has the following general features:

• Upload of CT scans
• Segmentation of the airway
• Design of a patient specific stent from segmented airway
• Order management of designed stents

The provided text is a 510(k) Summary for the VisionAir Patient-Specific Airway Stent, which focuses on demonstrating substantial equivalence to a predicate device. It primarily discusses the device description, indications for use, technological characteristics, and a list of nonclinical performance and functional tests conducted.

However, the document does not contain the detailed information required to fulfill the request regarding acceptance criteria and the study that proves the device meets those criteria. Specifically, it lacks:

1. A table of acceptance criteria and reported device performance: While it lists types of tests, it does not provide specific quantitative acceptance criteria or the actual results from these tests.
2. Sample size used for the test set and data provenance: No information is given about the sample size for any clinical or performance test, nor the origin or nature of the data (retrospective/prospective, country).
3. Number of experts used to establish ground truth and qualifications: This information is completely absent.
4. Adjudication method for the test set: Not mentioned.
5. Multi-Reader Multi-Case (MRMC) comparative effectiveness study details: No MRMC study is described; the testing mentioned is primarily non-clinical or related to software validation/verification, not human-AI comparative effectiveness.
6. Standalone (algorithm-only) performance: While "Software Verification and Validation Testing" and "Airway Segmentation Process Testing" are mentioned, no specific standalone performance metrics (e.g., accuracy, precision for segmentation) or acceptance criteria are provided.
7. Type of ground truth used: The document mentions "Airway Segmentation Process Testing" and refers to a predicate device (Mimics) for "performance reference specification" for dimensional testing of airway segmentation. This implies that the ground truth for segmentation would likely be derived from expert-reviewed segmentations or potentially from known anatomical measurements, but the method is not explicitly detailed.
8. Sample size for the training set: There is no mention of a "training set" or any machine learning model that would require one. The software aspect described is for physician-guided design and semi-automated segmentation, not explicitly an AI/ML model that undergoes a training phase in the typical sense for medical image analysis.
9. How the ground truth for the training set was established: Not applicable, as no training set is described.

The document states: "Reference devices, Mimics (K073468) and Osirix MD (K101342) were used for reference software performance specifications." and "Dimensional Testing of Airway Segmentation (reference device Mimics K073468 used for performance reference specification)". These statements hint at software validation, especially for the segmentation component, but do not provide the detailed study design, acceptance criteria, or results.

In summary, the provided text does not contain the necessary information to answer the request in detail, as it focuses on demonstrating substantial equivalence through non-clinical performance and functional testing rather than a clinical study with acceptance criteria for device performance based on human reader interaction or AI model performance.

Ask a specific question about this device

The VISIONAIR™ system is a software application intended to be used with third-party endoscopic systems in the measurement of the nasal respiratory airway. The VISIONAIR™ system measures the nasal respiratory airway from the endoscopic images taken in the region of the internal nasal valve (INV) and nasal cavum (NC).

The VISIONAIR™ software can be utilized to automatically measure the cross-section area of the Internal Nasal Valve (INV) and Nasal Cavum (NV) and measure the nasal respiratory airway in this region of the anatomy. The VISIONAIR™ system consists of the following components: - The VISIONAIR™ algorithm which performs the Internal Nasal Valve and Nasal Cavum cross-section area segmentations. - The VISIONAIR™ Graphical User Interface (GUI) used for data entry, view the endoscopic image from third party endoscopes and display the data analysis to the user. - A smart device such as tablet or laptop which runs on Windows 10 or a later operating system with the VISIONAIR™ application installed. - A cloud service that runs in the background and can be activated by the user when a particular dataset for a case is desired to securely and anonymously be stored to the Cloud Server (REAI). - USB memory used to encrypt and anonymize the patient information, whether the data is stored locally or to the cloud, and stores the credits needed to activate the VISIONAIR™ software for each case. The VISIONAIR™ application interfaces with third-party endoscopic systems via the ports located on the smart device. The smart device ports enable the third-party systems endoscopic video display to be streamed on the VISIONAIR™ application endoscopic video display. In this 510(k) submission, a FDAcleared endoscope (K970247) was selected as the reference device to support the scientific methodology. The VISIONAIR™ application automatically analyzes the endoscopic images using its trained AI algorithm to measure the nasal valve and nasal cavum surface areas. The VISIONAIR™ application also provides a database file system to manage the data and interface securely and anonymously with the cloud server via the REAl module.

The provided FDA 510(k) summary for the VISIONAIR™ system offers details on its intended use and comparison to a predicate device, as well as a list of non-clinical tests performed. However, it does not explicitly state specific acceptance criteria (e.g., minimum accuracy thresholds) or present the detailed results of a study designed to prove the device meets those criteria with statistical significance.

Instead, it lists tests performed, implying that these tests confirmed design specifications and functionality. The "Substantial Equivalence Table" focuses on comparing attributes to a predicate device and concluding that differences do not raise new safety or effectiveness concerns.

Therefore, many of the requested details about acceptance criteria, specific study results, sample sizes, ground truth establishment, expert qualifications, and MRMC studies are not present in the provided text.

Based on the available information, here's what can be extracted and what is missing:

Acceptance Criteria and Reported Device Performance

The document does not explicitly state numerical acceptance criteria (e.g., "accuracy > 90%"). Instead, the "Non-clinical Performance Data" section lists various tests performed to ensure the device functions according to design specifications and for substantial equivalence in terms of safety and effectiveness. The "reported device performance" is largely implied by the statement that these tests were "performed" and that the device is deemed "substantially equivalent."

Detailed Study Information (Based on available text):

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

   • Test Set Sample Size: Not specified for any of the listed tests.
   • Data Provenance: Not specified (e.g., country of origin). The document mentions "endoscopic images" and "CT scans" were used, but no details on their origin or whether they were retrospective/prospective.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience):

   • Number of Experts: Not specified.
   • Qualifications of Experts: The "VISIONAIR™ AI Segmentation Accuracy Test" mentions "experienced clinicians" were used for comparison, but their specific qualifications (e.g., specialty, years of experience) are not provided.

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

   • Not specified. The document only mentions "comparison" in the segmentation accuracy tests.

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 explicitly described as an MRMC comparative effectiveness study where human readers' performance with and without AI assistance is measured.
   • Effect Size: Not provided. The document mentions "User Validation Test" by clinicians and "comparison of segmented endoscopic images by VISIONAIR™ application vs. segmented endoscopic images by experienced clinicians," but not an assessment of human reader improvement.

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

   • The "VISIONAIR™ AI application confirmation of successful segmentation" in the Nasal Respiratory Airway Analysis Test, and the "CT vs Segmentation Accuracy Test" and "VISIONAIR™ AI Segmentation Accuracy Test" imply a standalone evaluation of the algorithm's performance in segmentation against various ground truths (CT scans, experienced clinicians' segmentations). However, exact methodology and metrics are not detailed.

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

   • CT Scans: Used as a ground truth for cross-sectional areas in the "CT vs Segmentation Accuracy Test." This implies measurements from CT scans were considered the reference.
   • Experienced Clinician Segmentations: Used as a ground truth for segmented endoscopic images in the "VISIONAIR™ AI Segmentation Accuracy Test." This suggests individual or consensus segmentations by clinicians served as the reference.
   • Implicitly, other tests depend on functional specifications and user observation.

7. The sample size for the training set:

   • Not specified in the document. The document refers to the "trained AI algorithm" but does not give details about its training data.

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

   • Not specified in the document.

Ask a specific question about this device

The SoftSmile Vision is intended for use as a medical front-end device providing tools for management of orthodontic models, systematic inspection, detailed analysis, treatment simulation and virtual design of a series of dental casts, which may be used for sequential aligner trays or retainers, based on 3D models of the patient's dentition before the start of an orthodontic treatment. It can also be applied during the treatment to inspect and analyze the progress of the treatment. It can be used at the end of the treatment to evaluate if the outcome is consistent with the planned/desired treatment objectives. The use of SoftSmile Vision requires the user to have the necessary training and domain knowledge in the practice of orthodontics, as well to have received a dedicated training in the use of the software.

SoftSmile Vision is orthodontic planning and treatment simulation software for use by dental professionals. SoftSmile Vision imports patient 3-D digital scans and allows the user to plan the orthodontic treatment needs of the patient and develop a treatment plan. The output of the treatment plan may be downloaded as files in standard stereolithographic (STL) format for fabrication of dental casts, which may be used to fabricate by a manufacturer sequential aligner trays or retainers.

Here's an analysis of the provided text, focusing on acceptance criteria and the study proving device performance:

1. Table of Acceptance Criteria and Reported Device Performance

The provided FDA 510(k) summary does not explicitly state specific, quantifiable acceptance criteria or a direct table comparing them to reported device performance. Instead, it relies on a statement of meeting acceptance criteria established during software verification and validation. The primary form of "performance" discussed is the software functioning as intended and being substantially equivalent to the predicate device.

Therefore, a table with specific performance metrics cannot be generated from the given text.

The document states:

• "All test results met acceptance criteria, demonstrating the Vision software performs as intended, raises no new or different questions of safety or effectiveness and is substantially equivalent to the predicate device."

This is a general statement of compliance rather than a detailed report of performance against predefined thresholds.

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

The document does not specify the sample size used for the test set. It also does not mention the country of origin of the data or whether the data was retrospective or prospective.

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

The document does not specify the number of experts used to establish ground truth or their qualifications. The study described is primarily focused on software verification and validation, not clinical performance reviewed against expert-derived ground truth.

4. Adjudication Method for the Test Set

The document does not mention any adjudication method (e.g., 2+1, 3+1, none) for a test set. This type of method is typically used when human readers or experts are involved in establishing ground truth for evaluating diagnostic or predictive devices, which is not the focus of the described "study."

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

No. The document does not mention a Multi-Reader Multi-Case (MRMC) comparative effectiveness study. The focus is on software validation relative to a predicate device, not on comparing human performance with and without AI assistance. Therefore, there is no effect size reported for human readers improving with AI.

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

Yes, inferentially. The "study" described is a "Software and integration verification and validation testing." This type of testing assesses the algorithm's performance and functionality in a standalone manner, ensuring it operates as designed, without human intervention during the core processing. The statement "demonstrating the Vision software performs as intended" implies standalone evaluation of the software's functions.

7. The Type of Ground Truth Used

The document does not explicitly state the type of ground truth used in the context of clinical outcomes or expert consensus. Given the nature of a software verification and validation study, the "ground truth" would likely be defined by:

• Software requirements specifications: The expected behavior and output of the software.
• Predicate device behavior: The established functionality and output of the legally marketed predicate device (ULab Systems UDesign (K171295)).
• Engineering specifications: Correctness of calculations, data handling, and file exports according to predefined digital standards.

8. The Sample Size for the Training Set

The document does not mention a training set or its sample size. This is consistent with the device being a "front-end" software for treatment planning and simulation, rather than a machine learning model that requires a large training dataset for inference.

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

Since no training set is mentioned, there is no information on how its ground truth might have been established.

Ask a specific question about this device

The software is intended for the viewing and diagnosis of image data in relation to dental issues. Its proper use is documented in the operating instructions of the corresponding image-generating systems. Image-generating systems that can be used with the software include optical video cameras, image plate scamers, extraoral X-ray devices, intraoral scanners and TWAIN compatible image sources.

The software must only be used by authorized healthcare professionals in dental areas for the following tasks:

• Filter optimisation of the display of 2D and 3D images for improved diagnosis
• Acquisition, storage, management, display, analysis, editing and supporting diagnosis of digital/digitised 2D and 3D images and videos
• Forwarding of images and additional data to external software (third-party software)

The software is not intended for mammography use.

VisionX 3.0 imaging software is an image management system that allows dentists to acquire, display, edit, view, store, print, and distribute medical images. VisionX 3.0 software runs on user provided PCcompatible computers and utilize previously cleared digital image capture devices for image acquisition.

The VisionX 3.0 device includes new AI-powered functions such as automatic nerve canal tracing, automatic image rotation, and improved panoramic curve detection. The 510(k) summary provided does not contain a specific study demonstrating the device meets acceptance criteria for these AI functions. Instead, it states that "Full functional software cross check testing was performed." and that "The verification testing demonstrates that the device continues to meet its performance specifications and the results of the testing did not raise new issues of safety or effectiveness." This implies that the internal performance specifications were met, but details on these specifications and the testing methodology are not provided in the summary.

Here's the information that can be extracted from the provided text, along with details that are explicitly stated as not available or not applicable based on the given document:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size for Test Set: Not specified in the provided document.
• Data Provenance: Not specified in the provided document.

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

• Number of Experts: Not specified or implied in the provided document.
• Qualifications of Experts: Not specified or implied in the provided document.

4. Adjudication method for the test set

• Adjudication Method: Not specified or implied in the provided document.

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

• MRMC Study: No, an MRMC comparative effectiveness study is not mentioned in the provided document.
• Effect Size: Not applicable, as no MRMC study was mentioned.

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

• The document implies that the AI features (e.g., automatic nerve canal tracing) operate in a standalone capacity within the software, as they are listed as "new functions." However, no specific standalone performance metrics (e.g., accuracy, sensitivity, specificity of the algorithm alone) are provided in the summary. The "full functional software cross check testing" suggests validation of the software's operation, but without specific performance data for the AI components in isolation.

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

• Type of Ground Truth: Not specified in the provided document.

8. The sample size for the training set

• Sample Size for Training Set: Not specified in the provided document.

9. How the ground truth for the training set was established

• Ground Truth Establishment for Training Set: Not specified in the provided document.

Ask a specific question about this device