Search Results

Chemfort® is a single use, sterile Closed System Transfer Device (CSTD) that mechanically prohibits the release of drugs, including antineoplastic and hazardous drugs, in vapor, aerosol or liquid form during administration and preparation, thus minimizing exposure of individuals, healthcare personnel, and the environment to hazardous drugs. Chemfort® prevents the introduction of microbial and airborne contaminants into the drug or fluid path for up to 7 days.

The Chemfort® Closed System Transfer Device (CSTD) is developed by Simplivia Healthcare Ltd. The system is used by pharmacists, nurses or other healthcare professionals to prepare drugs, including cytotoxic drugs, and allow the safe reconstitution of powder and liquid drugs transfer for infusion containers (infusion bags, semi-rigid bottles, and collapsible plastic containers), injection, or administration. It is supplied sterile with a sterility assurance level (SAL) of 10-6.

The Chemfort® Female Luer Lock Adaptor is part of the Chemfort® system of devices. The Chemfort® Female Luer Lock Adaptor is intended for the safe drug transfer from one syringe to another and allows closed access via Chemfort® devices to any standard male Luer connection (see below in more details).

1. Syringe to Syringe connection:
   The Chemfort® Female Luer Lock Adaptor is connected to the Chemfort® Luer Lock Adaptor. The Chemfort® Luer Lock Adaptor port is connected to an empty / saline containing syringe (syringe "A"), equipped with a Chemfort® Syringe Adaptor or Chemfort® Syringe Adaptor Lock. A drug containing syringe (syringe "B"), equipped with a Chemfort® Syringe Adaptor or Chemfort® Syringe Adaptor Lock is connected to the Chemfort® Female Luer Lock Adaptor. This assembly of devices allows drug transfer from one syringe "A" to the other, syringe "B", for drug dilution (if syringe "A" contains saline) or drug dosage (if syringe "A" is empty). This procedure allows safe drug transfer from one syringe to another. The drug in Syringe "A" can then be injected to an intravenous (IV) bag through the Chemfort® spike or in a bolus through another Chemfort® Luer Lock Adaptor connected to a Y-site on an IV set.

Note that this procedure also involves the Chemfort® Vial Adaptor to allow to withdraw the drug from the drug vial to syringe "B".

2. Connection to IV sets:
   The Chemfort® Female Luer Lock Adaptor is connected to an IV set through the luer lock connection (proximal end or infusion line). The Chemfort® port can then connect to one of the Chemfort® Closed Administration (CADM) IV sets. This setup transfers an open IV set connection to a closed connection.

The Chemfort® Female Luer Lock Adaptor can be in contact with concentrated or diluted drugs.

The Chemfort® Female Luer Lock Adaptor is a single-use device intended for use on adults, children and infants.

The provided FDA 510(k) clearance letter and supporting documentation (Chemfort® Female Luer Lock Adaptor 510(k) Summary) describe the performance testing and acceptance criteria for a physical medical device, not a software or AI-driven diagnostic device.

Therefore, many of the requested categories in your prompt (e.g., number of experts for ground truth, adjudication method, MRMC study, sample size for training set, how ground truth for training set was established, standalone performance) are not applicable to this type of device submission. These categories are typically relevant for AI/ML-based diagnostic devices where performance data relies heavily on expert annotations, comparative effectiveness studies involving human readers, and distinct training/test datasets.

However, I can extract the relevant acceptance criteria and performance data for the Chemfort® Female Luer Lock Adaptor based on the provided document.

Acceptance Criteria and Device Performance for Chemfort® Female Luer Lock Adaptor

This document outlines the performance data and acceptance criteria for the Chemfort® Female Luer Lock Adaptor, a physical medical device. The study performed demonstrates the device's adherence to established safety and performance standards for intravascular administration sets.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for this device are primarily based on established international standards and internal validation procedures for medical devices of this type. The "Results" column from the provided Table 2 in the 510(k) summary indicates that all tests met their acceptance criteria, demonstrating the device's compliance.

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

• Sample Size: The document does not explicitly state the numerical sample sizes for each performance test (e.g., number of units tested for particulate analysis, bidirectional flow, etc.). However, it indicates that "Simplivia conducted several performance tests to demonstrate that the Chemfort® Female Luer Lock Adaptor is safe and effective..." implying a sufficient number of samples were tested to meet the requirements of the listed standards and internal procedures.
• Data Provenance: The tests were conducted by Simplivia Healthcare LTD. (an Israeli company) for regulatory submission to the FDA. The data provenance is laboratory testing performed by the manufacturer, rather than clinical data from human subjects. The tests are prospective in nature, as they involve testing newly manufactured devices against predetermined specifications.

3. Number of Experts Used to Establish Ground Truth and Their Qualifications

This question is not applicable to the type of device being cleared. The "ground truth" for the performance of a physical device like the Chemfort® Female Luer Lock Adaptor is established by adherence to validated engineering specifications, material properties, and functionality defined by international standards (e.g., ISO, USP) and internal quality control procedures. It does not involve expert interpretations of images or signals for diagnostic purposes.

4. Adjudication Method for the Test Set

This question is not applicable. Adjudication methods (like 2+1, 3+1) are used to resolve discrepancies in expert annotations or interpretations, typically in studies involving human readers or AI outputs for diagnostic tasks. For a physical device, performance is evaluated against objective, measurable criteria with pass/fail outcomes, not subjective interpretations requiring adjudication.

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

No, an MRMC comparative effectiveness study was not done. MRMC studies are specific to evaluating the diagnostic performance of medical imaging devices or AI algorithms, often comparing human reader performance with and without AI assistance across multiple cases. This device is an intravascular administration set, not an imaging or diagnostic AI device.

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

This question is not applicable. There is no "algorithm" to be evaluated in a standalone manner for this physical device. Its function is mechanical and fluidic.

7. The Type of Ground Truth Used

The "ground truth" for this device is based on engineering specifications, material science, and compliance with recognized international standards (e.g., ISO 80369-7, ISO 10993 series, USP monographs). These standards define the acceptable performance characteristics, physical properties, and safety profiles for devices of this type. For example, for "Luer Test," the ground truth is defined by the dimensional and functional requirements of ISO 80369-7:2021. For "Biocompatibility," the ground truth is defined by the specific tests and acceptance criteria within the ISO 10993 series.

8. The Sample Size for the Training Set

This question is not applicable. This device is a physical product, not an AI/ML model that requires a training set.

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

This question is not applicable for the same reason as #8.

Ask a specific question about this device

TumorSight Viz is intended to be used in the visualization and analysis of breast magnetic resonance imaging (MRI) studies for patients with biopsy proven early-stage or locally advanced breast cancer. TumorSight Viz supports evaluation of dynamic MR data acquired from breast studies during contrast administration. TumorSight Viz performs processing functions (such as image registration, subtractions, measurements, 3D renderings, and reformats).

TumorSight Viz also includes user-configurable features for visualizing and analyzing findings in breast MRI studies. Patient management decisions should not be made based solely on the results of TumorSight Viz.

TumorSight Viz is an image processing system designed to assist in the visualization and analysis of breast DCE-MRI studies.

TumorSight reads DICOM magnetic resonance images. TumorSight processes and displays the results on the TumorSight web application.

Available features support:

• Visualization (standard image viewing tools, MIPs, and reformats)
• Analysis (registration, subtractions, kinetic curves, parametric image maps, segmentation and 3D volume rendering)

The TumorSight system consists of proprietary software developed by SimBioSys, Inc. hosted on a cloud-based platform and accessed on an off-the-shelf computer.

Here's a breakdown of the acceptance criteria and the study details for the TumorSight Viz device, based on the provided FDA 510(k) clearance letter:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by the reported performance metrics, where the device's performance is deemed "adequate" and "clinically acceptable" if the variability is similar to inter-radiologist variability or differences in error are clinically insignificant.

The document states: "We found that all tests met the acceptance criteria, demonstrating adequate performance for our intended use." This indicates that the reported performance metrics were considered acceptable by the regulatory body. For measurements where inter-radiologist variability is provided (e.g., longest dimension, tumor-to-skin), the device's error is compared to this variability. For other metrics, the acceptance is based on demonstrating "adequate performance," implying that the reported values themselves were within a predefined acceptable range.

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

• Sample Size for Test Set: 266 patients (corresponding to 267 samples, accounting for bilateral disease).
• Data Provenance:
  • Country of Origin: U.S.
  • Retrospective/Prospective: The document does not explicitly state "retrospective" or "prospective." However, the description of "DCE-MRI were obtained from... patients" and establishment of ground truth by reviewing images suggests a retrospective acquisition of data for validation. The mention of "All patients had pathologically confirmed invasive, early stage or locally advanced breast cancer" further supports a retrospective gathering of existing patient data.
  • Clinical Sites: More than eight (8) clinical sites in the U.S.

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

• Number of Experts: Three (3) U.S. Board Certified radiologists.
• Qualifications: U.S. Board Certified radiologists. (No specific experience in years is mentioned, but Board Certification implies a high level of expertise.)

4. Adjudication Method for the Test Set

• Adjudication Method: 2+1 (as described in the document).
  • For each case, two radiologists independently measured various characteristics and determined if the candidate segmentation was appropriate.
  • In cases of disagreement between the first two radiologists ("did not agree on whether the segmentation was appropriate"), a third radiologist provided an additional opinion, and the ground truth was established by majority consensus.

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

The document does not describe an MRMC comparative effectiveness study where human readers' performance with and without AI assistance is directly measured and compared.

Instead, it compares the device's performance to:

1. Ground Truth: Radiologist consensus measurements.
2. Predicate Device: Its own previous version.
3. Inter-radiologist Variability: The inherent variability between human expert readers.

Therefore, no effect size of how much human readers improve with AI vs. without AI assistance is provided, as this type of MRMC study was not detailed.

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

Yes, a standalone performance study was done. The sections titled "Performance Tests" and the tables detailing "Validation Testing (Mean Abs. Error ± Std. Dev.)" describe the algorithm's performance in comparison to the established ground truth. This is a standalone evaluation, as it assesses the device's output intrinsically against expert-derived truth without measuring human interaction or improvement. The statement "The measurements generated from the device result directly from the segmentation methodology and are an inferred reflection of the performance of the deep learning algorithm" supports this.

7. The Type of Ground Truth Used

• Type of Ground Truth: Expert Consensus (specifically, pathologist-confirmed lesions measured and evaluated by a consensus of U.S. Board Certified radiologists). The initial diagnosis of early-stage or locally advanced breast cancer for patient selection was based on pathology ("biopsy proven"). However, the ground truth for measurements and segmentation appropriateness for the study was established by radiologists.

8. The Sample Size for the Training Set

• Sample Size for Training Set: One thousand one hundred fifty-six (1156) patients/samples.

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

The document states: "DCE-MRI were obtained from one thousand one hundred fifty-six (1156) patients from more than fifteen (15) clinical sites in the U.S. for use in training and tuning the device."

However, the document does not explicitly detail how the ground truth for this training set was established. It describes the ground truth establishment method only for the validation dataset (by three U.S. Board Certified radiologists with 2+1 adjudication). For training data, it is common practice to use similar rigorous methods for labeling, but the specifics are not provided in this excerpt.

Ask a specific question about this device

The Patriot SI Implant System is intended for sacroiliac joint fusion for conditions including sacroiliac joint disruptions and degenerative sacroiliitis.

The Patriot SI Implant System is a minimally invasive sacroiliac joint fusion implant that pierces the cortical bone of the ilium and sacrum and is intended for the purpose of stabilizing and fusing the sacroiliac joint with intrinsic fixation features. It is available in one size and may be implanted using the designated surgical instruments into the SI joint space. Bone graft materials may be used with the Patriot SI Implant System. The Patriot SI Implant System device is made from additively manufactured titanium alloy, Ti-6Al-4V-ELI per ASTM F3001 and is offered with or without a hydroxyapatite (HA) coating per ASTM F1185. The Patriot SI Implant System device is provided sterile and individually packed.

The provided FDA 510(k) clearance letter for the Patriot SI Implant System does not contain any information regarding acceptance criteria or the study that proves the device meets those criteria for the purposes of an AI/software device.

The document is for a physical medical implant device (sacroiliac joint fusion implant). The information it provides is:

• Device Type: Patriot SI Implant System (a physical implantable device)
• Intended Use: Sacroiliac joint fusion for conditions including sacroiliac joint disruptions and degenerative sacroiliitis.
• Materials: Additively manufactured titanium alloy, Ti-6Al-4V-ELI, with or without hydroxyapatite (HA) coating.
• Testing Information: "Non-clinical cadaveric biomechanical testing was performed to support substantial equivalence of the Patriot SI Implant system." This type of testing is relevant for mechanical implants, not AI/software.
• Predicate Device: Patriot-SI Posterior Implant System (K232259).

Therefore, I cannot provide details on acceptance criteria and study design for an AI/software device based on this document. The questions posed in your request (sample size, expert qualifications, MRMC studies, standalone performance, ground truth types) are universally applicable to AI/software performance studies, but the source document is entirely about a physical hardware device.

If you have a document describing an AI/software medical device, I would be happy to analyze it according to your criteria.

Ask a specific question about this device

The Shadow Catheter™ is intended to be used in conjunction with steerable guidewires in order to access discrete regions of the coronary and peripheral arterial vasculature, to facilitate placement and exchange of guidewires and other interventional devices, for use during two guidewire procedures and to subselectively infuse/deliver diagnostic or therapeutic agents.

The Shadow Guidewire Positioning Catheter is a dual lumen over-the-wire catheter, compatible with a 6F or larger guiding catheter and 0.014" guidewires. The Catheter is designed to support and aim steerable guidewires. The Catheter consists of a distal tip with markers, torque shaft and guidewire introducer. The distal end of the Catheter (the nosecone) has two ports, one to load a tracking guidewire axially (via distal port) and the other for the positioning guidewire to exit radially (via side port). The distal nosecone is coated with a hydrophilic coating.

The Shadow Catheter™ has three markers in the nosecone. The guidewire introducer accommodates an on-axis tracking guidewire, a tracking guidewire flush port, as well as a positioning guidewire introducer port that doubles as a flush port. The handle may be rotated or orientated to adjust or aim the direction of the positioning guidewire exiting the side port at the distal end.

The Catheter is placed in a packaging hoop, sealed in a Tyvek® pouch, and packaged in a shelf carton. There are no diagnostic or therapeutic agents known to be incompatible with the Shadow Catheter™. The Shadow Catheter™ is sterilized with ethylene oxide.

The provided text is a 510(k) Premarket Notification from the FDA for a medical device called the "Shadow Catheter™." It details the device's description, intended use, technological characteristics, and non-clinical tests performed to demonstrate substantial equivalence to a predicate device.

However, the text does not contain any information about acceptance criteria or a study that proves the device meets those criteria related to an AI/ML-based medical device. The product is a physical catheter, and the testing described focuses on physical properties and biocompatibility. There is no mention of a test set, data provenance, expert ground truth, MRMC studies, or standalone algorithm performance.

Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and reported device performance related to AI/ML: The document discusses physical device performance (e.g., bond strength, kink test, flow rate), but not AI/ML performance metrics.
2. Sample size used for the test set and data provenance: No test set is described for AI/ML evaluation.
3. Number of experts used to establish ground truth and qualifications: Not applicable, as there's no AI/ML component.
4. Adjudication method for the test set: Not applicable.
5. MRMC comparative effectiveness study: Not mentioned, as it's not an AI-assisted device.
6. Standalone (algorithm only) performance: Not applicable.
7. Type of ground truth used: Not applicable for AI/ML.
8. Sample size for the training set: No training set is mentioned.
9. How the ground truth for the training set was established: Not applicable.

The document explicitly states: "Clinical Study: Not Applicable. The Shadow Catheter™ was not evaluated in a clinical study." and "The results of the testing met the specified acceptance criteria and did not raise new questions of safety or effectiveness; therefore, the subject device is substantially equivalent to the predicate device." This refers to non-clinical, bench testing of the physical catheter.

In summary, the provided FDA 510(k) document is for a physical medical catheter, not an AI/ML device, and thus does not contain the information required to answer your specific questions regarding AI/ML acceptance criteria and study details.

Ask a specific question about this device

Sim&Size enables visualization of cerebral blood vessels for preoperational planning and sizing for neurovascular interventions and surgery. Sim&Size also allows for the ability to computationally model the placement of neurointerventional devices.

General functionalities are provided such as:

• Segmentation of neurovascular structures
• Automatic centerline detection
• Visualization of X-ray based images for 2D review and 3D reconstruction
• Placing and sizing tools
• Reporting tools

Information provided by the software is not intended in any way to eliminate, replace or substitute for, in whole or in part, the healthcare provider's judgment and analysis of the patient's condition.

Sim&Size is a Software as a Medical Device (SaMD) for simulating neurovascular implantable medical devices. The product enables visualization of cerebral blood vessels for preoperational planning for neurovascular interventions and surgery. It uses an image of the patient produced by 3D rotational angiography. It offers clinicians the possibility of simulating neurovascular implantable medical devices in the artery or in the aneurysm to be treated through endovascular surgery and provides support in the treatment for the sizing and positioning of implantable medical devices.

Each type of implant device is simulated in a simulation module of Sim&Size:

• FDsize, a module that allows pre-operationally planning Flow-Diverter (FD) devices.
• IDsize, a module that allows pre-operationally planning Intrasaccular (ID) devices.
• STsize, a module that allows pre-operationally planning Stent (ST) devices.
• FCsize, a module that allows pre-operationally planning First and filling coils (FC) devices.

Associated with these four modules, a common module is intended to import DICOM and to provide a 3D reconstruction of the vascular tree in the surgical area.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary for Sim&Size:

Acceptance Criteria and Device Performance

The provided document highlights performance testing without explicitly stating quantitative acceptance criteria. However, the nature of the tests implies the device must accurately "predictive behavior of the implantable medical device with its theoretical behavior," accurately "compare the device placement in a silicone phantom model with the device simulation," and accurately "compare the in vitro retrospective cases with the device simulation."

Given the context of a 510(k) submission, the implicit acceptance criterion is that the device's performance is substantially equivalent to the predicate device and that the new features do not raise new questions of safety and effectiveness.

Here's a table based on the types of performance tests conducted:

Study Details:

Based on the provided document, here's what can be inferred about the studies conducted:

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

   • Test Set Sample Size: Not explicitly stated in the document.
   • Data Provenance:
     • "Retrospective in vivo testing" suggests real-world patient data, but the phrase "in vitro retrospective cases" implies these were lab-based re-creations or analyses of that data. The specific country of origin is not mentioned, but given the company's address (Montpellier, France), it's plausible the data could originate from Europe, although this is not confirmed.
     • "Bench testing" uses a "silicone phantom model," which is an experimental setup, not clinical data provenance.
     • "Verification testing" involves comparing theoretical behavior, which doesn't involve a dataset in the same way clinical or phantom models do.

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

   • This information is not provided in the document. The document refers to "theoretical behavior," "silicone phantom model," and "in vitro retrospective cases" as benchmarks, but it doesn't detail how the ground truth for "in vitro retrospective cases" was established or if experts were involved in defining the "theoretical behavior" or validating the phantom results.

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

   • This information is not provided in the document.

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 MRMC study is explicitly mentioned. The device "enables visualization of cerebral blood vessels" and "allows for the ability to computationally model the placement of neurointerventional devices," but it's stated that "Information provided by the software is not intended in any way to eliminate, replace or substitute for, in whole or in part, the healthcare provider's judgment and analysis of the patient's condition." This indicates it's a tool for assistance, but the document does not detail studies on human reader performance improvement with this AI.

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

   • The "Verification testing," "Bench testing," and "Retrospective in vivo testing" (comparing simulations to "in vitro retrospective cases") all describe methods that would assess the algorithm's standalone performance without a human in the loop for the actual comparison/measurement, although human input (e.g., in segmentation, placing/sizing tools) is part of the device's intended use. The wording "compares the predictive behavior... with its theoretical behavior" and "compares the device placement... with the device simulation" explicitly refers to the device's performance, implying a standalone assessment of the algorithmic component.

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

   • Theoretical Behavior: Used for "Verification testing" (e.g., physical laws, engineering models of device deployment).
   • Physical Phantom Model: Used for "Bench testing" (measurements from a physical silicone model).
   • "In vitro retrospective cases": Used for "Retrospective in vivo testing." This implies a ground truth derived from actual patient data, analyzed or re-created in a laboratory (in vitro). It's not explicitly stated if this ground truth was pathology or outcomes data, but rather a representation of the in vivo reality.

7. The sample size for the training set:

   • This information is not provided in the document. This section focuses on validation testing, not the training of any underlying models.

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

   • This information is not provided as the document does not detail the training process.

Ask a specific question about this device

TumorSight Viz is intended to be used in the visualization and analysis of breast magnetic resonance imaging (MRI) studies for patients with biopsy proven early-stage or locally advanced breast cancer. TumorSight Viz supports evaluation of dynamic MR data acquired from breast studies during contrast administration. TumorSight Viz performs processing functions (such as image registration, subtractions, measurements, 3D renderings, and reformats).

TumorSight Viz also includes user-configurable features for visualizing findings in breast MRI studies. Patient management decisions should not be made based solely on the results of TumorSight Viz.

TumorSight Viz is an image processing system designed to assist in the visualization and analysis of breast DCE-MRI studies.

TumorSight reads DICOM magnetic resonance images. TumorSight processes and displays the results on the TumorSight web application.

Available features support:

• . Visualization (standard image viewing tools, MIPs, and reformats)
• . Analysis (registration, subtractions, kinetic curves, parametric image maps, segmentation and 3D volume rendering)
• . Communication and storage (DICOM import, retrieval, and study storage)

The TumorSight system consists of proprietary software developed by SimBioSys, Inc. hosted on a cloud-based platform and accessed on an off-the-shelf computer.

Here's a breakdown of the acceptance criteria and study details for the TumorSight Viz device, based on the provided document:

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria implicitly relate to the device's performance in comparison to expert variability and the predicate device. The study aims to demonstrate that the error in measurements produced by TumorSight Viz is consistent with the variability observed among expert radiologists.

The table below summarizes the performance metrics from the validation testing, which serves as the reported device performance against the implicit acceptance criterion of being comparable to inter-radiologist variability.

Segmentation Accuracy:

Comparison to Predicate Device and Inter-Radiologist Variability:

The study concludes that "all tests met the acceptance criteria, demonstrating adequate performance for our intended use," and that the "differences in error between the mean absolute errors (MAE) for the predicate and subject device are clinically acceptable because they are on the order of one to two voxels for the mean voxel size in the dataset. These differences are clinically insignificant."

2. Sample Size and Data Provenance

• Test Set (Validation Dataset) Sample Size: 216 patients, corresponding to 217 samples (when accounting for bilateral disease).
• Data Provenance:
  • Country of Origin: U.S. (from more than 7 clinical sites).
  • Retrospective/Prospective: Not explicitly stated, but the description of data collection and review for ground truth suggests it was retrospective. The data was "obtained" and "collected," implying pre-existing data.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Three (3)
• Qualifications: U.S. Board Certified radiologists. No specific years of experience are mentioned.

4. Adjudication Method for the Test Set

• Method: Majority Consensus (2+1). For each case, two radiologists independently reviewed measurements and segmentation appropriateness. "In cases where the two radiologists did not agree on whether the segmentation was appropriate, a third radiologist provided an additional opinion and established a ground truth by majority consensus."

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

• Was it done? No, an MRMC study comparing human readers with and without AI assistance was not performed as described in the document. The study primarily focused on the standalone performance of the AI algorithm (TumorSight Viz) and its comparison to the predicate device, with ground truth established by expert radiologists. It did compare the device's measurements to inter-radiologist variability, but not in a human-in-the-loop setup.
• Effect Size: Not applicable, as an MRMC comparative effectiveness study was not performed.

6. Standalone (Algorithm Only) Performance

• Was it done? Yes. The performance metrics listed in the tables (Mean Absolute Error, Volumetric Dice, Surface Dice) are indicators of the standalone performance of the TumorSight Viz algorithm against the established ground truth.

7. Type of Ground Truth Used

• Type: Expert Consensus. The ground truth was established by three (3) U.S. Board Certified radiologists through a defined review and adjudication process (majority consensus).
• For measurements: Radiologists measured various characteristics including longest dimensions and tumor to landmark distances.
• For segmentation: Radiologists reviewed and deemed the candidate segmentation "appropriate."

8. Sample Size for the Training Set

• Training Dataset: 676 samples.
• Tuning Dataset: 240 samples.
• Total Patients for Training and Tuning: 833 patients (corresponding to 916 samples total for training and tuning).

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

The document states that the training and tuning data were used to "train and tune the device," but it does not explicitly describe how the ground truth for this training data was established. It only details the ground truth establishment for the validation dataset. It is common for deep learning models to require labeled data for training, but the process for obtaining these labels for the training set is not provided here.

Ask a specific question about this device

The Wolff's Law Anterior Cervical Plate System is indicated for use in the temporary stabilization of the cervical spine (C2-C7) during the development of solid spinal fusion in patients with instability caused by the following:

• Degenerative Disc Disease (DDD) – as defined by neck pain of discogenic origin with degeneration of the disc confirmed by patient history and radiographic studies;

• · Spondylolisthesis;
• Spinal Stenosis:
• · Trauma (including fractures);
• · Tumor;
• · Deformity (i.e., scoliosis, kyphosis, and/or lordosis);
• · Pseudoarthrosis; and
• · Failed previous fusions

The Spinal Simplicity Wolff's Law Anterior Cervical Plate System is a dynamic cervical plate designed for the anterior cervical spine (C2-C7). The Wolff's Law Plate System consists of one-level plates in multiple lengths with both fixed- and variable-angle screws. The plates are translatable and use a nitinol Compression Element to provide continuous compression at each level. The Wolff's Law Cervical Plate consists of components made from titanium alloy Ti6Al4V ELI per ASTM F136 and superelastic nitinol per ASTM F2063. The fixed and variable screws are made from Titanium alloy Ti6Al4V ELI per ASTM F136. The Anterior Cervical Plate System is provided to the end-user sterile and is single use.

The FDA 510(k) summary for the "Wolff's Law Anterior Cervical Plate System" describes non-clinical performance testing rather than a study involving an AI/CAD software device with specific acceptance criteria and human readers.

Therefore, I cannot provide information on the following as it is not present in the provided document:

• A table of acceptance criteria and the reported device performance for an AI/CAD device.
• Sample size used for the test set and data provenance.
• Number of experts used to establish the ground truth and their qualifications.
• Adjudication method for the test set.
• Multi-reader multi-case (MRMC) comparative effectiveness study, including effect size.
• Standalone performance (algorithm only) of an AI/CAD device.
• Type of ground truth used for an AI/CAD device.
• Sample size for the training set.
• How the ground truth for the training set was established.

However, based on the provided document, I can extract information related to the performance study of the Wolff's Law Anterior Cervical Plate System (a medical device, not an AI/CAD software):

1. Type of Study:
Non-clinical mechanical tests were performed to establish substantial equivalence for the Wolff's Law Anterior Cervical Plate System. Clinical performance testing was explicitly not performed for this submission.

2. Tests Performed and Guidance:
The study utilized FDA Guidance Document "Spinal Plating Systems - Performance Criteria for Safety and Performance Based Pathway: Guidance for Industry and Food and Drug Administration Staff" and the following ASTM tests:

• ASTM F1717 Static Compression Bending
• ASTM F1717 Static Torsion
• ASTM F1717 Static Tension Bending
• ASTM F1717 Dynamic Compression Bending
• ASTM F543 Axial Screw Pullout/Pushout
• ASTM F2129 & ASTM F3044 Corrosion Testing
• ASTM F1877 Particulate Analysis
• ASTM F2004 Transformational Temperature

3. Purpose of the Study:
The purpose of these non-clinical tests was to demonstrate that the Wolff's Law Anterior Cervical Plate System is capable of performing as intended and is substantially equivalent to the legally marketed predicate device. The document explicitly states: "Performance testing device has mechanical performance substantially equivalent to that of the predicate."

4. Acceptance Criteria (Implied):
While not explicitly presented in a table in the provided text, the acceptance criteria for these mechanical tests are implicitly that the Wolff's Law Anterior Cervical Plate System must have mechanical performance substantially equivalent to the predicate device(s). This substantial equivalence is assessed against the standards outlined in the FDA Guidance Document and the specific ASTM standards listed. The document does not provide specific numerical thresholds or target values that define "substantial equivalence" in this summary.

5. Predicate Devices:
The predicate devices used for comparison are:

• K083020 DynaTran™ Anterior Cervical Plating (ACP) System
• K143626 SC-AcuFix® Ant-Cer Dynamic Cervical Plating System
• K051665 Synthes Vectra-T System

In summary, the provided document details non-clinical mechanical testing for a spinal implant, not an AI/CAD system. Therefore, most of the requested information regarding AI/CAD specific acceptance criteria and study details are not applicable or available in this text.

Ask a specific question about this device

The Patriot-SI Posterior Implant System is intended for sacroiliac joint fusion including sacroiliac joint disruptions and degenerative sacroiliitis. When the Patriot Implant System (i.e., an "in-line" or "in-line" or "intraarticular" device) is implanted, it must be used with a Spinal Simplicity Liberty-SI Lateral System device (i.e., a "transfixing" device) implanted across the same sacroiliac joint to create a hybrid SI joint fusion construct.

The Patriot-Sl Posterior Implant System is a minimally invasive sacrolliac joint fusion implant that is intended for implantation on a trajectory in line with the joint space (i.e., the device is an in-line or intra-articular implant). The Patriot Implant System device is required to be implanted with the Spinal Simplicity Liberty-Sl Lateral System device implanted across the same sacroiliac joint to create a hybrid SI joint fusion construct for the purpose of stabilizing and fusing the sacroiliac joint. It is available in one size and may be implanted using the designated surgical instruments through a posterior approach into the Sl joint space, fixating on both the sacrum and ilium via external threads. Bone graft materials may be used with the Patriot-Sl Posterior Implant System. The Patriot-SI Posterior Implant System device is manufactured titanium alloy, Ti-6AI-4V-ELI per ASTM F3001 and is offered with or without a hydroxyapatite (HA) coating per ASTM F1185. The Patriot-SI Posterior Implant System device is provided sterile and individually packed.

This document describes a spinal implant device, not an AI/ML device. Therefore, the requested information about acceptance criteria, study details, ground truth, and AI-specific metrics (like MRMC studies or standalone AI performance) is not applicable.

The document is a 510(k) premarket notification for the "Patriot-SI Posterior Implant System," which is a physical medical device for sacroiliac joint fusion. The FDA letter confirms that the device is substantially equivalent to a legally marketed predicate device (NADIA® SI Fusion System, K190580) based on non-clinical mechanical tests and cadaver testing.

Here's a breakdown of the provided information, emphasizing why the AI/ML-specific questions are not applicable:

1. Table of Acceptance Criteria and Reported Device Performance:

Since this is a physical implant, "acceptance criteria" and "reported device performance" are based on mechanical properties and safety/effectiveness relative to its predicate, rather than AI model metrics like sensitivity, specificity, or AUC. The document lists the types of non-clinical mechanical tests performed to support substantial equivalence:

The conclusion states that "performance testing provided in this 510(k) application demonstrates that the Patriot SJ Posterior Implant System is capable of performing as intended and is as safe and effective as the legally marketed predicate device." Specific numerical acceptance criteria or performance values are not included in this summary document.

2. Sample Size for Test Set and Data Provenance:

Not applicable, as this is a physical device. Mechanical tests involve test specimens, and cadaver testing involves human cadavers, but these are not "datasets" in the AI/ML sense. Data provenance regarding country of origin or retrospective/prospective is not relevant here.

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

Not applicable. Ground truth for mechanical testing is derived from engineering principles and standards, and for cadaver testing, it pertains to the anatomical and biomechanical performance, typically evaluated by biomechanical engineers and potentially surgeons. There isn't a "ground truth" established by a panel of medical experts in the way it would be for an AI diagnostic algorithm.

4. Adjudication Method:

Not applicable. This concept pertains to resolving discrepancies in expert labeling or diagnoses for AI training/testing, which is not relevant for a physical implant's mechanical and cadaver testing.

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

Not applicable. This type of study assesses the impact of AI on human reader performance for diagnostic tasks. The Patriot-SI system is a surgical implant, not a diagnostic AI.

6. Standalone (i.e., algorithm only without human-in-the-loop performance) Study:

Not applicable. There is no algorithm to evaluate in a standalone manner.

7. Type of Ground Truth Used:

For the mechanical tests, the "ground truth" is defined by the requirements of the ASTM standards (F3574 and F2077) and the performance characteristics of the predicate device. For cadaver testing, it relates to the successful implantation and biomechanical stability observed. This is distinct from pathology, expert consensus, or outcomes data used for AI models.

8. Sample Size for the Training Set:

Not applicable. There is no AI model, and therefore no training set.

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

Not applicable. As there's no training set, there's no ground truth to establish for one.

Ask a specific question about this device

The Minuteman G5 MIS Fusion Plate is a posterior, non-pedicle fusion device, intended for use at a single interspace in the non-cervical spine (T1-S1). It is intended for plate fixation/attachment to spinous processes for the purpose of achieving instrumented posterior arthrodesis (i.e., fusion) in the following conditions:
• Lumbar spinal stenosis;
· degenerative disc disease (DDD) (defined as back pain of discogenic origin with degeneration of the disc confirmed by history and radiographic studies); and/or
• spondylolisthesis.
The Minuteman G5 MIS Fusion Plate is intended for use with bone graft material. The device may be implanted via a lateral transverse approach (L1-S1) or a posterior approach (T1-S1).

The Minuteman G1 (Posterior Fusion Plate /HA Posterior Fusion Plate) is a posterior, non-pedicle fusion device, intended for use at a single interspace in the non-cervical spine (T1-S1). It is intended for plate fixation/attachment to spinous processes for the purpose of achieving instrumented posterior arthrodesis (i.e., fusion) in the following conditions:
· Lumbar spinal stenosis;
· degenerative disc disease (DDD) (defined as back pain of discogenic origin with degeneration of the disc confirmed by history and radiographic studies); and/or
· spondylolisthesis.
The Minuteman G1 (Posterior Fusion Plate /HA Posterior Fusion Plate) is intended for use with bone graft material. The device may be implanted via a lateral transverse approach (L1-S1) or a posterior approach (T1-S1).

The HA Minuteman G3-R MIS Fusion Plate is a posterior, non-pedicle fusion device, intended for use at a single interspace in the non-cervical spine (T1-S1). It is intended for plate fixation/ attachment to spinous processes for the purpose of achieving instrumented posterior arthrodesis (i.e., fusion) in the following conditions:
• Lumbar spinal stenosis;
· degenerative disc disease (DDD) (defined as back pain of discogenic origin with degeneration of the disc confirmed by history and radiographic studies); and/or
• spondylolisthesis.
The HA Minuteman G3-R MIS Fusion Plate is intended for use with bone graft material. The device may be implanted via a lateral transverse approach (L1-S1).

The Minuteman G3/HA Minuteman G3 MIS Fusion Plate is a posterior, non-pedicle fusion device, intended for use at a single interspace in the non-cervical spine (T1-S1). It is intended for plate fixation/attachment to spinous processes for the purpose of achieving instrumented posterior arthrodesis (i.e., fusion) in the following conditions:

• · Lumbar spinal stenosis;
  · degenerative disc disease (DDD) (defined as back pain of discogenic origin with degeneration of the disc confirmed by history and radiographic studies); and/or
• · spondylolisthesis.
  The Minuteman G3/HA Minuteman G3 MIS Fusion Plate is intended for use with bone graft material. The device may be implanted via a lateral transverse approach (L1-S1) or a posterior approach (T1-S1).

The Minuteman MIS Fusion Plate Implants consist of bilateral Plates and a Body/Post that connects the Plate components include several gripping features for attachment of the spinous processes. The Minuteman MIS Fusion Plate Implants are available in multiple sizes to accommodate varying patient anatomy. The Minuteman MIS Fusion Plate Implants are made from Ti6A4V and Ti6A4V ELI. The HA Minuteman MS Fusion Plate have an additional hydroxyapatite coating on the distal regions of the device.

The provided text is a 510(k) Premarket Notification from the FDA for a spinal fusion plate. It describes the device, its intended use, and states that non-clinical evaluations were performed to support substantial equivalence to a predicate device.

However, the document does not contain any information regarding acceptance criteria, study details, sample sizes, expert qualifications, adjudication methods, or specific performance metrics typically associated with studies proving device performance against acceptance criteria for an AI/ML medical device.

The essential conclusion from the document is that:

• The device is a physical medical device (spinal fusion plate), not an AI/ML-based software device.
• Substantial equivalence was established through non-clinical evaluations against a predicate device, not through a study involving acceptance criteria and performance metrics described in the prompt.

Therefore, I cannot provide the requested information from the given text because it is not relevant to the type of device and evaluation described in the document.

To directly answer your prompt, based on the provided text:

1. A table of acceptance criteria and the reported device performance: Not applicable. The document refers to physical device testing for "substantial equivalence" to a predicate, not performance against specific acceptance criteria for an AI/ML output.
2. Sample sized used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective): Not applicable. No test set or data provenance for an AI/ML device is mentioned.
3. 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): Not applicable. No ground truth establishment for an AI/ML device is mentioned.
4. Adjudication method (e.g., 2+1, 3+1, none) 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.
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.
8. The sample size for the training set: Not applicable.
9. How the ground truth for the training set was established: Not applicable.

Ask a specific question about this device

DASI Dimensions is a standalone, non-invasive, clinical decision support software solution that is intended for use by cardiologists and radiologists in context of the aortic stenosis population.

DASI Dimensions provides the end-user with pre-defined images and measurements (diameters, lengths, angles, areas, and perimeters) of cardiovascular structures.

The clinician receiving the results the responsibility for interpreting and validating all information and making all patient treatment decisions.

DASI Dimensions is not intended to replace the clinician's decision or device's instructions for use.

DASI Dimensions is prescription use only.

DASI Dimensions is an image post-processing software system intended for clinical decision support in the context of pre-procedural planning of Transcatheter Aortic Valve Replacement (TAVR) procedures. The software provides users with a report of generated dimensions of cardiac structures. DASI Dimensions software is not operated by physicians.

DASI Dimensions is an off-site software system that receives cardiologists input via upload of patient multiphase DICOM computed tomography angiography (CTA) chest image files through DASI Simulations web portal. The processed report is then available for viewing and downloading. The report is generated using proprietary algorithms that (a) detect key aortic root control points with the assistance of a static deep learning artificial intelligence (Al) model and (b) calculate anatomical measurements relevant for pre-TAVR evaluation. DASI Simulations engineers perform quality checks at both steps before releasing the report to the end user via the portal.

DASI Dimensions does not contact with the patient, nor does it control any life sustaining devices. The information provided by DASI Dimensions is not diagnostic, nor does it determine recommended medical care.

The cardiologists and/or radiologists receiving the responsibility for interpreting and validating all information and making all patient treatment decisions.

DASI Dimensions:

· Supports quantification of cardiac structures for pre-procedural planning of aotic stenosis patients in consideration for potential TAVR procedures.

· Provides the measurement of different structures of the heart, e.g., aortic root, aortic valve.

The DASI Dimensions (V1.0) device's acceptance criteria and the study proving it meets these criteria are outlined below.

1. Table of Acceptance Criteria and Reported Device Performance

Ask a specific question about this device