Search Results

EOSedge is intended for use in general radiographic exams and applications, excluding the evaluation of lung nodules and exams involving fluoroscopy, angiography, and mammography.

EOSedge allows the radiographic acquisition of either one or two orthogonal X-ray images, for diagnostic purposes, in one single scan of the whole body or a reduced area of investigation of a patient, in the upright or seated position. The Micro Dose feature is indicated for assessing global skeletal deformities in follow-up pediatric exams.

The EOSedge™ system is a digital radiography system comprised of an acquisition workstation, a gantry including an electrical cabinet housing the system power and communication controls, and an acquisition software to obtain diagnostic images. Two sets of detectors and X-ray tubes are positioned orthogonally to generate frontal and lateral images simultaneously by scanning the patient over the area of interest. If desired, the Micro Dose feature enables image acquisition for assessing global skeletal deformities in pediatric follow-up exams.

The diagnostic images are stored in a local database and are displayed on a high-resolution medical-quality non-diagnostic monitor. The diagnostic image can be transmitted through a DICOM compatible digital network for printing and archiving.

The provided text outlines the substantial equivalence of the EOSedge device to its predicate, rather than detailing a specific clinical study with AI assistance demonstrating performance against acceptance criteria for an AI/ML powered device. The document describes changes to an existing, cleared device (EOSedge, K202394), primarily the activation of a dual-energy detection mode within already integrated detectors.

Therefore, the information required to fully answer the question regarding acceptance criteria and a study proving a device meets these criteria for an AI/ML powered device is largely not present in the provided text. The document focuses on showing the modified EOSedge is substantially equivalent to the cleared EOSedge system, implying that the previous clearances and tests are sufficient.

However, based on the provided text, I can infer and extract some relevant (though limited) information regarding performance testing that aligns with aspects of an AI/ML device, particularly concerning image quality and software:

Acceptance Criteria and Reported Device Performance (Inferred from "Performance Data" and "Technological Characteristics" sections):

• No specific acceptance criteria for AI/ML performance metrics (e.g., sensitivity, specificity, AUC) are stated. The performance data section focuses on general device standards and image quality.
• The document does not detail specific "reported device performance" in terms of clinical accuracy or an AI model's output metrics. It states that the device "performs according to specifications and is as safe and effective as the predicate device."

Here's a table synthesizing the types of performance criteria and the general statement of performance, as can be extracted from the document:

Since the document is a 510(k) summary focused on demonstrating substantial equivalence of a modified X-ray system, it does not contain the detailed information typically found in a clinical study report for an AI/ML-powered diagnostic device.

Missing Information (for an AI/ML powered device, based on the provided text):

1. Sample sizes used for the test set and data provenance: Not explicitly stated for any clinical performance evaluation of an AI component. The document mentions "bench testing."
2. Number of experts used to establish ground truth & qualifications: Not applicable/not stated, as no clinical ground truth establishment for AI performance is described.
3. Adjudication method for the test set: Not applicable/not stated.
4. MRMC comparative effectiveness study: Not mentioned. The document is for an imaging system, not an AI assistance tool for human readers.
5. Standalone (algorithm only) performance: Not mentioned, as it's a hardware system with software, not a pure AI algorithm.
6. Type of ground truth used: Not applicable/not stated for an AI/ML performance evaluation. Only "bench testing" is mentioned.
7. Sample size for the training set: Not applicable; no AI training set is mentioned.
8. How ground truth for the training set was established: Not applicable; no AI training set is mentioned.

In conclusion, the provided text is a regulatory filing for an X-ray imaging system (EOSedge) demonstrating substantial equivalence to a predicate device, focusing on hardware and software modifications. It does not describe an AI/ML device, nor does it present clinical study data for AI performance against defined acceptance criteria. The "Performance Data" section primarily addresses compliance with general X-ray system standards (IEC 60601-1, IEC 62220-1-1) and software verification/validation, concluding that the modified device is as safe and effective as its predecessor.

Ask a specific question about this device

The ArtVentive Endoluminal Occlusion System - EOS-X is indicated for arterial and venous embolization in the peripheral vasculature.

The ArtVentive Endoluminal Occlusion System (EOS-X) has been developed for arterial and venous embolization in the peripheral vasculature. The system consists of three major components: a preloaded implant, the delivery catheter, and the guide catheter with dilator. The EOS-X is intended for single use only.

Like the predicate ArtVentive Endoluminal Occlusion System (EOS)™, the ArtVentive Endoluminal Occlusion System (EOS-X) is comprised of an implant made of a Nitinol coil scaffold with an ePTFE occlusion membrane and is designed with radial force sufficient to provide stiffness and strength against the vessel wall and minimize post-deployment migration. The delivery system is made up of a delivery catheter and the guide catheter with dilator. The implant delivery catheter contains one implant loaded on the distal end and a deployment handle on the proximal end connected by the shaft. The delivery catheter has a low profile and is flexible to allow for trackability and pushability. The implant itself and the catheter's distal end are visible under fluoroscopy.

The guide catheter is a braided shaft with a stiff proximal section and a more flexible distal section to enable tracking through tortuous peripheral vasculature. A radiopaque marker on the distal end of the catheter is visible under fluoroscopy. The guide catheter is tapered to fit over the dilator. The dilator fits inside the guide catheter exiting out through the distal end. The dilator also has a tapered end for ease of advancement into the blood vessel. The guidewire and dilator are removed from the guide catheter once it is in position for delivery of the implant.

The provided text describes the ArtVentive Endoluminal Occlusion System (EOS-X), a vascular embolization device, and its substantial equivalence to a predicate device (ArtVentive Endoluminal Occlusion System, EOS). However, the document does not contain acceptance criteria for device performance, nor details of a study proving the device meets specific performance criteria in the way requested (e.g., using metrics like sensitivity, specificity, or accuracy compared to a ground truth).

Instead, the document focuses on demonstrating substantial equivalence to a previously cleared device (ArtVentive Endoluminal Occlusion System, EOS). This is a common regulatory pathway for medical devices in the US, where a new device can be cleared if it is shown to be as safe and effective as a legally marketed predicate device.

The "study" referenced in this document is primarily a series of engineering performance studies and design verification/validation testing. This testing is to ensure the new device, particularly the new 16mm size and minor design modifications to existing sizes, performs as intended and is comparable to the predicate.

Here's an attempt to answer your questions based on the provided text, while acknowledging the absence of some requested information:

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

The document does not explicitly state acceptance criteria in terms of performance metrics (like accuracy, sensitivity, or specificity) or numerical thresholds for clinical outcomes. The "reported device performance" is described as performing "as intended" and being "substantially equivalent" to the predicate.

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

The document explicitly states "Engineering Performance Studies" and "design verification/validation testing." These are typically bench and pre-clinical tests, not clinical studies with human patient data. Therefore, concepts like country of origin for patient data or retrospective/prospective designations are not applicable. The sample sizes for these engineering tests are not specified in the provided text.

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

This type of information is generally relevant for clinical studies where expert consensus or diagnostic accuracy is being assessed. Given that the document refers to engineering and design verification/validation tests, there is no mention of external experts establishing a "ground truth" for a test set in the conventional clinical sense. The ground truth for engineering tests would be defined by established manufacturing specifications, industry standards, and the performance characteristics of the predicate device.

4. Adjudication method for the test set

Not applicable, as this is typically used in clinical studies involving human interpretation or subjective measurements. The engineering tests would likely have objective pass/fail criteria.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

Not applicable. The device described is a physical vascular embolization system, not an AI-assisted diagnostic tool.

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

Not applicable. As above, this is a physical medical device, not an algorithm.

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

For the engineering performance studies and design verification/validation, the "ground truth" would be defined by:

• Design specifications and requirements: The device's components and overall system must meet predetermined engineering and material specifications.
• Performance of the predicate device: The EOS-X is compared to the established performance of its predicate, EOS.
• Industry standards and regulatory guidelines: The device must conform to relevant standards for medical devices of its type.

8. The sample size for the training set

Not applicable, as this is not an AI/machine learning algorithm.

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

Not applicable.

In summary, the provided document details the regulatory clearance of a medical device (ArtVentive Endoluminal Occlusion System, EOS-X) via the 510(k) pathway, which relies on demonstrating substantial equivalence to a predicate device. The "studies" referenced are engineering performance tests and design verification/validation to ensure the new device, including a new size and minor modifications, performs comparably to the predicate. It does not contain information about clinical trials, acceptance criteria based on clinical performance metrics, or the involvement of human experts in establishing ground truth for a test set in the context of diagnostic accuracy.

Ask a specific question about this device

The EOS PMP hollow fiber oxygenator is intended for use in patients who undergo cardiopulmonary bypass surgery requiring extracorporeal circulation with a maximum blood flow rate of 5 LPM. It provides oxygenation and carbon dioxide removal from venous blood. The integrated heat exchanger provides blood temperature control and allows the use of hypothermia or aids in the maintenance of normothermia during surgery. The device is intended to be used for 6 hours or less.

The EOS PMP Hollow Fiber Oxygenator (hereinafter identified as EOS PMP) consist of an oxygenator with an integrated heat exchanger.

The EOS PMP consist of the following main components

• a heat exchanger consisting of a grooved and pleated stainless steel that is placed into a polycarbonate housing with integrated Hansen connectors and is sealed with resin potting at both ends. it controls blood temperature and allows the use of hypothermia or aids in the maintenance of normothermia during surqery.
• . an oxygenating module element made of a coiled bundle of polypropylene microporous hollow fibers rolled on the heat exchanger sub assembly. The hollow fiber membrane provides oxygenation and carbon dioxide removal from venous blood or suction blood..

The modified device is a modified version of the currently marketed EOS product.

Here's a breakdown of the acceptance criteria and study information for the EOS PMP device, based on the provided text:

Device: EOS PMP Hollow Fiber Oxygenator

1. Table of Acceptance Criteria and Reported Device Performance

The provided text describes performance testing related to the modification of the EOS PMP device (addition of an epoxy phenolic primer coating to the heat exchanger). The acceptance criteria are implicitly that the modified device performs comparably to the unmodified predicate device and meets established standards.

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

• Test Set Sample Size: Not explicitly stated. The text mentions "in vitro testing was performed" and "This performance testing was conducted on sterile aged devices." It does not provide a specific number of units tested.
• Data Provenance: The studies were retrospective in the sense that they evaluated a modified version of an existing device (EOS PMP) against its unmodified predicate. The testing itself (heat exchanger performance, mechanical integrity, flaking/leaching) appears to be laboratory-based and controlled, thus prospective in execution within that controlled environment. The country of origin of the data is not specified beyond "Sorin Group Italia S.R.L." which suggests it was likely performed in Italy or by a contracted lab.

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

• This question is not applicable as the evaluation was based on non-clinical (in vitro) performance data against established standards and a predicate device, rather than on expert interpretation of patient data.

4. Adjudication Method for the Test Set

• This question is not applicable as the evaluation did not involve human interpretation or adjudication of results in the traditional sense; it was based on meeting pre-defined physical and chemical performance metrics.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• No, an MRMC comparative effectiveness study was not done. This device is a medical device (oxygenator), not an AI diagnostic tool. The document states: "No clinical testing was conducted in support of the EOS PMP, as the indications for use are equivalent to those of the predicate, which have been on the market for many years."

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

• No, a standalone (algorithm only) performance study was not done. This is a physical medical device, not an algorithm or AI system.

7. The Type of Ground Truth Used

• The ground truth used was based on established industry standards and regulatory guidance (ISO 10993-1, FDA Guidance for Cardiopulmonary Bypass Oxygenators, ISO 7199), and the performance of the legally marketed predicate device (Unmodified EOS PMP). The goal was to prove "substantial equivalence" of the modified device to the predicate for specific performance characteristics.

8. The Sample Size for the Training Set

• This question is not applicable as the device is a physical medical device, not a machine learning model, and therefore does not have a "training set" in the AI/ML context.

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

EOS Air Cleaner is a device intended for medical purposes that is used to destroy bacteria and viruses in the air by exposure to ultraviolet radiation in general medical environment.

The core technology components of the EOS Air Cleaner have been demonstrated to destroy MS2 bacteriophage bioaerosol entrained on the filter to achieve an average 4 log reduction over 4 hours in a 30 cubic meter chamber.

EOS Air Cleaner employs an ultraviolet air purification technology that destroys bacteria and viruses in air in hospital, nursing homes, medical facilities, but not in specialized medical place such as operating rooms.

EOS Air Cleaner is a free-standing device, which has a well-sealed metal box including a fine filter, motor, two UV-C lamps, and a HEPA filter. By sucking surrounding air into the device, EOS Air cleaner can suction the air into the device and filtering the air by fine filter with UV-C light radiation, then the purified air is expelled from the cabinet.

The bacteriophage deposited onto the surface of EOA Air Cleaner's proprietary photocatalytic coated filter media will be killed after exposure to EOS Air Cleaner's UV-C light

UV-C light in 255 nm which is commonly called germicidal kills any remaining bacteria and viruses, as the radiation penetrates the cell walls of bacteria and is absorbed by the organic structures within the bacterial and virus, causing them to decompose and the cell to die.

Here's the breakdown of the acceptance criteria and study information for the EOS Air Cleaner, based on the provided document:

Acceptance Criteria and Device Performance

Note regarding the Bacteriophage Test's Reported Performance: The "Indications for Use" section and the "Comparison of Technological Characteristics" table provide more specific performance details:

• The core technology components have been demonstrated to destroy MS2 bacteriophage bioaerosol entrained on the filter to achieve an average 4 log reduction over 4 hours in a 30 cubic meter chamber.
• Specific log reductions at different speeds (Speed 1: 4.05 / 4 hours, Speed 5: 4.22 / 4 hours, Speed 10: 4.45 / 4 hours) are also reported.

Study Details

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

   • The document does not explicitly state the sample size for the bacteriophage tests (e.g., number of test runs or replicates).
   • The data provenance is from non-clinical testing, likely conducted in a laboratory setting, and the manufacturer is Guangzhou Ajax Medical Equipment Co., Ltd. in China. The document does not specify if the data is retrospective or prospective, but it implies prospective testing for regulatory submission.

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

   • The document does not mention individual experts or their qualifications for establishing ground truth for the non-clinical tests. These types of tests typically rely on standardized laboratory protocols and measurements rather than expert consensus on individual "cases."

3. Adjudication Method for the Test Set:

   • Not applicable as this involves non-clinical laboratory testing against pre-defined performance metrics, not human expert interpretation requiring adjudication.

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

   • No, an MRMC comparative effectiveness study was not done. The device is an air cleaner, and its performance is measured mechanically and biologically, not through human reader interpretation of medical images or data.

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

   • Yes, the provided studies are standalone evaluations. The "Bacteriophage Test," "Aging Test," and "Software Validation" all evaluate the device's inherent performance and functionality without human interaction beyond operating and monitoring the device.

6. Type of Ground Truth Used:

   • For the Bacteriophage Test and Aging Test: Direct measurement of viral load reduction (specifically MS2 bacteriophage bioaerosol) in a controlled environment. This is a scientific and empirical ground truth.
   • For IEC 60601-1/60601-1-2 and Software Validation: Adherence to established international standards and design criteria.

7. Sample Size for the Training Set:

   • The document does not mention a training set or machine learning component for the EOS Air Cleaner. The device's function relies on physical processes (UV radiation, filtration) rather than an AI/ML algorithm that requires training data.

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

   • Not applicable, as there is no mention of a training set or AI/ML algorithm.

Ask a specific question about this device

EOSedge is intended for use in general radiographic exams and applications, excluding the evaluation of lung nodules and exams involving fluoroscopy, and mammography. EOSedge allows the radiographic acquisition of either one or two orthogonal X-ray images, for diagnostic purposes, in one single scan, of the whole body or a reduced area of investigation of a patient, in the upright or seated position.

The Micro Dose feature is indicated for assessing global skeletal deformities in follow-up pediatric exams.

The EOSedge system is a digital radiography system comprised of an acquisition workstation, a gantry including an electrical cabinet housing the system power and communication controls, and an acquisition software to obtain diagnostic images. Two identical sets of detectors and X-ray tubes are positioned orthogonally to generate frontal and lateral images simultaneously by scanning the patient over the area of interest. If desired, the Micro Dose feature enables image acquisition for assessing global skeletal deformities in follow-up pediatric exams. The two sets of detectors and X-ray tubes are identical between the predicate device and the subject device. The image acquisition can be performed with a MANUAL mode or an AUTO mode of patient examination. To select the area of interest (acquisition area), a vertical collimation is set using green lasers and to correctly position the patient in the EOSedge, a centering system is used based on red lasers. The diagnostic images are stored in a local database and are displayed on a high-resolution medical-quality non-diagnostic monitor. The diagnostic image can be transmitted through a DICOM compatible digital network for printing and archiving.

The provided text describes a 510(k) premarket notification for the EOSedge™ system, an updated digital radiography system. The document focuses on demonstrating that the updated device is substantially equivalent to a previously cleared predicate device (EOS imaging's EOSedge System K192079).

Based on the provided text, the acceptance criteria and study proving the device meets these criteria are primarily based on bench testing and comparative analysis with a predicate device, rather than a clinical study evaluating diagnostic performance.

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

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly tied to demonstrating substantial equivalence to the predicate device, implying that the updated device must perform at least as safely and effectively. The performance data section refers to conformity to various IEC standards and internal functional testing.

• Quantity: 2
• Type: Hybrid CdTe-CMOS dual energy photons counting X-ray detector
• Dimensions: Width 585 mm x 98 mm, Thickness 131 mm
• Weight: 131 000 gray levels)
• Nominal input voltage: 12 VDC – 20 A
• Temperature control: Internal check, Peltier + PWM, Ventilator system checked
• DQE type: RQA5 spectrum ~ 80%
• MTF type: ~70% @ 2lp / mm, ~25% @ 5lp / mm
• Pixel Depth: 17 bits (> 131 000 grey levels)
• Pixel Size: 100 µm
• Resolution: 3.7 lp/mm
• Typical Dynamic Range: > 100 dB |
  | Average Acquisition Time | Must be comparable or improved compared to predicate. | Current Device (EOSedge™): 7 seconds for a spine and 13 seconds for an entire body
  Predicate Device (EOSedge System K192079): 8 seconds for a spine and 15 seconds for an entire body (Improved performance stated for current device) |

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

The document does not describe a clinical test set with patient data for evaluating diagnostic performance. The testing described is primarily bench testing and software verification/validation. Therefore, there are no details on sample size for a test set of patient images or their provenance (country of origin, retrospective/prospective). The assessment is based on technical specifications and comparison to the predicate device.

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

As there is no clinical test set for diagnostic performance described, there is no information on experts establishing ground truth for such a set. The ground truth for the engineering/technical tests would be the established specifications and accepted performance metrics for medical imaging devices, as defined by relevant IEC and FDA guidance.

4. Adjudication Method for the Test Set

Not applicable, as no clinical test set requiring expert adjudication is described in the provided text.

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

No, an MRMC comparative effectiveness study was not explicitly done or described in the provided text. The submission focuses on demonstrating substantial equivalence through technical performance data and comparison to a predicate device, not on improved human reader performance with AI assistance. The device itself is an X-ray imaging system, not an AI diagnostic assistant.

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

Not explicitly applicable in the context of an X-ray imaging system. The performance evaluated here is the image acquisition and processing capabilities of the X-ray device itself, which operates as a standalone system to produce images for human interpretation.

7. The Type of Ground Truth Used

The ground truth used for these tests is based on established engineering and performance standards for X-ray imaging devices (e.g., IEC standards, FDA guidance for solid-state X-ray imaging devices). For comparative purposes, the predicate device's cleared performance serves as a benchmark for substantial equivalence.

8. The Sample Size for the Training Set

Not applicable. The document describes a medical imaging device (hardware and software for image acquisition), not a machine learning algorithm that requires a training set of data for inference.

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

Not applicable, as there is no training set for a machine learning algorithm described.

Ask a specific question about this device

EOSedge is intended for use in general radiographic exams and applications, excluding the evaluation of lung nodules and exams involving fluoroscopy, angiography, and mammography. EOSedge allows the radiographic acquisition of either one or two orthogonal X-ray images, for diagnostic purposes, in one single body or a reduced area of investigation of a patient, in the upright or seated position.

The Micro Dose feature is indicated for assessing global skeletal deformities in follow-up pediatric exams.

The EOSedge system is a digital radiography system comprised of an acquisition workstation, a gantry including an electrical cabinet housing the system power and communication controls, and an acquisition software to obtain diagnostic images. Two sets of detectors and X-ray tubes are positioned orthogonally to generate frontal and lateral images simultaneously by scanning the patient over the area of interest. If desired, the Micro Dose feature enables image acquisition for assessing global skeletal deformities in follow-up exams. The diagnostic images are stored in a local database and are displayed on a highresolution medical-quality non-diagnostic image can be transmitted through a DICOM compatible digital network for printing and archiving.

The provided text is a 510(k) summary for the EOS imaging's EOSedge System. It describes the device, its intended use, and compares it to a predicate device (EOS System K152788) to demonstrate substantial equivalence.

However, the document does not contain information about acceptance criteria for an AI/algorithm's performance, nor does it describe a study that proves a device meets such criteria. It focuses on the substantial equivalence of an X-ray imaging system to its predecessor, based on design, technical specifications, and general performance testing (bench testing for dosing and image quality).

Therefore, I cannot fulfill your request for information regarding acceptance criteria and a study proving an AI device meets them based on the provided text. The document is about a conventional X-ray imaging system, not an AI-driven device with specific performance metrics like sensitivity, specificity, or AUC established through clinical studies with ground truth.

The "Performance Data" section (page 4) states: "Bench performance testing were conducted based on FDA's Guidance for the Submission of 510/k)'s for Solid-State X-ray Imaging Devices (September 1, 2016), to verify that EOSedge performs according to specifications and is as safe and effective as the predicate device." This refers to engineering and image quality tests common for X-ray hardware, not an AI algorithm evaluation.

Ask a specific question about this device

EOS is intended for use in general radiographic examinations and applications, excluding the evaluation of lung nodules and examinations involving fluoroscopy, angiography, and mammography. EOS allows the radiographic acquisition of either one or two orthogonal X-ray images for diagnostic purposes, in one single scan, of the whole body or a reduced area of investigation of a patient in the upright or seated position.

The Micro Dose feature is indicated for imaging with a patient entrance dose of 10 to 90 µGy for assessing global skeletal deformities in follow-up pediatric examinations. Micro Dose is not indicated for focal skeletal abnormalities and/or other pediatric abnormalities. Micro Dose is not indicated for use in patients with a Body Mass Index over 30.

EOS is a digital radiography system in which two sets of xenon gas filled digital detectors and X-ray tubes are positioned orthogonally to generate frontal and lateral images simultaneously by scanning the patient over the area of interest. An acquisition feature named Micro Dose allows image acquisition with a patient entrance dose of 10 to 90 uGv for assessing global skeletal deformities in follow-up pediatric exams. The diagnostic images are stored in a local database and are displayed on a high-resolution, medical-quality monitor, where the diagnosis is performed. The diagnostic image can be transmitted through a DICOM 3.0 compatible digital network for printing and archiving.

The provided text describes the EOS System, a stationary x-ray system, and states that it has been determined to be substantially equivalent to a legally marketed predicate device. However, this document does not contain details about specific acceptance criteria or an explicit study proving device performance against those criteria in the way you've outlined for clinical performance.

Instead, the document focuses on demonstrating substantial equivalence to an existing cleared device (K142773) based on:

• Same Intended Use/Indications for Use: Both the modified and predicate EOS systems share the same intended use for general radiographic examinations, excluding lung nodules, fluoroscopy, angiography, and mammography. They both also offer the "Micro Dose" feature for assessing global skeletal deformities in follow-up pediatric examinations (with specific dose and BMI limitations).
• Similar Technological Characteristics/Principles of Operation: The fundamental technological characteristics of the modified EOS are unchanged from the cleared EOS. Minor modifications (hardware component supplier changes, electrical component changes due to obsolescence, mirror sticker accessory, software modification related to a recall, optimization of default acquisition protocols, improvement of image processing, and addition of new features like Dose Structured Report and Reject and Repeat Analysis) are described as not altering the core function or safety.
• Performance Data (Bench Testing): The document mentions "Performance data demonstrates that the modified EOS is as safe and effective as the cleared predicate device." This includes "bench testing to confirm appropriate dosing and image quality." It also states, "Performance testing has demonstrated that this modification allows reducing the entrance dose for the changed protocols, with maintaining equivalent or better image quality than the cleared EOS" (referring to the optimization of default acquisition protocols).

Therefore, I cannot fill in your requested table and many of the study details because the provided text does not describe a clinical performance study with defined acceptance criteria and results for the device itself, but rather an argument for substantial equivalence of a modified device to a predicate device based on technical performance and safety.

Here's what I can extract and state based on the provided text, while also noting what is not present:

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

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Not explicitly mentioned. The document refers to "bench testing" and "performance and functional testing," which typically involves phantoms or test objects, not patient datasets with "test sets" in the clinical sense.

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/Not mentioned. Since this was a substantial equivalence submission based on technical modifications and bench testing, there's no indication of expert review for clinical ground truth on a 'test set.'

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

• Not applicable/Not mentioned.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• No. This document describes an X-ray system, not an AI-powered diagnostic device. Therefore, no MRMC study or AI-related effectiveness is discussed.

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

• Not applicable. As the device is an X-ray imaging system, "standalone" performance refers to its ability to acquire images, which is addressed by the "bench testing" and "performance and functional testing" mentioned. There is no algorithm performance discussed in the context of diagnostic interpretation.

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

• Not applicable/Not mentioned for clinical ground truth. The "ground truth" for the performance claims appears to be based on physical measurements of dose and objective assessments of image quality (e.g., spatial resolution, contrast-to-noise ratio) from bench testing, rather than clinical outcomes or pathology.

8. The sample size for the training set

• Not applicable/Not mentioned. This is not an AI/machine learning device that would require a training set in the typical sense.

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

• Not applicable/Not mentioned.

Ask a specific question about this device

The ArtVentive Endoluminal Occlusion System (EOS) is intended for arterial and venous embolization in the peripheral vasculature.

The ArtVentive Medical Group Endoluminal Occlusion System™ (AVMG EOS™) has been developed for arterial and venous embolizations in the peripheral vasculature. The system consists of three major components: a preloaded implant, the delivery catheter, and the guide catheter with dilator. The AVMG EOS™ is intended for single use only.

Like the parent ArtVentive Endoluminal Occlusion System - EOS, the proposed 11mm size of the device is comprised of an implant made of a Nitinol coil scaffold with an ePTFE occlusion membrane and is designed with radial force sufficient to provide stiffness and strength against the vessel wall and minimize post-deployment migration. The delivery system is made up of a delivery catheter and the guide catheter with dilator. The implant delivery catheter contains one implant loaded on the distal end and a deployment handle on the proximal end connected by the shaft. The delivery catheter has a low profile and is flexible to allow for trackability. The implant itself and the catheter's distal end are visible under fluoroscopy.

The guide catheter is a braided shaft with a stiff proximal section and a more flexible distal section to enable tracking through tortuous peripheral vasculature. A radiopaque marker on the distal end of the catheter is visible under fluoroscopy. The tip of the guide catheter is tapered to fit over the dilator. The dilator fits inside the guide catheter exiting out through the distal end. The dilator also has a tapered end for ease of advancement into the blood vessel. The guidewire and dilator are removed from the guide catheter once it is in position for delivery of the implant.

This document is a 510(k) Pre-Market Notification from the FDA regarding the ArtVentive Medical Group's Endoluminal Occlusion System (EOS). It primarily establishes substantial equivalence to a predicate device rather than detailing a clinical study with acceptance criteria in the typical sense of a diagnostic or accuracy study.

However, based on the provided text, we can piece together what functioned as "acceptance criteria" through performance data and a comparison to a predicate device.

1. Table of Acceptance Criteria and Reported Device Performance

The design verification and validation testing was repeated as necessary for the minor design modifications to the cleared 5mm and 8mm delivery catheter/implant and the 6 Fr guide catheter. |
| Material Equivalence: Nitinol coil with an ePTFE polymeric cover | The device uses a Nitinol coil with an ePTFE polymeric cover, which is the same as the predicate device. |
| Design Features Equivalence: Flexibility, low profile, immediate/acute occlusion, ePTFE cover, retrievability, two-stage deployment handle, stiff proximal/flexible distal catheter sections, side port for flushing/pre-expansion. | The device is described with flexible, low profile for immediate, acute occlusion, incorporates an ePTFE cover, is retrievable, has a two-stage deployment handle, a stiff proximal section for pushability and a flexible distal section for trackability, and a side port to accommodate syringe attachment to flush and pre-expand the ePTFE membrane. These features are directly compared and found to be the same as the predicate device. |
| Mechanical Detachment Method Equivalence: Mechanical in nature | The detachment mechanism is mechanical in nature, same as the predicate device. |
| Treatment Method Equivalence: Permanent Implant | The treatment method is described as a permanent implant, same as the predicate device. |
| Application Method Equivalence: Via delivery catheter through guide catheter to target vessel | The device is applied via a delivery catheter through a guide catheter to the target vessel, same as the predicate device. |

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

The document explicitly states "Bench studies" and "design verification and validation testing." This indicates in-vitro or laboratory testing rather than testing on human or animal subjects. Therefore, human test set sample size and provenance information is not applicable. The data provenance would be from internal laboratory testing.

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

This section is not applicable as the document describes bench testing and design verification/validation, not a study requiring expert clinical assessment for ground truth. The "ground truth" here would be defined by engineering specifications and predicate device performance characteristics.

4. Adjudication method for the test set

This is not applicable as the document describes bench testing and design verification/validation, not a study requiring adjudication of expert opinions.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. The document describes bench studies and design verification/validation directly comparing the device characteristics to a predicate, not a study involving human readers' performance.

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

This refers to a device, not an algorithm. Therefore, an algorithm-only standalone performance study is not applicable. The device's performance was evaluated in bench studies (standalone performance relative to engineering specifications and predicate device).

7. The type of ground truth used

The ground truth used for this submission is implicitly based on:

• Engineering specifications and design requirements: The device's physical dimensions, material properties, and functional capabilities (e.g., radial strength, trackability) were measured and compared against established requirements.
• Predicate device characteristics: The device was compared feature-by-feature (technological characteristics, mechanism of action, intended use, physical characteristics, materials, detachment method, application method) to a legally marketed predicate device (K133924 ArtVentive Medical Group, Inc./EOS).
• Performance "as intended": Demonstrating that the device performs according to its designed function in bench tests.

8. The sample size for the training set

This document describes a 510(k) submission focused on proving substantial equivalence based on bench testing and design verification. It details the device's characteristics and compares them to a predicate. There is no mention of a "training set" in the context of machine learning or AI, as this is a medical device approval based on physical and functional characteristics.

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

As there is no mention of a "training set", this question is not applicable.

Ask a specific question about this device

EOS PMP Integrated: Hollow Fiber Oxygenator with Integrated Hardshell Venous/Cardiotomy Reservoir
The device is intended for use in patients who undergo cardiopulmonary bypass surgery requiring extracorporeal circulation with a maximum blood flow rate of 5 liters /minute. It provides oxygenation and carbon dioxide removal from venous blood. The integrated heat exchanger provides blood temperature control and allows the use of hypothermia or aids in the maintenance of normothermia during surgery. The venous reservoir with cardiotomy filter is intended to collect blood aspirated from the operating field during surgical procedures and the blood from patient's veins (gravity or vacum assisted) during nomal operation to assure the proper oxygenation capability of the device. The device is intended to be used for 6 hours or less.

EOS PMP: Hollow Fiber Oxygenator
The device is intended for use in patients who undergo cardiopulmonary bypass surgery requiring extracorporeal circulation with a maximum blood flow rate of 5 liters /minute. It provides oxygenation and carbon dioxide removal from venous blood. The integrated heat exchanger provides blood temperature control and allows the use of hypothermia or aids in the maintenance of normothermia during surgery. The device is intended to be used for 6 hours or less.

The EOS PMP is a high efficiency hollow fiber diffusion membrane oxygenator with integrated heat exchanger.
The device provides oxygenation and carbon dioxide removal from patient's blood. The integrated heat exchanger controls blood temperature and allows the use of hypothermia, or aids in the maintenance of normothermia during surgery.
The device can be operated at flow rates up to 5 liters per minute (I/min).
The device can be connected with, but not limited to, the D905 EOS reservoir (K043323) that collects, defoams, and filters patient's blood.
The EOS PMP is a modified version of the currently marketed D905 EOS (K043323).

The provided text describes a 510(k) premarket notification for a medical device, the EOS PMP and EOS PMP Integrated, which are hollow fiber oxygenators. The document focuses on demonstrating substantial equivalence to a legally marketed predicate device (D905 EOS).

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based only on the provided text:

Summary of Device Performance and Acceptance Criteria:

Study Details:

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

   • The document states that "In vitro testing was conducted on the oxygenating module that is the only device element subject to modifications with respect to the unmodified device." However, it does not specify the sample size (e.g., number of devices tested) for these in vitro tests.
   • Data provenance: The tests were "in vitro," meaning they were conducted in a controlled, non-living environment (e.g., laboratory setting), rather than with human or animal subjects. The document does not specify a country of origin for the data; the submitter is "Sorin Group Italia," suggesting the tests might have been performed in Italy or by a third-party laboratory.

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 tests are described as "in vitro" and against "relevant requirements of 'Guidance for Cardiopulmonary Bypass Oxygenators 510(k) Submissions; Final Guidance for Industry and FDA Staff, November 13, 2000'," suggesting objective, measurable criteria rather than expert interpretation of results.

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

   • This information is not provided as the testing involved in-vitro performance measurements against established guidances/standards, not expert adjudication of subjective findings.

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 comparative effectiveness study was done or mentioned. This device is a cardiopulmonary bypass oxygenator, not an AI-assisted diagnostic tool requiring human reader involvement.

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

   • This question is not applicable. The device is a physical medical device (an oxygenator), not an algorithm or software. The "standalone performance" was assessed through the in-vitro functional/performance tests.

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

   • The ground truth for the in-vitro performance tests was based on pre-defined acceptance criteria derived from "relevant requirements of 'Guidance for Cardiopulmonary Bypass Oxygenators 510(k) Submissions; Final Guidance for Industry and FDA Staff, November 13, 2000'" and ISO 10993-1 for biological evaluation. These guidances and standards establish objective measurable benchmarks for safe and effective performance of such devices.

7. The sample size for the training set:

   • This information is not applicable as this is not a machine learning/AI device that requires a training set. The "modified device" (EOS PMP) was compared to an "unmodified device" (D905 EOS) and evaluated against established performance criteria.

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

   • This information is not applicable as there is no training set for this type of device.

Ask a specific question about this device

EOS is intended for use in general radiographic examinations and applications, excluding the evaluation of lung nodules and examinations involving fluoroscopy, angiography, and mammography. EOS allows the radiographic acquisition of either one or two orthogonal X-ray images for diagnostic purposes, in one single scan, of the whole body or a reduced area of investigation of a patient in the upright or seated position.

The Micro Dose feature is indicated for imaging with a patient entrance dose of 10 to 90 µGy for assessing global skeletal deformities in follow-up pediatric examinations. Micro Dose is not indicated for focal skeletal abnormalities and/or other pediatric abnormalities. Micro Dose is not indicated for use in patients with a Body Mass Index over 30.

EOS is a digital radiography system in which two sets of xenon gas filled digital detectors and Xray tubes are positioned orthogonally to generate frontal and lateral images simultaneously by scanning the patient over the area of interest. A new acquisition feature named Micro Dose allows image acquisition with a patient entrance dose of 10 to 90 µGy for assessing global skeletal deformities in follow-up pediatric exams. The diagnostic images are stored in a local database and are displayed on a high-resolution, medical-quality monitor, where the diagnosis is performed. The diagnostic image can be transmitted through a DICOM 3.0 compatible digital network for printing and archiving.

Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:

Device: EOS System
Feature under evaluation: Micro Dose

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document does not explicitly state numerical acceptance criteria for image quality (e.g., minimum landmark visibility score, specific accuracy/reproducibility metrics). The reported performance is a qualitative statement of efficacy based on the assessments performed.

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

The document does not provide specific details on the sample size used for the clinical test set or the data provenance (e.g., country of origin, retrospective/prospective nature of the data). It only mentions "clinical testing."

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

The document does not specify the number of experts used to establish the ground truth or their qualifications. It mentions "rating the visibility of the anatomical landmarks" and "assessing the reproducibility and the accuracy of the measurements of clinically relevant scoliosis angles," which implies expert review, but no further details are given.

4. Adjudication Method for the Test Set

The document does not describe the adjudication method used for the test set.

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

The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with AI assistance versus without. The study described focuses on the standalone performance and image quality of the Micro Dose feature.

6. Standalone (Algorithm Only) Performance Study

Yes, a standalone performance study was done. The "Performance Data" section describes testing designed to "confirm the ability of the EOS System's Micro Dose acquisition feature to generate very low X-ray dose images allowing for the follow-up assessment of global skeletal deformities in pediatric patients." This indicates an evaluation of the device's output (images) directly, independent of a human-in-the-loop scenario. The assessment focused on the quality of these images for diagnostic purposes.

7. Type of Ground Truth Used

The ground truth appears to be based on expert assessment/consensus related to:

• Visibility of anatomical landmarks: This would involve experts evaluating whether critical anatomical points are clearly discernible in the low-dose images.
• Reproducibility and accuracy of measurements: This suggests that measurements (e.g., scoliosis angles) were taken from the Micro Dose images and compared against either a gold standard measurement (though not explicitly stated what that standard was) or assessed for consistency by experts. The "clinically relevant scoliosis angles" imply that expert clinical judgment was involved in defining and assessing these.

8. Sample Size for the Training Set

The document does not mention any sample size for a training set. Given that the EOS System is a digital radiography system with a new acquisition feature (Micro Dose), and not explicitly an AI/ML algorithm that requires a dedicated training set beyond its physics-based image processing, a "training set" in the context of supervised machine learning might not be applicable here. The focus is on the performance of the image acquisition and processing pipeline at a reduced dose.

9. How Ground Truth for the Training Set Was Established

As no training set is mentioned in the context of an AI/ML algorithm, the method for establishing its ground truth is not applicable or described. The performance evaluation is related to the image quality produced by the system for specific diagnostic tasks.

Ask a specific question about this device