Search Results

The Pilot TLS is indicated for use in positioning of PICCs. The Pilot TLS provides real-time catheter tip location information by displaying changes in the patient's cardiac electrical activity. Pilot TLS is indicated for use as an alternative method to chest X-ray or fluoroscopy confirmation of PICC tip placement in adult patients.

Note: Limited, but not contraindicated, situations for this technique are patients where cardiac rhythms may change presentation of the P-wave:

• Atrial fibrillation
• Atrial flutter
• Severe tachycardia
• Pacemaker-Driven Rhythm
• Chronic obstructive pulmonary disease (COPD)

Such patients are easily identified prior to PICC insertion. Use of additional method is necessary to confirm catheter tip location.

Pilot TLS is designed to support quidance and tip positioning of Peripherally Inserted Central Catheters (PICCs) of at least 3 Fr in size. Pilot TLS provides real-time catheter tip location information by using the patient's cardiac electrical activity and is indicated for use as an alternative method to chest X-ray and fluoroscopy for PICC tip placement confirmation for adults. The device includes a medical tablet preloaded with Pilot software, a Pilot TLS module, an ECG cable accessory, and a Vygocard accessory.

The device is only provided in one configuration, and non-sterile. The system is composed of:

• . A medical tablet with a kickstand attached on the back
• . The medical tablet's power supply
• . A Pilot TLS module attached to a USB-A cable
• A stabilization base (option to maintain the black ECG lead for its connection to Vygocard saline connector
• An ECG cable with 4 leads (red, white, green, black)
• 2 USB flash drives

Vygocard is an accessory provided sterile.

This document, a 510(k) Premarket Notification for the "Pilot TLS" device, primarily focuses on demonstrating substantial equivalence to a predicate device, the "C3 Wave," rather than presenting a standalone study with detailed acceptance criteria and performance data in the format requested.

However, based on the provided text, here's what can be extracted and inferred regarding performance and testing:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with corresponding device performance metrics. Instead, it lists various non-clinical tests conducted to verify performance requirements. These tests are generally designed to ensure compliance with standards and safety, not necessarily to quantify specific performance metrics against a defined acceptance criterion for a clinical study.

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

The document does not provide details on a specific test set size for clinical performance evaluation. It explicitly states: "No human clinical data was provided to support substantial equivalence."

The "human factors study" mentioned could be considered a usability test set, but details about its size or provenance (country, retrospective/prospective) are not disclosed in this document.

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

As "No human clinical data was provided," there is no information about experts used to establish ground truth for a clinical test set. For the human factors study, the participants are referred to as "independent clinician participants," but their number or specific qualifications (e.g., years of experience) are not provided.

4. Adjudication Method for the Test Set

Not applicable, as "No human clinical data was provided" for a clinical test set that would require ground truth adjudication.

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

No, the document explicitly states: "No human clinical data was provided to support substantial equivalence." Therefore, no MRMC study or effect size for AI assistance is reported.

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

The document describes the "Pilot TLS" as a device providing "real-time catheter tip location information by displaying changes in the patient's cardiac electrical activity." This implies human interaction as "displaying" information requires interpretation by a user. The software verification and validation would test the algorithm's functionality, but a formal "standalone" performance study in a clinical context (without human interaction) is not described. The device is intended as an "alternative method to chest X-ray or fluoroscopy confirmation," which inherently involves a human interpreting the device's output.

7. The Type of Ground Truth Used

Given the statement "No human clinical data was provided to support substantial equivalence," there is no mention of ground truth established through expert consensus, pathology, or outcomes data for clinical performance. The comparison to chest X-ray or fluoroscopy implies these are the traditional "ground truth" methods for PICC tip placement confirmation, but no data is presented where the Pilot TLS's output is validated against these.

8. The Sample Size for the Training Set

Not applicable. The document does not describe the development or training of a machine learning algorithm, and thus no training set sample size is mentioned. This device relies on "identification of a maximum P-wave in the patient's intravascular ECG signal," which is a known physiological principle, not a machine learning model requiring a training set in the typical sense.

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

Not applicable, as no training set for a machine learning model is mentioned.

Ask a specific question about this device

For nasogastric oralgastric enteral feeding, incorporating safety connectors which eliminates the risk of IV administration through the feeding tube.

Nutrifit is a combined system of feeding tubes and extension sets. The feeding tubes are available in several configurations: Not made with DEHP PVC and Polyurethane (PUR). The PUR versions are available without stylet. All tubes include centimeter numerical markings from 5 to 35 cm for the 40, 50 and 75 cm feeding tubes and markings from 5 to 70 cm for the 90, 125 and 160 cm feeding tubes.

The Nutrifit devices are single-use, disposable devices intention in adults and children. Nutrifit PVC feeding tubes are intended for enteral nutrition and for a short-term use, not longer than 5 days. Nutrifit PUR feeding tubes are intended for enteral nutrition and for a short-term use, not longer than 29 days.

The Nutrifit accessories for this submission sets, which enable longer connections for the feeding tubes. They allow greater freedom of movement and greater flexibility and are available with or without a pinch clamp.

Nutrift is ENFit compliant, meeting requirements for design and functional performance of small-bore connectors intended to be used for connections on enteral medical devices and accessories as detailed in ISO 80369-3.

The provided text is a 510(k) summary for the Vygon USA Nutrifit device, a gastrointestinal tube and accessories. It asserts the device's substantial equivalence to a predicate device (Nutrisafe 2) based on non-clinical performance bench testing.

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

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not specify the sample size used for the test set for any of the bench tests mentioned. It states "Adequate non-clinical performance bench testing was conducted" and "The VYGON's Nutrifit device met all predetermined acceptance criteria."
The data provenance is from non-clinical performance bench testing conducted by Vygon; the country of origin is not explicitly stated but implied to be internal testing by the manufacturer. The data is prospective for this device's evaluation.

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

This information is not provided in the document. The tests performed are engineering/performance-based bench tests, not clinical evaluations requiring expert interpretation of ground truth in the traditional sense (e.g., medical image interpretation). The "ground truth" for these tests would be the established specifications and standards (e.g., ISO 80369-3).

4. Adjudication Method for the Test Set

This is not applicable as the tests are objective, performance-based bench tests against defined specifications, not subjective assessments requiring adjudication by multiple experts.

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

No, an MRMC comparative effectiveness study was not done. The document explicitly states "Bench Testing was conducted in order to support this submission." There is no mention of human readers or AI assistance.

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. The Nutrifit is a medical device (tubing and accessories), not an AI algorithm or software. The testing focuses on its physical performance and safety characteristics.

7. The Type of Ground Truth Used

The ground truth used for the performance testing cited is based on established engineering specifications, international standards (ISO 80369-3), and FDA guidance protocols (e.g., "Gravity Flow Rate Testing in Enteral Tube"). This falls under objective technical standards rather than expert consensus, pathology, or outcomes data.

8. The Sample Size for the Training Set

This information is not applicable as the Nutrifit device is a physical medical device, not an AI algorithm that requires a training set.

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

This information is not applicable for the same reason as point 8.

Ask a specific question about this device

Leaderflex mini and Leaderflex nano are indicated for:
•Peripheral venous catheterization (midline) in any patient population with consideration given to the adequacy of vascular anatomy and appropriateness of procedure, or
· Arterial catheterization

Leaderflex Mini and Leaderflex Nano are a radiopaque biostable polyurethane catheters suitable for peripheral venous catheterization (midline) in any patient population with consideration given to the adequacy of vascular anatomy and appropriateness of procedure. Leaderflex Mini and Leaderflex Nano catheters are inserted via Seldinger technique, same as the predicate device. The Leaderflex mini and Leaderflex nano catheters are intended to be used by clinicians such as nurses at in- and out-patient locations. The primary requirement for environment of use is to ensure the environment is appropriate for supporting aseptic technique. These catheters are typically inserted into a peripheral vein on the forearm or leg, with the catheter tip located below the axilla of the arm or below the groin of the leg; however, the catheter is not limited to these anatomical placement locations. This is the same environment of use and anatomical location as the predicate device.
The subject Leaderflex Mini and Leaderflex Nano devices are accompanied by compatible accessories necessary to perform the Seldinger technique; these include: an introducer needle, guidewire, and guidewire insertion aid. The predicate Leaderflex device (K141026) is currently available in 22G configurations with usable lengths of 4cm, 6cm, 8cm and 20cm. The subject device will extend the device configurations to include 24G (Leaderflex Mini) and 26G catheters (Leaderflex Nano) with usable lengths of 2cm, 3cm, and 4cm and will add introducer needle and guidewires.
The subject device also introduces a new guidewire insertion aid for all gauge sizes. The overall device description of the subject and predicate Leaderflex models is the same.

Here's a breakdown of the acceptance criteria and study information for the Leaderflex Mini and Leaderflex Nano devices, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The FDA 510(k) summary focuses on demonstrating substantial equivalence to a predicate device (Leaderflex K141026) rather than defining explicit "acceptance criteria" as pass/fail thresholds for clinical performance metrics (like sensitivity, specificity, accuracy). Instead, the acceptance criteria are implicitly met by demonstrating that the new devices (Leaderflex Mini and Nano) are as safe and effective as the predicate device, despite minor design changes. This is primarily shown through adherence to recognized standards and bench testing.

The "reported device performance" is described through the comparison of technological characteristics and compliance with various international standards for medical devices.

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

This submission is for a medical device (intravascular catheter) which primarily relies on non-clinical (bench) testing and comparison to a predicate device for demonstrating substantial equivalence. It does not involve a "test set" in the context of an AI/algorithm-driven device with a dataset of patient cases.

• Sample Size for Test Set: Not applicable in the context of a dataset of patient cases. Performance testing was conducted on samples of the physical devices.
• Data Provenance: The data provenance for non-clinical testing refers to the standards (e.g., ISO, AAMI, ASTM) that govern the methodologies. The document does not specify a country of origin for the test data, as it's typically bench testing performed by the manufacturer or accredited labs. The testing is prospective in the sense that the tests were performed on the new device designs to demonstrate compliance, but not in the clinical trial sense.

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

Not applicable. This is a physical medical device, not an AI/software device requiring expert-labeled ground truth for a test set of images or clinical outcomes.

4. Adjudication Method for the Test Set

Not applicable. There's no "ground truth" to adjudicate in the typical sense of a diagnostic software. Device compliance is determined by meeting the specified requirements of the various ISO and ASTM standards.

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

Not applicable. This device is an intravascular catheter; it is not an AI-assisted diagnostic tool.

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

Not applicable. This device is not an algorithm or AI.

7. The Type of Ground Truth Used

The "ground truth" for this device's performance is established by the requirements of recognized international and national standards (e.g., ISO 10555-1 for intravascular catheters, ISO 10993-1 for biocompatibility). Device performance is measured against these established engineering and biological criteria through bench testing.

8. The Sample Size for the Training Set

Not applicable. This is a physical medical device. There is no training set as would be used for machine learning.

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

Not applicable. There is no training set.

Ask a specific question about this device

The catheters are indicated for short term access to the peripheral venous system intravenous therapies, blood sampling, and power injection of contrast media. These catheters may be used for any patient with consideration given to adequacy of vascular anatomy and appropriateness of the catheters are suitable for use with power injectors.

The Vygon Midline Catheters are EO sterilized, single-use, polyurethane, reverse taper, short-term, peripheral venous system access catheters. They include materials containing barium sulfate for radiopacity.

The provided text is a 510(k) Summary for the Vygon Midline Catheters. It details the device's characteristics, intended use, and a comparison to a predicate device to demonstrate substantial equivalence. However, it does not describe a study involving an AI/Machine Learning device.

Therefore, I cannot extract information regarding:

• Sample sizes for test or training sets
• Data provenance (country of origin, retrospective/prospective)
• Number of experts or their qualifications for ground truth establishment
• Adjudication methods
• MRMC comparative effectiveness studies or effect sizes
• Standalone algorithm performance
• Type of ground truth (expert consensus, pathology, outcomes)
• How ground truth for the training set was established

The document explicitly states under "Clinical Testing": "No Clinical Testing was performed." This further confirms that the type of study you are asking about (related to AI performance, human reader improvement, and ground truth establishment) was not conducted for this medical device.

The study described is primarily bench testing and biocompatibility testing to demonstrate that the Vygon Midline Catheters are substantially equivalent to a previously cleared predicate device.

Here's the relevant information that can be extracted, pertaining to acceptance criteria and performance for this non-AI medical device:

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

The document lists various bench tests and biocompatibility tests along with their results. The "Acceptance Criteria" are implied by the "Result" column consistently stating "Passed" or specific equivalent findings.

Table of Acceptance Criteria (Implied) and Reported Device Performance

2. Sample sizes used for the test set and the data provenance
The document does not explicitly state the sample sizes (number of devices tested) for each bench or biocompatibility test, nor does it specify data provenance as this is not a study involving human data or image data as typically seen with AI devices. The testing is laboratory-based "bench testing" of the physical devices.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable, as this is a physical medical device clearance, not an AI/ML device where expert ground truth is established. Performance is determined by standardized laboratory tests adhering to ISO standards and internal requirements.

4. Adjudication method
Not applicable.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done
No, this type of study was not performed. The document explicitly states "No Clinical Testing was performed."

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
Not applicable, as this is a physical medical device, not an algorithm.

7. The type of ground truth used
Not applicable for the reasons stated above. The "ground truth" for this device's performance is compliance with international and national standards for medical devices (e.g., ISO, ASTM, FDA guidance) and internal requirements, demonstrated through bench and biocompatibility testing.

8. The sample size for the training set
Not applicable. This is not an AI/ML device.

9. How the ground truth for the training set was established
Not applicable. This is not an AI/ML device.

Ask a specific question about this device

The catheter is indicated for short or long term peripheral access to the central venous system for intravenous therapy, power injection of contrast media, and allow(s) for central venous pressure monitoring, infusion or therapy, use 4 French or larger catheter. The maximum recommended infusion rate is 5mL/section of contrast media. For central venous pressure monitoring, it is recommended that catheter lumen of 20 gauge or larger be used.

The Vygon PICCs are sterile, single-use, polyurethane PICCs with the same intended use, indications for use, similar design, similar sizes, similar or the same materials, and similar properties as the predicate device.

The provided document details the Vygon PICCs device, its intended use, and substantial equivalence to a predicate device, focusing on various performance and safety tests. However, the document does not describe an algorithm or AI-driven device, nor does it present acceptance criteria and performance data in the context of such a device.

Therefore, many of the requested items (e.g., sample size for AI test sets, number of experts for ground truth, MRMC study, standalone performance, training set details) are not applicable to this submission, as it pertains to a physical medical device (Vygon PICCs) and not a software or AI-based diagnostic/screening tool.

The document primarily focuses on bench testing, sterilization testing, and biocompatibility testing to demonstrate that the Vygon PICCs are substantially equivalent to the predicate device (5 Fr DL PowerPICC® Catheter).

Here's an attempt to extract the relevant information based on the provided document, addressing the prompt's categories where applicable:

1. Table of Acceptance Criteria and Reported Device Performance

For a traditional medical device like a PICC, the "acceptance criteria" are typically the satisfactory completion of standardized tests and meeting the requirements outlined in those standards. The "reported device performance" is whether the device "Passed" each test.

2. Sample sized used for the test set and the data provenance:
For a physical device, "sample size" refers to the number of units tested. The document does not explicitly state the sample sizes for each bench, sterilization, or biocompatibility test. The data provenance is internal testing performed by Vygon USA (the submitter). The context implies these are prospective tests conducted on the final device. No country of origin for the data is specified beyond the submitter's location (Lansdale, PA).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
Not applicable. This device is subjected to standardized physical and chemical tests, not an assessment requiring expert "ground truth" derived from clinical cases or images.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
Not applicable. Adjudication methods are relevant for subjective assessments, typically in clinical studies or image interpretations. The tests performed are objective, pass/fail criteria based on adherence to international standards and internal requirements.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
Not applicable. This is not an AI-driven device or study.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
Not applicable. This is not an algorithm.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
Not applicable. The "ground truth" for this device is compliance with established engineering and biological standards and specifications.

8. The sample size for the training set:
Not applicable. This is not an AI/algorithm-based device, so there is no training set.

9. How the ground truth for the training set was established:
Not applicable. There is no training set.

Ask a specific question about this device

The Nutrisafe 2 – ENFit adaptor is indicated for enteral use only. It enables the connection between an administration set equipped with a female ENFit connector at its distal end and a Nutrisafe 2 feeding tube equipped with a male Nutrisafe 2 connector at its proximal end.

The Nutrisafe 2 – ENFit adaptor is indicated for enteral use only. It enables the connection between an administration set equipped with a female ENFit connector at its distal end and a Nutrisafe 2 feeding tube equipped with a male Nutrisafe 2 connector at its proximal end. Vygon has not previously submitted any 510(k)s for the subject device.

The provided text is a 510(k) summary for the "Nutrisafe 2 - ENFit Adaptor" device. It describes the device's indications for use, technological characteristics, and non-clinical testing. However, it does not contain information about acceptance criteria or a study proving the device meets such criteria in the context of an AI/ML device.

The document refers to a "non-clinical verification" through "bench testing" that confirmed physical attributes and device performance meet "the requirements of standards performance." It lists several tests that were performed (dimensional analysis, fluid leakage, stress cracking, resistance to separation, resistance to overriding, disconnection by unscrewing, flow testing, and misconnection risk analysis). However, it does not specify the numerical acceptance criteria for each of these tests, nor does it provide the detailed results of these tests.

Therefore, I cannot fulfill your request for the specific information regarding acceptance criteria and a study proving an AI device's performance. The document describes a traditional medical device (an adaptor) and its regulatory submission, not an AI/ML powered device.

Ask a specific question about this device

Leaderflex catheters are indicated for:

• Arterial catheterization in adults
• Central venous catheterization (jugular, subclavian) in children
• Peripheral venous catheterization (Midline) in any patient population with consideration given to adequacy of vascular anatomy and appropriateness of procedure

Leaderflex is a radiopaque biostable polyurethane catheter suitable for a variety of venous and arterial applications. Leaderflex is inserted via Seldinger technique.

The provided text is a 510(k) Premarket Notification submission for the Leaderflex catheter. The document does not describe an acceptance criteria table, a study proving device performance against such criteria, or any of the detailed study parameters requested in the prompt (sample sizes, expert qualifications, adjudication methods, MRMC studies, standalone performance, ground truth types, or training set details).

Instead, the submission focuses on demonstrating substantial equivalence to predicate devices. This means that the manufacturer is asserting their device is as safe and effective as devices already legally marketed, rather than presenting new clinical study data to prove performance against specific acceptance criteria.

The key points from the provided text are:

• Device: Leaderflex intravascular catheter
• Intended Use: Arterial catheterization in adults, central venous catheterization in children, peripheral venous catheterization (Midline) in any patient population.
• Predicate Devices: Vygon Leaderflex (K052564), Bard Powerglide Midline Catheter (K121073), Bard Poly Per-Q-Cath Midline (K001901).
• Demonstration of Equivalence: The submission states, "Leaderflex is identical to the legally marketed Vygon predicate device. The subject device shares the midline indication with both the Bard Powerglide and Poly Per-Q-Cath Midline catheters. A risk analysis has been completed to show that the safety and effectiveness of the device has not been altered with the addition of the midline indication." This is the core of their argument for substantial equivalence.

Therefore, I cannot populate the requested table or provide information on the study parameters because the document does not contain this type of performance data or study design. The FDA's 510(k) clearance in this case is based on the claim of substantial equivalence to existing devices, not on new clinical performance data meeting specific criteria.

Ask a specific question about this device

For nasogastric/oralgastric enteral feeding, incorporating safety connectors which reduce the risk of misconnections between feeding tubes and intravenous connectors.

The Nutrisafe 2 silicone feeding tubes are utilizing a different formulation of silicone material I he Nutrisate 2 silicone feeding tubes. The feeding tubes. The feeding tubes are available in several than the catisting Nutrioure is a unique connection does not incorporate a luer, reducing SIZCS, and the leveling system connains an IV administration set or other medical delivery the fisk of madvertenity connection reduces the risk of involuntary disconnection; voluntary systems: "The is achieved by simply unscrewing the hub connections.

The Nutrisafe 2 Feeding Tube's acceptance criteria and the study proving its performance are detailed below. It's important to note that this device is a medical device, and the provided text from a 510(k) submission primarily focuses on demonstrating substantial equivalence to predicate devices through non-clinical bench testing, rather than a clinical study with human subjects, AI systems, or extensive statistical performance metrics typically found for diagnostic or AI-driven medical devices.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: The document does not specify a distinct "test set" sample size in terms of the number of feeding tubes or components used for the non-clinical bench testing. It broadly states that "Non-Clinical verification... was conducted through in-vitro bench testing."
• Data Provenance: The data is from in-vitro bench testing, meaning it was conducted in a laboratory setting. The country of origin for the data is not explicitly stated, but the submission is to the US FDA, implying the tests were conducted either by the applicant (Vygon Corp. in Montgomeryville, PA, USA) or a certified laboratory for the purpose of US market approval. The testing is retrospective in the sense that it evaluates the performance of the manufactured device in a controlled environment as part of the market submission process, rather than a prospective clinical trial.

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

This section is not applicable as the provided information describes non-clinical bench testing of a physical medical device, not a diagnostic or AI-driven system requiring expert-established ground truth from images or clinical data. The "ground truth" here is determined by engineering specifications and physical measurements, and the conformity to these is assessed by technical personnel.

4. Adjudication Method for the Test Set

This section is not applicable for the same reasons as point 3. Adjudication methods like 2+1 or 3+1 are used for resolving disagreements among multiple human readers on a diagnosis or interpretation, which is not relevant to the described non-clinical bench testing.

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

This section is not applicable. The provided document is for a physical medical device (feeding tube) and does not involve AI assistance, human readers, or image interpretation. Therefore, an MRMC study or effect size calculation with AI assistance is not relevant.

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

This section is not applicable. The device is a physical feeding tube, not an algorithm or software. Therefore, standalone algorithm performance is not relevant.

7. The Type of Ground Truth Used

The ground truth used for this premarket notification is based on engineering specifications and intended use requirements. The non-clinical bench testing verified that the Nutrisafe 2 Feeding Tube, despite a change in silicone material formulation, continued to meet these established specifications and its intended use, which includes safety features related to connection types.

8. The Sample Size for the Training Set

This section is not applicable. There is no "training set" in the context of this device's non-clinical verification. Training sets are relevant for machine learning algorithms, which are not part of this submission. Device manufacturers conduct design and development activities where prototypes might be tested, but this is distinct from an "AI training set."

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

This section is not applicable as there is no training set for this device.

Ask a specific question about this device

For nasogastric/oralgastric enteral feeding, incorporating safety connectors which reduce the risk of misconnections between feeding tubes and intravenous connectors.

The Nutrisafe 2 feeding tubes are a product line extension to the existing Nutrisafe 2 feeding tubes. The subject feeding tubes are available in several sizes and in two materials. The feeding system contains a unique connection that does not incorporate a luer, reducing the risk of inadvertently connecting to intravenous connectors. The locking connection reduces the risk of involuntary disconnection; voluntary disconnection is achieved by simply unscrewing the hub connections.

The provided text describes a 510(k) premarket notification for a medical device, the Nutrisafe 2 Feeding Tube, and its substantial equivalence to a predicate device. However, it does not involve an AI/ML device or a study that evaluates its performance against acceptance criteria in the way described in your request. The document focuses on the regulatory clearance process for a common medical device (feeding tube) based on its technological characteristics and intended use, rather than an AI algorithm's diagnostic or predictive capabilities.

Therefore, many of the requested categories in your prompt are not applicable to the provided information. I will, however, outline what can be extracted from the text in relation to your request.

Summary of Provided Information Regarding Acceptance Criteria and Study:

The provided document, K100163, is a 510(k) summary for a medical device (Nutrisafe 2 Feeding Tube), which is a product line extension. This type of regulatory submission assesses substantial equivalence to a predicate device, rather than proving performance against specific quantitative acceptance criteria of an AI model.

The "study" mentioned is a non-clinical verification through in-vitro bench testing. This type of testing ensures the device meets its specifications and intended use, primarily focusing on physical and functional characteristics suitable for a feeding tube, such as the integrity of the connection system, material compatibility, and flow rates. It does not involve human subjects, comparison to AI, or expert adjudication of outcomes.

Here's how the information aligns (or doesn't align) with your request categories:

1. Table of Acceptance Criteria and Reported Device Performance: This kind of quantitative data (e.g., sensitivity, specificity, AUC) is not present because this is a physical medical device, not an AI/ML diagnostic tool. The general "acceptance criteria" for this device would be its ability to meet specifications for a feeding tube as determined by the in-vitro bench testing.

   Metric/Criteria	Reported Device Performance
   All Specifications and Intended Use	"meets all specifications and intended use."

2. Sample size used for the test set and the data provenance: Not applicable in the context of an AI/ML device. The "test set" here would refer to the physical samples of the Nutrisafe 2 Feeding Tubes used in the in-vitro bench testing. The document does not specify the number of tubes tested, nor their manufacturing origin beyond "Vygon, Montgomeryville, PA 18936." This was in-vitro testing, not human data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth, in the context of an AI/ML model, refers to validated diagnoses or outcomes. For a physical feeding tube, "ground truth" is established by engineering standards and functional tests. No external experts or adjudication were involved in establishing "ground truth" for the device's functional performance beyond the internal verification process.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not applicable. This method is used for resolving discrepancies in expert labeling or diagnoses for AI/ML validation datasets.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: Not applicable. This study type is for evaluating the impact of AI assistance on human diagnostic performance. The Nutrisafe 2 Feeding Tube is a standalone medical device, not an AI component.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Not applicable. This refers to the performance of an AI algorithm alone.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): For this device, the "ground truth" for its performance is derived from engineering specifications and in-vitro functional and safety testing results. For example, the "locking connection reduces the risk of involuntary disconnection" is a functional characteristic tested against design requirements.

8. The sample size for the training set: Not applicable. This device does not have a "training set" in the context of AI/ML.

9. How the ground truth for the training set was established: Not applicable.

In summary, the provided document describes a traditional medical device (feeding tube) and its regulatory clearance based on substantial equivalence and non-clinical bench testing, not an AI/ML device. Therefore, most of the detailed questions regarding AI/ML study methodologies are not relevant to this specific premarket notification.

Ask a specific question about this device

The Neurocath Ag catheter is designed to be temporarily implanted (less than 30 days) for the drainage of cerebrospinal fluid (CSF) to reduce and control increased intracranial pressure.

The Neurocath Ag is an external drainage catheter composed of polyurethane and impregnated with the silver ions for the purpose of radionacity. The catheter is available with 3 holes off-set at 120" or 16 holes, in lengths of 32, 23.5, and 15.5cm. Biocompatibility and performance testing demonstrates the safety and efficacy of these devices. The Neurocath Ag is supplied with a stainless steel stylet (for introducing it into the ventricle), a stainless steel subgaleal trochar (for tunneled catheter placement), a male luer connector, a slitted wing and a compression hub (for connecting the cathetex to the tubing set). The Neurocath Ag eatherer is available individually or packaged with the tubing set.

The provided text describes a 510(k) premarket notification for a medical device called Neurocath Ag, an external drainage catheter. This type of submission focuses on demonstrating substantial equivalence to a predicate device, rather than proving novel effectiveness through clinical studies with specific acceptance criteria.

Therefore, the document does not contain the information requested regarding acceptance criteria, a study proving the device meets acceptance criteria, sample sizes for test/training sets, data provenance, number or qualifications of experts, adjudication methods, MRMC studies, standalone performance studies, or type of ground truth used in such studies.

The document states:

• "Biocompatibility and performance testing demonstrates the safety and efficacy of these devices."
• "Biocompatibility testing of the material demonstrate that it is nonirritant and non-toxic. Performance testing demonstrates that the changes do not affect safety or efficacy. Risk Assessment was conducted in compliance with ISO 14971."
• "Biocompatibility testing, performance testing and risk assessment demonstrate that the Neurocath Ag is safe and effective to use, when used in accordance with the supplied instructions for use."

These statements indicate that some type of testing was performed, but they do not provide the detailed information requested in your prompt. The focus of this 510(k) summary is on demonstrating equivalence to predicate devices, particularly highlighting a change in material (from barium impregnated silicone and silver impregnated silicone to polyurethane impregnated with silver ions) and asserting that this change does not negatively impact safety or efficacy based on testing.

Ask a specific question about this device