Search Results

For vascular access devices flushing only. Sterile fluid path only. Not for use on a sterile field.

The Praxiject™ SP 0.9% NaCl prefilled syringe is a single use plastic piston syringe with a Luer lock connection fitting, prefilled to labeled volume of 10mL with 0.9% Sodium Chloride Injection, USP, with no preservatives (normal saline), and capped with a plastic tip cap. The Praxiject™ SP 0.9% NaCl prefilled syringe is designed to maintain a sterile fluid path only and is individually packaged in a clear flexible plastic film, flow-wrapped heatsealed pouch that functions only as a protective barrier (dust cover). The device is terminally sterilized by gamma irradiation.

The provided text is a 510(k) Pre-market Notification for a medical device called Praxiject™ SP 0.9% NaCl, a prefilled saline flush syringe. The document describes the device, its intended use, comparison to a predicate device, and non-clinical testing performed to demonstrate substantial equivalence. It explicitly states that "Clinical testing was not required for device evaluation."

Therefore, based on the information provided, it's not possible to answer questions related to clinical studies, human reader performance, multi-reader multi-case (MRMC) studies, or the establishment of ground truth for a test set or training set in the context of an AI/algorithm-driven device. This document describes a medical device, not an AI/ML algorithm.

However, I can extract information related to the acceptance criteria and the non-clinical study that proves the device meets those criteria, as detailed in the "Summary of Non-Clinical Testing" section.

Here's the breakdown of the acceptance criteria and reported device performance from the non-clinical testing:

Acceptance Criteria and Reported Device Performance (Non-Clinical Testing)

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

The document provides a table outlining performance characteristics, the applicable performance standards, and the acceptance criteria. It then states, "The design and manufacturing of the Praxiject™ SP 0.9% NaCl prefilled syringe is subject to risk assessment per ISO 14971 and verification and validation testing in conformance with regulatory guidance and consensus standards applicable to this device type." This implies that the device successfully met all listed acceptance criteria through this testing, although specific "reported device performance" values are not explicitly given in the table beyond the acceptance limits.

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

The document does not specify sample sizes for each non-clinical test beyond implication from standard compliance. These tests are typically conducted on batches of manufactured devices following established quality control procedures. Given the manufacturing details, data provenance would be MedXL Inc., Canada. The testing is prospective in nature, as it's part of the pre-market validation for the device.

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. This is not an AI/ML device requiring human expert annotation or ground truth establishment in the traditional sense. The "ground truth" for non-clinical testing of a physical medical device refers to the objective, measurable properties and performance standards themselves, verified by laboratory testing protocols and validated analytical methods (e.g., chemical assays, sterility tests, physical integrity tests).

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

Not applicable, as this is not a study involving subjective human interpretation or multi-reader scenarios. The testing involves objective, measurable 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 is a prefilled saline flush syringe, not an AI-assisted diagnostic or therapeutic tool.

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

Not applicable. The "device" itself is a physical medical product, not an algorithm.

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

For non-clinical testing of this device, the "ground truth" is defined by established consensus standards and pharmacopeial specifications (e.g., USP standards, ISO standards) for chemical composition, sterility, physical integrity, and biological safety. These are objective, measurable parameters.

8. The sample size for the training set

Not applicable. This is not an AI/ML device that requires a training set.

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

Not applicable.

Ask a specific question about this device

Flush Syringe (Prefilled 0.9% normal saline solution) is intended for use in flushing compatible intravenous administration sets and indwelling intravenous access devices.

Flush Syringe (Prefilled 0.9% normal saline solution) is a polypropylene plastic syringe filled with 0.9% sodium chloride for injection, USP, and capped with a polypropylene syringe tip cap. The Flush Syringe (Prefilled 0.9% normal saline solution) consists of barrel, plunger, gasket and thread stopper which is used after the intended purpose is achieved to cover the barrel tip of the device. The Flush Syringe (Prefilled 0.9% normal saline solution) is sterile, non-pyrogenic and for single use.

The provided document describes the acceptance criteria and a summary of non-clinical testing for the "Flush Syringe (Prefilled 0.9% normal saline solution)". This is a medical device, and the testing outlined is for its safety and performance, not for an AI model. Therefore, many of the requested fields related to AI/algorithm performance (e.g., effect size of human readers with AI assistance, standalone algorithm performance, training set details) are not applicable.

Here's the information extracted from the provided text, focusing on the device's acceptance criteria and the study proving it:

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)

The document does not specify the exact sample sizes for each test conducted. It only lists the tests performed, the methods used, and the acceptance criteria. The provenance of the samples (e.g., country of origin, retrospective/prospective) is also not mentioned. These tests are laboratory-based non-clinical tests rather than studies involving patient data.

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. This is a medical device, and the performance testing is based on established international and national standards and laboratory methods, not expert interpretation of outputs like in AI/CAD systems.

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

Not applicable. Adjudication methods like 2+1 or 3+1 are typically used in clinical studies or for establishing ground truth in AI model evaluations, not for the direct physical and chemical testing of a sterile medical device.

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 document is for the premarket notification of a physical medical device (flush syringe), not an AI or CAD system. Thus, 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. This device is not an algorithm or AI system.

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

The "ground truth" for this device is established by adherence to recognized consensus standards and validated chemical/physical testing methods (e.g., ISO, ASTM, USP). The acceptance criteria for each test (e.g., pH range, bacterial endotoxin limits, physical strength) serve as the objective ground truth.

8. The sample size for the training set

Not applicable. This device is not an AI model, so there is no training set.

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

Not applicable. There is no training set for a physical medical device.

Ask a specific question about this device

The Hantech Pre-filled 0.9% Normal Saline Flush Syringes, are in flushing compatible intravenous administration sets and indwelling intravenous access devices. Use according to the manufacturer for the appropriate device.

The Hantech Pre-filled 0.9% Normal Saline Flush Syringes is a polypropylene plastic syringe filled with 0.9% sodium chloride for injection, USP, and capped with a polypropylene syringe tip cap. The device will be marketed as 10mL syringe with a 3mL, 5mL or10mL fill volume according to the market needs. It is terminally sterilized by steam sterilization. The product has a shelf life of 1 years.

The provided document (K231363) is a 510(k) summary for Hantech Pre-filled 0.9% Normal Saline Flush Syringes. This type of device is a sterile medical product, not an AI/ML-driven diagnostic or image analysis tool.

Therefore, the concepts of acceptance criteria, test sets, ground truth establishment by experts, MRMC studies, standalone algorithm performance, and training sets do not apply in the context of this device and the information provided in the 510(k) summary.

The document describes non-clinical bench testing to demonstrate the substantial equivalence of the Hantech Pre-filled 0.9% Normal Saline Flush Syringes to a legally marketed predicate device. The "acceptance criteria" here refer to the predefined standards and limits for the physical, chemical, and biological properties of the syringe and its contents, as well as the sterilization process, which are based on recognized international and national standards (e.g., ISO, USP).

Here's an interpretation of the relevant information provided:

1. Table of Acceptance Criteria and Reported Device Performance:

The document provides a table summarizing the non-clinical testing performed. The "Acceptance criteria" column lists the standards/criteria the device must meet, and the "Conclusion" column indicates "Pass" for all tests, meaning the device met these criteria.

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

The document explicitly states "Summary of clinical Testing: N/A," meaning no clinical trials were conducted. The testing described is bench testing (laboratory-based, non-human, non-animal testing) of the physical product, its components, and its contents. The sample sizes for each specific test (e.g., how many syringes were tested for dimensions, or how many batches for chemical composition) are not provided in this summary document. Data provenance would be the manufacturer's internal testing facilities in China. The testing is prospective in the sense that it was conducted specifically for this 510(k) submission to demonstrate compliance.

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

This question is not applicable. The "ground truth" for a medical device like a syringe is established by validated measurement methods and recognized standards, not by expert consensus on clinical findings. For example, the pH of the saline is measured by a pH meter against a standard, not by an expert's opinion.

4. Adjudication Method for the Test Set:

Not applicable. This concept is relevant for studies involving human interpretation or subjective assessments, like image reading, not for objective bench testing of a physical product.

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

No, an MRMC study was not done. This type of study is typically performed for diagnostic devices (e.g., AI in radiology) where the performance of human readers, with and without AI assistance, is compared. This device is a pre-filled saline syringe.

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

No, this concept is entirely irrelevant for a medical device such as a pre-filled saline syringe. This applies to AI/ML algorithms.

7. The Type of Ground Truth Used:

The "ground truth" (or more accurately, the reference standard) for this device's performance is based on:

• Recognized consensus standards: International Organization for Standardization (ISO) standards (e.g., ISO 7886-1, ISO 80369-7, ISO 10993 series)
• United States Pharmacopeia (USP) monographs and general chapters: (e.g., USP for pH, USP for identification tests, USP for particulate matter, USP for Bacterial Endotoxins, USP31- for Sterility tests, USP monographs for Sodium Chloride Injection)
• Manufacturer's internal specifications: Which must meet or exceed these recognized standards.

8. The Sample Size for the Training Set:

Not applicable. This device is not an AI/ML algorithm that requires a "training set."

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

Not applicable, as there is no training set for this type of device.

Ask a specific question about this device

The Pre-Filled Normal Saline Flush Syringe is intended to be used only for the flushing vascular access devices.

Not Found

I am sorry, but the provided text does not contain information about acceptance criteria or a study proving that a device meets those criteria. The document is an FDA 510(k) clearance letter for a medical device called "TK Pre-Filled Normal Saline Flush Syringe."

The letter acknowledges the submission of a premarket notification and states that the device is substantially equivalent to legally marketed predicate devices. It also outlines regulatory requirements but does not include details about performance testing, study designs, sample sizes, ground truth establishment, or expert qualifications.

Therefore, I cannot generate the requested table and information based on the given input.

Ask a specific question about this device

Pre-Filled Normal Saline Flush Syringe is intended for use in flushing compatible intravenous administration sets and indwelling intravenous access devices. Use according to the recommendations of the manufacturer for the appropriate device.

Pre-Filled Normal Saline Flush Syringe is a polypropylene syringe filled with 0.9% sodium chloride for injection. It contains 3ml, 5ml and 10ml and consists of tip cap, barrel, piston, and plunger. This is a single use, disposable device(s), provided sterile.

The provided document is a 510(k) summary for a medical device called "Pre-Filled Normal Saline Flush Syringe." This document focuses on demonstrating substantial equivalence to a legally marketed predicate device through non-clinical testing. It does not describe a study involving an AI/CADe device or human readers. Therefore, I cannot provide information regarding acceptance criteria and studies typical for AI/CADe devices, such as those related to multi-reader multi-case studies, effect size of AI assistance, expert qualifications, or ground truth establishment for training and test sets in an AI context.

However, I can extract the acceptance criteria and performance data for the non-clinical (bench) tests conducted on the Pre-Filled Normal Saline Flush Syringe to demonstrate its safety and effectiveness.

Here's the information based on the provided text, specifically from Section VII "Summary of Non-clinical Testing (Bench)":

1. Table of Acceptance Criteria and the Reported Device Performance

Note on ISO standards in the table: There appears to be a typo for test IDs 4.2 and 4.3 in the provided document (ISO 10995 instead of ISO 10993 for biocompatibility tests). I have kept the text as written but noted the likely correct standard.

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

• Sample Size: "Real time aged samples from three non-consecutive lots were tested for all performance criteria."
• Data Provenance: The document does not specify the country of origin for the test samples or explicitly state if the study was retrospective or prospective. It implies prospective testing of manufactured lots.

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 non-clinical, bench testing study for a physical medical device, not an AI/CADe device requiring expert-established ground truth from medical images or patient data.

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

Not applicable, as this is bench testing. The results are based on objective measurements against established standard 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

No, an MRMC comparative effectiveness study was not done. This device is not an AI/CADe device, and the study did not involve human readers or AI assistance.

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

Yes, in a sense. The "device" in this context is the physical syringe. The performance tests conducted are standalone tests of the device itself (its materials, chemical contents, physical properties, and biocompatibility), without specific human-in-the-loop performance measurement beyond standard laboratory procedures.

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

The "ground truth" for this device's performance is established by internationally recognized consensus standards (e.g., ISO, USP, AAMI TIR) which define the acceptable limits and test methodologies for the physical, chemical, and biological properties of the device.

8. The sample size for the training set

Not applicable. This is not an AI/ML device that requires a training set.

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

Not applicable. This is not an AI/ML device that requires a training set or ground truth establishment for it.

Ask a specific question about this device

The 0.9% Sodium Chloride Injection, USP, BD PosiFlush™ SF Saline Flush Syringes are intended to be used only for the flushing of indwelling vascular access devices.

0.9% Sodium Chloride Injection, USP, BD PosiFlush™ SF Saline Flush Syringe is a polypropylene syringe intended to flush indwelling vascular access devices. It is a sterile, single use syringe prefilled with 0.9% sodium chloride injection, USP, and sealed with a tip cap. The device is packaged in a film-on-film blister pack and sterilized by gamma irradiation. External sterility of the device enables it to be used in the sterile field. The subject device is available only in 10mL syringe configuration.

This document pertains to the 510(k) premarket notification for the "0.9% Sodium Chloride Injection, USP BD PosiFlush™ SF Saline Flush Syringe," a medical device, not an AI/ML-driven device or an imaging system. Therefore, the questions regarding AI/ML performance metrics, expert consensus for ground truth, MRMC studies, or training/test set details are not applicable to this submission.

This submission focuses on demonstrating substantial equivalence to a predicate device (K153481) through bench performance testing, packaging integrity, and biocompatibility tests. The "acceptance criteria" here refer to the specifications for these non-clinical tests, rather than diagnostic performance metrics of an AI model.

Here's the information extracted that aligns with the request, re-interpreting "acceptance criteria" and "study" in the context of this device's submission:

1. Table of Acceptance Criteria and Reported Device Performance

Note 1: Result is a qualitative statement, not a numerical pass/fail against a specific threshold listed in the table.

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

The document does not specify numerical sample sizes for each of the performance, packaging, or biocompatibility tests. It only states that "appropriate performance tests and biocompatibility tests were performed" and the gamma sterilized test samples were evaluated. The data provenance (country of origin, retrospective/prospective) is also not specified, as these are bench and lab-based tests, not clinical studies involving patient data.

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

Not applicable. This submission is for a physical medical device, not an AI/ML imaging device. Ground truth, in this context, refers to the established standards, monograph requirements (e.g., USP, ISO), and validated internal specifications to which the device performance is measured against. Experts here would be the laboratory personnel and engineers performing the tests and
interpreting results against these defined criteria, but their specific number or detailed qualifications are not provided in the summary.

4. Adjudication Method for the Test Set:

Not applicable. Since this is not an AI/ML diagnostic device, there is no "adjudication" of expert opinions on image interpretation. The tests performed are laboratory or bench-based, with results measured against predetermined quantitative or qualitative acceptance 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. This is not an AI/ML device, and no MRMC study was performed. The device's safety and effectiveness are demonstrated through non-clinical performance, packaging, and biocompatibility testing.

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

Not applicable. This device is a physical product (saline syringe), not an algorithm or software. No standalone algorithm performance was assessed.

7. The Type of Ground Truth Used:

The "ground truth" for this device's evaluation is primarily based on:

• Established Standards: e.g., ISO 10993 series for biocompatibility, ASTM F2096-11 for vacuum bubble leak, ANSI AAMI ST72:2019 for Bacterial Endotoxins.
• Pharmacopoeia Monographs: e.g., USP43-NF38 for NaCl Injection, pH, Iron, Heavy Metals, Particulate Matter, Bacterial Endotoxin.
• Validated Internal Specifications: "BD validated force" or "BD validated internal value" for mechanical/physical properties like tip cap removal torque, reflux, breakout force, sustaining force, retaining ring force, and seal strength.
• Qualitative Observations: e.g., "No evidence of Tip Cap leakage," "No leakage of solution past the stopper ribs," "Solution and components are clear," "No defects in packaging seals when visually inspected."

Essentially, the ground truth is defined by recognized industry standards, pharmacopoeial requirements, and the manufacturer's own validated specifications for product performance and safety.

8. The Sample Size for the Training Set:

Not applicable. This is not an AI/ML device; there is no "training set."

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

Not applicable. As there is no training set for an AI/ML model, this question does not apply.

Ask a specific question about this device

The Praxiject™ 0.9% NaCl prefilled syringe with 0.9% Sodium Chloride Injection, USP, is intended only for flushing vascular access devices. May be placed on a sterile field.

The Praxiject™ family of 0.9% NaCl prefilled syringes marketed in the U.S.A. includes the following models: 37043US (3 mL/5 cc), 3704US (5 mL/5 cc), 37053US (3 mL/10 cc), 37055 US (5 mL/10 cc), 3705CUS (10 mL/10 cc), 3705-1US (10 mL/10 cc) and 3706US (20 mL/20 cc). These devices are single use plastic piston syringes with a Luer lock connection fitting, prefilled to labeled volume with 0.9% Sodium Chloride Injection USP, with no preservatives (normal saline), and capped with a plastic tip cap. Model 3705-1US (10 mL/10 cc) is individually packaged in a heat-sealed foil pouch, all other models are individually packaged in a heat-sealed peel pouch. All Praxiject™ 0.9% NaCl prefilled syringes are terminally sterilized by gamma irradiation.

The provided document is a 510(k) Pre-Market Notification for a medical device called Praxiject™ 0.9% NaCl, which is a prefilled saline flush syringe. The purpose of this notification is to demonstrate that the modified device is substantially equivalent to legally marketed predicate devices.

The document does not describe a study involving an AI/ML device, a "test set" of data, or "ground truth" as typically understood in the context of evaluating AI/ML performance. Instead, it details the analytical and performance testing conducted for a physical medical device to ensure its safety and effectiveness.

Therefore, many of the requested categories (2, 3, 4, 5, 6, 7, 8, 9) are not applicable to this document as they are specific to AI/ML device evaluation.

However, I can extract information related to acceptance criteria and device performance based on the non-clinical testing summary.

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

The document provides a comprehensive table of "Device Specification," "Standard," and "Acceptance Criteria" under the "Summary of Non-Clinical Testing" section. The "reported device performance" is implicitly stated as meeting these acceptance criteria, as the conclusion states, "The conclusions drawn from the non-clinical testing demonstrate that the modified Praxiject™ 0.9% NaCl prefilled syringe, is as safe, as effective, and performs as well as or better than the legally marketed primary predicate device." This implies all listed acceptance criteria were met.

Here is a summary of the acceptance criteria:

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

This information is not provided in a way that is applicable to an AI/ML "test set." The document describes non-clinical testing of a physical device. While specific sample sizes and testing methodologies are implied by the listed standards (e.g., ISO, ASTM, USP), the exact sample sizes for each test are not explicitly enumerated in this summary. Data provenance, in terms of country of origin or retrospective/prospective collection, is not relevant for this type of device submission.

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. "Ground truth" and "experts" are terms used in the context of evaluating diagnostic AI/ML models. This document describes the physical and chemical testing of a medical device.

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

Not applicable. This refers to methods for resolving discrepancies in expert interpretations, which is not relevant for physical device 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

Not applicable. This is a type of study specifically for evaluating AI/ML diagnostic tools.

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

Not applicable. This refers to the standalone performance of an AI/ML algorithm.

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

Not applicable. The "ground truth" for this device's performance is objective measurements against established international and USP standards for product quality, safety, and performance (e.g., pH, sterility, particle count, leakage, biocompatibility).

8. The sample size for the training set

Not applicable. This concept pertains to AI/ML model development.

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

Not applicable. This concept pertains to AI/ML model development.

Ask a specific question about this device

Pentaflush saline 0.9% NaCl prefilled syringe is intended only for flushing in situ vascular access devices. May be placed on a sterile field. Pentaflush saline 0.9% NaCl prefilled syringe is intended for single patient and single use only.

The PentaFlush saline 0.9% NaCl prefilled syringe is a single-use device intended only for flushing in-situ vascular access devices. It is a polypropylene syringe containing an isotonic solution of sterile and non-pyrogenic 0.9% sodium chloride solution. These are ready for use devices that can be placed on sterile field. The product is available in volumes of 3ml, 5ml and 10ml of saline solution in 10 ml syringes, which has a larger diameter in order to avoid that, with the same force applied on the shaft button, the higher pressure generated in the 3ml capacities may cause the vascular catheter to rupture. What differentiates the three versions is the graduated scale, whose maximum capacity coincides with the nominal capacity of each version (3ml, 5ml and 10ml). In all capacities Luer Lock connector of the barrel is closed with a cap. The barrel is filled with a 0.9% NaCl isotonic solution, sterile, pyrogen-free, up to the nominal capacity of the scale; an acitotoxic synthetic rubber piston is assembled to the polypropylene plunger, whose fiducial line is positioned at the nominal capacity of the syringe. The primary packaging of PentaFlush pre-filled syringes can be in: a blister of medical paper and PE/PE peel, or an aluminum pouch of PET/ALL/PE peel. PentaFlush saline 0.9% NaCl prefilled syringes are used only by healthcare professionals, is intended for single patient and single use only. Does not contain preservatives. Not made with natural rubber latex. Rx Only.

This document describes the non-clinical testing for the PentaFlush saline 0.9% NaCl prefilled syringe. This device is an "Intravascular catheter" (Product Code: NGT) used for flushing in-situ vascular access devices. The study conducted is a non-clinical study to demonstrate conformance to applicable standards.

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

1. Table of Acceptance Criteria and Reported Device Performance

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

The document describes non-clinical testing performed on the device itself and its components. It does not refer to a "test set" in the context of patient data or clinical samples. The tests mentioned are laboratory-based and generally involve a specified number of samples of the device and its materials as required by the referenced standards. The data provenance is Pentaferte Italia S.r.l., based in Italy. The tests are prospective in the sense that they are conducted on the manufactured device to verify its compliance with standards.

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

This point is not applicable to the provided document. The study described is a non-clinical, laboratory-based testing of a medical device's physical, chemical, and biological properties according to established international standards. The "ground truth" is determined by the specific criteria outlined in each standard for each test, not by expert consensus on clinical data.

4. Adjudication method for the test set

This point is not applicable to the provided document. Adjudication methods like 2+1 or 3+1 typically refer to clinical studies involving multiple readers for interpreting medical images or data. The non-clinical tests described have predefined pass/fail criteria based on the relevant 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

This point is not applicable. The device is a prefilled saline syringe, not an AI-powered diagnostic or assistive tool for human readers.

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

This point is not applicable. The device is a medical product (prefilled saline syringe), not an algorithm.

7. The type of ground truth used

The ground truth used for these non-clinical tests is based on established international and national standards and monographs. For example, USP monographs for chemical assays, ISO standards for biocompatibility and sterilization, and ASTM standards for mechanical testing. These standards define the acceptable limits and methodologies against which the device performance is measured.

8. The sample size for the training set

This point is not applicable. The study is a non-clinical performance verification, not a study involving machine learning or AI that would require a training set.

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

This point is not applicable for the reasons mentioned in point 8.

Ask a specific question about this device

The Pre-filled Syringe with Saline is intended for use in flushing compatible intravenous administration sets and indwelling intravenous access devices. Use according to the recommendations of the manufacturer for the appropriate device.

Not Found

This document is an FDA 510(k) clearance letter for a "Pre-filled Syringe with Saline." It does not contain any information about acceptance criteria or a study proving device performance as would be relevant for an AI/ML or diagnostic device.

The provided text deals with:

• The FDA's determination of substantial equivalence for a medical device (a pre-filled saline syringe).
• Regulatory classifications and requirements for medical devices.
• Indications for Use for the specific device.

Therefore, I cannot provide the requested information about acceptance criteria and a study proving device performance because the document does not discuss these aspects for an AI/ML or diagnostic device. The device in question is a simple medical device (a saline syringe), not one that would typically undergo the kind of performance studies involving AI, ground truth, expert readers, or MRMC studies.

Ask a specific question about this device

The AMSafe® Pre-Filled Normal Saline Flush Syringe, is intended for use in flushing compatible intravenous administration sets and indwelling intravenous access devices. Use according to the recommendations of the manufacturer for the appropriate device.

AMSafe® Pre-Filled Normal Saline Flush Syringe is a polypropylene plastic syringe filled with 0.9% sodium chloride for injection, USP, and capped with a polypropylene syringe tip cap.

This document describes the premarket notification (510(k)) for the AMSafe® Pre-Filled Normal Saline Flush Syringe. The information provided outlines the device's technical characteristics, intended use, and comparison to a legally marketed predicate device (K183473). The study performed is a non-clinical bench testing study, not an AI/ML-based clinical study, therefore, many of the requested elements for an AI/ML study (e.g., sample size for test set, number of experts, MRMC study, training set details) are not applicable.

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

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria and reported device performance are detailed in "Table 5-2" on page 6 of the document.

Additionally, shelf life was evaluated:

• Test: Shelf life
• Method: ASTM F1980-16
• Acceptance Criteria/Conclusion: Verify that the device will remain within specification during the prescribed shelf life when stored under labeled conditions. (Implied Pass, as per overall conclusion).

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

The document describes non-clinical bench testing of manufacturing characteristics and chemical composition, not an AI/ML-based study with a "test set" composed of patient data. Therefore, the concept of sample size for a test set (e.g., number of images, patient records) and data provenance (country of origin, retrospective/prospective) as typically understood for AI/ML studies are not applicable. The tests were performed on samples of the device itself. The specific number of units tested for each criterion is not provided, but it would typically be a predetermined number based on the statistical requirements of the specific test methods (e.g., ISO, ASTM, USP standards).

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

Not Applicable. This was a bench study, not an AI/ML study requiring expert labeling of data. The "ground truth" for these tests are the established physical, chemical, and biological standards and methodologies outlined in the referenced ISO, ASTM, and USP documents.

4. Adjudication Method for the Test Set

Not Applicable. This was a bench study; there was no human-in-the-loop expert adjudication process as would be typical for AI/ML algorithm evaluation.

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

No, an MRMC study was not done. This is a review of a physical medical device (pre-filled syringe), not an AI/ML diagnostic or assistive tool where human reader performance would be a relevant metric.

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

Not Applicable. This document describes the performance of a physical medical device, not an algorithm.

7. The Type of Ground Truth Used

The "ground truth" for the non-clinical tests is based on established industry standards and pharmacopeial specifications. This includes:

• Physical Properties: Standards like ISO7886-1, ISO80369-7, ASTM F2338-09.
• Chemical Composition: United States Pharmacopeia (USP) monographs such as USP, USP, USP6-466, USP6-471, USP, USP, USP, USP.
• Biocompatibility: ISO10993 series (ISO10993-11, ISO10993-10, ISO10993-5) and ASTM F756-17.
• Sterility Assurance: The mention of 10-6 SAL (Sterility Assurance Level) indicates adherence to established sterilization standards.

8. The Sample Size for the Training Set

Not Applicable. This is a physical device, not an AI/ML algorithm that requires a training set.

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

Not Applicable. As there is no training set for a physical device, there is no ground truth establishment process in that context.

Ask a specific question about this device