Search Results

It is intended to be used with vein puncture needle and vacuum blood collection tube for multiple collections of venous blood. It is for adult use only.

Blood collection tube holders is single use and sterile, it is intended to be used with vein puncture needle and vacuum blood collection tube for multiple collections of venous blood. It is sterile and to be used for assisting blood collection. The device consists of a puncture needle hub, puncture needle, rubber boot and holder. It is packaged in a sealed sterility barrier. This is a single-use device and delivered sterile. Sterilization process is validated according to EN ISO 11135. Shelf life is 5 years.

This FDA 510(k) clearance letter is for a Blood Collection Tube Holder, which is a Class II medical device. The information provided heavily focuses on the comparison to a predicate device and nonclinical (bench) testing, rather than AI-specific criteria. This document does not contain any information about an AI/ML powered device, therefore the specific requests for AI-related study details (MRMC studies, standalone algorithm performance, training set details, expert ground truth adjudication) cannot be answered from the provided text.

However, I can extract the relevant information for the device's acceptance criteria and the study that proves it meets them based on the provided document.

Device: Blood Collection Tube Holders
Device Type: Medical Device (Non-AI/ML specific, per the provided document)
Regulatory Class: Class II

1. Table of Acceptance Criteria and Reported Device Performance

Given that this is a non-AI/ML physical medical device, the "acceptance criteria" are based on compliance with established international standards and successful performance in specific physical and biological tests.

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

• Sample Size: The document does not specify the exact sample sizes (number of devices) used for each nonclinical performance test (e.g., puncture force, tensile strength). It generally states "Performance testing was conducted."
• Data Provenance: Not explicitly stated for each test, but the manufacturer is Promisemed Hangzhou Meditech Co., Ltd. in China, implying testing was likely conducted in China or by labs serving Chinese manufacturers. The testing itself is nonclinical (bench) testing, not human data. It is inherently "prospective" in the sense that the tests were performed on newly manufactured devices for the submission.

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 a physical medical device (blood collection tube holder), not an AI/ML system requiring expert interpretation of medical images or data for ground truth. The "ground truth" for this device's performance is established by objective physical and chemical measurements against internationally recognized standards (ISO, ASTM) and internal engineering specifications, not human expert consensus.

4. Adjudication method for the test set

• Not applicable. As above, this is for physical device performance testing, not interpretive data requiring adjudication. Compliance is determined by meeting the specified thresholds or parameters of 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

• Not applicable. This document describes a physical medical device (blood collection tube holder), not an AI-powered diagnostic or assistive tool. Therefore, MRMC studies are not relevant.

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

• Not applicable. This document describes a physical medical device, not an AI algorithm.

7. The type of ground truth used

• The "ground truth" for this device's performance is established by objective, measurable criteria defined by international standards (e.g., ISO, ASTM) and engineering specifications. Examples include specific force measurements, material properties, sterility levels, and biological reactivity thresholds. These are derived from established scientific and engineering principles for medical device safety and efficacy.

8. The sample size for the training set

• Not applicable. This is a physical medical device, not an AI/ML model where "training sets" are used.

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

• Not applicable. See point 8.

Ask a specific question about this device

The needle is used to access surgically implanted vascular ports.

Safety Huber Needles is a standard non coring intravascular infusion set with a non-coring Huber type right angle needle and a manually activated needle stick prevention safety mechanism which reduces the risk of accidental needlestick injuries by sheathing the needle. This device is for adult use only.

In addition, when used with ports that are indicated for power injection of contrast media into the central venous system, the high pressure resistant model is indicated for high-pressure injection of contrast media for CT imaging.

Safety Huber Needle is a standard non-coring intravascular infusion set with a non-coring Huber type right angle needle and a manually activated needle-stick prevention safety mechanism which reduces the risk of accidental needlestick injuries by sheathing the needle.

The device includes an integrated extension set consisting of a Huber needle and safety mechanism (Type B, Type D and Type E), needle infusion tubing (pressure resistance or non-pressure resistance), Y-injection site, clamp and female Luer lock adapter. The pressure resistance tubing can be used for power injection up to 330 psi. The device will be retained on patient for 24h to 7 days.

This submission is new design primarily involve changes to addition of new needle lengths and specifications.

The provided FDA 510(k) clearance letter and summary for the Promisemed Safety Huber Needles details a medical device that is a physical product (a needle), not a software-based AI/ML medical device. Therefore, the information requested about acceptance criteria and studies related to AI/ML device performance (e.g., sample size for test sets, number of experts for ground truth, MRMC studies, standalone performance, training set details) does not apply to this specific device.

The 510(k) submission for the Promisemed Safety Huber Needles focuses on demonstrating substantial equivalence to a predicate device (K243332) primarily through non-clinical performance testing for physical and mechanical properties, and a comparison of technological characteristics.

Here's a breakdown of the relevant information provided in the document:

Device Description and Purpose:

The Promisemed Safety Huber Needle is a non-coring intravascular infusion set with a right-angle needle and a manually activated needle-stick prevention safety mechanism. It is used to access surgically implanted vascular ports and, for the high-pressure resistant model, can be used for high-pressure injection of contrast media for CT imaging. It is for adult use only.

Nature of This Submission:

This 510(k) submission is for a device modification that primarily involves:

1. Addition of new needle lengths (16mm, 17mm, 20mm) for Type D and Type E needles.
2. Addition of a new specification: "without lubrication" for the needle tip.

The manufacturer asserts that these changes "do not introduce new risks as the fundamental technology and operation remain the same" and that the device remains "substantially equivalent" to its predicate device.

Acceptance Criteria and Study for This Device:

Since this is a physical medical device and not an AI/ML system, the "acceptance criteria" are based on meeting established performance specifications and international standards for hypodermic needles and infusion sets. The "study" that proves the device meets these criteria is the suite of non-clinical (bench) tests performed.

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

The document lists the types of tests performed and the standards they adhere to, implying that the acceptance criteria are successful completion according to these standards. It does not provide specific quantitative acceptance thresholds (e.g., "puncture force must be X-Y Newtons") nor the raw performance data, but rather states that "All verification and validation tests passed without deviations."

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

• Sample Size: Not explicitly stated in the 510(k) summary. For physical device performance testing, sample sizes are typically determined by statistical methods based on specified confidence levels or are prescribed by the testing standards themselves (e.g., a certain number of units per lot).
• Data Provenance: The tests were conducted by Promisemed Hangzhou Meditech Co., Ltd. in China ("Promisemed Hangzhou Meditech Co., Ltd. completed the following non-clinical tests"). This is a retrospective collection of data for the purpose of the 510(k) submission.

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

• N/A. This concept applies to AI/ML device ground truth establishment, often involving clinical image interpretation. For a physical device like a needle, "ground truth" is established by adherence to engineering specifications and international standards, tested by qualified engineers and technicians using calibrated equipment.

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

• N/A. This concept relates to human expert consensus in clinical data annotation for AI/ML validation. Physical device testing relies on objective measurements against defined 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:

• N/A. An MRMC study is for evaluating the impact of AI assistance on human diagnostic performance. This device is a physical medical instrument, not an AI software.

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

• N/A. This pertains to AI algorithm performance. The device here is a standalone physical needle.

7. The type of ground truth used:

• Engineering Specifications and International Standards: For a physical device, "ground truth" is adherence to predefined engineering specifications (e.g., dimensions, material properties, force resistance) and compliance with internationally recognized standards (like ISO 7864, ISO 9626, ASTM F3212). The testing confirms that the device's physical properties and functionality meet these established objective benchmarks.

8. The sample size for the training set:

• N/A. This concept is relevant for AI/ML model development. This device does not involve a "training set" in the computational sense.

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

• N/A. As above, this applies to AI/ML.

Summary of Key Takeaways from the Document:

The 510(k) submission successfully demonstrated substantial equivalence by confirming through non-clinical testing that the modified Promisemed Safety Huber Needles:

• Maintain the same intended use, technological characteristics, and principle of operation as the predicate device.
• The added needle lengths and the "without lubrication" option do not introduce new safety or effectiveness risks.
• All required performance tests (appearance, dimensions, needle point, fragment, sheath/cap, puncture force) passed without deviations, confirming adherence to relevant ISO and ASTM standards.
• No clinical testing was deemed necessary for this type of modification, reinforcing that the changes were not considered to impact fundamental safety or effectiveness parameters requiring human clinical data.

Ask a specific question about this device

The needle is used to access surgically implanted vascular ports.

Safety Huber Needles is a standard non coring intravascular infusion set with a non-coring Huber type right angle needle and a manually activated needle stick prevention safety mechanism which reduces the risk of accidental needlestick injuries by sheathing the needle. This device is for adult use only.

In addition, when used with ports that are indicated for power injection of contrast media into the central venous system, the high pressure resistant model is indicated for high-pressure injection of contrast media for CT imaging.

Safety Huber Needle is a standard non-coring intravascular infusion set with a non-coring Huber type right angle needle and a manually activated needle-stick prevention which reduces the risk of accidental needlestick injuries by sheathing the needle.

The device includes an integrated extension set consisting of a Huber needle and safety mechanism (Type B, Type D and Type E), needle infusion tubing (pressure resistance or non-pressure resistance), Yinjection site, clamp and female Luer lock adapter. The pressure resistance tubing can be used for power injection up to 330 psi. The device will be retained on patient for 24h to 7 days.

This submission is new design primarily involve changes to the type C name, the addition of new needle lengths and new type E.

The FDA 510(k) submission document for the Promisemed Safety Huber Needles details the device's characteristics and its substantial equivalence to a predicate device (K230715). The document does not describe a study involving an AI/software device that requires extensive acceptance criteria, an MRMC study, or the establishment of ground truth by multiple experts.

The provided document is a 510(k) premarket notification for a Class II medical device, specifically a hypodermic single lumen needle. This type of device approval primarily relies on demonstrating substantial equivalence to a legally marketed predicate device through non-clinical testing, rather than a clinical study with complex AI performance metrics.

Therefore, many of the requested details, such as the number of experts, adjudication methods, MRMC studies, standalone algorithm performance, and ground truth establishment for training sets, are not applicable to the content of this document.

However, based on the non-clinical testing described, we can extract information relevant to the device's acceptance criteria and how its performance was verified.

Here's an interpretation based on the provided document:

Acceptance Criteria and Device Performance for Promisemed Safety Huber Needles

The acceptance criteria for this device are primarily based on meeting established industry standards and design specifications, ensuring the new design (specifically Type D and Type E, and changes in needle lengths for Type D) is as safe and effective as the predicate device.

1. Table of Acceptance Criteria and Reported Device Performance

• Appearance
• Dimension
• Safety mechanism operation | Full performance was tested, including appearance, dimension, safety mechanism, etc., and found to comply with:
• ISO 7864 (Sterile hypodermic needles for single use)
• ISO 9626 (Stainless steel needle tubing for the manufacture of medical devices)
• ASTM F3212-16 (Standard Test Method for Performance of Safety Mechanism on Needles Used for Accessing Implanted Ports)
• ISO 23908 (Sharps injury protection features for single-use containers, sharps disposal containers and medical sharps)
  Result: Complied with all specified standards. |
  | No New Risks (Safety and Effectiveness) | The tests demonstrated that the product modifications did not introduce any new risks related to safety or effectiveness when compared to the predicate device. |

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

• Sample Size: The document does not specify the exact sample sizes (e.g., number of needles) used for each non-clinical test (visual inspections, dimensional measurements, and performance tests). It generally states "verification and validation tests passed without deviations."
• Data Provenance: The document implies that the testing was conducted by Promisemed Hangzhou Meditech Co., Ltd. in China ("No. 1388 Cangxing Street, Cangqian Community, Yuhang District, Hangzhou City, 311121 Zhejiang, P. R. China."). The testing is described as "Nonclinical test," which typically refers to laboratory-based evaluations rather than human subject data. These tests are retrospective in the sense that they are performed on manufactured devices to prove compliance, not prospective data collection from clinical use.

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

• Not applicable. This is not an AI/software device requiring human expert annotation or ground truth determination based on clinical interpretation. The "ground truth" here refers to compliance with engineering specifications and recognized international standards (ISO, ASTM).

4. Adjudication Method for the Test Set

• Not applicable. As noted above, this isn't a study involving human interpretation or AI output that would require adjudication. Compliance is determined against quantitative and qualitative engineering specifications and standards.

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

• Not applicable. This is a physical medical device (needle), not an AI algorithm. Therefore, an MRMC study is irrelevant.

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

• Not applicable. This is a physical medical device, not an algorithm.

7. The Type of Ground Truth Used

• The "ground truth" for this device's acceptance is based on adherence to international consensus standards (ISO, ASTM) and the manufacturer's internal design specifications and drawing requirements. This includes:
  • Dimensional accuracy (e.g., outer diameter and length of needles).
  • Functional performance of the safety mechanism.
  • Material properties and biocompatibility (implied by compliance with standards for medical devices).
  • Labeling accuracy.

8. The Sample Size for the Training Set

• Not applicable. There is no concept of a "training set" for a physical medical device in this context, as no AI model is being trained.

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

• Not applicable. As there is no training set, there is no ground truth to establish for it.

Ask a specific question about this device

The safety winged blood collection set is single-use, sterile, winged venipuncture needle bonded to a flexible tubing with or without a luer adapter and/or tube holder. The device is used for blood collection and/or the short-term infusion of intravenous fluids (up to 2 hours under direct clinical supervision). The blood-collection needle is designed to be covered with a safety mechanism, which can be activated to cover the needle immediately following venipuncture to aid in the protection against accidental needlestick injury.

The Promisemed Safety Blood Collection sets are single-use, sterile, venipuncture needles used for blood collection or short-term infusion of intravenous fluids (up to 2 hours under direct clinical supervision). The blood-collection needle is designed to be covered with a safety mechanism, which can be activated to cover the needle immediately following venipuncture to aid in the protection against accidental needlestick injury.

This document is a 510(k) summary for a medical device called "Safety Winged Blood Collection Sets" (K243806) from Promisemed Hangzhou Meditech Co., Ltd. It declares substantial equivalence to a predicate device (K211293).

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria and reported device performance in the format usually seen for AI/ML performance. This is because the device is a physical medical device (blood collection set), not an AI/ML diagnostic system. The "acceptance criteria" here are implied by adherence to recognized international standards and successful completion of non-clinical tests.

However, based on the provided text, we can infer some "acceptance criteria" and "performance" statements related to the modifications made (specifically the addition of model RBC and changes in needle sizes/materials).

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

• Sample size: The document does not specify a numerical sample size for any of the non-clinical tests conducted. Statements like "Visual inspections were conducted on unit packaging" and "Full performance was tested" indicate tests were performed but don't provide the number of units tested.
• Data provenance: The data provenance is from the manufacturer's internal non-clinical testing. It is implicitly "prospective" in the sense that the tests were conducted specifically to demonstrate the performance of the modified device for this 510(k) submission. No specific country of origin for the data is mentioned other than the manufacturer's location in China.

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 this is a 510(k) for a physical medical device (blood collection set), not an AI/ML device that generates diagnostic outputs requiring expert interpretation or ground truth labeling in that sense. The "ground truth" for these types of devices is established by adherence to engineering specifications and international performance standards.

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

This is not applicable for the same reason as above. No "adjudication" or consensus reading by experts is required for the non-clinical performance and design verification tests reported.

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 is not applicable as the device is not an AI/ML system, nor does it involve human readers or cases in an interpretive diagnostic context.

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

This is not applicable as the 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 medical device is adherence to established technical specifications, engineering drawings, and relevant international performance standards (ISO 6009, ISO 8536-4, ISO 9626, ISO 23908). Biocompatibility is "ground-truthed" by ISO 10993 series testing (e.g., in vitro cytotoxicity).

8. The sample size for the training set

This is not applicable as there is no AI/ML algorithm requiring a training set.

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

This is not applicable as there is no AI/ML algorithm requiring a training set or its associated ground truth establishment.

Ask a specific question about this device

It is to be used in conjunction with an endoscope to perform endoscopic injections, such as for the treatment of esophageal and gastric varices and for submucosal dye marking in the GI tract.

It is a flexible, sterile, sharp bevel-edged, hollow tubular device intended to be manually-operated through a compatible endoscope to perform needle functions (e.g., injection) during endoscopy. It is designed with appropriate shape, materials and gauge to function through the working channel of an endoscope. This is a single-use device.

The provided document is a 510(k) summary for the "Endoscopic Injection Needles" (K240675) from Promisemed Hangzhou Meditech Co., Ltd. It focuses on demonstrating substantial equivalence to a predicate device (Single Use Injection Needle, K210917) through non-clinical performance testing.

Here's an analysis of the acceptance criteria and study information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't present a formal table of acceptance criteria with specific numerical targets and results in the format requested. Instead, it lists the performance items tested and concludes that the testing "successfully demonstrated essential performance" and that the device "is at least equivalent to the predicate device."

Here's a breakdown of the tested performance items:

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

The document
does not specify the sample sizes
used for each individual non-clinical performance test. It only states that "Performance testing was conducted."

Regarding data provenance, the document indicates that Promisemed Hangzhou Meditech Co., Ltd. is the manufacturer, located in Hangzhou City, China. The biocompatibility testing was conducted by a "third GLP laboratory," but its location is not specified. All tests described are retrospective in the sense that they were conducted for the purpose of this 510(k) submission, likely in a controlled laboratory environment.

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

This information is not applicable as the provided document details non-clinical, benchtop performance testing, not studies involving human subjects or expert assessment of clinical data to establish a "ground truth" as might be done for diagnostic devices. The acceptance criteria for these tests are based on established engineering standards and specifications rather than expert consensus on medical conditions.

4. Adjudication Method for the Test Set:

This information is not applicable for the same reasons as point 3. Benchtop performance tests typically involve objective measurements against predefined specifications, not subjective assessments requiring adjudication among 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: "No clinical test is included in this submission." and "No reference devices were used in this submission." This type of study is relevant for diagnostic imaging devices where human interpretation is involved.

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

No, a standalone algorithm performance study was not done. This device is an Endoscopic Injection Needle, a physical medical instrument, not a software algorithm. Therefore, the concept of "standalone algorithm performance" (without human intervention) is not applicable.

7. The Type of Ground Truth Used:

The ground truth for the non-clinical tests described is based on:

• Engineering specifications and design requirements for the device.
• Established national and international standards for medical device testing (e.g., ISO 11135, AAMI/ANSI/ISO 10993-7, ASTM F1980-16, ISO 11607-1, ISO 11607-2, ISO 10993 series, USP ).
• Comparison to the predicate device's performance characteristics to establish substantial equivalence.

8. The Sample Size for the Training Set:

This information is not applicable. As this is a physical medical device and not a machine learning or AI-driven system, there is no "training set." The device's design is based on engineering principles and prior knowledge.

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

Verifine® Pen Needle is intended for use with pen injector device for the subcutaneous injection of drugs.

Verifine® Pen Needles, manufactured by Promisemed Hangzhou Meditech Co., Ltd, are designed for use with pen injectors for the administration of drugs. These are standard pen needles without integrated safety features. The devices are single-use, non-pyrogenic, and maintain a Sterility Assurance Level (SAL) of 10 °. The differences between the PromiseMed current cleared common type needle pen and the new design primarily involve changes to the trade name, the addition of new models, and modifications in some materials and dimensions. Key updates include a change in the trade name, the introduction of new models (FPN and NPN), the addition of new needle sizes and a 5-bevel needle tip option, and a shift from a specific intended use (administering insulin) to a general intended use (administering drugs). The materials used have also been slightly modified, such as changing the needle shield material from polypropylene (PP) to polyethylene (PE) for certain models, which only contact intact skin, ensuring no increased risk. These devices are intended for over-the-counter (OTC) use and require manual insertion by the user during drug administration.

The provided text is a 510(k) summary for a medical device (Verifine® Pen Needles). This document focuses on demonstrating substantial equivalence to a predicate device, rather than proving a new device meets acceptance criteria through a clinical or performance study that quantifies specific metrics like sensitivity, specificity, accuracy, or human reader improvement with AI assistance.

The context of your request (acceptance criteria, effect size, MRMC studies, ground truth) is typical for the evaluation of AI/ML-enabled medical devices, especially those involving image analysis or diagnostic support. The provided document describes a physical medical device (hypodermic needle) where the primary concerns are mechanical performance, biocompatibility, and compatibility with existing pen injectors. Therefore, information related to AI/ML device evaluation criteria is largely not applicable to this document.

Here's a breakdown of why many of your excellent questions cannot be answered by this document, followed by what can be extracted:

Why most questions are not applicable:

• AI/ML Device Evaluation: The document does not describe an AI/ML device. It's a pen needle. Therefore, concepts like "effect size of human readers improve with AI vs without AI assistance," "standalone (algorithm only) performance," "number of experts for ground truth," "adjudication method," "sample size for training set," or "data provenance" (in the context of image data) are irrelevant.
• Clinical Performance Data: The summary explicitly states: "No clinical data was necessary to determine the substantial equivalence of this device." This means there was no human-centric clinical study (like an MRMC study) performed to evaluate the diagnostic or treatment benefits in a clinical setting against a "ground truth" established by experts.

What can be extracted or inferred from the document regarding acceptance criteria and device performance for this physical device:

The "acceptance criteria" here are implied by the standards and bench testing performed to demonstrate substantial equivalence to the predicate device and compliance with relevant ISO standards.

1. Table of Acceptance Criteria and Reported Device Performance:

The document focuses on demonstrating that changes to the device (new models, sizes, material change, labeling updates) do not raise new questions of safety or effectiveness and that the modified device still meets the performance attributes of the predicate and relevant standards.

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

• Test Set Sample Size: Not explicitly stated in terms of a "test set" as one would for an AI/ML model or a clinical trial. However, non-clinical performance and biocompatibility testing were conducted. The sample size for these specific engineering tests (e.g., how many needles were tested for dose accuracy) is not detailed in this summary.
• Data Provenance: The tests were "completed by Promisemed Hangzhou Meditech Co., Ltd." (China). The data origin is thus the manufacturer's testing facilities. The tests are "non-clinical" (benchtop/lab-based), not from patients. It's not retrospective or prospective in the sense of clinical data collection.

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, in the AI/ML sense (e.g., expert consensus on clinical images), is not relevant here. Performance is measured against engineering specifications and international standards (ISO).

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

• Not Applicable. No adjudication method for expert review of data is mentioned or relevant.

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 study was NOT done. This type of study is specifically for evaluating diagnostic performance of AI/ML systems with human readers. The device is a physical pen needle, not an AI diagnostic tool.

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

• Not Applicable. There is no algorithm or software being evaluated for standalone performance. Performance tests are against ISO standards for the physical device.

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

• For this device, the "ground truth" or reference for performance is established by international standards (e.g., ISO 11608-2 for pen needles, ISO 10993-1 for biocompatibility) and the manufacturer's engineering specifications/drawing requirements. It is not clinical diagnostic ground truth.

8. The sample size for the training set:

• Not Applicable. The concept of a "training set" is for AI/ML models. This is a physical device.

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

• Not Applicable. Same as above.

Ask a specific question about this device

The device is used for endoscopic clip placement within the gastrointestinal(GI) tract for the purpose of endoscopic marking, hemostasis for mucosal/submucosal defects less than 3cm, bleeding ulcers, arteries less than 2mm, polyps less than 1.5cm in diameter and diverticula in the colon. Anchoring to affix jejunal feeding tubes to the wall of the small bowel. Closure of Gl tract lumenal perforations less than 20mm that can be treated conservatively.

The Single Use Hemoclip is a sterile, single use device that consists of metal clip that detaches from the introducer to maintain approximation of tissue to achieve hemostasis and endoscopic marking in the gastrointestinal tract. The device is provided sterile (EO). The large clip opening design meets various clinical treatment demands. It can be opened and closed repeatedly and can achieve repositioning. The 360 rotatable design is convenient for clinical use. lt consists of two main components, delivery system and clip assembly. And it is offered in different dimensions.

The provided document is a 510(k) summary for a medical device (Single Use Hemoclips) and does not describe a study involving acceptance criteria and device performance in the context of AI or software. Instead, it details the substantial equivalence of the subject device to a predicate device through non-clinical bench testing.

Therefore, I cannot provide the requested information about acceptance criteria and study details related to device performance, sample sizes, data provenance, expert ground truth adjudication, MRMC studies, standalone performance, training set details, or how ground truth was established for a study because this information is not present in the given text.

The document focuses on non-clinical testing to demonstrate substantial equivalence to a predicate device, as required for 510(k) clearance by the FDA.

Ask a specific question about this device

It is intended to inject fluids into the body or withdraw blood for medical purposes. After injection, the needle tube will be retracted into the barrel when the safety features are manually activated to minimize the risk of accidental sharps injury.

Safety Sterile Syringes is a sterile device consisting of a calibrated barrel, plunger, piston, push button, retraction cylinder, sealing ring, spring and a needle. It is made of plastic, stainless steel and silicone materials. Safety Sterile Syringes have two types: Type F and type D. Type F is a syringe with a fixed needle. Type D is a syringe with a detachable needle. The detachable needle is secured by rotating it through the front needle hub into the back needle hub located on the syringe. Safety Sterile Syringes is using plunger to fill syringe as well as discharge the fluid. After use, by continuing to press the push-button down to depress the plunger all of the way within the barrel, the safety mechanism will be triggered, then the needle tube, needle hub and retraction cylinder will be retracted into the barrel completely under the force of the spring to minimize the risk of accidental sharps injury. Product is delivered sterilization process is validated according to EN ISO 11135. This is a single-use device. Safety Sterile Syringes is intended to be used in professional healthcare facility/hospital and transport environment.

The provided document is a 510(k) Premarket Notification from the FDA for a medical device called "VeriSafe Safety sterile syringes." This type of document focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than detailing a specific clinical study with acceptance criteria in the same way one might for a novel diagnostic or therapeutic AI device.

Therefore, the requested information elements related to AI/algorithm performance, ground truth establishment for AI, sample sizes for test/training sets in an AI context, expert qualifications, and MRMC studies are not directly applicable to this submission. This document describes bench testing verifying physical and material properties of a medical device (a syringe).

However, I can extract the relevant "acceptance criteria" (standards and tests) and how the device "meets" them based on the provided summary.

1. Table of Acceptance Criteria and Reported Device Performance

• Seal strength, dye penetration, and sterility tests performed and met criteria. |
  | Shelf-Life (ASTM F1980-16) | - 3 years (validated using accelerated aging) |

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

• Test Set Sample Size: Not specified in terms of specific number of units tested for each standard. The document states "The bench testing performed verifies that the performance of the subject device is substantially equivalent..." implying tests were conducted on representative samples of the device as required by the listed ISO and ASTM standards.
• Data Provenance: The device manufacturer is Promisemed Hangzhou Meditech Co., Ltd. in Hangzhou, Zhejiang, China. The tests cited are international standards (ISO, ASTM, USP), indicating the testing was conducted to these globally recognized specifications. The document doesn't explicitly state if the testing was performed retrospectively or prospectively, but standard device testing for 510(k) submissions is typically conducted during product development and validation, and is inherently "prospective" in relation to the submission itself.

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)

This section is Not Applicable (N/A). The "ground truth" here is defined by performance against established international consensus standards (e.g., ISO, ASTM, USP) for physical, chemical, and biological properties of a medical device (syringe), not by expert clinical judgment or interpretation of data. The standards themselves are developed by committees of experts, but this is not what is typically asked for in terms of "ground truth" for a device's performance in a clinical or AI context.

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

This section is Not Applicable (N/A). Performance is measured objectively against the criteria defined by the listed standards, not through adjudication by multiple human reviewers.

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 (N/A). This device is a sterile safety syringe and does not involve AI or human "readers" in the context of its function or assessment for this submission.

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

This section is Not Applicable (N/A). This device is a sterile safety syringe and does not involve an algorithm.

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

The "ground truth" for this device's performance is the objective criteria and acceptable limits defined within the cited international consensus standards (ISO 7886-1, ISO 9626, ISO 7864, ISO 23908, ISO 10993 series, ISO 11135, ASTM F1980-16, ASTM D4169-16, ASTM F88/F88-15, ASTM F1929-15, USP, USP42-NF37, USP, USP38-NF33_C71). These standards specify the test methods and the performance thresholds that the device must meet to be considered compliant and safe/effective.

8. The sample size for the training set

This section is Not Applicable (N/A). There is no AI model involved, therefore no training set.

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

This section is Not Applicable (N/A). There is no AI model involved, therefore no training set or ground truth establishment for it.

Ask a specific question about this device

The needle is used to access surgically implanted vascular ports.

Safety Huber Needles is a standard non coring intravascular infusion set with a non-coring Huber type right angle needle and a manually activated needle stick prevention safety mechanism which reduces the risk of accidental needlestick injuries by sheathing the needle. This device is for adult use only.

In addition, when used with ports that are indicated for power injection of contrast media into the central venous system, the high pressure resistant model is indicated for high-pressure injection of contrast media for CT imaging.

Safety Huber Needle is a standard non-coring intravascular infusion set with a non-coring Huber type right angle needle and a manually activated needlestick prevention safety mechanism which reduces the risk of accidental needlestick injuries by sheathing the needle.

The device includes an integrated extension set consisting of a Huber needle and safety mechanism (Type B and Type C), needle infusion tubing (pressure resistance or non-pressure resistance), Y-injection site, clamp and female Luer lock adapter. The pressure resistance tubing can be used for power injection up to 330 psi. The device will be retained on patient for 24h to 7 days.

The provided text describes a 510(k) premarket notification for the Promisemed Safety Huber Needle. This document focuses on demonstrating that the new device is substantially equivalent to a legally marketed predicate device (Surecan Safety II, K170897) rather than providing a detailed study proving the device meets specific acceptance criteria for a novel technology.

The 510(k) clearance process does not typically involve a comparative effectiveness study (MRMC) with human readers or standalone AI performance studies, as it's for devices demonstrating substantial equivalence to pre-existing products, not necessarily for proving the clinical utility or superiority of a new diagnostic algorithm.

Therefore, the requested information about acceptance criteria and a study proving device performance in a clinical diagnostic context (e.g., accuracy, sensitivity, specificity, expert ground truth, MRMC studies) is not applicable to this type of device and submission. The "performance" discussed in this document refers to the adherence to engineering and safety standards.

However, I can extract the relevant "acceptance criteria" and "device performance" in the context of this 510(k) submission, which focuses on various engineering, material, and safety tests to demonstrate substantial equivalence.

Here's a breakdown of the requested information based on the provided document, noting where aspects are not applicable (N/A) due to the nature of a 510(k) submission for a physical medical device like a needle:

1. Table of acceptance criteria and the reported device performance:

2. Sample sized used for the test set and the data provenance:

• Sample Size: The document does not specify exact sample sizes for each test. For medical device testing against standards (like ISO or ASTM), sample sizes are generally specified by the standard or determined through a statistical rationale to ensure confidence in the results. This is common for bench testing.
• Data Provenance: The tests are "bench testing," meaning they were conducted in a laboratory setting. The manufacturer is Promisemed Hangzhou Meditech Co., Ltd. in Hangzhou City, Zhejiang, China. The data would be prospective, as these are tests performed on the manufactured device models to demonstrate compliance.

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

• N/A. This information is not relevant to the type of device and submission. "Ground truth" established by experts (e.g., radiologists interpreting images) is specific to diagnostic AI/imaging devices. For a physical device like a needle, performance is assessed against engineering standards and material properties, not clinical expert consensus on diagnostic interpretations.

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

• N/A. Not applicable as there is no "adjudication" in the context of testing a physical device against engineering specifications. The results are physical measurements or observations of compliance.

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:

• N/A. No MRMC comparative effectiveness study was done. This type of study is specifically for evaluating the impact of a diagnostic aid (often AI) on human reader performance, which doesn't apply to a Huber needle.

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

• N/A. No standalone algorithm performance was done. This device is a physical medical instrument, not an AI algorithm.

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

• For this device, the "ground truth" and "acceptance criteria" are defined by established international and national standards (e.g., ISO, ASTM, USP) for medical device design, manufacturing, safety, and performance. The performance tests yield objective measurements and observations (e.g., "No cytotoxicity," "Complied with ISO 23908") which serve as the "ground truth" of compliance with these standards.

8. The sample size for the training set:

• N/A. This device is not an AI/ML algorithm that requires a "training set."

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

• N/A. Not applicable, as there is no training set for a physical medical device.

Ask a specific question about this device

Insulin Syringe is intended for subcutaneous injection of U-40 and U-100 insulin in the treatment of diabetes.

The proposed device Insulin Syringe, a sterile device consisting of a calibrated barrel with plunger, is intended to be used to administer an injection of insulin to a patient subcutaneously. A non-retractable integrated needle is included. The syringe is made of plastic and silicone materials and allowing smooth plunger movement. This is a single-use device. The device is the same as K193273. The purpose of the submission is to add OTC labeling.

The provided document is an FDA 510(k) premarket notification for an Insulin Syringe. It describes the device, its intended use, and compares it to a predicate device. However, it does not contain information about acceptance criteria and a study proving the device meets those criteria in the context of an AI/ML medical device, which is implied by your detailed request.

The document describes typical non-AI medical device testing, such as:

• Bench Testing: Verifies physical performance characteristics (e.g., needle tube length, bond strength, leakage, fit of plunger, dead space, penetration force, particulate contamination).
• Biocompatibility Testing: Assesses biological safety (cytotoxicity, irritation, sensitization, systemic toxicity, hemolysis, pyrogens).
• Sterilization and Shelf-life Testing: Validates sterilization method and confirms shelf life.

Therefore, I cannot fulfill your request for information related to AI/ML device acceptance criteria, performance metrics (like sensitivity, specificity, AUC), sample sizes for AI test sets, expert ground truth establishment, MRMC studies, or training set details because this information is not present in the provided text. The device in question is a physical insulin syringe, not an AI/ML-based diagnostic or therapeutic device.

Ask a specific question about this device