Search Results

The Electric Breast Pump (F5055) is intended to express milk from lactating women and collect milk from their breast. The device is intended for single user.

The Electric Breast Pump (F5055) is a powered breast pump to be used by lactating women to express and collect milk from their breast. The Electric Breast Pump (F5055) is intended for a single user. The proposed device is electrically powered and software-controlled. The device operates via a microprocessor-driven air pump, which generates suction on the breast to extract milk. The proposed device is available in one model, F5055. The provided non-sterile and is not to be sterilized by the user prior to use. The device includes a breast shield assembly, bottles, pump unit, tubing, an adapter, and pump unit. The breast shield assembly includes a silicone breast shield and polypropylene breast shield body that contacts the user's breast.

The provided text is a 510(k) Summary for an Electric Breast Pump (F5055). This document details the manufacturer's claim of substantial equivalence to a predicate device, as required for FDA premarket notification.

However, the provided text does not contain information related to an AI/ML powered medical device, nor does it discuss acceptance criteria and a study proving the device meets those criteria in the context of AI/ML performance. The device described is an "Electric Breast Pump," a hardware device with software controls, but it does not appear to involve AI or machine learning for diagnostic or assistive functions that would require the typical performance study details asked in the prompt.

Therefore, I cannot fulfill the request for information on acceptance criteria and a study proving an AI/ML device's performance based on the provided text, as the text describes a non-AI/ML medical device.

To directly answer your prompt based on the provided text, focusing on the type of acceptance criteria and performance testing presented for this specific device (an electric breast pump):

The acceptance criteria for this medical device are primarily focused on safety and effectiveness as demonstrated through non-clinical performance testing, and comparison of technological characteristics and indications for use with a legally marketed predicate device.

Here's a breakdown of the "acceptance criteria" (implicitly, the aspects where the device must perform acceptably) and the study/testing performed, as per the document, rather than a typical AI/ML study:

Acceptance Criteria and Reported Device Performance (as inferred for an Electric Breast Pump):

Regarding the specific questions posed, adapted to the context of this non-AI/ML device:

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

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

   • The document does not specify sample sizes for the non-clinical performance tests (e.g., how many units were tested for electrical safety, or how many cycles for pump performance).
   • Data provenance is not explicitly stated in terms of country of origin for the testing itself, nor is it described as retrospective or prospective data collection from human subjects. The tests are non-clinical, so they are likely laboratory-based.

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

   • This question is largely not applicable to this type of device and testing. There is no "ground truth" establishment by experts in the sense of image interpretation or diagnostic accuracy.
   • The "ground truth" for non-clinical performance testing typically refers to the established engineering specifications and international standards (e.g., IEC, ISO) that the device must meet. The "experts" involved would be qualified test engineers and quality assurance personnel performing and verifying these tests. Their qualifications are not detailed in this summary.

4. Adjudication method for the test set:

   • This is not applicable as there is no subjective interpretation or consensus process like in clinical image review. Performance criteria are objective and quantitative (e.g., measured suction strength within a range, successful completion of electrical safety tests).

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:

   • Definitely not applicable. This is not an AI/ML diagnostic or assistive device. No human reader studies (MRMC) are mentioned or necessary for this type of product.

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

   • Not applicable in the context of AI/ML algorithm performance. The "standalone" performance here refers to the device itself meeting its engineering specifications rather than an algorithm's diagnostic accuracy. The non-clinical tests (suction strength, cycle speed, etc.) represent the standalone performance of the device.

7. The type of ground truth used:

   • For this device, the "ground truth" is defined by engineering specifications, international safety standards (IEC, ISO), and functional requirements. For example, a certain suction strength is a specified operating range, and the test verifies the device achieves this.

8. The sample size for the training set:

   • Not applicable. This device does not use a "training set" in the sense of machine learning. The design and development process for such a hardware device involves prototyping, testing, and refinement, but not machine learning training on a dataset.

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

   • Not applicable, as there is no training set for an AI/ML model for this device. Ground truth for the device's functionality is established by engineering and regulatory standards.

Ask a specific question about this device

Optiflux® Enexa™ dialyzers are intended for patients with acute kidney injury or chronic kidney disease when conservative therapy is judged to be inadequate.

The Optiflux Enexa F500 dialyzer is a high-flux, single-use, e-beam sterilized hemodialyzer that contains the additive Endexo SMM1 blended into the fiber. The dialyzer is provided blood pathway sterile and non-pyrogenic. The membrane surface area is 1.5 m².

The Optiflux Enexa F500 dialyzer is a high-flux, sterile device designed for single-use in acute and chronic hemodialysis. The dialyzer is configured to connect to a bloodline set which connects to a patient's vascular access system when used with a hemodialysis machine equipped with ultrafiltration control. During hemodialysis, blood is pumped from the patient's body through an extracorporeal circuit, one component of which is the dialyzer. The dialyzer contains a semi-permeable membrane that allows for diffusion and/or ultrafiltration to transport toxins and excess fluid from the blood compartment (fiber lumen) to the dialysate compartment. Dialyzers utilize a counter-current flow in which dialysate and blood flow in opposite directions in the dialyzer. The counter-current flow maintains the concentration gradient across the membrane for waste and fluid removal.

The provided document is for a medical device called the "Optiflux Enexa F500 Dialyzer," which is a high-permeability hemodialysis system. The document outlines the device's characteristics, intended use, and performance data from various tests, including a clinical study, to demonstrate its substantial equivalence to a predicate device.

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

1. Table of Acceptance Criteria and the Reported Device Performance:

The document doesn't explicitly list specific quantitative acceptance criteria in a table format for all tests. However, it states that "All testing met predetermined acceptance criteria" and "Results of the proposed device design verification tests met the requirements and demonstrated that... the Optiflux Enexa F500 dialyzer is safe and effective for its intended use."

Here's a table combining the key performance characteristics mentioned, with the understanding that "acceptable" means meeting the undefined predetermined acceptance criteria. The In vitro Urea Clearance is the only performance number explicitly given with a standard testing configuration.

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

• Clinical Study (as a test set for human subjects):

  • Sample Size: Eighteen (18) hemodialysis (HD) subjects with chronic renal failure. They received 664 HD treatments.
  • Data Provenance: The document does not explicitly state the country of origin. It indicates it was a "prospective, multi-center, open-label clinical study."

• In Vitro Performance Tests: The sample size for in vitro tests (clearance, ultrafiltration, structural integrity, etc.) is not specified in the summary, but it states "All testing met predetermined acceptance criteria." The tests were conducted according to ISO 8637-1:2017 and FDA Guidance.

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 question is not directly applicable to a medical device like a hemodialyzer in the way it would be for an AI diagnostic algorithm. Ground truth for a hemodialyzer's performance is typically established through:

• In vitro measurements: Using standardized laboratory methods for analyzing fluid samples and physical properties. This doesn't involve "experts" establishing ground truth in the sense of image interpretation.
• Clinical outcomes/physiological measurements: In the clinical study, ground truth for patient health and device performance (e.g., urea removal, complement activation, adverse events) is established by direct measurement of patient parameters and clinical observation by medical staff (physicians, nurses). The document does not specify the number or qualifications of these clinical experts, but it is implied they are qualified medical professionals responsible for patient care and data collection in a clinical trial setting.

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

The concept of an adjudication method (like 2+1, 3+1 for consensus in image interpretation) is not applicable to this type of device and study. The "ground truth" or performance assessment is based on direct measurements and clinical observation in the clinical study, not on expert consensus reading of independent data.

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 medical device (hemodialyzer), not an AI diagnostic algorithm or imaging device requiring human reader interpretation. No MRMC study was conducted or is relevant to this device.

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

Not Applicable. This is a medical device, not an algorithm. Therefore, "standalone performance" in the context of an algorithm is not relevant.

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

For the Optiflux Enexa F500 Dialyzer, the "ground truth" for its performance and safety validation was established through:

• In vitro quantitative measurements: For characteristics like urea clearance, ultrafiltration, pressure drop, structural integrity, and various other physical and chemical properties.
• Biocompatibility testing: Standardized in vitro and in vivo (e.g., guinea pig, mouse lymphoma) biological tests for material safety, often following ISO 10993.
• Clinical Outcomes Data: For the clinical study, the ground truth was derived from direct physiological measurements (e.g., spKt/V, urea removal rates, ß2-microglobulin removal rates, serum albumin, C5a, C3a, sC5b-9, hematologic parameters, platelet counts) and observed adverse events, including thrombus scores. These are objective measures collected during clinical practice.

8. The sample size for the training set

Not Applicable. This device is a hemodialyzer, not an AI algorithm that requires a "training set."

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

Not Applicable. As no AI algorithm is involved, there is no "training set" or "ground truth for the training set" in the context of this device.

Ask a specific question about this device

The F5 Corpus VS powered wheelchair is to provide indoor mobility, including stand-up feature, to persons limited to a seating position that are capable of operating a powered wheelchair.

F5 Corpus VS Powered Wheelchair is battery powered, front wheel motor driven and is controlled by the R-net 120 amp controller. The user interface is a joystick. The F5 Corpus VS is powered by two 12VDC, Group M24, approximate driving range on fully charged batteries is up to 25km (15.5 miles), depending on use and the terrain the chair is driven on. The chair frame is a steel construction and includes two front drive units (motor, gear and brake), two batteries and two rear pivoting casters. Depending on the user's needs, the joystick motor control is mounted to the left or right armrest. When the user activates the joystick, the controller receives a signal to release the brakes. With the brakes released, the chair is allowed to move in the joystick is actuated. When the user releases the joystick, the chair slows to a stop and the brakes are automatically re-engaged. The solenoid electromechanical brakes allow the user to stop by letting go of the joystick. F5 Corpus VS will enable the user to stand up, completely or partially, to facilitate reaching, working eye to eye with colleagues. The standing sequence is controlled by the joystick and gives the user the possibility to come to a standing position. The seating, chest support and knee stop stabilize the user during the stand-up or sitdown operation.

This document (K191874) is a 510(k) premarket notification for a powered wheelchair, the F5 Corpus VS. It compares the device to two predicates: the Quickie® Q700-UP M (K172384) and the F5 (K143014).

Based on the provided text, here is an analysis of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are generally demonstrated by compliance with various ISO and RESNA standards for wheelchairs. The document does not present a single table explicitly listing "acceptance criteria" against "reported device performance" in a quantitative manner for all aspects. Instead, it states compliance with standards and provides some performance specifications when comparing the device to its predicates.

Here's an attempt to compile relevant information, though a direct "acceptance criteria" column is not explicitly defined in the document for each performance characteristic:

The document emphasizes that the F5 Corpus VS passes the requirements in ISO 7176 and RESNA WC-1:2009 Section 20.

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 refers to "Non-Clinical Testing" which involves compliance with a long list of ISO standards and RESNA WC-1. These are physical performance tests for the device itself (e.g., stability, brake effectiveness, strength).

• Sample size for the test set: Not explicitly stated as a number of devices or units. Typically, for device performance testing against standards, a representative sample (e.g., a few units or prototypes) is tested. The nature of these tests does not involve patient data or human subjects for the "test set" in the context of an AI/algorithm study.
• Data provenance: Not applicable in the context of patient data for an algorithm. The tests are for the physical wheelchair device. The Permobil AB company is based in Sweden. The tests were conducted to international standards.

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 information is not applicable as the device is a physical powered wheelchair, not an AI/algorithm that requires expert-established ground truth from medical images or patient data. The "ground truth" here is the physical performance of the device as measured by standardized engineering and safety tests.

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

This information is not applicable as the device is a physical powered wheelchair, not an AI/algorithm study involving adjudication of clinical findings. Compliance with standards is typically measured objectively through specified test procedures.

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 information is not applicable. The device is a physical powered wheelchair. There is no AI component or human reader in the context of medical image interpretation that would warrant an MRMC study.

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

This information is not applicable. The device is a physical powered wheelchair, not a standalone algorithm.

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

The "ground truth" for the F5 Corpus VS device is its physical performance, safety, and functional characteristics as measured and validated against established international standards (ISO 7176 series and RESNA WC-1:2009 Section 20). These standards define objective test methods and acceptable performance limits.

8. The sample size for the training set

This information is not applicable. The device is a physical powered wheelchair. There is no AI/algorithm being trained on a dataset. The design and manufacturing process would involve engineering principles and testing, not machine learning training.

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

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

Ask a specific question about this device

Pasture F550S, Pasture F550CS, Pasture A520S, Pasture A520CS, Pasture E520S, and Pasture E520CS is a NIOSH certified N95 respirator, and is indicated to be used by the healthcare personnel during procedures to protect both the patient and the healthcare personnel from the transfer of microorganisms, body fluids, and particulate material.

Pasture F550S and Pasture F550CS respirators are disposable duck bill shaped N95 respirators with NIOSH certification number TC-84A-7504. They contain 5 layers composed of polypropylene, with a nose cushion, a synthetic elastic loop or strap, and a nosepiece which is the combination of zinc wires and embedded polyester inside of layers. F550CS is the same respirator as the F550S, but F550CS contains an adjustable buckle on the headband.

Pasture A520S and Pasture A520CS respirators are cup shaped N95 respirators with NIOSH certification number TC-84A-7454. They contain 4 layers composed of polypropylene with a synthetic elastic loop or a strap. A520CS is the same respirator as the A520S, but A520CS contains an adjustable buckle on the headband.

Pasture E520S and Pasture E520CS respirators are cup shaped N95 respirators with NIOSH certification number TC-84A-7453. They contain 4 layers composed of polypropylene with a nose cushion, synthetic elastic loop or strap, and an aluminum nosepiece. E520CS is the same respirator as E520S, but E520CS contains an adjustable buckle on the headband.

This document describes the premarket notification for several models of Pasture Surgical N95 Respirators (F550S, F550CS, A520S, A520CS, E520S, E520CS). The provided information is insufficient to answer all parts of the request as it pertains to medical device AI/ML performance studies. However, I can extract the relevant information from the document regarding the acceptance criteria and performance of these N95 respirators. The questions asked are typically for AI/ML devices, not for surgical respirators.

Here's an analysis based on the provided text, adapted to the context of a physical medical device (N95 respirator) and its regulatory submission.

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

The acceptance criteria for these N95 respirators are based on various performance standards and regulatory requirements for surgical masks and N95 respirators. The document primarily demonstrates substantial equivalence to a predicate device (WILLSON ONE-FIT HEALTHCARE PARTICLE RESPIRATOR AND SURGICAL MASK, HC-NB095) through performance testing.

The following questions are not applicable to the provided document, as it concerns a physical medical device (N95 respirator) and not an AI/ML algorithm or software as a medical device (SaMD). The document does not describe a study involving readers, ground truth establishment by experts, or training/test sets in the context of an AI/ML device.

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

• Not Applicable. This document describes a 510(k) premarket notification for physical N95 respirators, not an AI/ML device or its test set. Performance testing is typically conducted on a sample of manufactured devices according to established test methods for physical properties and biocompatibility. The specific sample sizes for each test (e.g., fluid resistance, flammability) are not detailed in this summary but would be specified in the full test reports referenced by the NIOSH certification and ASTM standards. The provenance of the data would be from the laboratories that performed these physical tests.

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 context of expert consensus is relevant for diagnostic AI/ML algorithms. For N95 respirators, the "ground truth" is determined by physical and chemical test results against a defined standard (e.g., NIOSH standards, ASTM F1862). Expert qualifications would pertain to the technicians conducting these standardized tests, ensuring they follow protocols, not to clinical interpretation of data.

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 used in AI/ML performance studies to resolve discrepancies in expert interpretations to establish a robust ground truth. For N95 respirators, performance is objectively measured by standardized tests, not by expert consensus on clinical findings.

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. MRMC studies are designed to assess the impact of AI assistance on human reader performance, typically in diagnostic imaging. This document does not pertain to an AI device.

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

• Not Applicable. This question relates to the performance of an AI algorithm in isolation. The product is a physical N95 respirator.

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

• For physical devices like N95 respirators, the "ground truth" for performance is defined by adherence to established industry standards and regulatory requirements (e.g., NIOSH N95 certification, ASTM F1862 for fluid resistance, 16 CFR 1610 for flammability, ISO 10993 for biocompatibility). The tests objectively measure specific characteristics.

8. The sample size for the training set

• Not Applicable. Training sets are used for machine learning algorithms. This document describes a hardware device.

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

• Not Applicable. As above, training sets are not relevant to this type of device.

Ask a specific question about this device

The intended use of the F5 powered wheelchair is to provide indoor mobility to persons limited to a seating position that are capable of operating a powered wheelchair.

The intended use of the F5 powered wheelchair is to provide outdoor and indoor mobility to persons limited to a seated position that are capable of operating a powered wheelchair.

F5 Powered Wheelchair is battery powered, front wheel motor driven and is controlled by the R-net 120 amp controller. The user interface is a joystick.

The F5 is powered by two 12VDC 73Ah. Group M24. approximate driving range on fully charged batteries is up to 25km (15.5 miles), depending on use and the terrain the chair is driven on. The chair frame is a steel construction and includes two front drive units (motor, gear and brake), two batteries and two rear pivoting casters. Depending on the user's needs, the joystick motor control is mounted to the left or right armrest.

When the user activates the joystick, the controller receives a signal to release the brakes. With the brakes released, the chair is allowed to move in the joystick is actuated. When the user releases the joystick, the chair slows to a stop and the brakes are automatically reengaged. The solenoid electromechanical brakes allow the user to stop by letting go of the joystick.

This document is a 510(k) premarket notification for the Permobil F5 Powered Wheelchair. It does not describe a study involving an AI/ML device, but rather a traditional medical device (a powered wheelchair). Therefore, most of the questions relating to acceptance criteria, ground truth, expert adjudication, and AI performance metrics are not applicable.

However, I can extract information related to the device's performance based on the provided safety and performance standards.

Here's the relevant information based on the provided text:

1. Table of acceptance criteria and the reported device performance

For a traditional medical device like a powered wheelchair, "acceptance criteria" are typically defined by compliance with recognized performance standards. The "reported device performance" is implicitly that the device met these standards, as indicated by the statement "The F5 complies to the below standards" and "The submitted device are tested and having same or improved results as the already predicated device."

2. Sample size 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 the document. For a physical device like a wheelchair, "test set" would typically refer to the specific units or prototypes of the device that underwent testing. The document states "The submitted device are tested," implying testing was performed on at least one F5 unit, but the exact number is not specified. The manufacturer, Permobil AB, is based in Timrå, Sweden, so the testing would likely have been conducted there or by a certified testing facility.

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 is not applicable as this is a physical device, not an AI/ML diagnostic tool requiring expert interpretation for ground truth. The "ground truth" for a wheelchair's performance is determined by meeting objective engineering and safety standards.

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

Not applicable for a physical device compliance 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 physical device, not an AI/ML-assisted diagnostic tool.

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

Not applicable. This is a physical device.

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

The "ground truth" for the F5 Powered Wheelchair is defined by its compliance with internationally recognized safety and performance standards (ISO 7176 series). This involves objective measurements and tests rather than subjective expert consensus.

8. The sample size for the training set

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

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

Not applicable.

Ask a specific question about this device

This device is a disposable filtering facepiece respirators intended for use by the general public in public health medical emergencies - Pasture™ A520G Respirator and Pasture™ F550G Respirator

Pasture F550G respirator is a duck bill mask as described in NIOSH N95 standard It 1s in 5 layers and composed of spunbond, meltblown and polyester, also with nose cushion, elastic loops and/or strip and nosepiece which is the combination of zinc wires and embedded polyester inside of layers

Pasture A520G respirator is a cone shaped mask as described in NIOSH N95 standard It is in 4 layers and composed of spunbond, meltblown and polyester, also with synthetic rubber band which is coated with polyester and free of latex

The provided text describes a 510(k) summary for Filtering Facepiece Respirators (Pasture™ F550G & A520G). This document focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed study with specific acceptance criteria, sample sizes, and expert evaluations as would be expected for a diagnostic or AI-driven device.

Therefore, many of the requested items (e.g., sample size for test set, number of experts, adjudication method, MRMC study, standalone performance, ground truth type for test/training sets, training set size) are not applicable or not available in this type of submission. This 510(k) is for a physical device (respirator), and the "performance" discussed is related to its physical properties and NIOSH certification, not an AI algorithm.

Here's the information that can be extracted or derived from the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The "acceptance criteria" here are typically the requirements for NIOSH certification and meeting the performance of the predicate device. The document primarily relies on comparative testing to the predicate device and NIOSH certification.

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

• Sample Size: Not specified in the 510(k) summary. For physical products like respirators, testing typically involves a sufficient number of units to demonstrate consistent performance against standards (e.g., NIOSH testing protocols would define sample sizes for particle filtration, breathability, fit, etc.). However, these specific numbers are not provided here.
• Data Provenance: Not explicitly stated regarding country of origin or retrospective/prospective. The testing would have been conducted to support the NIOSH certification and biocompatibility claims. This is prospective testing specifically for the device submission.

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

• Not Applicable. This is a physical device (respirator), not an AI diagnostic. "Ground truth" in the context of diagnostic performance by experts is not relevant here. Performance is assessed against physical and biochemical standards.

4. Adjudication Method for the Test Set

• Not Applicable. As above, no expert adjudication is involved for physical performance testing of a respirator.

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

• No. This is not an AI diagnostic device, so an MRMC study comparing human readers with and without AI assistance is not relevant.

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

• Not Applicable. There is no algorithm. The device itself is the "standalone" product.

7. The Type of Ground Truth Used

• Physical/Chemical Standards: The "ground truth" for a respirator's performance is established by standardized testing methods defined by bodies like NIOSH (e.g., particle filtration efficiency, breathing resistance, fit testing protocols) and biocompatibility standards (e.g., ISO 10993 for cytotoxicity, sensitization, irritation). The predicate device's performance also acts as a reference for substantial equivalence.

8. The Sample Size for the Training Set

• Not Applicable. There is no "training set" as this is not an AI/machine learning device.

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

• Not Applicable. No training set is involved.

Ask a specific question about this device

The Verigene System is a bench-top molecular diagnostics workstation that automates the analysis and detection of nucleic acids using gold nanoparticle probe technology.

The Verigene F5 Nucleic Acid Test is Indicated as an aid to diagnosis in the evaluation of patients with suspected thrombophilia. The test is an in vitro diagnostic for the detection and genotyping of a single-point mutation (G to A at position 1691; also known as Factor V Leiden) of the human Factor V gene (F5; Coagulation Factor V gene), from Isolated genomic DNA obtained from whole blood samples. The test is intended to be used on the Verigene System.

The Verigene F2 Nucleic Acid Test is indicated as an aid to diagnosis in the evaluation of patients with suspected thrombophilia. The test is an in vitro diagnostic for the detection and genotyping of a single-point mutation (G to A at position 20210) of the human Factor II gene (F2; prothrombin gene), from isolated genomic DNA obtained from whole blood samples. The test is intended to be used on the Verigene System.

The Verigene MTHFR Nucleic Acid Test is indicated as an aid to diagnosis in the evaluation of patients with suspected thrombophilia and elevated levels of homocysteine or altered folate metabolism. The test is an in vitro diagnostic for the detection and genotyping of a single-point mutation (C to T at position 677) of the human 5,10 methylenetetrahydrofolate reductase gene (MTHFR), from isolated genomic DNA obtalned from whole blood samples. The test is intended to be used on the Verigene System.

The Verigene System is an in vitro diagnostic device for processing and genotyping multiple genes in a DNA sample. The Verigene System consists of two instruments, the Verigene Processor and the Verigene Reader, and utilizes single-use, disposable Test Cartridges to process and genotype multiple genes in a DNA sample in approximately 1½ hours. Clinicians use one or more of the three genes (F5, F2, MTHFR) and their associated single nucleotide polymorphisms (SNPs) to help diagnose patients' hereditary contributory factors in forming blood clots (thrombi). On the Verigene System, hypercoagulation testing can include one or more of three genotypes that are associated with hypercoagulation (i.e., thrombophilia). These tests use extracted and purified DNA, mixed with hybridization buffer, loaded into the sample well of the Test Cartridge. The genotyping process occurs with a hybridization of the target analyte to a synthetic gene-specific oligonucleotide capture strand on the Test Cartridge's substrate. A synthetic mediator target-specific oligonucleotide is included with the test-specific sample buffer to form a hybridization "sandwich" with the gene sequence of interest. Washing steps following the target hybridization remove the unbound DNA from the hybridization chamber. A probe, composed of a gold nanoparticle with covalently bound oligonucleotides complementary to a sequence on the intermediate oligonucleotide, is introduced after the target wash. After the probe hybridization is completed, a series of washing steps remove the unbound probe from the hybridization chamber. A two-part signal enhancement reagent is added to the hybridization chamber and reacts with the gold nanoparticle to amplify the signal for the Verigene Reader scanning and analysis. Upon completion of the genotyping process, the user removes the Test Cartridge from the Verigene Processor which is now ready for the next test. Once the reagent portion of the Test Cartridge is removed by the user, the substrate is inserted into the Verigene Reader. The Verigene Reader illuminates the signal-enhanced nanoparticles specifically bound to either the wild type or mutant captures for the gene. A photosensor reads the relative brightness of each spot and the Verigene Reader outputs a result based on relative levels of brightness of the wild type to mutant signals.

Here's a summary of the acceptance criteria and study information for the Nanosphere Verigene System and its associated nucleic acid tests, based on the provided text:

Acceptance Criteria and Reported Device Performance

The acceptance criteria are implied through the reported performance for diagnostic sensitivity and specificity, and the call rate. While explicit numerical acceptance criteria for these metrics aren't stated as "acceptance criteria," the reported 100% diagnostic sensitivity and specificity, and the high call rates, indicate successful performance for a device seeking substantial equivalence.

Study Details

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

   • Reproducibility Study #1:
     • F5: 118 samples (Site 1, Operators A & B), 60 samples (Site 2, Operators C & D), 58 samples (Site 3, Operator E), 59 samples (Site 3, Operator F). Total = 295 samples. (Note: The "Correct Calls (%)" sums slightly differently across operators for F5, F2, MTHFR, so this is derived from the "Total Calls" which is 118 for Site 1, 60 for Site 2, 58 for Operator E Site 3, and 59 for Operator F Site 3. The footnote clarifies that 10 cartridges failed to run, meaning the total tests attempted were higher.)
     • F2: Similar sample numbers as F5 for each site and operator.
     • MTHFR: Similar sample numbers as F5 for each site and operator.
     • Data Provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective).
   • Diagnostic Sensitivity/Specificity & Call Rate: Values are based on a total of 287 calls made (for Call Rate), implying a test set of at least 287 samples when considering successful calls. The specific number of samples for diagnostic sensitivity and specificity calculation is presented with 95% confidence intervals, but the raw count is not provided (e.g., "out of X positive samples" or "out of Y negative samples").
   • Data Provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective).

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

   • The document does not specify the number of experts or their qualifications used to establish the ground truth for the test set. The nature of the device (genotyping) suggests the ground truth would likely be established by a reference genetic test or sequencing.

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

   • The document does not describe any adjudication method.

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

   • No MRMC comparative effectiveness study was done. This device is a diagnostic test for genetic mutations, not an imaging device requiring human reader interpretation, nor does it involve AI assistance for human readers.

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

   • Yes, a standalone performance study was done. The performance characteristics (reproducibility, analytical sensitivity, call rate, diagnostic sensitivity, diagnostic specificity) are for the Verigene System itself, operating as an automated in vitro diagnostic device. Human operators are involved in sample preparation and loading, but the genotyping analysis and detection are automated by the system.

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

   • The document does not explicitly state the method for establishing ground truth, but for genetic tests, the ground truth is typically established by orthogonal genetic testing methods such as DNA sequencing or a clinically validated reference method for detecting the specific gene mutations (e.g., PCR-based assays from a reputable lab). The predicate devices are also nucleic acid test kits, supporting this assumption.

7. The sample size for the training set:

   • The document does not specify a training set or its sample size. This type of device relies on established probe chemistry and detection algorithms based on biophysical principles, rather than machine learning models that require a distinct training phase.

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

   • As no training set is described, there's no information on how its ground truth would have been established.

Ask a specific question about this device

The Model 7500 Microcurrent TENS Device is intended to be used for the relief of chronic intractable pain.

A number of TENS and microcurrent devices have been cleared for marketing by FDA that have just a few discrete output settings, rather than having a continuously adjustable output. Such devices have been shrinking in size in recent years as advances in integrated circuits and other components allow for smaller circuits. Now NewCare Products is introducing a microcurrent TENS device that has the generator unit builtin to the back of the electrodes. By eliminating the bulky controls, the generator may be made very small and can be mounted on the electrode pad.

By providing three versions of the device, three different output levels The three versions of the Model 7500 are equivalent to are obtained. one traditional generator with three discrete output levels.

The provided text is a 510(k) summary for the Model 7500 Microcurrent TENS Device, which seeks to establish substantial equivalence to predicate devices. It does not describe a study involving specific acceptance criteria, device performance metrics, or the typical elements of a clinical trial used to prove a device meets acceptance criteria in the way a diagnostic or AI-driven device might.

Instead, the submission focuses on demonstrating that the Model 7500 Microcurrent TENS Device is substantially equivalent to already legally marketed predicate devices, meaning it has the same intended use and similar technological characteristics. The "testing" section refers to conformance with recognized electrical safety and performance standards for TENS devices, rather than clinical efficacy studies with specific performance metrics.

Therefore, many of the requested categories for a clinical study on acceptance criteria cannot be extracted from this document, as such a study was not performed or described in this 510(k) summary. I will answer based on the information available and indicate where information is not present.

Acceptance Criteria and Study for Model 7500 Microcurrent TENS Device

This 510(k) submission, K013167, for the Model 7500 Microcurrent TENS Device, aims to demonstrate substantial equivalence to existing legally marketed predicate devices, rather than proving a specific performance metric against a set of acceptance criteria through a clinical trial. The "acceptance criteria" in this context refer to conformance with established electrical safety and performance standards for TENS devices, not diagnostic accuracy or efficacy metrics.

The "study" conducted for this device was primarily focused on bench testing to ensure compliance with these recognized standards.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Not applicable. The "test set" in this context refers to the device itself being subjected to bench testing against engineering standards, not a clinical data set.
• Data Provenance: Not applicable. The testing described is bench testing of the device hardware, not data derived from patients.

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

• Number of Experts: Not applicable. The "ground truth" for compliance with electrical and safety standards is determined by the standards themselves and objective measurements during bench testing, not by expert human interpretation in a clinical sense.
• Qualifications of Experts: Not applicable.

4. Adjudication method for the test set

• Adjudication Method: Not applicable. Compliance with standards is typically determined by measurement against predefined limits, not by an adjudication panel.

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

• MRMC Study: No, an MRMC comparative effectiveness study was not done. This device is a microcurrent TENS device for pain relief, not a diagnostic imaging device utilizing AI that would involve human readers.
• Effect Size of AI: Not applicable.

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

• Standalone Performance Study: No, a standalone performance study in the context of an algorithm or AI was not done. The device does not incorporate AI; it is an electronic medical device with discrete electronic components. Two of the predicate devices employed software, but the Model 7500 and the Healthonics unit do not.

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

• Type of Ground Truth: The "ground truth" for this 510(k) submission relates to the device meeting established electrical safety and performance standards. This is determined by objective measurements and verifications against the specifications outlined in documents like ANSI/AAMI NS4, UL2601-1, and IEC 60601-2-10. It is not based on expert consensus, pathology, or outcomes data related to patient treatment efficacy in a clinical trial.

8. The sample size for the training set

• Sample Size: Not applicable. This device is not an AI/ML algorithm requiring a training set.

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

• Ground Truth Establishment for Training Set: Not applicable.

Ask a specific question about this device

Ask a specific question about this device

Allergen ImmunoCAPTM is the solid phase component of the Pharmacia & Upjohn in vitro immunodiagnostic systems which measure specific IgE to the respective allergen bound to the ImmunoCAP™. Allergen ImmunoCAP™ are intended to be used with Pharmacia CAP System™ RAST FEIA and UniCAP® Specific IgE in vitro diagnostic assays.

Pharmacia CAP System RAST® FEIA and UniCAP® Specific IgE are intended for in vitro diagnostic use as an aid in the clinical diagnosis of IgE mediated allergic disorders in conjunction with other findings, and are to be used in clinical laboratories, as well as, physician office laboratories.

Allergen ImmunoCAP™ consists of a cellulose sponge matrix to which allergenic components are covalently coupled. The matrix is encased in a small round plastic capsule. This capsule is at the same time a holder of the matrix for convenient automation and a reaction chamber.

The sponge matrix is manufactured from activated cellulose derivative to which allergen extract solution is added under defined optimized conditions for the allergen coupling. This solid phase is an excellent carrier of allergens and provides favorable reaction conditions.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of quantitative acceptance criteria with corresponding performance metrics. Instead, it describes a functional verification process:

• With a history or indication of allergy to the specific allergen (expected positive results).
• Established negative samples (expected negative results).
  Results show an outstanding agreement of outcome concerning positive and negative samples in both systems (Pharmacia CAP System™ and UniCAP™). |
  | Reproducibility | Demonstrated by "Reproducibility between production lots." (No specific quantitative metric provided in this summary.) |
  | Stability | Demonstrated by "stability studies." (No specific quantitative metric provided in this summary.) |
  | Clinical Relevance | "The importance of each allergen is demonstrated with relevant literature references covering frequency, clinical use and description of related allergens." (This is a qualitative acceptance, demonstrating the need for testing these allergens.) |

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

• Sample Size for Test Set: Not explicitly stated. The document mentions "clinical serum samples, with a history or indication of allergy to the specific allergen, and established negative samples." The exact number of samples for each allergen or overall is not provided.
• Data Provenance: Not explicitly stated. Given that the manufacturer is Pharmacia & Upjohn, Diagnostics AB in Uppsala, Sweden, and the US operation is in Kalamazoo, MI, it is likely that samples came from either or both regions, but this is not confirmed. The study appears to be retrospective, as it uses "clinical serum samples" and "established negative samples," implying samples collected prior to the study.

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

• Number of Experts: Not specified.
• Qualifications of Experts: The document states that the samples were "clinical serum samples, with a history or indication of allergy to the specific allergen, and established negative samples." This implies that the ground truth (positive or negative for allergy) was established by clinical diagnosis or history, likely by medical professionals (e.g., allergists, physicians) based on patient symptoms, history, and potentially other diagnostic tests, but the specific role and qualifications of experts in establishing this ground truth for the study are not detailed.

4. Adjudication Method for the Test Set

• Adjudication Method: Not specified. The document states that "results show an outstanding agreement of outcome concerning positive and negative samples" between the two test systems, but it doesn't describe a process for resolving discrepancies or establishing a definitive ground truth through adjudication for the study. The ground truth appears to be pre-established clinical history.

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

• MRMC Study: No, this was not an MRMC comparative effectiveness study in the typical sense of evaluating human readers with and without AI assistance. This device is an in-vitro diagnostic (IVD) test system (ImmunoCAP™) that measures specific IgE antibodies, not an AI-driven image analysis or diagnostic aid for human readers. The study compares the performance of the new ImmunoCAP™ allergens within two existing automated test systems (Pharmacia CAP System™ and UniCAP™).

6. Standalone Performance (Algorithm Only)

• Standalone Performance: Yes, in a way. The "device" is the Allergen ImmunoCAP™ itself, which is a component of an automated laboratory test. The performance characteristics described are for the ImmunoCAP™'s ability to bind specific IgE and yield accurate positive/negative results when run on the automated systems. There is no "human-in-the-loop" performance to consider for this type of diagnostic test. The study evaluates the performance of the ImmunoCAP™ as a standalone component within the larger automated diagnostic process.

7. Type of Ground Truth Used

• Type of Ground Truth: The ground truth for the test set was based on clinical history or indication of allergy for positive samples and "established negative samples." This is essentially a form of clinical diagnosis/history.

8. Sample Size for the Training Set

• Sample Size for Training Set: Not applicable. This document describes the safety and effectiveness of physically manufactured in-vitro diagnostic components (ImmunoCAPs) that are chemically coupled with allergens. There is no "algorithm" or machine learning model that requires a training set in the conventional sense. The "training" for such components involves optimization during manufacturing (e.g., allergen coupling conditions) and quality control, not data-driven model training.

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

• How Ground Truth for Training Set was Established: Not applicable, as there is no training set for an algorithm. The development and optimization of the ImmunoCAP™ manufacturing process (e.g., allergen coupling) would rely on analytical performance characteristics (e.g., binding efficiency, signal-to-noise ratio) and iterative testing, rather than a "ground truth" derived from patient data in a training set context.

Ask a specific question about this device