Search Filters

Search Results

Found 12 results

510(k) Data Aggregation

    K Number
    K013305
    Date Cleared
    2002-08-23

    (323 days)

    Product Code
    Regulation Number
    864.7525
    Reference & Predicate Devices
    N/A
    Why did this record match?
    Applicant Name (Manufacturer) :

    CARDIOVASCULAR DIAGNOSTICS, INC.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Rapidpoint™Coag Enoxaparin Test card (ENOX) is a qualitative test intended for exclusive use with the Rapidpoint Coag analyzer to detect the anticoagulant effects, ≥ 1.0 IU/ml, of the low molecular weight heparin (LMWH), Lovenox®/Clexane® (enoxaparin sodium)¹, in arterial citrated whole blood from patients with unstable angina (UA)/non-ST segment elevation myocardial infarction (NSTEMI) who may transition to percutaneous intervention (PCI). The ENOX test is intended for use at either the point of care or in the central laboratory. The device does not discriminate between values of enoxaparin below 1.0 IU/ml and the absence of drug.

    The test provides information on the patient's citrated arterial whole blood response to enoxaparin by measurement of the clotting time using a factor Xa activated clotting method and should be interpreted in conjunction with other clinical data available to the clinician

    Device Description

    The RapidPoint Enoxaparin (ENOX) test is a one-step dry coagulation method performed on the RapidPoint Coag analyzer. All of the components necessary to perform the assay, with the exception of patient sample, are included in the reaction chamber of the test card.

    In the ENOX test, factor X is rapidly converted to factor Xa by a specific factor X activator initiating the clotting process. Enoxaparin, from the patient's blood, complexes with antithrombin (AT), to inhibit factor Xa and lengthen the clotting time. Reported clotting times in excess of the assay cut-off indicate an enoxaparin concentration greater than or equal to 1.0 International Units per milliliter. The results generated by the ENOX test are indicative of the anticoagulant effect produced by enoxaparin in citrated arterial whole blood.

    The test card formulation contains purified Factor Xa activator, calcium, phospholipid and stabilizers. Paramagnetic iron oxide particles (PIOP) are included to provide an optical detection mechanism in the presence of patient sample.

    AI/ML Overview

    Here's a summary of the acceptance criteria and study details for the Thrombolytic Assessment System (TAS) or Rapidpoint™ Coag Enoxaparin (ENOX) Test Card.

    1. Table of Acceptance Criteria and Reported Device Performance

    The acceptance criteria are implicitly defined by the clinical study's results in relation to the intended use. The device is intended to detect enoxaparin levels ≥1.0 IU/mL. The study uses a clotting time cutoff of ≥ 260 seconds to indicate this.

    Acceptance Criteria (Implied)Reported Device Performance (Clinical Study)
    Detect enoxaparin ≥1.0 IU/mL (indicated by clotting time ≥ 260 seconds)Sensitivity: 96.3% (95% CI: 89.4-99.2)
    Discriminate enoxaparin
    Ask a Question

    Ask a specific question about this device

    K Number
    K994194
    Date Cleared
    2000-03-28

    (106 days)

    Product Code
    Regulation Number
    864.7140
    Reference & Predicate Devices
    N/A
    Why did this record match?
    Applicant Name (Manufacturer) :

    CARDIOVASCULAR DIAGNOSTICS, INC.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Rapidpoint Low range Heparin Management Test Card is to be used with the Rapidpoint Coag (formerly TAS) Analyzer to monitor the effects of low to moderate levels of unfractionated heparin on coagulation in noncitrated arterial whole blood samples from patients undergoing diagnostic and interventional procedures.

    The test is for in vitro diagnostic use. It is especially suited for professional use in decentralized areas of the hospital near the patient's bedside, in the cardiac catheterization lab, and other areas where patients are treated with low to moderate levels of heparin.

    Device Description

    The Rapidpoint LHMT provides a method to measure the response of a patient to heparin. A noncitrated whole blood sample can be used for this test. The test card has a magnetic stripe on the back, which encodes lot specific information such as number, expiration date, and mathematical factors specific to that lot. A room temperature test card is removed from the pouch and the card is passed through the card reader of the instrument to instrument to run a test. The instrument instructs the operator to insert a test card and then requests patient and sample information. The card is warmed and the operator is prompted to add a drop of blood to the card sample well. The sample flows into the card and rehydrates the reagent, which begins the reaction. As the reaction proceeds and clotting begins, the movement of the particles decreases, and the instrument signals the clotting time.

    AI/ML Overview

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

    Device: Rapidpoint Low range Heparin Management Test (LHMT) Card

    1. Table of Acceptance Criteria and Reported Device Performance:

    The document doesn't explicitly state "acceptance criteria" in a quantitative, pass/fail manner. However, it does describe performance characteristics that were likely evaluated for market clearance. The primary evidence presented is the correlation to a predicate device.

    Performance CharacteristicAcceptance Criteria (Implied)Reported Device Performance
    Linearity/RangeLinear response to heparinResponds in a linear manner from 0 to 3.0 U/ml of heparin.
    SensitivitySensitive to heparin effectsSensitive to the effects of heparin on coagulation.
    SpecificityInsensitive to intrinsic/common coagulation pathway deficiencies, and certain interfering substances.Relatively insensitive to deficiencies in the intrinsic and common coagulation pathways. Lipid (to at least 15 mg/ml), nitroglycerin (to 1 ug/ml), and Dextran (to 6 mg/ml) had no effect.
    Temperature EffectNo effect of sample temperatureNo effect of sample temperature (2 - 37°C).
    Correlation to Predicate Device (ACT)Substantially equivalent to predicate devices (ACT or ACT-LR)Overall correlation of 0.93 of the LHMT card to the ACT (for noncitrated samples from all sites combined).
    Normal RangeEstablish normal rangeNormal ranges (mean +/- 2 SD) were 65 to 175 seconds for noncitrated whole blood. Baseline samples from patients ranged from 53 to 195 seconds.

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

    • Sample Size:
      • Normal Donors: 120 (59 males, 61 females) for establishing normal ranges.
      • Patient Samples: 429 samples from 232 individuals undergoing various treatments.
    • Data Provenance:
      • Normal Donors: "normal, healthy donors," likely gathered prospectively for this study.
      • Patient Samples: "samples drawn from individuals expected to have abnormal LHMT results" undergoing "a variety of treatments." The description "Field testing and clinical testing were done at large hospitals" suggests these were prospective clinical studies in multiple locations. The document does not specify the country of origin, but given the submission to the FDA in the US, it's highly probable the studies were conducted in the US.

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

    The document does not mention the use of experts to establish a "ground truth" for the test set in the traditional sense of consensus reading or adjudication. The ground truth for the comparison was established by:

    • Predicate Device Results: The results from the Hemochron ACT or ACT-LR device served as a comparative "ground truth" for assessing equivalence.
    • Chromogenic Anti-Xa Assay: A chromogenic anti-Xa assay (Diagnostica Stago's Stachrom Heparin) was used as a "reference, tiebreaker method" to determine heparin concentration, which is a more direct measure of heparin activity.

    Therefore, no panel of human experts was used for adjudication or establishing ground truth in the way one might see in image-based diagnostic studies.

    4. Adjudication Method for the Test Set:

    Not applicable in the context of this device. The study design involved comparing the LHMT device's quantitative output to established, quantitative measurements from a predicate device and a reference assay. There was no subjective interpretation that would require an adjudication method.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, What Was the Effect Size of How Much Human Readers Improve With AI vs Without AI Assistance:

    No, an MRMC comparative effectiveness study was not done. This device is not an AI-assisted diagnostic tool for human interpretation; it's an automated in vitro diagnostic test for measuring coagulation time in the presence of heparin. Therefore, there's no "human reader" component to improve.

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

    Yes, the study described is a standalone performance study of the Rapidpoint LHMT device. The device itself performs the measurement, and the results are then compared to other quantitative measures (predicate device, reference assay). There is no "human-in-the-loop" interaction in the production of the primary diagnostic result from the LHMT card.

    7. The Type of Ground Truth Used:

    The ground truth for evaluating the LHMT device's performance was:

    • Comparative Measurement: Results from the predicate device (Hemochron ACT or ACT-LR) for assessing substantial equivalence.
    • Reference Method: Results from a chromogenic anti-Xa assay (Stachrom Heparin), which directly measures heparin concentration and served as a "reference, tiebreaker method." This provides a more objective, gold-standard-like measure of heparin activity.

    8. The Sample Size for the Training Set:

    The document describes nonclinical performance data ("Preclinical testing was done at CDI") and then clinical performance data. It does not explicitly separate data into "training" and "test" sets in the context of a machine learning or algorithm development paradigm. The "nonclinical performance data" could be considered part of the development/training phase, but no specific sample size is given for it. The clinical data (120 normal donors, 429 patient samples) are presented as the primary "test set" for demonstrating performance and substantial equivalence.

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

    As mentioned in point 8, the concept of a "training set" with established ground truth as distinct from a "test set" isn't explicitly detailed as it would be for an AI algorithm.

    • Preclinical Testing: The preclinical testing likely involved internal laboratory studies to characterize the device's basic performance (linearity, sensitivity, specificity, temperature effects). The "ground truth" for these studies would have been established through controlled experimental conditions, using known concentrations of heparin and other interfering substances, and comparing results to established laboratory methods or internal standards.
    • Clinical Testing: For the clinical evaluation data presented, the "ground truth" for comparison was the measurements from the predicate device (ACT) and the reference anti-Xa assay.
    Ask a Question

    Ask a specific question about this device

    K Number
    K994159
    Date Cleared
    2000-02-15

    (68 days)

    Product Code
    Regulation Number
    864.5425
    Reference & Predicate Devices
    N/A
    Why did this record match?
    Applicant Name (Manufacturer) :

    CARDIOVASCULAR DIAGNOSTICS, INC.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The new Rapidpoint Coaq HMP controls are intended to be used exclusively with the Rapidpoint Coag Analyzer and the Rapidpoint Coag Heparin Management Test (HMT), Heparin Titration Test (HTT), and Protamine Response Test (PRT) cards to provide a method for quality control of the system. The controls produce clotting times that must be within accepted, standard ranges, when tested at CVDI before release of product for sale, to indicate that the analyzer and test cards are functioning properly and thereby help assure the accuracy of HMT. HTT. and PRT card results.

    Device Description

    Not Found

    AI/ML Overview

    The provided documentation [0-3] is a 510(k) summary for a medical device called "Rapidpoint™ Coag Heparin Management Panel Controls (HMP Controls)" and its marketing authorization. This document outlines the regulatory process and approval of the device but does not contain information about the acceptance criteria or a study proving that the device meets those criteria, nor does it provide details about algorithm performance.

    The document states, "The controls produce clotting times that must be within accepted, standard ranges, when tested at CVDI before release of product for sale, to indicate that the analyzer and test cards are functioning properly and thereby help assure the accuracy of HMT. HTT. and PRT card results" [3]. However, it does not specify what those "accepted, standard ranges" are, nor does it detail any specific clinical study data to demonstrate the device's performance against defined acceptance criteria.

    Therefore, I cannot provide the requested information based on the given input. The categories below are left blank as the information is not present in the provided text.


    CriteriumAcceptance CriteriaReported Device Performance
    Specific Performance MetricsNot specified in the provided document.Not specified in the provided document.
    Statistical ThresholdsNot specified in the provided document.Not specified in the provided document.

    Study Details:

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

      • Not specified in the provided document. The document describes controls for a system, not a diagnostic or AI algorithm with a test set of patient data.
    2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience):

      • Not applicable/Not specified. This document pertains to the regulatory approval of quality control materials, not an AI algorithm requiring expert ground truth for a test set.
    3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

      • Not applicable/Not specified.
    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:

      • Not applicable. This document is for quality control materials for a coagulation system, not an AI-assisted diagnostic device.
    5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

      • Not applicable. This document does not describe an algorithm.
    6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

      • Not applicable/Not specified.
    7. The sample size for the training set:

      • Not applicable/Not specified.
    8. How the ground truth for the training set was established:

      • Not applicable/Not specified.
    Ask a Question

    Ask a specific question about this device

    K Number
    K993519
    Date Cleared
    2000-01-14

    (88 days)

    Product Code
    Regulation Number
    864.5680
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    CARDIOVASCULAR DIAGNOSTICS, INC.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Rapidpoint Accent is an accessory to the Rapidpoint Coag Analyzer. When used in conjunction with the Rapidpoint Coag and the Heparin Management Panel Cards (Heparin Management Test, Heparin Titration Test, and Protamine Response Test) Cards, its intended use is to generate information on heparin management.

    Device Description

    The Rapidpoint Accent is an accessory to the Rapidpoint Coag Analyzer. The Analyzer is a point of care instrument designed to determine hemostatic parameters of blood and plasma samples. The Accent works in conjunction with the Analyzer to provide dosing information for heparin and protamine during cardiopulmonary bypass procedures. The Accent determines this information by combining test results from the Analyzer with patient data entered into the Accent by the user. During the course of a CPB procedure, the user must perform a series of tests using the Analyzer, The test cards that must be used include the Heparin Management Test (HMT™), the Heparin Titration Test (HTT™), and the Protamine Response Test (PRT™). The results of these tests provide the Accent with information on how the patient's blood will respond to the addition of Heparin and Protamine. The Accent uses this information to calculate recommended dosages of Heparin or Protamine to be given to the patient to reach a target value entered into the Accent by the user. The target value may be either a heparin concentration or a clotting time.

    The Accent includes an eight-inch diagonal touch screen for user interface and a built in printer for recording test results. The case is designed with a protective front cover that doubles as a holder for the Analyzer when the system is in use. The Accent is powered by an internal power supply that also orovides power to the Analyzer. The Accent and the Analyzer communicate through a serial cable that must be plugged into the Analyzer and is permanently attached to the Accent.

    The HTT card provides a method to determine the response of a patient to heparin. Before heparin administration, baseline Heparin Management Test (HMT) and HTT values are determined for the patient with the Rapidpoint" Coag (formerly TAS) Analyzer. Using these values, the Rapidpoint ACCENT will calculate the dose of heparin necessary to produce a desired concentration or effect of this drug in the patient's blood. Both citrated or noncitrated whole blood samples can be used for these tests.

    The test card has a magnetic stripe on the back, which encodes lot specific information such as number, expiration date, and mathematical factors specific to that lot. A room temperature test card is removed from the pouch and the card is passed through the card reader of the instrument to program the instrument to run a test. The instrument instructs the operator to insert a test card and then requests patient and sample information. The card is warmed and the operator is prompted to add a drop of blood to the card sample well. The sample is drawn into the card and rehydrates the reagent, which begins the reaction. As the reaction proceeds and clotting begins, the movement of the particles decreases, and the instrument signals the clotting time.

    The PRT card is made for use with citrated or noncitrated blood samples containing heparin. The PRT is a modification of the HMT card and consists of a single test card that contains calcium chloride to initiate coagulation in citrated blood samples, celite as activator, stabilizers. and protamine sulfate. The test results will depend on heparin activity in the blood, which in turn depend on the levels of heparin, of coagulation factors, and of heparin inhibitors in the sample. The higher the level of heparin activity, the greater the protamine sulfate dosage required to inhibit it. The results of the PRT card are used with values produced on HMT cards with samples taken just before protamine administration, to determine the response of the individual to the agent. The values are stored by the ACCENT, which performs the calculations to determine dose recommended to neutralize the heparin present in the patient.

    The test card has a magnetic stripe on the back, which encodes lot specific information such as number, expiration date, and mathematical factors specific to that lot. A room temperature test card is removed from the pouch and the card is passed through the card reader of the instrument to program the instrument to run a test. The instrument instructs the operator to insert a test card and then requests patient and sample information. The card is warmed and the operator is prompted to add a drop of blood to the card sample well. The sample is drawn into the card and rehydrates the reagent, which begins the reaction. As the reaction proceeds and clotting begins, the movement of the particles decreases, and the instrument signals the clotting time.

    AI/ML Overview

    Here's an analysis of the provided text regarding the acceptance criteria and study for the Rapidpoint Accent, Heparin Titration Test (HTT) Card, and Protamine Response Test (PRT) Card:

    1. Table of Acceptance Criteria and Reported Device Performance

    The documents do not explicitly state quantitative acceptance criteria in a pass/fail format. Instead, the studies aim to demonstrate "substantial equivalence" to predicate devices. For both the HTT and PRT cards, the key outcome measured was the calculated heparin/protamine dosage, and the acceptance criterion was "No significant differences (p = ≥0.05) in dosage were observed between the two systems by ANOVA testing."

    Characteristic/TestAcceptance Criteria (Implicit)Reported Device Performance
    HTT CardSubstantial equivalence to predicate device (Hepcon Heparin Dose Response (Medtronic)) in calculating heparin dosages. Specifically, no significant difference (p = ≥0.05) in dosage between the two systems as determined by ANOVA.Samples from 139 individuals. "No significant differences (p = ≥0.05) in dosage were observed between the two systems by ANOVA testing." (HTT vs. Hepcon HDR)
    PRT CardSubstantial equivalence to predicate device (Hepcon Heparin Assay cartridges (Medtronic)) in calculating protamine sulfate dosages. Specifically, no significant difference (p = ≥0.05) in dosage between the two systems as determined by ANOVA.Samples from 139 individuals. "No significant differences (p = ≥0.05) in dosage were observed between the two systems by ANOVA testing." (PRT vs. Hepcon Heparin Assay Cartridges)
    HTT Card Stability Refrigerated (
    Ask a Question

    Ask a specific question about this device

    K Number
    K990566
    Date Cleared
    1999-05-14

    (81 days)

    Product Code
    Regulation Number
    864.5425
    Reference & Predicate Devices
    N/A
    Why did this record match?
    Applicant Name (Manufacturer) :

    CARDIOVASCULAR DIAGNOSTICS, INC.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The TAS analyzer with software version 4.0 is intended to be used with TAS test cards to monitor the hemostatic activity of whole blood and plasma samples. The TAS analyzer is a portable system designed to be used in non-laboratory testing environments by healthcare professionals. TAS test results are reported in quantitative units of measurement.

    Device Description

    The TAS Analyzer with software version 4.0 provides a method of testing for coagulation parameters in samples of citrated or non-citrated blood or citrated plasma. The instrument is designed to be used with disposable test cards. The test cards are approximately the size of a credit card with a magnetic stripe on the back which is encoded with data including the test type and lot specific test parameters. The cards contain dried reagent which includes paramagnetic iron oxide particles in a small thin reaction chamber. When a sample is added to the test card, the reagent, particles, and sample mix. The instrument has a permanent magnet and an electromagnet which move the particles in the sample. The particle motion is monitored with a light source and detector. The electromagnet is energized repeatedly for half a second then turned off for half a second. When the electromagnet is on, the particles alian themselves with the magnetic field lines produced by the electromagnet. When the electromagnet is off, the particles align with the weaker field lines of the permanent magnet. As the sample clots, the motion of the particles is restrained. Software algorithms monitor the change in particle motion and determine features such as clotting time, lysis time, or other mathematically derived characteristics. These values are then reported to the user.

    The software provides additional features to the operator such as optional operator identification codes, storage of 1000 test results, and a QC lockout mode which helps ensure that controls are performed. Most features are available to the user in one of two ways. Features which are intended for any operator to access are listed as options on the User menu. Features which are limited to supervisors are listed as options on the Supervisor menu. Access to the Supervisor menu is limited by a password.

    This new software version adds new features such as Electronic Quality Control and improves some existing features. Many of the changes are minor modifications to the user interface. Other changes are more significant, providing the user with four new test types and a few new options.

    A 510(k) will be filed for each of the new tests individually. In each case, the addition to the software of the capability to process the test does not allow the operator to perform the test without having the new test cards. The test cards for each of these tests will not be sold for human diagnostic or prognostic purposes until clearance has be granted by the FDA. This 510(k), which is for the new software version, does not address the clinical performance or efficacy of these new test cards.

    The 4.0 software version has been developed under design control with the features verified and the design validated. The design, verification, and validation of the new and modified operator features in the 4.0 software version are covered in this submission.

    AI/ML Overview

    The provided text does not contain acceptance criteria for device performance or any study details that would prove the device meets such criteria.

    The document is a 510(k) summary for a software update (version 4.0) to a Thrombolytic Assessment System (TAS) Analyzer. The primary purpose of this submission is to demonstrate that the new software version is substantially equivalent to a previously cleared version (2.03) and that there are no new safety or effectiveness issues.

    The document explicitly states:

    • "This 510(k), which is for the new software version, does not address the clinical performance or efficacy of these new test cards." (Page 2)
    • The software provides "additional features to the operator" and new test types, but the clinical performance or efficacy of these new tests are not addressed in this submission, as separate 510(k)s will be filed for each new test.

    Therefore, I cannot extract the requested information from the provided text. The document focuses on demonstrating substantial equivalence based on software modifications and features, not on establishing or proving performance against specific acceptance criteria through a clinical or performance study for the device's diagnostic capabilities.

    Ask a Question

    Ask a specific question about this device

    K Number
    K981206
    Date Cleared
    1998-05-26

    (55 days)

    Product Code
    Regulation Number
    864.5400
    Reference & Predicate Devices
    N/A
    Why did this record match?
    Applicant Name (Manufacturer) :

    CARDIOVASCULAR DIAGNOSTICS, INC.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The TRAQS is a database management system that is designed specifically to collect, organize, and store Thrombolytic Assessment System (TAS) analyzer records

    Device Description

    TRAQS is a software package designed for computers running the Windows 95 operating system. TRAQS provides features which allow the user to collect, view, and sort patient and control results from Thrombolytic Assessment System (TAS) analyzers. TRAQS also provides a method for the user to enter normal ranges and then compare the stored data set against the ranges. Stored results which fall outside the appropriate range are flagged on the screen and in printouts as out of range. Sets of stored TAS results displayed on the screen can be saved to archive files for later viewing or printing. TRAQS also keeps track of the number of results collected from TAS analyzers and can display this data by TAS serial numbers. No capability is provided to alter the data associated with TAS results. A comprehensive users manual is supplied with the software.

    AI/ML Overview

    The provided text describes the "TAS Result Acquisition System (TRAQS)" software, its intended use, development, and testing. However, it does not contain specific quantitative acceptance criteria or a study demonstrating device performance against such criteria in the way typically expected for clinical devices (e.g., sensitivity, specificity, accuracy).

    Instead, the document details a software validation process focused on meeting functional specifications and requirements.

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

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

    Acceptance Criteria (Stated as Pass/Fail Criteria)Reported Device Performance (Summary of Test Results)
    "all test scripts are completed successfully by the version of software under test." (This implies that all stated functional requirements are met).The "Test Data Summary" section describes the systematic testing performed:
    • Testing of TRAQS features: Viewing, sorting, and archiving records were methodically tested using modified TRAQS database files with known record sets.
    • Handling of TAS analyzer records: TRAQS was tested to ensure proper handling of all combinations of data (test type, sample type, error condition, patient ID, length, etc.) that could be received from a TAS analyzer. This included viewing, sorting, printing, and archiving.
    • Year 2000 (Y2K) compliance: A subset of records specifically tested the software's ability to handle Y2K issues.
      The overall implication is that these tests were successful, as the device received 510(k) clearance. |

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

    • Sample Size: The text does not provide a specific number for the sample size of the test set. It refers to "known record sets" and "a special set of test records" representing "every possible combination of test type, sample type, error condition, patient id, length, etc." This indicates a comprehensive, but unquantified, test set.
    • Data Provenance: The data was synthetically generated or modified for the purpose of software testing.
      • "modified TRAQS database files" (for known record sets)
      • "TAS records received from a TAS analyzer running with modified software. The modification to the TAS analyzer created a function which filled the TAS analyzer's memory with a special set of test records."
        It does not appear to be real patient data, nor is there information on the country of origin. This was a simulated/generated dataset for software validation.

    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. The ground truth for this software validation was the expected output or behavior defined by the functional specifications. The "known record sets" and the "special set of test records" were specifically designed with expected outcomes against which the software's performance was compared. This is a characteristic of functional software testing, not clinical validation requiring expert review of primary data like medical images or pathology slides.

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

    • Not applicable. As described above, the testing involved comparing the software's output against predefined expected behaviors from the "Functional Specification" and the design of the "known record sets" and "special set of test records." There was no human adjudication process involved in establishing ground truth for individual cases.

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

    • No. This device is a software system for collecting, viewing, and organizing results from TAS analyzers, and indicating if results are within user-defined ranges. It is not an AI-assisted diagnostic tool or an imaging modality that would involve human readers making interpretations.

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

    • Yes, in essence. The validation described is of the standalone software functionality. The tests verified that the TRAQS software independently collected, sorted, viewed, archived data, and correctly flagged out-of-range results as per its defined specifications. There is no "human-in-the-loop" aspect to its core functional validation; it's about the software performing its programmed tasks correctly.

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

    • The ground truth was established by the Functional Specification documents and the design of the test data sets. The "known record sets" and the "special set of test records" were created with predefined expected results, allowing for direct comparison against the software's output. This is typical for rigorous software validation.

    8. The sample size for the training set

    • Not applicable. This is a rule-based software for data management, not a machine learning or AI algorithm that requires a "training set" in the conventional sense. The software's functionality is derived from its programming according to specifications, not from learning from data.

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

    • Not applicable, as there was no training set for a machine learning model.
    Ask a Question

    Ask a specific question about this device

    K Number
    K981178
    Date Cleared
    1998-04-27

    (26 days)

    Product Code
    Regulation Number
    864.5425
    Reference & Predicate Devices
    N/A
    Why did this record match?
    Applicant Name (Manufacturer) :

    CARDIOVASCULAR DIAGNOSTICS, INC.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    Intended for use with the TAS analyzer and TAB LHMT cards to provide a method for quality control of the system.

    Device Description

    The controls for TAS LHMT cards consist of two separate vials. One was designed to mimic a sample from a normal individual, and the second to mimic a sample from a patient with a prolonged clotting time due to administration of heparin. These controls are made with pig plasma. To make the controls as easy to use as possible for point-of-care testing, we chose the patented packaging system of Medtox, (Burlington, NC). This consists of a closed, crushable glass ampoule containing lyophilized plasma which is inside a plastic sleeve. The sleeve contains water for diluent and has a capped dropper top with a filter in the tip (to remove glass shards from the sample). The entire assembly is shrink wrapped with a label and plastic seal. To use, the ampoule is crushed inside the plastic sleeve, which allows the diluent to mix with the Ivophilized plasma. The mixture is reconstituted by shaking or vortexing the capped vial. The plastic seal and cap are removed and three drops of plasma suspension are discarded into a biohazard waste container (to eliminate the dilution effect of the diluent that is contained in the filter). A drop of the plasma suspension is added to a TAS LHMT card in an analyzer. The rest of the test procedure and the manner of signal production is identical to that for a patient sample.

    AI/ML Overview

    The provided text describes the TAS LHMT Controls, a device used for quality control of the TAS Analyzer and TAS LHMT cards in coagulation studies.

    Here's an analysis of the acceptance criteria and the study that demonstrates device performance:

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

    The document does not explicitly state formal "acceptance criteria" or specific thresholds the device must meet for approval. Instead, it demonstrates the device's performance through precision studies. The primary goal is to show that the TAS LHMT Controls perform "comparably" and are "substantially equivalent" to the predicate device (TAS HMT controls) and produce consistent clotting times within expected ranges.

    Therefore, the "acceptance criteria" are implicitly derived from the reported precision (low CV%) for both normal and heparin controls, and the demonstration that the control produces clotting times "like that of a normal individual" and "mimics the response of a patient given a moderate level of heparin." The stability data (room temperature and freezer stability) also functions as a performance measure.

    CharacteristicAcceptance Criteria (Implicit)Reported Device Performance (TAS LHMT Controls)
    Within-day PrecisionLow Coefficient of Variation (CV%) for clotting timesNormal Control: Mean 151 sec, SD 1.7, CV 1.1%
    Heparin Control: Mean 296 sec, SD 9.8, CV 3.3%
    Lot-to-lot PrecisionLow Coefficient of Variation (CV%) across different lotsNormal Control (3 lots): Mean 152-153 sec, CV 1.0-2.3%
    Heparin Control (3 lots): Mean 293-296 sec, CV 3.7-5.7%
    Mimicry of physiological statesNormal control produces clotting time like a normal individual; Heparin control mimics a patient with moderate heparin.Normal control produced clotting time "like that of a normal individual"; Heparin control "mimics the response of a patient given a moderate level of heparin."
    Stability (Room Temp)Stable for a specified period (e.g., at least 6 weeks)Stable for at least 6 weeks at 20-25°C indicating probable refrigerator stability of at least six months.
    Stability (Reconstituted)Stable for a specified short periodReconstituted vials are stable for five minutes.
    Stability (Freezing)Little to no effect on performanceNo significant difference in mean or CV produced by controls stored at -80°C compared to refrigerated vials.
    Effect of HeatingAvoid significant increase in clotting timeHeating intact vials to 37°C for several days causes an increase in mean clotting time. (This is a condition to avoid, not a criterion to meet, showing understanding of limits).
    Dispensing AngleLittle to no effect on resultsLittle effect on mean clotting times or CV.

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

    • Sample Size for Precision Studies:
      • Within-day precision: The sample size (n) for the within-day precision is not explicitly stated in the provided table. It gives a single mean, SD, and CV, suggesting multiple measurements were taken to derive these metrics.
      • For Lot-to-lot precision: "n = 30 each" is stated, meaning 30 measurements were taken for each of the three lots for both the Normal and Heparin controls. So, 30 measurements for Normal Lot 1, 30 for Normal Lot 2, 30 for Normal Lot 3, and similarly for the Heparin lots.
    • Data Provenance: The document does not specify the country of origin of the data. The studies appear to be retrospective analyses, conducted by the manufacturer, Cardiovascular Diagnostic, Inc., to characterize the performance of their TAS LHMT Controls.

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

    This information is not applicable to this submission. The device (TAS LHMT Controls) is a quality control material intended to verify the proper functioning of an analyzer and test cards. Its "ground truth" is its inherent chemical and physical properties that, when measured by the TAS system, produce expected clotting times. There are no human "experts" establishing a diagnostic ground truth for individual cases. The "ground truth" for the controls themselves (e.g., what constitutes a "normal" clotting time or a "heparinized" clotting time) is established by the design of the control material to mimic these states.

    4. Adjudication method for the test set

    This information is not applicable. Since this device is a quality control material, there is no need for expert adjudication of results, as there would be for a diagnostic device interpreting patient samples. The measurements are objective clotting times from the control material.

    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. This device is a quality control reagent, not an AI-assisted diagnostic tool. Therefore, MRMC studies and the concept of "human readers improving with AI" do not apply.

    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 control material, not an algorithm. Its performance is measured through its objective chemical properties and the reproducibility of results obtained from the measurement system it is designed to control.

    7. The type of ground truth used

    The "ground truth" for the TAS LHMT Controls are:

    • Designed chemical properties: The controls are made with pig plasma and formulated to produce specific clotting times under defined conditions.
    • Mimicry of physiological states: The "Normal" control is designed to produce a clotting time similar to a normal individual, and the "Heparin" control is designed to mimic a patient with a moderate level of heparin. This is the intended performance characteristic that the control aims to represent.
    • Comparison to predicate device: The performance is also validated by comparing it to the predicate TAS HMT controls, ensuring "no significant differences" in performance.

    8. The sample size for the training set

    This information is not applicable. This is a quality control reagent, not a machine learning or AI-based device that requires a "training set." The controls are manufactured based on established chemical formulations and tested for consistency and performance.

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

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

    Ask a Question

    Ask a specific question about this device

    K Number
    K971748
    Date Cleared
    1997-05-29

    (17 days)

    Product Code
    Regulation Number
    864.5425
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    CARDIOVASCULAR DIAGNOSTICS, INC.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The new TAS PT-NC Controls are intended to be used with the TAS Analyzer and PT-NC test cards to provide a method for quality control of the system. The controls produce clotting times which must be within accepted, standard ranges, to indicate that the analyzer and test cards are functioning properly and thereby help assure the accuracy of PT-NC test card results. These controls were designed to allow CVDI's point of care customers to maintain accepted laboratory standards and requirements. These controls also can be used to determine system (TAS Analyzer and PT-NC test cards) precision. The controls are substantially equivalent in Intended use to other control materials used in coagulation tests.

    Device Description

    The controls for TAS PT-NC test cards consist of two separate vials. One was designed to mimic a sample from a normal individual, and the second to mimic a sample from a patient with an abnormally prolonged clotting time due to a deficiency of extrinsic coagulation factors. These controls are made with human plasma screened for antibodies to and antigens of hepatitis and Human Immunodeficiency viruses. To make the controls as easy to use as possible for point-of-care testing, we chose the patented packaging system of EDITek (Burlington, NC). This consists of a closed, crushable glass ampoule containing lyophilized plasma which is inside a plastic sleeve. The sleeve contains water for diluent and has a capped dropper top with a filter in the tip (to remove glass shards from the sample). The entire assembly is shrink wrapped with a label and plastic seal. To use, the ampoule is crushed inside the plastic sleeve, which allows the diluent to mix with the lyophilized plasma. The mixture is reconstituted by shaking or vortexing the capped vial. The plastic seal and cap are removed and three drops of plasma suspension are discarded into a biohazard waste container (to eliminate the dilution effect of the diluent that is contained in the filter). A drop of the plasma suspension is added to a TAS PT-NC test card in an analyzer. The rest of the test procedure and the manner of signal production is identical to that for a patient sample.

    AI/ML Overview

    Here's an analysis of the provided text to extract information about the device's acceptance criteria and the study proving it, formatted as requested:

    Device: TAS PT-NC Controls

    1. Table of Acceptance Criteria and Reported Device Performance

    The document doesn't explicitly state "acceptance criteria" in a numerical, pass/fail format for the performance studies. However, it implicitly uses a comparison to a predicate device and stability/precision metrics as indicators of acceptable performance. The "normal ranges" for the within-day precision essentially serve as the expected performance.

    CharacteristicAcceptance Criteria (Implicit/Stated Goal)Reported Device Performance
    Intended UseAssure performance of system by functional testing (comparison to predicate)Substantially equivalent to predicate, produces clotting times within set limits.
    Stability (Room Temp)At least 13 weeks of storage at room temperature (20-25°C)Stable for at least 13 weeks.
    Stability (Refrigerator)Probable refrigerator stability of at least one yearProbable refrigerator stability of at least one year (inferred from room temp stability).
    Stability (Frozen)Little to no effect on performance at -80°CNo significant difference in mean or CV compared to refrigerated vials.
    Stability (High Temp)Not explicitly stated as a pass/fail, but adverse effect noted.Heating to 37°C for several days causes an increase in mean clotting time.
    Within Day Precision (Normal Control)Clotting time like that of a normal individual; expected range 9.3 - 11.0 secMean: 10.1 sec, SD: 1.4, CV: 4.1% (within 9.3 - 11.0 range)
    Within Day Precision (Abnormal Control)Responds like a patient with extrinsic coagulation factor deficiency; expected range 40.4 - 55.6 secMean: 43.3 sec, SD: 2.9, CV: 6.6% (within 40.4 - 55.6 range for 5-10 drops)
    Overall CV (Abnormal Control - "first drop")Expected CV ~7% for QA testing in the fieldOverall CV for abnormal control (all days, all experiments, "first drop" analysis): 7%
    Lot-to-Lot Precision (Normal Control)Not directly stated numerically, but expected to be low variation.Mean (sec): 10.1, 11.9, 12.2; CV (%): 4.2, 5.8, 6.1 (for 3 lots)
    Lot-to-Lot Precision (Abnormal Control)Not directly stated numerically, but expected to be low variation.Mean (sec): 43.5, 41.4, 41.8; CV (%): 6.9, 8.3, 9.1 (for 3 lots)
    Field Study (Normal Control)(Comparison to predicate/internal lab results)Site A: Mean 10.7, CV 9.9; Site B: Mean 10.5, CV 6.3
    Field Study (Abnormal Control)(Comparison to predicate/internal lab results)Site A: Mean 45.2, CV 13.6; Site B: Mean 49.7, CV 8.0

    2. Sample Size for the Test Set and Data Provenance

    • Sample Size:
      • Within-day precision: "Most of these studies were done with five to ten drops from the same vial." The tables show "mean ranges" for normal and abnormal controls, implying multiple measurements. For lot-to-lot precision, n = 40 each is stated, referring to individual measurements for each lot.
      • Field study: "tested at least in duplicate each day for 20 days" at each site. This means a minimum of 40 measurements per control type per site (2 measurements/day * 20 days).
    • Data Provenance: Retrospective (implicitly, as the studies are completed before submission).
      • Country of Origin: United States (Cardiovascular Diagnostic, Inc. is in Raleigh, NC; EDITek is in Burlington, NC; clinical study sites are not explicitly named with country, but the submission is to FDA, implying US studies).
      • Type of Study: Laboratory studies for stability and precision, and a multi-site field study for variation.

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

    Not applicable. This device is a quality control material, not a diagnostic device that interprets clinical data or images requiring expert consensus for ground truth. Its "ground truth" is its measured clotting time characteristics, stability, and precision when run on the TAS Analyzer.

    4. Adjudication Method for the Test Set

    Not applicable for a quality control device's performance study. The "ground truth" is the empirically measured clotting time.

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

    No, an MRMC study was not done. This device is a quality control material intended to verify instrument and test card function, not a diagnostic tool requiring human interpretation or assistance.

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

    Yes, the studies presented are essentially standalone performance evaluations of the TAS PT-NC Controls themselves, measuring their inherent characteristics (stability, precision) when used with the TAS Analyzer and PT-NC test cards. There is no human interpretation component of the control material's result that would be assisted by an "algorithm." The algorithm is embedded within the TAS Analyzer for determining the clotting time from the sample.

    7. The Type of Ground Truth Used

    The ground truth for this device (a quality control material) is based on:

    • Empirical Measurement: Directly measured clotting times in seconds using the TAS Analyzer system.
    • Comparison to Predicate: Performance is compared to the established TAS PT controls.
    • Physiological Mimicry: The controls are designed to mimic a normal individual or a patient with an abnormally prolonged clotting time due to extrinsic coagulation factor deficiency.

    8. The Sample Size for the Training Set

    The document does not explicitly describe a "training set" in the context of machine learning or algorithm development. The device is a physical control material. The data presented are for validation/testing the performance of the manufactured control materials.

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

    Not applicable as there is no mention of a "training set" for an algorithm. The ground truth for the development of the control material itself would involve careful formulation, characterization, and comparison to known clinical samples or established reference materials, but this information is not detailed in the summary provided.

    Ask a Question

    Ask a specific question about this device

    K Number
    K961814
    Date Cleared
    1996-08-13

    (95 days)

    Product Code
    Regulation Number
    864.5425
    Reference & Predicate Devices
    N/A
    Why did this record match?
    Applicant Name (Manufacturer) :

    CARDIOVASCULAR DIAGNOSTICS, INC.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use
    Device Description
    AI/ML Overview
    Ask a Question

    Ask a specific question about this device

    K Number
    K961189
    Date Cleared
    1996-06-05

    (71 days)

    Product Code
    Regulation Number
    864.5425
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    CARDIOVASCULAR DIAGNOSTICS, INC.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The new TAS aPTT Controls are intended to be used with the TAS Analyzer and aPTT cards, cleared by the FDA, to provide a method for quality control of the system. The controls produce clotting times which must be within accepted, standard ranges, to indicate that the analyzer and test cards are functioning properly and thereby help assure the accuracy of aPTT test results. The controls are substantially equivalent in intended use to other controls used in coagulation assays.

    Device Description

    The controls for TAS aPTT cards consists of two separate vials. One was designed to mimic a sample from a normal individual, and the second to mimic a sample from a patient with a clotting factor deficiency of the intrinsic or common coagulation pathway. These controls are made with human plasma screened for antibodies to and antigens of human immunodeficiency and hepatitis viruses. To make the controls as easy to use as possible for point-of-care testing, we chose the patented packaging system of EDItek. This consists of a closed, crushable glass ampule containing lyophilized plasma which is inside a plastic sleeve. The sleeve contains water for diluent and has a capped dropper top with a filter tip. The entire assembly is shrink wrapped with a label and plastic seal. To use, the ampule is crushed inside the plastic sleeve, which allows the diluent to mix with the lyophilized plasma. The mixture is reconstituted by shaking or vortexing the capped vial. The plastic seal and cap are removed, two drops of plasma are discarded into a biohazard waste container, and a drop of the plasma suspension is added to a TAS aPTT test card in an analyzer. The rest of the test procedure and the manner of signal production is identical to that for a patient sample.

    AI/ML Overview

    This PAC summary is based on the provided text, which appears to be a regulatory submission for a medical device (TAS aPTT Controls). The information is primarily focused on demonstrating substantial equivalence to a predicate device rather than a comprehensive study report with detailed acceptance criteria and standalone performance metrics typically found in AI/ML device studies.

    1. Table of acceptance criteria and the reported device performance

    Based on the provided text, the primary acceptance criteria for the TAS aPTT Controls are related to their ability to provide clotting times that are comparable to a legally marketed predicate device (Ci-trol; Dade; Baxter Diagnostics, Inc.) and to fall within established standard ranges. The device performance is generally qualitative, stating that results "compared well" and that there were "no significant differences."

    Acceptance CriteriaReported Device Performance (TAS aPTT Controls)
    Produce clotting times comparable to legally marketed predicate control device (Ci-trol; Dade) when used with TAS Analyzer and aPTT test cards."In clinical comparison studies the TAS aPTT Controls provided results that compared well with other legally marketed controls for the aPTT test (Ci-trol; Dade; Baxter Diagnostics, Inc.) when used to test the operation of the TAS Analyzer and test cards."
    Clotting times must be within accepted, standard ranges."The controls produce clotting times which must be within accepted, standard ranges, to indicate that the analyzer and test cards are functioning properly and thereby help assure the accuracy of aPTT test results." (Implied to be met for adequate performance.)
    Normal control produces a clotting time like that of a normal individual."The normal control produces a clotting time like that of a normal individual (but have different times for different reagent/instrument combinations)."
    Abnormal control responds like a patient with a severe factor deficiency of the intrinsic coagulation pathway."Like other control manufacturers, we chose to make an abnormal control that responds like a patient that has a severe factor deficiency of the intrinsic coagulation pathway."
    No significant differences in performance compared to the predicate device."There were no significant differences in the performance of the TAS aPTT Controls and the control from another manufacturer used as predicate device." (This is a summary statement of the comparison study's findings.)

    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 mentions "clinical comparison studies" for the TAS aPTT Controls. However, the specific sample size for the test set is not provided. The data provenance (e.g., country of origin, retrospective or prospective) is also not explicitly stated. Given the context of a regulatory submission, it is highly likely these were prospective studies conducted in a clinical or laboratory setting.

    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 or not provided for this type of device and study. The "ground truth" for a coagulation control is its measured clotting time using a reference method or instrument, compared against established norms or predicate device performance, not typically requiring human expert consensus in the same way an AI diagnostic imaging system would.

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

    This information is not applicable or not provided. Since the "ground truth" for this device involves objective measurements (clotting times) and comparison to a predicate device, an adjudication method for conflicting expert opinions would not be 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, a multi-reader multi-case (MRMC) comparative effectiveness study was not mentioned or conducted as this device is an in vitro diagnostic control, not an AI/ML-assisted diagnostic tool that would involve human readers interpreting results.

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

    This question is not directly applicable in the context of this device. The TAS aPTT Controls are a reagent used with an analyzer and test cards. Their performance is inherently tied to the system they are controlling. The "standalone" performance, in this case, would refer to the performance of the control when used as intended, which is precisely what the comparison studies aimed to evaluate. There isn't an "algorithm only" component separate from the physical control and its interaction with the analyzer.

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

    The "ground truth" for the TAS aPTT Controls is established by:

    • Comparison to a legally marketed predicate device: The clotting times generated by the TAS aPTT Controls are compared to those generated by the Dade controls, which are already accepted as accurate.
    • Established standard ranges: The clotting times are expected to fall within predetermined, accepted standard ranges for normal and abnormal controls, reflecting known physiological states (normal individual, severe factor deficiency).
    • Functional testing: The device's ability to indicate that the associated analyzer and test cards are functioning properly, thereby assuring the accuracy of aPTT test results.

    8. The sample size for the training set

    Not applicable. This device is an in vitro diagnostic control, not an AI/ML system that requires a "training set" in the conventional sense. The "development" of the control involved designing formulations to mimic specific physiological states and then validating their performance against existing methods.

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

    Not applicable. As indicated in point 8, there is no "training set" in the AI/ML context for this device. The "ground truth" for the development of the controls would have been based on established clinical and laboratory standards for aPTT testing, characteristics of normal plasma, and plasma from patients with known coagulation factor deficiencies, along with the performance metrics of existing, validated control materials.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 2