Search Results

The ACL TOP Family 50 Series (ACL TOP 750; ACL TOP 750 CTS; ACL TOP 750 LAS; ACL TOP 550 CTS; ACL TOP 350 CTS) are bench top, fully automated, random access analyzers designed specifically for in vitro diagnostic clinical use in the hemostasis laboratory for coagulation and/or fibrinolysis testing in the assessment of thrombosis and/or hemostasis. The systems provide results for both direct hemostasis measurements and calculated parameters.

The ACL TOP Family 50 Series are fully automated coagulation analyzers that utilize the same intuitive software, the same consumables, reagents, calibrators and controls, and provide the same analytical methodology for routine and specialty assay result reporting as the predicate ACL TOP Family.

The ACL TOP Family 50 Series instrument performs the following types of tests, using the same optical measuring wavelengths and test parameters as the predicate ACL TOP Family:

• Coagulometric (Turbidimetric) Measurements
• . Chromogenic (Absorbance) Measurements
• . Immunological Measurements

The ACL TOP Family 50 Series also offers new pre-analytical features not available on the current ACL TOP Family as described below. These features are not intended to replace laboratory quality policies. The features simply alert the instrument operator to a potential HIL (Hemoglobin, Icteric and Lipemia) interference situation specific to the assays requested for a sample, underfilled sample tubes or a detected clog. The user will determine how to handle these situations (for example, by not reporting the results, or reporting the results with, or without, additional comments).

The provided text does not contain detailed acceptance criteria and a study proving the device meets those criteria in the traditional sense of a clinical or performance study for a diagnostic device.

This document is a 510(k) summary for a Special 510(k) submission, focusing on software changes (new remote features and enhanced cybersecurity measurements) to an existing device, the ACL TOP Family 50 Series. The key statement regarding acceptance criteria and proof of performance is:

"The software verification and validation study results demonstrate that the ACL TOP Family 50 Series with updated nonanalytical features is safe and effective for its intended purpose and equivalent in performance to the predicate device (K150877)."

This indicates that the "acceptance criteria" were related to the software's functionality, security, and the assertion that these non-analytical changes do not impact the analytical performance of the instrument. The "study" mentioned is a "software verification and validation study."

Given this, I will extract and infer the information based on the context of a software-focused 510(k) for a device where analytical performance is already established by a predicate.

Here's the breakdown based on your requested format:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample size used for the test set and the data provenance
The document refers to a "software verification and validation study results." For software changes, the "test set" would typically involve functional and security testing scenarios rather than patient data. The document does not specify a sample size in terms of patient data or the provenance (country of origin, retrospective/prospective) because the changes are non-analytical software updates to an existing, already cleared device.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable based directly on the provided text, as the "ground truth" for these software functionalities would be their correct operation and security posture, established by software engineers, cybersecurity experts, and regulatory experts. The document does not detail specific experts or their qualifications for the V&V study.

4. Adjudication method for the test set
Not applicable. Adjudication methods like 2+1 or 3+1 are typically used for clinical studies involving human interpretation of medical images or tests. For software verification and validation of non-analytical features, testing protocols and bug reporting/resolution processes would be used.

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 coagulation analyzer, not an AI-powered diagnostic imaging device involving "human readers." The changes specifically "do not impact the analytical performance of the instrument."

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This is a device that runs algorithms for coagulation measurements, and the "standalone" performance of these measurement algorithms was established by the predicate device (K150877). The new features are remote control and cybersecurity updates, not new analytical algorithms. The software verification and validation focused on these new non-analytical features operating correctly without human intervention (e.g., remote update deployment), but this is not an "algorithm only" performance study in the typical sense for clinical impact.

7. The type of ground truth used
For the software verification and validation related to the new remote and cybersecurity features, the "ground truth" would be:

• Functional Specification Adherence: The software correctly performs the defined remote control and update delivery functions according to its design specifications.
• Security Standard Compliance: The cybersecurity features meet established security standards and mitigate identified risks.
• Non-Interference: The new features do not interfere with the validated analytical performance of the device.

8. The sample size for the training set
Not applicable. This is a software update for an existing medical device, not a machine learning or AI algorithm development that requires a "training set" of data.

9. How the ground truth for the training set was established
Not applicable, as there is no training set for the software changes described.

Ask a specific question about this device

The ACL TOP Family 70 Series (ACL TOP 370, ACL TOP 570 and ACL TOP 770 / 770s / 770 LAS) are bench top, fully automated, random access analyzers designed specifically for in vitro diagnostic clinical use by health care professionals in the hemostasis laboratory for coagulation and/or fibrinolysis testing in the assessment of thrombosis and/or hemostasis. The systems provide results for both direct hemostasis measurements and calculated parameters.

The ACL TOP Family 70 Series are fully automated coagulation analyzers that utilize the same intuitive software, the same consumables, reagents, calibrators and controls, and provide the same analytical methodology for routine and specialty assay result reporting as the predicate ACL TOP Family 50 Series.

The ACL TOP Family 70 Series instrument performs the following types of tests, using the same optical measuring wavelengths and test parameters as the predicate ACL TOP Family 50 Series:

• . Coagulometric (Turbidimetric) Measurements
• Chromogenic (Absorbance) Measurements .
• . Immunological Measurements

The ACL TOP Family 70 Series also offers the same pre-analytical features available on the ACL TOP Family 50 Series. These features alert the instrument operator to a potential HIL (Hemoglobin, Icteric and Lipemia) interference situation specific to the assays requested for a sample, underfilled sample tubes or a detected clog.

Here's a breakdown of the acceptance criteria and study details for the ACL TOP Family 70 Series device, based on the provided document:

Acceptance Criteria and Reported Device Performance

The core acceptance criterion for the ACL TOP Family 70 Series appears to be demonstrating equivalent analytical performance to its predicate device, the ACL TOP Family 50 Series, across various representative assays. This equivalency is assessed through precision and method comparison studies.

Table of Acceptance Criteria and Reported Device Performance:

• HemosIL D-Dimer HS 500: Low Control Total %CV 4.8, High Control Total %CV 2.1
• HemosIL Factor VIII: Normal Control Total %CV 3.4, Abnormal Control Total %CV 4.8
• HemosIL RecombiPlasTin 2G (PT): Normal Control Total %CV 1.8, High Abn Control %CV 4.0
• HemosIL RecombiPlasTin 2G (Fibrinogen): Normal Control Total %CV 3.9, Low Fibrinogen Control %CV 8.1
• HemosIL Liquid Anti-Xa: UF Low Control Total %CV 1.8, LMW High Control Total %CV 2.2 |
  | Method Comparison | Linear regression analysis (slope, intercept, correlation coefficient 'r') between the subject device and predicate device should demonstrate equivalent performance across the analytical measuring range (AMR), according to established guidelines (CLSI EP09c. 3rd Ed). | Successfully met criteria. All studies showed strong correlation (r ≥ 0.998) and slopes close to 1 with intercepts close to 0, indicating equivalence. Examples:
• HemosIL D-Dimer HS 500: Slope 1.022, Intercept 0.5575, r 0.998
• HemosIL Factor VIII: Slope 1.006, Intercept -0.0587, r 0.998
• HemosIL RecombiPlasTin 2G (PT): Slope 1.012, Intercept -0.0940, r 1.000
• HemosIL RecombiPlasTin 2G (Fibrinogen): Slope 0.9756, Intercept -1.1220, r 0.999
• HemosIL Liquid Anti-Xa: Slope 0.9804, Intercept -0.0145, r 0.999 |
  | Overall Conclusion | Updates introduced do not impact the labeled performance data of the current menu of FDA-cleared assays. Device is safe and effective for its intended purpose and equivalent in performance to the predicate device. | Analytical study results demonstrate that the ACL TOP Family 70 Series, with updated non-analytical features, is safe and effective for its intended purpose and equivalent in performance to the predicate device (K150877). |

Study Details:

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

   • Precision Studies:
     • For each material/control for the selected representative assays, samples were run for 20 days at two runs per day, 2 replicates per run, resulting in a total of n=80 data points per material.
     • Provenance: Not explicitly stated, but based on the context of an FDA submission for an in vitro diagnostic device, these would typically be laboratory-generated samples or commercial control materials. The studies were performed internally by the manufacturer ("Instrumentation Laboratory Company").
   • Method Comparison Studies:
     • Sample sizes varied per assay:
       • HemosIL D-Dimer HS 500: N = 116 clinical samples
       • HemosIL Factor VIII: N = 104 clinical samples
       • HemosIL RecombiPlasTin 2G (PT): N = 116 clinical samples
       • HemosIL RecombiPlasTin 2G (Fibrinogen): N = 114 clinical samples
       • HemosIL Liquid Anti-Xa: N = 207 clinical samples
     • Provenance: The studies included "clinical samples spanning each assay's analytical measuring range (AMR)." The country of origin of these clinical samples is not specified, but they are prospectively collected or selected for the study based on their span across the AMR.

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

   • This being an in vitro diagnostic (IVD) device for laboratory analysis, the "ground truth" for the test set is established by the measurement itself on a recognized, cleared, and well-characterized comparator device (the predicate ACL TOP Family 50 Series), or by the known concentrations/activity of control materials. It's not a subjective interpretation task that requires human adjudication or expert consensus in the same way as, for example, image-based diagnostic AI. Therefore, no human experts are explicitly mentioned as establishing a subjective ground truth for these analytical performance studies. The "ground truth" for method comparison is the performance of the predicate device.

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

   • None. Adjudication methods like 2+1 or 3+1 are typically used in studies involving subjective human interpretation (e.g., radiology reads) where discrepancies need to be resolved. For analytical performance studies of a medical device measuring quantitative analytes, the ground truth is objective (the measured value from the predicate device or a known concentration in a control).

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. An MRMC study is not applicable here as this is an in vitro diagnostic instrument, not an AI-assisted diagnostic tool that involves human readers interpreting cases. The device automatically performs coagulation and/or fibrinolysis testing.

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

   • Yes, effectively. The entire study evaluates the analytical performance of the device itself (the ACL TOP Family 70 Series) in a standalone manner. While trained lab personnel operate the instrument, the performance metrics (precision, method comparison) are about the instrument's ability to produce accurate and precise results, independent of human interpretive intervention for the results themselves. The device's "algorithm" (its internal measurement and calculation processes) is being evaluated.

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

   • For precision studies, the ground truth is the known concentration/activity of control and plasma pool materials.
   • For method comparison studies, the ground truth is the measured values obtained from the predicate device (ACL TOP Family 50 Series) for the same clinical samples. The principle is to see if the new device produces equivalent results when compared to an already accepted diagnostic method.

7. The sample size for the training set:

   • The document does not mention a training set in the context of machine learning or AI model development. This device is an IVD instrument that utilizes established analytical methodologies (coagulometric, chromogenic, immunological measurements) and software, rather than a machine learning model that requires a discrete training phase with labeled data. The studies performed are verification and validation studies to demonstrate performance and equivalency to a predicate.

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

   • As there is no mention of a "training set" in the context of an AI/ML model, this question is not applicable. The device's operation is based on pre-defined analytical principles, not on learning from a training dataset to establish a ground truth.

Ask a specific question about this device

The QNext is a fully-automated, random-access instrument, intended for in vitro diagnostic use in clinical laboratories to perform hemostasis testing by detecting the changes in optical density.

DG-PT is a thromboplastin reagent for the quantitative determination of Prothrombin Time on human plasma samples collected in 3.2% sodium citrate.

The product is used for the evaluation of the extrinsic and common coagulation pathways in seconds and for the monitoring Oral Anticoagulant Therapy with warfarin in International Normalized Ratio (INR).

For use with ONext.

For clinical professional laboratory and prescription use only.

For in vitro diagnostic use.

The performance of this device has not been established in neonate and pediatric patient populations.

QNext is designed to automatically perform all stages of the procedures associated to hemostasis tests allowing the operator to:

• Absorb the workload involved in running hemostasis laboratory tests profiles, optimizing the execution of these profiles in the shortest time possible, and ensuring the maximum possible precision and accuracy in the results.
• Increase the reliability of the analytical process, eliminating any possible errors in the identification ● and treatment of samples and products and in the revision and transcription of the results.
• Reduce the risk of Operator contamination by minimizing interaction between the Operator and ● samples and products during the analytical process.

To perform the operations for which it has been designed, QNext automatically follows the steps listed below:

• Sample management: loading, positive identification, dilution (if required) and dispensation into cuvettes.
• Reagent management: loading, positive identification, cooling, stirring, aspiration and dispensation into cuvettes.
• Cuvette management: loading, transport, incubation during the reactions and management of used cuvettes.
• Management of test requests. ●
• Execution of test procedures.
• Result management: optical measurement of the reactions, algorithm calculation of analytical parameters from reaction curves, validation of results, traceability, bi-directional transmission of requests and results to the LIS.
• Management of disposable components. ●

The data analyzed can be stored, displayed and printed. Additionally, the analyzer allows conducting integrated functions, such as the analysis of urgent samples or the Quality Control module.

DG-PT consists of a glass vial containing lyophilized thromboplastin (tissue factor and phospholipids) from rabbit brain tissue, buffer, calcium ions and preservative. The closure system includes a stopper and a screw сар.

DG-PT reagent is used to perform PT tests for:

• the evaluation of the extrinsic and common coagulation pathways.
• The monitoring Oral Anticoagulant Therapy with warfarin.

The assay is based on the activation of the extrinsic coagulation pathway by the addition of the reagent to the plasma sample. The thromboplastin interacts with FVII and calcium ions activating a series of specific enzymes that comprise the extrinsic and common pathways of the coagulation cascade ultimately leading to the formation of a fibrin clot. The QNext reader measures the light change produced during the reaction.

The provided text describes the performance testing of the ONext instrument and DG-PT reagent for Prothrombin Time (PT) determination, but it does not contain information related to an AI/ML powered device. Therefore, many of the requested criteria regarding AI/ML device performance (e.g., multi-reader multi-case studies, human-in-the-loop performance, training set details, expert ground truth adjudication) are not applicable to this document.

However, I can extract and present the acceptance criteria and performance data for the described in-vitro diagnostic device:

Device: ONext (fully-automated hemostasis instrument) and DG-PT (thromboplastin reagent for PT determination).

Study Proving Device Meets Acceptance Criteria:
The submission details several performance studies conducted according to CLSI guidelines to demonstrate the substantial equivalence of the ONext and DG-PT to predicate devices.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state pre-defined quantitative acceptance criteria thresholds for each study (e.g., "Precision CV must be less than X%"). Instead, it presents the results of various performance studies (Precision, Reference Interval, Sensitivity, Specificity, Method Comparison) which are implicitly understood to meet the necessary performance characteristics for substantial equivalence. The "performance" column therefore reflects the observed results from these studies.

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

• Precision Studies:
  • Repeatability and Within-laboratory: 7 patient-derived samples. Data provenance not explicitly stated (e.g., country of origin), assumed to be clinical samples. Retrospective/prospective not specified, but typically for precision studies, these would be collected prospectively or obtained from a biobank.
  • Reproducibility: 7 patient-derived samples. Data provenance not explicitly stated (e.g., country of origin), assumed to be clinical samples. Retrospective/prospective not specified.
• Reference Interval Study: 243 reference samples. Data provenance not explicitly stated.
• Sensitivity Study: Not specified, but involved a set of samples spanning from 100% to

Ask a specific question about this device

The Sysmex® CS-5100 is a fully automated blood coagulation analyzer intended for in vitro diagnostic use using plasma collected from venous blood samples in 3.2% sodium citrate tubes to analyze clotting, chromogenic and immunoassay methods in the clinical laboratory.

For determination of:

· Prothrombin Time (PT) seconds and PT INR with Dade® Innovin®

• · Activated Partial Thromboplastin Time (APTT) with Dade® Actin® FSL
  · Fibrinogen (Fbg) with Dade® Thrombin Reagent

• · Antithrombin (AT) with INNOVANCE® Antithrombin
  · D-dimer with INNOVANCE® D-Dimer.

The performance of this device has not been established in neonate and pediatic patient populations.

The Sysmex CS-5100 is an automated blood coagulation instrument which can analyze samples using clotting, chromogenic and immunoassay methods. Analysis results are displayed on the Information Processing Unit (IPU) screen. They can be printed on external printers or transmitted to a host computer. Sold separately from the instrument are the associated:

• Reagents ■
• . Controls
• 트 Calibrators
• I Consumable materials

The subject of this 510(k) notification is to expand the use of the INNOVANCE® D-Dimer for the exclusion of Deep Vein Thrombosis on Sysmex CS-5100. All other established indications, performance and technology characteristics as cleared under K150678 remain unchanged.

Acceptance Criteria and Device Performance for Sysmex CS-5100 (D-Dimer DVT Exclusion)

This document describes the acceptance criteria and study proving the Sysmex CS-5100, specifically for the INNOVANCE® D-Dimer assay's extended indication for exclusion of Deep Vein Thrombosis (DVT), meets these criteria.

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria for the INNOVANCE® D-Dimer assay on the Sysmex CS-5100 for DVT exclusion are specifically defined by statistical measures of diagnostic accuracy, primarily Sensitivity, Specificity, and Negative Predictive Value (NPV), with a focus on their lower bound of the 95% confidence interval (LCL). The table below summarizes the reported device performance across different study populations. The predicate device (Sysmex CA-1500) data is included for comparison where available.

Comparison of DVT Exclusion Performance: Sysmex CS-5100 vs. Sysmex CA-1500 (Predicate)

*The predicate device's performance is listed as "The following instrument-specific sensitivity, specificity and negative predictive value (NPV) with upper and lower 95 % confidence limits (CL) were obtained with the INNOVANCE® D-Dimer clinical cutoff of 0.50 mg/L (FEU) for patients with unlikely pre-test probability." The specific wording for acceptance criteria for the new device is: "The values must be equal to or better than the predicate's performance while maintaining an equivalent confidence interval". The reported performance for the Sysmex CS-5100 matches or exceeds the predicate.

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

The DVT exclusion validation study for the Sysmex CS-5100 involved a initial prospective collection of 1907 consecutive outpatients with suspected DVT. After exclusions (including 213 patients with previously documented or chronic DVT), a total of 1317 patients were available for final analysis.

The data provenance is multicenter, prospective. The study included patients from both US and OUS (Outside US) sites:

• US sites: 803 patients
• OUS sites: 514 patients

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

The document does not explicitly state the number of experts or their specific qualifications used to establish the ground truth for the test set.

However, the ground truth was established by:

• Imaging methods (e.g., ultrasound) for patients with no or a positive D-dimer result by the study center's D-dimer assay, or at the physician's discretion for patients with a negative D-dimer.
• Three-month follow-up to evaluate potential development of DVT for all patients with a negative initial clinical diagnosis of DVT.

This implies that the ground truth was determined by clinical diagnosis using imaging results and clinical follow-up by treating physicians or specialists, rather than by independent expert reviewers of the D-Dimer results themselves.

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method for the test set in the traditional sense (e.g., 2+1, 3+1 expert review of independent interpretations).

The ground truth was established through a combination of:

• Imaging: Decisions based on imaging were likely made by radiologists or sonographers.
• Clinical follow-up: Clinical outcomes were assessed by physicians.

There is no mention of a formal adjudication process between multiple independent reviewers of the D-dimer results or the imaging findings.

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

There is no mention of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study being conducted as part of this submission for the Sysmex CS-5100's DVT exclusion indication.

This is an in vitro diagnostic device (automated coagulation analyzer), and its performance is evaluated based on the accuracy of its quantitative D-dimer measurements and the derived diagnostic metrics (Sensitivity, Specificity, NPV) against clinical ground truth, rather than human interpretation with and without AI assistance.

6. Standalone (Algorithm Only) Performance

The study primarily evaluates the standalone performance of the INNOVANCE® D-Dimer assay on the Sysmex CS-5100. The device generates a D-dimer result, which is then interpreted by comparing it to a cut-off value (0.50 mg/L FEU) to determine a positive or negative diagnosis for DVT exclusion. This is an "algorithm only" type of performance, as it quantifies a biomarker without direct human visual interpretation of an image or signal.

7. Type of Ground Truth Used

The ground truth used was a combination of clinical outcomes data and diagnostic imaging:

• Diagnostic Imaging: "Patients with no or a positive D-dimer result with the D-dimer assay used at the respective study center were evaluated by imaging methods, e.g. ultrasound."
• Outcomes Data (Clinical Follow-up): "All patients with a negative clinical diagnosis of DVT at presentation were followed up after three months to evaluate potential development of DVT."

This establishes a robust clinical diagnosis of DVT as the ground truth.

8. Sample Size for the Training Set

The document does not provide information on a specific training set size or methodology for the INNOVANCE® D-Dimer assay on the Sysmex CS-5100 related to its DVT exclusion indication.

This submission is for an extended indication of an existing device (Sysmex CS-5100) and an existing assay (INNOVANCE® D-Dimer), which likely had its primary development and calibration (analogous to training) performed prior to this specific DVT exclusion validation study. The current study focuses on clinical validation of the assay's performance for this specific indication.

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

As noted above, the document does not describe a specific training set or how its ground truth was established for the DVT exclusion indication. The information provided pertains to the validation (test) set.

It can be inferred that earlier development work for the INNOVANCE® D-Dimer assay, possibly on previous Sysmex analyzers, involved methods similar to the current validation study to establish its accuracy for general D-dimer measurements. However, details of such "training set" establishment are not part of this 510(k) summary for the extended DVT exclusion indication.

Ask a specific question about this device

The ACL TOP is a bench top, fully automated, random access analyzer designed specifically for in vitro diagnostic clinical use in the hemostasis laboratory for coagulation and/or fibrinolysis testing in the assessment of thrombosis and/or hemostasis. The system provides results for both direct hemostasis measurements and calculated parameters.

The ACL TOP Family are fully automated coagulation analyzers that utilize the same intuitive software, the same consumables, reagents, calibrators and controls, and provide the same analytical methodology for routine and specialty assay result reporting as the predicate ACL TOP Family. The ACL TOP Family instrument performs the following types of tests, using the same optical measuring wavelengths and test parameters as the predicate ACL TOP Family: Coagulometric (Turbidimetric) Measurements Chromogenic (Absorbance) Measurements Immunological Measurements

This document is a 510(k) premarket notification for a medical device called ACL TOP. The purpose of this submission is to demonstrate that the updated ACL TOP device, which has switched its operating system from Windows XP to Windows 7, is substantially equivalent to its legally marketed predicate devices.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria here is "Substantial Equivalence" to the predicate device. For a Special 510(k) submission, this means there are no changes to the indications for use or operating principle, and no changes to labeled performance claims, hardware, data reduction software, test parameters, calibration, quality controls, or consumables/reagents.

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

The document does not detail a specific test set, its sample size, or data provenance (e.g., country of origin, retrospective/prospective). This is a Special 510(k) submission primarily focused on an operating system change, where the core assumption is that due to no changes in critical operational aspects (hardware, reagents, methodology, etc.), the performance remains substantially equivalent to the predicate. Such submissions typically rely on verification and validation activities demonstrating that the new software does not negatively impact existing performance, rather than a full clinical study with a patient test set.

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

Not applicable. This type of submission relies on technical verification and validation of the software change, ensuring that it operates as intended and does not alter the established clinical performance of the device previously demonstrated for the predicate. There is no mention of expert-established ground truth for a clinical test set in this document.

4. Adjudication Method for the Test Set

Not applicable. As noted above, there is no clinical test set described that would require an adjudication method.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size

No. This document does not mention a MRMC comparative effectiveness study. This device is a coagulation instrument, not an AI-assisted diagnostic imaging device that would typically undergo such a study.

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

The device is an automated coagulation analyzer. Its "standalone" performance is its fundamental operation (i.e., producing test results). The change to the operating system is intended to maintain this standalone performance. No separate "algorithm-only" study distinct from the device's inherent function is described in the context of this submission.

7. The Type of Ground Truth Used

The "ground truth" for this submission is implicitly the established and cleared performance of the predicate ACL TOP Family devices. The updated device is considered substantially equivalent if it performs identically or comparably to the predicate for all stated measurement parameters and clinical indications. The document describes the device's functionality as "results for both direct hemostasis measurements and calculated parameters," implying that the accuracy of these measurements against established principles and validated methods would be the "ground truth" for the device's function.

8. The Sample Size for the Training Set

Not applicable. This device is an in-vitro diagnostic instrument for coagulation testing, not a machine learning or AI algorithm in the context of a "training set" as commonly referred to in AI development. The software change is an operating system update, which would involve software development and testing, but not typically a "training set" in the AI sense.

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

Not applicable, as there is no "training set" in the AI sense for this device. The ground truth for the device's performance would have been established during the development and clearance of the predicate devices, likely through extensive analytical and clinical validation studies against reference methods and clinical outcomes.

Ask a specific question about this device

The ACL TOP Family 50 Series (ACL TOP 750; ACL TOP 750 CTS; ACL TOP 750 LAS; ACL TOP 550 CTS; ACL TOP 350 CTS) are bench top, fully automated, random access analyzers designed specifically for in vitro diagnostic clinical use in the hemostasis laboratory for coagulation and/or fibrinolysis testing in the assessment of thrombosis and/or hemostasis. The systems provide results for both direct hemostasis measurements and calculated parameters.

The ACL TOP Family 50 Series are fully automated coagulation analyzers that utilize the same intuitive software, the same consumables, reagents, calibrators and provide the same analytical methodology for routine and specialty assay result reporting as the predicate ACL TOP Family. The ACL TOP Family 50 Series instrument performs the following types of tests, using the same optical measuring wavelengths and test parameters as the predicate ACL TOP Family: Coagulometric (Turbidimetric) Measurements, Chromogenic (Absorbance) Measurements, Immunological Measurements. The ACL TOP Family 50 Series also offers new pre-analytical features not available on the current ACL TOP Family: Pre-Analytical HIL Check, Pre-Analytical Tube Fill Height (THF) Check, and Pre-Analytical Clog Detection.

Acceptance Criteria and Device Performance for ACL TOP Family 50 Series

This document outlines the acceptance criteria and the results of the studies demonstrating that the ACL TOP Family 50 Series coagulation analyzers meet these criteria. The device is intended for in vitro diagnostic clinical use for hemostasis and fibrinolysis testing.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for this device are established through internal and external precision, linearity, and method comparison studies, specifically aiming for performance comparable to the predicate device (ACL TOP Family) and within CLSI guidelines. While explicit numeric acceptance criteria are not presented as a single consolidated table, the pass/fail status indicated in the reproducibility study and the strong correlation coefficients/slopes in the method comparison studies serve as de-facto acceptance criteria. The device consistently passed these criteria across various assays and models.

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

• Precision Study (Internal):

  • Sample Size: 80 replicates per level for each of 12 assays on each instrument model (ACL TOP 350 CTS, ACL TOP 550 CTS, ACL TOP 750 CTS, ACL TOP 750). This involved commercially available assays and their assayed control materials, as well as a prepared patient plasma pool.
  • Data Provenance: Internal, not specified country of origin, retrospective or prospective not explicitly stated but implies prospective as part of a 20-day study.

• Precision Study (External):

  • Sample Size: 80 replicates per level for each of 11 assays (two levels of control materials) on one ACL TOP 550 CTS model at three external US sites.
  • Data Provenance: Three US external sites, implies prospective as part of a 20-day study.

• Reproducibility Study (External):

  • Sample Size: 30 replicates per level for each of 12 assays (two levels of control materials) on one ACL TOP 550 CTS model at three external US sites.
  • Data Provenance: Three US external sites, implies prospective as part of a 5-day study.

• Linearity Study (Internal):

  • Sample Size: Minimum of 9 levels tested in quadruplicate for each of 10 assays on each instrument model (ACL TOP 350 CTS, ACL TOP 550 CTS, ACL TOP 750 CTS, ACL TOP 750). This involved prepared plasma pool panels.
  • Data Provenance: Internal, not specified country of origin, implies prospective.

• Method Comparison Study (External):

  • Sample Size (Assays): Ranged from 61 to 146 patient samples per assay at each of the three US external sites.
  • Sample Size (HIL Check): Hemoglobin (244-269 samples), Bilirubin (249-267 samples), Lipemia (257-272 samples) at each of the three US external sites.
  • Data Provenance: Three US external sites, patient samples, implies prospective.

• Pre-Analytical Clog Detection Testing:

  • Sample Size: Not explicitly stated beyond "All instrument models" (2 ACL TOP 350 CTS; 2 ACL TOP 550 CTS; 2 ACL TOP 750; 2 ACL TOP 750 CTS; 1 ACL TOP 750 LAS).
  • Data Provenance: Internal, likely simulated occluded samples.

• Pre-Analytical Tube Fill Height Check Testing:

  • Sample Size: Not explicitly stated beyond "All instrument models" (2 ACL TOP 350 CTS; 2 ACL TOP 550 CTS; 2 ACL TOP 750; 2 ACL TOP 750 CTS).
  • Data Provenance: Internal, likely simulated underfilled tubes.

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

• For clinical assays (Precision, Linearity, Method Comparison): The ground truth is established by the calibrated reference methods and control materials themselves, which are well-established in clinical laboratory standards. No human "experts" are explicitly mentioned whose adjudication was required to establish ground truth for these quantitative measurements, as the values are determined by the analytical process and certified controls.
• For Pre-Analytical HIL Check (Lipemia): "Visual Matching" was used as a reference for Lipemia. While not explicitly stated, this would typically involve trained laboratory personnel or experts in visual assessment of lipemia. The number and qualifications of these individuals are not specified in the provided text.
• For Pre-Analytical Clog Detection and Tube Fill Height Check: The ground truth for these functional tests was whether the instrument correctly detected the intentionally created conditions (occluded probe, underfilled tube). This doesn't rely on expert human judgment for each instance, but rather on the designed functionality of the system.

4. Adjudication Method for the Test Set

• For the quantitative clinical assays, there is no indication of an adjudication method involving multiple human readers as the output is a numerical measurement. The CLSI guidelines followed (EP05-A2, EP09-A3) dictate statistical analysis of quantitative results.
• For the Lipemia "Visual Matching" reference method, no specific adjudication method (e.g., 2+1, 3+1) is mentioned.

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 MRMC comparative effectiveness study was done, as this device (ACL TOP Family 50 Series) is a fully automated laboratory instrument for coagulation testing, not an AI-assisted diagnostic imaging or interpretation tool that would involve human readers. The new pre-analytical features (HIL Check, Tube Fill Height Check, Clog Detection) are described as alerts to the instrument operator, but there is no mention of an AI component or a study on human reader performance with or without such assistance. The device's primary function is quantitative measurement.

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

Yes, the studies presented are all standalone validations of the instrument's performance. The "ACL TOP Family 50 Series" is a fully automated analyzer. The precision, linearity, and method comparison studies directly evaluate the algorithm's (instrument's) ability to accurately and precisely measure coagulation parameters and detect pre-analytical issues without human intervention in the measurement process itself. The "Pre-Analytical HIL Check," "Pre-Analytical Clog Detection," and "Pre-Analytical Tube Fill Height Check" are new algorithmic features designed to flag samples automatically. The performance of these flags is evaluated in a standalone manner against a reference method (for HIL) or by simply checking if the instrument's detection mechanism worked correctly (for clog and tube fill).

7. The type of ground truth used

• For clinical assays (Precision, Linearity, Method Comparison): The ground truth is primarily based on reference methods and assayed control materials with known concentrations/values, as per established clinical laboratory standards (e.g., CLSI guidelines). For method comparison, the predicate device (ACL TOP 500) served as the reference for patient samples.
• For Pre-Analytical HIL Check:
  • Hemoglobin: HemoCue (K000043) was used as the reference device.
  • Bilirubin: Envoy 500 (K945271) was used as the reference device.
  • Lipemia: "Visual Matching" was used as the reference.
• For Pre-Analytical Clog Detection and Tube Fill Height Check: The ground truth was known induced conditions (occluded probe, underfilled tubes) that the instrument was designed to detect.

8. The sample size for the training set

The provided document describes validation studies (precision, linearity, method comparison) for the ACL TOP Family 50 Series. It does not explicitly mention a "training set" or "test set" in the context of machine learning, implying that the device's algorithms for analytical measurements are based on established physicochemical principles and validated through these performance studies rather than being developed through a machine learning training paradigm. The studies described are for validation of the device's performance, not for training a model.

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

As there is no explicit mention of a "training set" in the context of machine learning for generating the core analytical measurements or the pre-analytical flagging algorithms, the question of how ground truth was established for a training set is not applicable based on the provided information. The device's foundational analytical capabilities would have been developed using known chemical/biological principles and standard calibration processes. The new pre-analytical features are described as programmed detections (e.g., measuring at 535 nm for HIL, pressure transducer for clogs, optical detection for tube fill) and their performance validated against reference methods or known conditions.

Ask a specific question about this device

The ACL TOP 700 LAS is a bench top, fully automated, random access analyzer designed specifically for in vitro diagnostic clinical use in the hemostasis laboratory for coagulation and/or fibrinolysis testing in the assessment of thrombosis and/or hemostasis.

The system provides results for both direct hemostasis measurements and calculated parameters.

The ACL TOP 700 LAS is being introduced as a new family member to the ACL TOP (K073377), with the added feature of an extra arm and hardware to interface with laboratory automation systems (LAS). A Point-in-Space design solution is utilized where the patient sample remains under the control of the laboratory automation system (i.e., the automation track) and the ACL TOP 700 LAS analyzer aspirates an aliquot for sample analysis without removing the primary container from the automation track. The instrument's system software was also modified to interface with an IM (interface module) computer, which controls the communications to the LAS system.

The provided text describes the regulatory clearance for the ACL TOP 700 LAS coagulation instrument, asserting its substantial equivalence to a predicate device (ACL TOP K073377). However, the document (a 510(k) summary) focuses on the reason for submission and comparison to predicate device, stating that testing demonstrated substantial equivalence rather than providing specific acceptance criteria and detailed study results for the new device.

Therefore, much of the requested information (acceptance criteria, specific performance metrics, sample sizes, ground truth establishment, expert qualifications, adjudication methods, MRMC studies, standalone performance, training set details) is not present in the provided text, as this type of detailed study report is typically found in the full 510(k) submission, not the publicly available summary.

Based on the provided text, here's what can be extracted and what cannot:

1. Table of Acceptance Criteria and Reported Device Performance:

This information is not explicitly provided in the given 510(k) summary. The summary states: "Testing demonstrated that the performance of the ACL TOP 700 LAS is substantially equivalent to the performance of the current legally marketed ACL TOP family (K073377)." This implies that the acceptance criteria for the new device were implicitly met by demonstrating performance equivalent to the predicate, but the specific criteria (e.g., precision, accuracy ranges) and the numerical results are not detailed.

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

This information is not provided in the 510(k) summary.

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

This information is not provided in the 510(k) summary. For a coagulation instrument, "ground truth" would typically relate to the accuracy and precision of its measurements compared to reference methods or established standards, rather than expert consensus on a diagnostic image.

4. Adjudication Method for the Test Set:

This information is not provided in the 510(k) summary.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size:

This information is not provided in the 510(k) summary. MRMC studies are typical for diagnostic imaging devices where human interpretation is involved. This device is a fully automated laboratory instrument; therefore, an MRMC study is unlikely to be relevant or performed.

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

The device is described as "fully automated," suggesting its performance would inherently be standalone (algorithm/instrument only). However, specific performance metrics of a standalone study are not detailed beyond the statement of substantial equivalence.

7. The Type of Ground Truth Used:

For a coagulation instrument, the "ground truth" would likely be established through reference methods, calibrated standards, and known-concentration samples. The 510(k) summary does not specify the exact type of ground truth used, but it implicitly relies on established laboratory practices for validating instrument performance.

8. The Sample Size for the Training Set:

This information is not provided in the 510(k) summary. For a coagulation instrument, "training set" might refer to data used for internal calibration or algorithm development, but it's not discussed in the context of clinical validation data in this summary.

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

This information is not provided in the 510(k) summary.

Summary of Available Information from the Provided Text:

• Device Name: ACL TOP 700 LAS
• Predicate Device: ACL TOP (K073377)
• Nature of Study: A substantial equivalence demonstration (Special 510(k)) based on testing that confirmed the new device's performance is equivalent to the predicate.
• Key Change: Addition of an extra arm and hardware for interface with Laboratory Automation Systems (LAS), allowing aspiration without removing the primary container from the automation track. System software was also modified for LAS interface.
• Claim: The ACL TOP 700 LAS shares the same intended use/indications for use, analytical technology/operating principle, analytical specifications, labeled performance characteristics, analytical data reduction, software, test parameters, and uses the same consumables and racks as the predicate.

To obtain the detailed acceptance criteria and study results, one would typically need to review the full 510(k) submission available through FDA, as the summary often omits these specifics.

Ask a specific question about this device

The ACL TOP is a bench top, fully automated, random access analyzer designed specifically for in vitro diagnostic clinical use in the hemostasis laboratory for coagulation and/or fibrinolysis testing in the assessment of thrombosis and/or hemostasis.

The system provides results for both direct hemostasis measurements and calculated parameters.

The ACL TOP is a bench top, fully automated, random access analyzer designed specifically for in vitro diagnostic clinical use in the hemostasis laboratory for coagulation and/or fibrinolysis testing in the assessment of thrombosis and/or hemostasis.

The system provides results for both direct hemostasis measurements and calculated parameters.

System Software V3.0.0 is being introduced on the ACL TOP family (instrument available with and without the feature of closed tube sampling) to support the conversion from the Windows 2000 Operating System to the Windows XP Operating System. This software also includes additional features and ease-of-use enhancements.

This 510(k) summary is for a software update (System Software V3.0.0) for an existing device, the ACL TOP coagulation analyzer. The purpose of the submission is to support the conversion from Windows 2000 to Windows XP operating system and to introduce additional features and ease-of-use enhancements.

Therefore, the study described here is focused on demonstrating that the updated software does not negatively impact the performance of the device and that it remains substantially equivalent to the predicate device. It is not a study to establish new performance metrics or efficacy.

Here's an analysis of the provided text in relation to your request:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not contain a table of specific acceptance criteria or reported device performance metrics in the way you might expect for a new device's clinical study. The submission focuses on demonstrating substantial equivalence, meaning the updated software does not alter the existing performance and indications for use.

Instead of quantitative performance metrics, the "acceptance criteria" here are implicitly met by showing that:

• There are no changes in ACL TOP test parameters.
• There are no changes to the labeled indications for use/intended use.
• There are no changes to the performance claims of the instrument or its reagents.

The "reported device performance" is the statement: "The performance of the ACL TOP family with System Software V3.0.0 is substantially equivalent to the performance of the current legally marketed ACL TOP (K063679)."

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

The document does not specify a sample size for a test set or data provenance (e.g., country of origin, retrospective/prospective). This is because the submission is for a software update to an existing, cleared device. The focus is on demonstrating that the software change itself doesn't affect the established performance, rather than re-evaluating the device's original performance with a new clinical study.

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

Not applicable. This submission is not evaluating a diagnostic algorithm where expert ground truth is established for images or clinical cases. It's a software update for a clinical laboratory instrument.

4. Adjudication Method for the Test Set

Not applicable. There is no "test set" in the context of diagnostic interpretation that would require adjudication.

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

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not conducted. This type of study assesses how AI impacts human reader performance, which is not relevant for a software update to a laboratory instrument that performs automated assays.

6. Standalone (Algorithm Only) Performance Study

No, a standalone performance study in the context of an algorithm interpreting data (like imaging or patient characteristics) was not explicitly described or performed. The device itself (ACL TOP) is a standalone automated analyzer, but the submission is about its operating software update, not a new diagnostic algorithm.

7. Type of Ground Truth Used

Not applicable/Implicit. For an automated coagulation instrument, the "ground truth" for its measurements would typically come from reference methods or established gold standards for coagulation testing. However, the software update submission focuses on ensuring the new software maintains the accuracy and reliability already established for the device. Therefore, no new "ground truth" was established for this specific submission; it relies on the predicate device's established performance.

8. Sample Size for the Training Set

Not applicable. This submission is not about an AI/machine learning algorithm that requires a training set of data. It's about an operating system and feature update for an existing instrument.

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

Not applicable. As there is no training set for an AI/ML algorithm, this question is not relevant.

Ask a specific question about this device

The ACL TOP is a bench top, fully automated, random access analyzer designed specifically for in vitro diagnostic clinical use in the hemostasis laboratory for coagulation and/or fibrinolysis testing in the assessment of thrombosis and/or hemostasis. The system provides results for both direct hemostasis measurements and calculated parameters.

The ACL TOP is a bench top, fully automated, random access analyzer designed specifically for in vitro diagnostic clinical use in the hemostasis laboratory for coagulation and/or fibrinolysis testing in the assessment of thrombosis and/or hemostasis. The system provides results for both direct hemostasis measurements and calculated parameters.

Major software/test parameter modifications to the factor assays include:

1. The calibration levels are now prepared by aspirating the calibrator directly from the calibrator vial (direct dilution instead of serial dilution).
2. The number of calibration points is being increased from 5 to either 7 or 8, dependent on the individual factor.
3. New mathematical tools are being implemented for generating the calibration curve, e.g. polynomial curve fitting capability as well as the capability for using segmented calibration curve (two different calibration curves for the lower and upper ends).
4. The robustness of the assays is increased by optimizing incubation time, transport air gap and probe rinse parameter modifications.

The provided 510(k) summary (K063679) describes modifications to the ACL TOP device, focusing on optimizing the performance of intrinsic and extrinsic factor assay applications. However, it does not contain a detailed study report with specific acceptance criteria and performance data in the format requested. The document primarily focuses on explaining what changes were made to the software and test parameters and noting that the performance of the optimized factor assay is substantially equivalent to the predicate device.

Specifically, the document lacks the following information required to fully answer the request:

• A table of acceptance criteria and reported device performance: The document states that the performance is "substantially equivalent" to the predicate, but it doesn't provide specific numerical acceptance criteria (e.g., precision limits, accuracy targets) or the measured performance values for the optimized assays.
• Sample sizes used for the test set and data provenance: No information is given regarding the number of samples used in any validation or verification testing, nor their origin (country, retrospective/prospective).
• Number of experts used to establish ground truth and their qualifications: This information is not provided as there is no mention of an expert panel or adjudication process for establishing ground truth for a test set. This type of device (coagulation analyzer) typically uses reference methods or calibrated controls for ground truth rather than expert interpretation of results in the way image-based diagnostics might.
• Adjudication method: Not applicable/not provided.
• Multi-reader multi-case (MRMC) comparative effectiveness study: Not applicable, as this is a benchtop analyzer, not an AI-assisted diagnostic tool for Human-in-the-Loop performance with human readers.
• Standalone performance study: The document doesn't provide a detailed standalone performance study report with specific metrics. It states the performance is equivalent but doesn't quantify it.
• Type of ground truth used: While implicitly using calibrated controls or reference methods for coagulation factor assays, the document does not explicitly state how ground truth was established for performance validation.
• Sample size for the training set: Not applicable and not provided, as this is not an AI/machine learning device that typically involves a separate training set. The "optimization" refers to mathematical tools for curve fitting, not a machine learning model trained on a dataset.
• How ground truth for the training set was established: Not applicable and not provided.

Based on the provided text, the most relevant information regarding "acceptance criteria" and "proving the device meets the acceptance criteria" is in the context of demonstrating substantial equivalence to a predicate device, rather than a detailed performance study against specific, quantified acceptance targets.

Here's a summary of what can be extracted or inferred, and what is explicitly missing:

1. Table of Acceptance Criteria and Reported Device Performance

Missing from the document: Specific numerical acceptance thresholds for performance metrics (e.g., %CV for precision, % bias for accuracy), or specific numerical results for these metrics before and after optimization.

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

• Sample Size: Not specified in the provided text.
• Data Provenance: Not specified in the provided text.

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/Not specified. This type of device relies on analytical performance against controls and reference methods, not expert consensus for ground truth.
• Qualifications of Experts: Not applicable/Not specified.

4. Adjudication method for the test set

• Adjudication Method: Not applicable/Not specified.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done

• MRMC Study: No, this is not applicable for this device type. The ACL TOP is an automated analyzer, not an imaging device or AI-assisted diagnostic requiring human reader input or comparison.

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

• Standalone Performance: The submission implies that the device itself (the "algorithm"/software modifications) was tested to confirm its performance is substantially equivalent. However, a detailed report of this standalone performance, with specific metrics and data, is not included in the provided 510(k) summary. The summary simply states that the performance is "substantially equivalent."

7. The type of ground truth used

• Type of Ground Truth: Not explicitly stated but inferred to be based on calibrated controls, reference materials, or recognized standard methods for coagulation factor assays, which are standard for laboratory instruments of this type.

8. The sample size for the training set

• Sample Size for Training Set: Not applicable. The "new mathematical tools" for calibration curve generation are described as established methods (polynomial curve fitting, segmented calibration) rather than a machine learning algorithm requiring a separate training set.

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

• Ground Truth for Training Set: Not applicable.

Ask a specific question about this device

The CoagCare Anticoagulation Management System (CoagCare®) is an interactive, internet-based (web-based), rules-based expert software system for the long-term management of patients undergoing warfarin anticoagulation therapy. The system is an accessory to prescription home-use prothrombin time devices that measure International Normalized Ratios (INRs), and it facilitates remote clinical management between patient and caregiver.

The CoagCare system is a software accessory to prescription-home use prothrombin time (INR) devices for effective anticoagulation management with warfarin. System Overview: The system consists of two components, the CoagCare Patient Interface and the CoagCare Caregiver Interface, both of which are accessed through an internet browser. The interface provides a structured therapeutic regimen developed for the individual patient. It prompts the patient for INR values, symptoms, and other disease related data, and provides the patient with recommended doses of warfarin and an INR testing schedule that can be adjusted based on parameters specified by the patient's caregiver. The patient is given recommendations for warfarin doses for each day until the next time of required INR testing. In cases of marked abnormal INR readings or disease signs or symptoms suggestive of over-treatment, the Patient Interface instructs the patient to contact his/her healthcare provider for further instructions.

The second component of the CoagCare system is the Caregiver Interface. The caregiver monitoring the patient's anticoagulant therapy accesses the Caregiver Interface at least daily. The Caregiver Interface is programmed to automatically identify patient problems such as patients who report thromboembolic or hemorrhagic symptoms, failure to check their INR on a prescribed day, etc. The Caregiver Interface prioritizes problems requiring the caregiver's attention. Once patients have checked their INRs and transmitted their results, if the caregiver agrees with the warfarin dosing instructions provided by the patient interface, no further interventions are required for that day. Patients with markedly abnormal results or recurrent problems are prioritized for caregiver intervention, whereas stable patients are listed with their results, eliminating the need for direct patient contact by the caregiver. The Caregiver Interface also allows the caregiver to override therapeutic instructions provided by the Patient Interface, or send a text message to the patient through the Patient interface. (For more emergent issues, the patient can be contacted directly by the caregiver by telephone.)

Here's an analysis of the CoagCare Anticoagulation Management System based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: 100 patients
  • 58 patients at Duke University Medical Center
  • 22 patients at the University of New Mexico Medical Center
  • 20 patients from a private practice in Miami
• Data Provenance: United States (Duke University, University of New Mexico, Miami private practice). The study was prospective, as patients were "switched to home INR monitoring and followed with the CoagCare system for six months" or "remained on the system from 3 to 4 months." Data on TTR prior to CoagCare was retrospective (likely collected from patient records before the intervention).

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

The document does not explicitly state the number or qualifications of experts used to establish a "ground truth" for the test set in the traditional sense of diagnostic accuracy studies. The study evaluates the effectiveness of the system in managing anticoagulation, where the "ground truth" is inferred from patient INR values (measured by home INR devices) and the resulting time in therapeutic range. The "caregivers" (physicians, nurses, pharmacists, or licensed professionals) monitoring the patients are the experts involved in overseeing the system and making clinical judgments.

4. Adjudication Method for the Test Set

The document does not describe a formal adjudication method for the test set as would typically be done for diagnostic interpretations. The CoagCare system provides recommendations, and caregivers monitor and can override instructions. The "ground truth" for TTR is derived from INR measurements and the patient's adherence to the warfarin dosing recommendations generated by the system (or overridden by the caregiver).

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

This was not a traditional MRMC study. It was a comparative effectiveness study comparing patient outcomes with the CoagCare system to their outcomes without the system (their historical TTR). The "readers" (caregivers) involved in managing the patients using the CoagCare system had their efficiency and satisfaction assessed.

• Effect Size of Human Readers Improve with AI vs. without AI assistance: The study primarily focuses on patient outcomes (TTR) and caregiver efficiency.
  • Patient Outcome (TTR): The TTR increased by 11% (from 62.5% to 73.5%) with the CoagCare system (which includes AI-like capabilities for dosing recommendations and problem prioritization) compared to prior management. This suggests the system assists caregivers in achieving better patient outcomes.
  • Caregiver Efficiency: Caregivers managing between 20-58 patients reported it took only 15-25 minutes a day. The note "managing 48 patients with CoagCare did not take much more time than managing 20" strongly suggests an improvement in caregiver efficiency due to the system's automation, but a specific "effect size" of improvement (e.g., X% more patients managed per hour) is not quantified or compared to an unassisted baseline.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) was Done

No, a standalone performance study was not done. The CoagCare system is explicitly described as a "software accessory" that facilitates "remote clinical management between patient and caregiver." The system provides recommendations, but "caregivers have the ability to override therapeutic instructions" and "requires tight professional oversight." It is a human-in-the-loop system.

7. The Type of Ground Truth Used

The primary "ground truth" or outcome measure used was:

• Outcomes Data: Specifically, the Time in Therapeutic Range (TTR) for International Normalized Ratios (INR) in warfarin-treated patients. This is a direct clinical outcome measure.
• Patient Feedback/Satisfaction: Self-reported patient preferences and perceptions of monitoring and control.
• Caregiver Reports: Reports on the time taken to manage patients.

8. The Sample Size for the Training Set

The document does not mention a distinct "training set" for the CoagCare system. The system "utilizes published and generally accepted algorithms to adjust medication doses and make treatment decisions." This implies that the algorithms were developed based on existing medical knowledge and clinical guidelines, rather than being trained on a specific, separate dataset within the context of this 510(k) submission.

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

As no specific training set is mentioned for the algorithm (which is described as rule-based using "published and generally accepted algorithms"), the concept of "ground truth for the training set" as it relates to machine learning models is not applicable here. The "ground truth" for these general algorithms would have been established through extensive medical research, clinical trials, and expert consensus over many years, leading to the "published and generally accepted algorithms" mentioned.

Ask a specific question about this device