Search Results

The CN-Series (CN-6000) is a fully automated coagulation analyzer intended for in vitro diagnostic use in the clinical laboratory. The instrument analyzes citrated plasma samples (3.2 % sodium citrate) collected from venous blood, using clotting, chromogenic and immunoassay methods.

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

The CN-Series (CN-6000) coagulation analyzer is an automated blood coagulation instrument which can analyze samples using clotting, chromogenic and immunoassay methods. Analysis results are displayed on the IPU (Information Processing Unit) screen. They can be printed on external printers or transmitted to a host computer.

Sold separately from the instrument are the associated reagents, controls, calibrators, and consumable materials. The subject of this 510(k) notification is the analyzer together with the reagent applications which perform the coagulation tests:

• 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 analysis principles used on the instrument are reflected by the reagent application testing provided in this submission and are described in the table below. These reagents were selected to show the analytical technology of the instrument while also selecting commonly used applications in coagulation laboratories in the United States.

This document describes the acceptance criteria and the study that proves the device meets the acceptance criteria for the Sysmex CN-6000 Automated Blood Coagulation Analyzer.

The provided text is a 510(k) clearance letter for an in vitro diagnostic device, specifically an automated blood coagulation analyzer. The information focuses on demonstrating substantial equivalence to a predicate device (Sysmex CS-5100 K150678) rather than providing detailed acceptance criteria and proof of exceeding them in the format typically seen for novel AI/ML devices. Therefore, the information has been extracted and interpreted as closely as possible to the requested structure, with explanations where the requested information is not explicitly present due to the nature of the document.

1. Table of Acceptance Criteria and Reported Device Performance

For an in vitro diagnostic device like the CN-6000, acceptance criteria are generally defined as meeting performance specifications comparable to the predicate device and within clinically acceptable ranges. The "acceptance criteria" for each study are generally defined as the results meeting these pre-established standards. The reported device performance is presented as the outcomes of these studies.

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

The "test set" in this context refers to the samples used in the performance evaluation studies.

• Method Comparison:
  • Total Combined Sites Sample Sizes:
    • PT (seconds): N = 847
    • PT (INR): N = 813
    • APTT: N = 638
    • Fibrinogen: N = 456
    • Antithrombin: N = 450
    • D-dimer: N = 395
  • Data Provenance: Conducted at three clinical sites. The document does not specify the country of origin of the data, but the context of an FDA 510(k) submission strongly implies data from within the United States. The samples included "Normal, abnormal samples, and samples at the medical decision levels" which typically implies retrospective clinical samples (existing patient samples) or potentially prospectively collected samples for the purpose of the study. It's common in IVD submissions for these to be retrospective collections.
• Precision: Commercial QC materials and plasma pools reflecting medical decision levels. No specific human patient sample size is given for precision, as it focuses on analytical performance using controlled materials.
• Linearity & Measuring Range: Not specified as human samples, but rather analytical samples/dilutions.
• Interference Studies: Not specified as human samples, but rather samples spiked with interfering substances.
• Heparin Sensitivity: n = 56 (patients receiving unfractionated heparin (UFH) therapy).
• Lupus Anticoagulant (LA) Sensitivity: 24 LA positive samples.
• Reference Range: Specific sample size per site not detailed, but stated as "adult samples" collected at "three external clinical sites within the United States."

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

For this type of in vitro diagnostic device, "ground truth" is established through laboratory reference methods and predicate device measurements, not typically by expert human readers' interpretations of images or clinical assessments in the same way as AI/ML imaging devices.

• No "experts" in the sense of radiologists, clinicians, or similar domain specialists directly establishing "ground truth" through consensus or interpretation for the test sets are mentioned.
• The "ground truth" for the method comparison and other performance studies is the result obtained from the predicate device (Sysmex CS-5100) or reference methods and established analytical specifications.
• The studies were conducted at three clinical sites, implying performance by trained laboratory professionals using standard operating procedures. The qualifications of these professionals (e.g., licensed medical technologists) are implicit in CLSI guidelines for such studies but not explicitly stated.

4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set

Not applicable for this type of IVD device. Adjudication methods like 2+1 or 3+1 are typical for AI/ML imaging diagnostics where multiple human readers independently interpret data (e.g., images) to establish a consensus ground truth, which is then compared against the AI's performance. For an automated coagulation analyzer, the "ground truth" is typically the quantitative result from a validated method/predicate device.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

Not applicable. This device is an automated in vitro diagnostic analyzer, not an AI-assisted diagnostic imaging or interpretation tool that would involve human readers or MRMC studies. Its primary function is to perform laboratory tests on blood samples, not to assist human interpretation of complex medical cases in a subjective way.

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

Yes, the studies performed (method comparison, precision, linearity, interference, carryover, etc.) represent the standalone performance of the CN-6000 analyzer. The device functions automatically to analyze samples and output results based on its internal algorithms (for clotting, chromogenic, and immunoassay methods). The comparison is against a predicate device or established analytical criteria, not against human performance.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

The ground truth for most of these studies is:

• Predicate device measurements: For the method comparison studies, the results from the Sysmex CS-5100 (K150678) serve as the comparative "ground truth."
• Defined analytical specifications/reference methods: For studies like precision, linearity, LoB/LoD/LoQ, and interference, the "ground truth" is adherence to established analytical limits, known concentrations of controls/calibrators, or the expected absence of interference, derived from CLSI guidelines and industry standards for chemical analyzers.
• Clinical status: For studies like Heparin Sensitivity and Lupus Anticoagulant Sensitivity, the ground truth relates to the clinical status of the patient samples (e.g., patients on UFH therapy, LA positive samples).

8. The Sample Size for the Training Set

This document describes the validation of a laboratory instrument, not an AI/ML model for which "training set" is a common term. The device's underlying principles (clotting, chromogenic, immunoassay) are well-established analytical methods, not learned from data in the way an AI model is. Therefore, there is no "training set" in the context of machine learning. The device's "training" would be its initial design and calibration using scientific principles and engineering practices, which doesn't involve a data-driven training set in the AI sense.

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

As explained in point 8, the concept of a "training set" and associated "ground truth" for a training set does not apply to this type of traditional in vitro diagnostic instrument where performance is based on established analytical principles rather than AI/ML model training. The instrument's design and calibration are based on physical and chemical principles of coagulation analysis.

Ask a specific question about this device