Search Results

The Sysmex® XE-2100 Series Hematology Analyzer is a quantitative, automated hematology analyzer and leukocyte differential counter For In Vitro Diagnostic Use in clinical laboratories. The Body Fluid Application adds a quantitative, automated procedure for analyzing cerebrospinal fluid, scrous fluid and synovial fluid to the XE-2100 Series, providing enumeration of the WBCs and the RBCs.

The XE-2100 Series is an automated hematology analyzer previously cleared by the FDA. The combination of side scatter, forward scatter, and fluorescent intensity of nucleated cells gives an image of each cell detected in the specimen.

Here's a breakdown of the acceptance criteria and study information for the Sysmex® XE-2100 Series Automated Hematology Analyzer, based on the provided text:

Acceptance Criteria and Device Performance

Study Information

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

• Test set size: Not explicitly stated. The text mentions "Studies were performed to evaluate the equivalency of the automated method to the predicate method," implying a test set was used, but the number of samples is not provided.
• Data provenance: Not explicitly stated. Likely retrospective, as it compares the new device to an established manual method. The country of origin is not specified.

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

• Number of experts: Not explicitly stated. The predicate method involves "manual cell counting in a counting chamber by a skilled, competent technologist." This implies a human expert performing the ground truth measurement, but the number and specific qualifications (beyond "skilled, competent technologist") are not detailed.

4. Adjudication method for the test set:

• Adjudication method: Not explicitly stated. Given the comparison to a manual method performed by a "skilled, competent technologist," it's likely the manual count served as the direct reference, without a formal adjudication process between multiple experts for the test set ground truth. The study's "good correlation" implies a direct comparison.

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

• MRMC study: No. This device is an automated hematology analyzer, not an AI-assisted diagnostic tool for human readers in the traditional sense of image interpretation. The comparison is between an automated machine and a manual human counting method, not about improving human reader performance with AI. Therefore, an effect size of human improvement is not applicable.

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

• Standalone performance: Yes. The study directly evaluates the "automated method" (the device) against the "predicate method" (manual counting). The performance comparison ("Comparison to manual count showed good correlation") indicates a standalone evaluation of the device's accuracy without a human-in-the-loop.

7. The type of ground truth used:

• Ground truth type: Expert consensus (implicitly, through a "skilled, competent technologist" performing manual counts) for cell enumeration. The predicate method is "manual cell counting in a counting chamber by a skilled, competent technologist," which serves as the reference standard.

8. The sample size for the training set:

• Training set size: Not applicable or provided. Automated hematology analyzers typically use established algorithms and calibration methods rather than machine learning training sets in the modern sense. The device was "previously cleared by the FDA," suggesting its core technology was already developed. The "Body Fluid Application" is an added quantitative, automated procedure for specific fluid types, implying an extension of existing capabilities, not necessarily a new machine learning model requiring a distinct training set.

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

• Ground truth for training set: Not applicable or provided. As inferred above, this device's development likely involved engineering and calibration against known standards rather than a machine learning training paradigm with annotated ground truth.

Ask a specific question about this device