(57 days)
The HPC (hematopoietic progenitor cell) parameter of the IMI Channel on the Sysmex® SE-9500 and XE-2100 for in Vitro Diagnostics is used as a screen for the optimal presence of hematopoietic progenitor cells in peripheral blood and cord blood samples.
The SE-9500 and XE-2100 have an immature myeloid information (IMI) channel, which identifies and enumerates immature cells in addition to the traditionally reported parameters of an automated cell differential. (Note: Special software/hardware is required to obtain results described.)
The provided text describes a 510(k) submission for the "HPC (Hematopoietic Progenitor Cell) parameter on the IMI Channel of the Sysmex® SE-9500 and XE-2100, Automated Hematology Analyzer." The document does not explicitly state "acceptance criteria" and "reported device performance" in a structured table or use these specific terms. However, it does present a "Comparison Table to Predicate Methods" that outlines the characteristics and performance of the new HPC parameter in relation to predicate devices (Colony Forming Unit (CFU) and Total Nucleated Count (TNC)) and a routine method (Flow Cytometry CD34+).
Based on the provided information, here's an attempt to extract the requested details:
1. Table of acceptance criteria and the reported device performance
The document does not explicitly define quantitative "acceptance criteria" like thresholds for accuracy, sensitivity, or specificity. Instead, it relies on demonstrating "substantial equivalence" to predicate methods, particularly in terms of "accuracy" (correlation to CFU).
| Acceptance Criteria (Inferred from comparison to predicates) | Reported Device Performance (HPC parameter of IMI Channel) |
|---|---|
| Intended Use: Screen for optimal presence of progenitor cells in stem cell harvest & cord blood. | Same as predicate methods (CFU, TNC, Flow Cytometry CD34+). |
| Methodology: Hematopoietic progenitor cell count from hematology analyzer. | Hematopoietic progenitor cell count from hematology analyzer. |
| Anticoagulant Type: EDTA (for HPC). | EDTA. |
| Specimen Type: Peripheral blood & cord blood. | Peripheral blood & cord blood. |
| Accuracy: Comparison to CFU should show good correlation. | Comparison to CFU showed good correlation. |
| Time Required (per sample): Short (90 seconds, comparable to TNC). | 90 seconds. |
| Cost (per sample): Low (Approx $1.35, comparable to TNC). | Approx $1.35. |
| Quality of Technical Support: Hematology laboratory personnel; Run in duplicate. | Hematology laboratory personnel; Run in duplicate. |
Study Proving Acceptance Criteria (Substantial Equivalence)
The study described is a comparison of the new HPC parameter to established predicate methods.
2. Sample size used for the test set and the data provenance
The document does not specify the sample size used for the test set or the data provenance (e.g., country of origin, retrospective/prospective). It only states: "the HPC parameter to the predica indicated equivalent performance. The performance data demonstrated substantial equivalence."
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The document does not provide information on the number of experts used or their qualifications for establishing ground truth.
4. Adjudication method for the test set
The document does not describe any adjudication method.
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 is not an MRMC study. The device is an automated hematology analyzer parameter, not an AI-assisted interpretation tool for human readers. Therefore, this question is not applicable.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
Yes, the performance described is that of the standalone device (HPC parameter on the Sysmex® SE-9500 and XE-2100 automated hematology analyzers). It functions without human-in-the-loop interpretation for its primary output. The "Quality of Technical Support" section mentions "Hematology laboratory personnel; Run in duplicate," which refers to the operation of the device and quality control checks, not human interpretation of the device's primary result.
7. The type of ground truth used
The primary ground truth appears to be the Colony Forming Unit (CFU) method. The document states: "Method of real counting of progenitor cells established as reference method" for CFU, and the accuracy of the HPC parameter (as well as TNC and Flow Cytometry CD34+) is assessed by "Comparison to CFU showed good correlation."
8. The sample size for the training set
The document does not provide information on the sample size used for training, nor does it explicitly describe a distinct "training set" in the context of typical machine learning models. This is a hematology analyzer parameter, and its development would likely involve calibration and validation rather than what is typically understood as an ML training set.
9. How the ground truth for the training set was established
Since a "training set" in the machine learning sense is not explicitly discussed, the establishment of ground truth for development/calibration would inherently rely on the same established methods, primarily the Colony Forming Unit (CFU) method, which is considered the "reference method" for real counting of progenitor cells.
§ 864.5220 Automated differential cell counter.
(a)
Identification. An automated differential cell counter is a device used to identify one or more of the formed elements of the blood. The device may also have the capability to flag, count, or classify immature or abnormal hematopoietic cells of the blood, bone marrow, or other body fluids. These devices may combine an electronic particle counting method, optical method, or a flow cytometric method utilizing monoclonal CD (cluster designation) markers. The device includes accessory CD markers.(b)
Classification. Class II (special controls). The special control for this device is the FDA document entitled “Class II Special Controls Guidance Document: Premarket Notifications for Automated Differential Cell Counters for Immature or Abnormal Blood Cells; Final Guidance for Industry and FDA.”