(87 days)
The intended use of the Sysmex KX-21 is as an automated cell counter for in vitro diagnostic use in clinical laboratories.
The Sysmex™ KX-21 is an automated blood cell counter intended for in vitro diagnostic use in clinical laboratories.
The Sysmex™ Automated Hematology Analyzer KX-21's acceptance criteria and performance are detailed through correlation studies against a predicate device, the Sysmex™ K-1000. The study aimed to demonstrate substantial equivalence by comparing the results of various hematological parameters.
Here's a breakdown of the requested information:
1. Table of Acceptance Criteria and Reported Device Performance:
The document implicitly uses the correlation coefficient (r) and coefficient of determination (r²) as the acceptance criteria for substantial equivalence to the predicate device. A high 'r' value (close to 1) indicates good correlation. While explicit numerical thresholds for acceptance (e.g., r > 0.95) are not stated, the reported values are presented as evidence of meeting performance claims.
| Parameter | n | Expected Acceptance Criteria (Implicit: High r/r²) | Reported Device Performance (r) | Reported Device Performance (r²) | Regression Equation |
|---|---|---|---|---|---|
| WBC | 194 | High (close to 1.0) | 0.990 | 0.981 | y = 0.944x + 0.265 |
| RBC | 195 | High (close to 1.0) | 0.996 | 0.993 | y = 1.002x + 0.053 |
| HGB | 195 | High (close to 1.0) | 0.997 | 0.995 | y = 0.979x + 0.405 |
| HCT | 195 | High (close to 1.0) | 0.996 | 0.992 | y = 0.989x + 1.025 |
| MCV | 195 | High (close to 1.0) | 0.997 | 0.995 | y = 0.95x + 4.846 |
| MCH | 195 | High (close to 1.0) | 0.967 | 0.934 | y = 0.989x + 0.297 |
| MCHC | 195 | High (close to 1.0) | 0.829 | 0.688 | y = 0.813x + 5.935 |
| Platelet | 193 | High (close to 1.0) | 0.996 | 0.993 | y = 1.079x - 12.881 |
| Lymph% | 150 | High (close to 1.0) | 0.995 | 0.991 | y = 1.017x - 0.072 |
| Mixed% | 150 | High (close to 1.0) | 0.874 | 0.763 | y = 1.055x + 1.35 |
| Neut% | 150 | High (close to 1.0) | 0.984 | 0.968 | y = 1.011x - 0.292 |
| RDW-SD | 198 | High (close to 1.0) | 0.976 | 0.953 | y = 0.942x + 5.96 |
| MPV | 179 | High (close to 1.0) | 0.961 | 0.924 | y = 0.947x + 0.611 |
2. Sample size used for the test set and the data provenance:
- Sample Size: The sample sizes vary by parameter:
- WBC: 194
- RBC, HGB, HCT, MCV, MCH, MCHC: 195
- Platelet: 193
- Lymph%, Mixed%, Neut%: 150
- RDW-SD: 198
- MPV: 179
- Data Provenance: The study evaluated "specimens from apparently healthy individuals and from patients with different pathological conditions." The country of origin is not explicitly stated, but the manufacturer is based in Kobe, Japan, and the importer/distributor is in Long Grove, IL, USA. The study design is prospective in the sense that specimens were evaluated using both devices for comparison.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
This information is not provided in the document. The study relies on correlation with a predicate device (Sysmex™ K-1000) rather than a separate expert-established ground truth.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
This information is not provided. As the study focuses on device-to-device correlation, an adjudication method for human-interpreted results is not applicable.
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:
A multi-reader multi-case (MRMC) comparative effectiveness study was not performed. This study is about the performance of an automated hematology analyzer, not about human reader performance or AI assistance.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
Yes, a standalone performance study was implicitly done in the form of correlation studies comparing the KX-21 to the K-1000. These are automated devices; their performance is measured directly, not in conjunction with human interpretation for the primary parameters.
7. The type of ground truth used:
The "ground truth" for the test set was the measurements obtained from the Sysmex™ K-1000 predicate device. The study aims to show that the new device (KX-21) produces results that correlate strongly with the established device (K-1000).
8. The sample size for the training set:
The document does not specify a separate training set. The study appears to be a performance evaluation against a predicate, where the algorithms of both the KX-21 and K-1000 are presumably already "trained" or designed.
9. How the ground truth for the training set was established:
As no separate training set is explicitly mentioned for the KX-21's development or the K-1000, this information is not provided. The ground truth for this correlation study is the predicate device's output.
§ 864.5200 Automated cell counter.
(a)
Identification. An automated cell counter is a fully-automated or semi-automated device used to count red blood cells, white blood cells, or blood platelets using a sample of the patient's peripheral blood (blood circulating in one of the body's extremities, such as the arm). These devices may also measure hemoglobin or hematocrit and may also calculate or measure one or more of the red cell indices (the erythrocyte mean corpuscular volume, the mean corpuscular hemoglobin, or the mean corpuscular hemoglobin concentration). These devices may use either an electronic particle counting method or an optical counting method.(b)
Classification. Class II (performance standards).