(63 days)
DM1200 is an automated cell-locating device.
DM1200 automatically locates and presents images of blood cells on peripheral blood smears. The operator identifies and verifies the suggested classification of each cell according to type.
DM1200 is intended to be used by skilled operators, trained in the use of the device and in recognition of blood cells.
DM1200 is an automated cell-locating device for differential count of white blood cells, characterization of red blood cell morphology and platelet estimation. DM1200 consists of a slide scanning unit (a robot gripper, a microscope and a camera) and a computer system containing the acquisition and classification software "CellaVision® DM software".
Here's an analysis of the acceptance criteria and study details for the CellaVision® DM1200 Automated Hematology Analyzer, based on the provided 510(k) summary:
1. Table of Acceptance Criteria and Reported Device Performance
The provided 510(k) summary states that "The results fulfilled the pre-defined requirements" for accuracy for cell-location, accuracy for verified classification for each cell class, precision for verified classification for each cell class, and clinical sensitivity and specificity. However, the specific quantitative acceptance criteria or the reported performance metrics (e.g., specific accuracy percentages, precision values, sensitivity, and specificity thresholds) are not detailed in the provided document. The summary only generally claims that the results fulfilled these requirements.
To illustrate what such a table would look like if the data were present, here's a hypothetical structure:
Hypothetical Acceptance Criteria and Reported Device Performance
| Performance Metric | Acceptance Criteria (Hypothetical) | Reported Device Performance (Hypothetical) |
|---|---|---|
| Accuracy for cell-location | > 95% | > 98% |
| Accuracy for verified classification | > 90% for all major cell classes | > 92% for all major cell classes |
| Precision for verified classification | CV 90% | > 93% |
| Clinical Specificity (overall WBC diff) | > 85% | > 88% |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: Not explicitly stated. The summary mentions "clinical tests" and "a pre-defined protocol for differentiation of the approved standard CLSI, H20-A2, Reference Leukocyte (WBC) Differential Count (Proportional) and Evaluation of Instrumental Methods." While this indicates a formal study, the specific number of blood smears or cells included in the test set is not mentioned.
- Data Provenance: Not explicitly stated. The document does not specify the country of origin of the data
- Retrospective or Prospective: Not explicitly stated.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
- Number of Experts: Not explicitly stated.
- Qualifications of Experts: The study was performed according to CLSI H20-A2, which typically involves experienced morphologists. However, the specific qualifications (e.g., "radiologist with 10 years of experience") are not provided in the summary. The device's intended use also states it needs to be used by "skilled operators, trained in the use of the device and in recognition of blood cells," implying that the experts establishing ground truth would be highly skilled in blood cell morphology.
4. Adjudication Method for the Test Set
- Adjudication Method: Not explicitly stated. The CLSI H20-A2 standard, which the study adhered to, typically uses an agreement process among multiple experts to establish a reference differential, which could involve consensus or adjudication. However, the exact method (e.g., 2+1, 3+1, none) is not detailed in this summary.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- MRMC Study: The summary discusses "comparison to the predicate device DM96 for differentiation of white blood cells" and "to confirm equivalence with the predicate device." However, it focuses on the device's performance against the predicate's results and adherence to standards, rather than a comparative effectiveness study showing human readers' improvement with AI vs. without AI assistance. The DM1200 is described as an "automated cell-locating device" where "The operator identifies and verifies the suggested classification of each cell." This indicates a human-in-the-loop system, but the study described does not quantify the improvement of human readers using the AI versus without it.
- Effect Size of Human Reader Improvement: Not applicable, as this specific type of MRMC study was not described.
6. Standalone (Algorithm Only Without Human-in-the-Loop) Performance
- Standalone Performance: No, a standalone performance study (algorithm only) was not explicitly described for the DM1200. The device's intended use clearly states: "The operator identifies and verifies the suggested classification of each cell according to type." This indicates that the device is designed to be used with a human reviewer in the loop, validating the AI's suggestions. The "accuracy for the verified classification" metric further supports this, suggesting the final classification is human-verified.
7. Type of Ground Truth Used
- Type of Ground Truth: Expert consensus with adherence to the CLSI H20-A2, Reference Leukocyte (WBC) Differential Count (Proportional) and Evaluation of Instrumental Methods; 2nd Ed. standard. This standard provides guidelines for establishing reference differentials, which typically rely on experienced morphologists. The summary states: "performed according to a pre-defined protocol for differentiation of the approved standard CLSI, H20-A2."
8. Sample Size for the Training Set
- Sample Size for Training Set: Not mentioned. The summary focuses on the clinical tests for demonstrating equivalence, not on the details of the model's development or training data.
9. How the Ground Truth for the Training Set Was Established
- Ground Truth for Training Set: Not mentioned. Similar to the training set size, the details of how the training data's ground truth was established are not provided in the 510(k) summary.
§ 864.5260 Automated cell-locating device.
(a)
Identification. An automated cell-locating device is a device used to locate blood cells on a peripheral blood smear, allowing the operator to identify and classify each cell according to type. (Peripheral blood is blood circulating in one of the body's extremities, such as the arm.)(b)
Classification. Class II (performance standards).