(62 days)
DM96 is an automated cell-locating device.
DM96 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.
DM96 is intended to be used by skilled operators, trained in the use of the device and in recognition of blood cells.
DM96 is an automated cell-locating device for differential count of white blood cells, characterization of red blood cell morphology and platelet estimation. DM96 consists of a slidescanning unit (a slide feeder, a microscope and a camera) and a computer system containing the acquisition and classification software "CellaVision Blood Differential software".
Here's an analysis of the provided text, extracting the requested information about device acceptance criteria and the supporting study:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state numerical acceptance criteria. Instead, it frames the performance in terms of "equivalence" to the predicate device (DiffMaster Octavia™) and the manual light microscopic process. The reported performance is that the DM96 "is equivalent in accuracy, precision and clinical sensitivity and specificity and fulfilled the pre-defined requirements for overview image quality."
| Characteristic | Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|---|
| Accuracy (White Blood Cell Classification) | Equivalent to DiffMaster Octavia™ and manual light microscopic process | Achieved equivalence to predicate and manual method |
| Precision (White Blood Cell Classification) | Equivalent to DiffMaster Octavia™ and manual light microscopic process | Achieved equivalence to predicate and manual method |
| Clinical Sensitivity (White Blood Cell Classification) | Equivalent to DiffMaster Octavia™ and manual light microscopic process | Achieved equivalence to predicate and manual method |
| Clinical Specificity (White Blood Cell Classification) | Equivalent to DiffMaster Octavia™ and manual light microscopic process | Achieved equivalence to predicate and manual method |
| Cell-Location Accuracy | Met pre-defined requirements | Achieved accuracy for cell-location |
| Overview Image Quality | Met pre-defined requirements | Fulfilled pre-defined requirements for overview image quality |
2. Sample Size Used for the Test Set and Data Provenance
The document does not explicitly state the sample size used for the clinical evaluation (test set) or the data provenance (e.g., country of origin, retrospective/prospective). It only mentions that "A clinical evaluation has been performed to confirm equivalence with the predicate method DiffMaster Octavia™ for differentiation of white blood cells."
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
This information is not provided in the document.
4. Adjudication Method for the Test Set
The document states that for both the predicate device and the DM96, "A competent operator is required to confirm or modify the suggested classification of each cell." This indicates a human-in-the-loop approach where human verification or reclassification is part of the final result. However, the specific adjudication method used for the initial ground truth (e.g., 2+1, 3+1 consensus) for the test set is not explicitly described.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size
The document describes a clinical evaluation to confirm equivalence with a predicate method, which is a comparative study. It also explicitly states that the device is intended for use by "skilled operators, trained in the use of the device and in recognition of blood cells," and that "The operator identifies and verifies the suggested classification of each cell according to type." This implies a human-in-the-loop scenario.
However, it does not explicitly state that it was a formal MRMC study, nor does it provide an effect size of how much human readers improve with AI vs. without AI assistance. The study focuses on demonstrating equivalence of the DM96 (with human verification) to existing methods.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
The device description consistently states that the "operator identifies and verifies the suggested classification of each cell." The technological characteristics section further elaborates that "The cell images are pre-classified and the operator verifies the suggested classification by accepting or reclassifying." This indicates that the device is not intended or tested for standalone, algorithm-only performance without a human-in-the-loop to verify classifications.
7. The Type of Ground Truth Used
The ground truth for the clinical evaluation appears to be based on expert consensus from a "competent human examiner" or "skilled operators" using either the manual light microscopic process or the predicate device (DiffMaster Octavia™) for comparison. The study aimed to show equivalence to these established methods, which rely on human expert interpretation.
8. Sample Size for the Training Set
The document provides no information regarding the sample size used for the training set of the deterministic artificial neural networks (ANNs).
9. How the Ground Truth for the Training Set Was Established
The document states that ANNs are "trained to distinguish between classes of white blood cells." However, it does not describe how the ground truth for this training data was established.
§ 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).