(192 days)
The Duet™ System is an automated scanning microscope and image analysis system. It is intended for in-vitro diagnosis use as an aiding tool to the pathologist in the detection, classification and counting of cells of interests based on particular color, intensity, size, pattern and shape.
The Duet™ System is intended to detect the following cell types:
- Hematopoietic cells stained by Giemsa stain, Immunohistochemistry or ISH (with bright field and fluorescent) prepared from cell suspension.
- Amniotic cells stained by FISH (using direct labeled DNA probes for chromosomes X, Y, 13, 18 and 21),
The Duet™ System is a fully integrated imaging and scanning platform that automates time-consuming and difficult laboratory tasks of slide screening by making a significant reduction in time and labor currently required.
The Duet™ scans in high resolution and in full color cell samples at high speed both in bright light illumination and in fluorescent illumination.
Duet™ suggests classification of the cells according to their morphological features, their staining (Giemsa, IHC) and fluorescent signals, and allows the user to quickly examine the results, correct them as needed and generate a report summarizing the sample's data. The unique feature of the Duet system allows the presents combined presentation of morphological and specific staining information of the same cell, for all the cells of the sample.
Here is the information about the acceptance criteria and the study that proves the device meets the acceptance criteria, based on the provided text:
1. A table of acceptance criteria and the reported device performance
| Acceptance Criteria (Stated Goal) | Device Performance |
|---|---|
| Accuracy: To determine accuracy using the NCCLS-EP9 guideline for method comparison and bias estimation. | Correlation Coefficient: 0.9843 (between Duet™ test and manual method for amniotic fluid cell analysis). |
| Slope: 0.9758 | |
| Intercept: 2.2316 | |
| Precision (Intra-system): To determine precision within a single Duet™ system using the NCCLS-EP5 guideline. | Coefficient of Variation (CV): 0.15% (no clinically significant differences observed) |
| Precision (Inter-system): To assess differences between readings of the same slides by different Duet™ systems compared to repeated readings on the same system using ANOVA. | No clinically significant differences between systems. |
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Test Set Sample Size: 133 slides of Amniotic fluid cells from samples of 68 ongoing pregnancies were used for the accuracy study. A set of four slides was used for the precision study.
- Data Provenance: The country of origin is not explicitly stated in the provided summary. The study appears to be prospective in nature, as it involved preparing slides and then examining them.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
The document primarily compares the Duet™ system's performance to the "routine manual method" or "human manual visualization by conventional microscopes" as a predicate. It does not explicitly state the number of experts or their specific qualifications used to establish the ground truth for the test set. However, it implies that the "manual method" represents the established ground truth.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not describe a specific adjudication method like 2+1 or 3+1. The ground truth for the comparative performance study for accuracy seems to be established by the "routine manual method". It implies a direct comparison rather than an adjudicated consensus.
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 explicitly described in the provided text. The study focused on comparing the device's performance against the "routine manual method," not on how human readers improve with AI assistance. The document states the Duet™ System is an "aiding tool to the pathologist," but the study described is a direct comparison to manual methods, not an assisted reading study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, a standalone study was performed. The described "Comparison of the routine manual method and the Duet method" and the "Evaluation of precision performance" assess the Duet™ System's performance in its automated capacity without explicit human intervention in the classification and counting steps being measured against the manual method. The device's role is to "suggest classification of the cells," implying the evaluation of its automated capabilities, with the user then allowed to "correct them as needed" which is a post-analysis step.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The type of ground truth used for the accuracy study was implicitly derived from the "routine manual method" of analysis. This suggests that the results obtained by cytogeneticists or pathologists using conventional microscopes were considered the reference standard.
8. The sample size for the training set
The document does not explicitly state the sample size used for the training set of the Duet™ system. It mentions that the "Duet™ System software as a whole was fully validated during its development process," and "Performance studies were accomplished to validate that the software and the system as a whole comply with the new indication," but does not provide details about training data.
9. How the ground truth for the training set was established
The document implicitly states that changes were incorporated to support the new intended use, and the software was validated. However, it does not describe how the ground truth for any potential training set 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).