(132 days)
The SE/RAM-1 is an In Vitro device for whole blood cell analysis in clinical laboratories. The SE-9000 portion is intended for blood cell analysis; the RAM-1 portion is intended for automated reticulocyte analysis. The instrument is a screening device for identifying abnormal blood specimens. Medical technologists are responsible for final review of abnormal cells.
The SE/RAM-1 is a table-top analyzer system consisting of a blood cell counting unit (SE-9000), a reticulocyte unit (RAM-1), a Data Management System, and a printer. A Sampler Unit is attached to the SE-9000 unit, which transports samples in cassette racks to the ID bar code reader and then to the Automatic mixing/Cap piercing device.
The SE/RAM-1 system has the capability of reporting up to 23 parameters. The 23 reportable parameters are as follows: RBC, Hgb, HCT, MCV, MCH, MCHC,RDW-CV, RDW-SD. PLT. MPV. WBC. NEUT%. LYMPH%. MONO%. EO%. BASO%, NEUT#, LYMPH#, MONO#, EO#, BASO# (all from SE-9000 unit), RETIC %, RETIC# (from RAM-1 unit).
The SRV of the SE-9000 contains a port (in the original design of the instrument) by which the reticulocyte module(RAM-1) is attached. The SRV splits the blood sample into 8 aliquots. 7 aliquots are delivered to the SE-9000 system, diluted with the appropriate diluent or lyse and sent to their respective detector blocks for analysis. The 8th aliquot is sent to the RAM-1 where it is diluted and stained, then sent to the flow cell for analysis. The SE/RAM-1 system uses a total of up to 13 reagents. All reagents are the same as used on the stand-alone SE-9000 and the R-3000 analyzers.
The provided text describes a 510(k) Summary of Safety and Effectiveness for the Sysmex™ SE/RAM-1 device. This document focuses on demonstrating substantial equivalence to previously cleared devices (Sysmex™ SE-9000 and R-3000) rather than presenting a detailed study with explicit acceptance criteria and performance metrics for a novel device. Therefore, much of the requested information regarding acceptance criteria, specific performance studies, sample sizes, expert involvement, and ground truth establishment is not available in this document.
The core argument for substantial equivalence is that the SE/RAM-1 is a combination of existing, cleared technologies with only minor software and tubing modifications, and that these modifications do not raise new issues of safety and effectiveness.
Here's an attempt to answer your questions based on the provided text, highlighting what is (and isn't) present:
1. A table of acceptance criteria and the reported device performance
This document does not present specific acceptance criteria in the format often seen for AI/novel device clearances (e.g., minimum sensitivity, specificity, accuracy thresholds). Instead, the "performance" of the SE/RAM-1 is primarily asserted to be "same" as the predicate devices based on the principle of substantial equivalence.
| Acceptance Criteria Category | Acceptance Criteria (Not explicitly stated as such, but inferred from equivalence claim) | Reported Device Performance (Asserted equivalent to predicate devices) |
|---|---|---|
| Intended Use | Must match or be substantially equivalent to predicate devices. | Same as SE-9000 (CBC analysis) and R-3000 (reticulocyte analysis). |
| Sample Type | Must process the same sample types as predicate devices. | Same as SE-9000 and R-3000 (EDTA anticoagulated whole blood). |
| Physical Safety | Must maintain the same safety profile as predicate devices. | Same as SE-9000 (K936023) and R-3000 (K912494). |
| Performance (General) | Performance characteristics must be equivalent to predicate devices. | Same as SE-9000 (K936023) and R-3000 (K912494). |
| Principles of Operation | Must utilize the same fundamental technologies. | RF/DC, Sheath flow (for SE-9000 portion); fluorescence intensity, forward scatter (for RAM-1 portion). |
| Physical Hardware | Must use substantially similar hardware components. | Hydraulic, electronic systems; shared pneumatic unit, SE sampler/barcode reader. |
| Software Programs | Functionality should be consistent with predicate devices, potentially with enhancements. | Full color display, 10000 sample storage, 12 QC files (RAM-1 portion). |
| Reagents | Must use the same reagents as predicate devices. | Same as used on stand-alone SE-9000 and R-3000 analyzers. |
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
This information is not provided in the document. The submission relies on the prior clearance of the SE-9000 and R-3000, implying that their performance data supports the combined system. No new, specific test set data for the SE/RAM-1 is detailed here.
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)
This information is not provided in the document. As new specific performance studies for the SE/RAM-1 are not detailed, there's no mention of experts establishing ground truth for a new test set.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not provided in the document.
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 document describes an in vitro diagnostic device for automated blood cell analysis, not an AI-assisted interpretation tool for human readers. Therefore, an MRMC comparative effectiveness study comparing human readers with and without AI assistance is not applicable and was not performed. The device is a screening tool, with "Medical technologists...responsible for final review of abnormal cells," implying that human expertise is still required for confirmation, but not in a "human-in-the-loop" AI augmentation sense for primary interpretation.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The device itself is a "standalone" automated analyzer in the sense that it performs the analysis and generates parameters without direct human intervention in the measurement process. However, it is explicitly stated that it is a "screening device for identifying abnormal blood specimens" and that "Medical technologists are responsible for final review of abnormal cells." This means the final diagnostic decision is not purely algorithmic. The document does not describe specific standalone performance studies for this combined device; instead, it refers to the performance of the predicate devices (K936023 for SE-9000 and K912494 for R-3000).
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
This information is not provided in this document. Any ground truth used for the predicate devices (SE-9000 and R-3000) would have been established during their respective clearance processes, but details are not given here. For blood analyzers, ground truth often involves manual microscopy and/or other validated laboratory methods.
8. The sample size for the training set
This information is not provided in the document. As this is not an AI/machine learning device being trained, the concept of a "training set" as commonly understood in that context does not apply. The device's operational principles are based on established biophysical detection methods.
9. How the ground truth for the training set was established
This information is not provided and is not applicable as there is no mention of a training set for an AI/ML model.
§ 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).