(28 days)
The Bayer ADVIA 2120 Hematology System with Autoslide is a quantitative, automated hematology analyzer that provides a complete blood cell count, leukocyte differential count and reticulocyte analysis for in vitro diagnostic use in clinical laboratories. In addition, the system provides the added capability to automatically prepare and stain high-quality blood smears on a microscope slide.
The ADVIA 2120 Hematology system with Autoslide is an integrated option of a Hematology analyzer with complete blood cell count, leukocyte differential cell count, reticulocyte analysis capability and a slide stainer designed to provide reflexive slide making/staining without user intervention based upon pre-selected, user-definable criteria.
The ADVIA 2120 Hematology system with Autoslide consists of the following: an analytical module that aspirates, dilutes, and analyzes whole blood samples; an autosampler that automatically mixes, identifies, and presents the samples for processing; a computer workstation that controls the instrument, provides primary user interface with the instrument and manages the data produced by the instrument; a printer that optionally generates reports based on the instrument results and an autoslide module that prepares a wedge smear from a drop of blood, places it on a microscope slide and stains the slide in accordance with Wright, Wright-Giemsa and May-Grunwald Giemsa Staining techniques.
The provided text does not contain specific acceptance criteria or a detailed study description for the ADVIA® 2120 with Autoslide. Instead, it focuses on demonstrating that the device is substantially equivalent to a predicate device (ADVIA 120 Hematology Analyzer) through a 510(k) submission.
The core argument for substantial equivalence is that the ADVIA 2120 with Autoslide performs the same functions (hematological analysis and automated slide preparation/staining) using similar technological characteristics as the predicate device, with the added functionality of the Autoslide module.
Therefore, many of the requested details about acceptance criteria, performance metrics, sample sizes, and expert adjudication are not present in this document. The 510(k) process for substantial equivalence often relies on demonstrating that the new device performs similarly to a legally marketed predicate device, rather than requiring extensive new performance studies against predefined acceptance criteria for every parameter.
However, I can extract information related to the device's capabilities and the nature of the submission.
Here's a breakdown of what can be inferred and what is not available from the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
Not explicitly provided. The document states that the new device is "substantially equivalent" to the predicate device. This implies that its performance is considered comparable to the predicate, which would have had its own performance data established. The exact acceptance criteria used to deem it substantially equivalent are not detailed.
Sufficient information is not provided to complete this table.
2. Sample Size Used for the Test Set and Data Provenance
Not explicitly provided. The document does not describe specific test sets, sample sizes, or data provenance used for performance evaluation of the ADVIA 2120 with Autoslide itself. The focus is on demonstrating technological similarity to the predicate device.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
Not applicable/provided. Since no specific performance study against a defined ground truth is detailed for this 510(k) submission, there is no mention of experts or their qualifications for establishing ground truth.
4. Adjudication Method for the Test Set
Not applicable/provided. As no detailed test set or ground truth establishment is described, an adjudication method is not mentioned.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No. The document does not describe an MRMC comparative effectiveness study where human readers' performance with and without AI assistance is evaluated. This device is an automated hematology analyzer and slide maker/stainer, not an AI-assisted diagnostic tool for human readers in the typical sense of an MRMC study.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Implicitly yes, in the context of the predicate device. The ADVIA 2120 with Autoslide is an automated system. Its performance, like its predicate (ADVIA 120), is inherent to the algorithms and hardware that perform the blood analysis and slide preparation. While not explicitly called a "standalone algorithm performance study" in modern AI terms, the device's measurements and slide quality are its standalone outputs. The 510(k) relies on the predicate device's established standalone performance and demonstrates that the new device performs similarly.
7. The Type of Ground Truth Used
Not explicitly described for this submission. For diagnostic devices like hematology analyzers, typical ground truth for analytical performance includes:
- Reference Methods: Highly accurate and validated laboratory methods for measuring specific analytes (e.g., manual differential counts, reference hemoglobinometry).
- Patient Samples: Using samples with known clinical conditions.
- Control Materials: Calibrated reference materials and controls.
Given the nature of a 510(k) for substantial equivalence, the ground truth would have been established for the predicate device, and the current submission argues the new device operates on the same (or similar) principles to achieve comparable results.
8. The Sample Size for the Training Set
Not applicable/provided. The document does not discuss a training set in the context of machine learning or AI algorithm development. This submission is for a medical device (hematology analyzer and automated slide stainer) that uses established analytical principles (laser light scatter, absorption, impedance, chemical reactions), not a machine learning model that requires a "training set."
9. How the Ground Truth for the Training Set Was Established
Not applicable/provided. As there is no "training set" described for an AI algorithm, this information is not relevant to the provided document.
§ 864.5220 Automated differential cell counter.
(a)
Identification. An automated differential cell counter is a device used to identify one or more of the formed elements of the blood. The device may also have the capability to flag, count, or classify immature or abnormal hematopoietic cells of the blood, bone marrow, or other body fluids. These devices may combine an electronic particle counting method, optical method, or a flow cytometric method utilizing monoclonal CD (cluster designation) markers. The device includes accessory CD markers.(b)
Classification. Class II (special controls). The special control for this device is the FDA document entitled “Class II Special Controls Guidance Document: Premarket Notifications for Automated Differential Cell Counters for Immature or Abnormal Blood Cells; Final Guidance for Industry and FDA.”