K Number
K982301
Date Cleared
1998-08-07

(37 days)

Product Code
Regulation Number
864.5260
Panel
HE
Reference & Predicate Devices
N/A
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

For In Vitro Diagnostic Use

Intelligent Medical Imaging, Inc.'s MICRO21® with Urine Sediment Analysis is a laboratory instrument for locating, digitally storing and displaying microscopic fields of view from urine sediments in a urine slide for examination by a qualified individual for use in reporting a urine microscopic result.

Device Description

The MICRO21 with Urine Sediment Analysis, is an automated microscopic system that locates formed elements of wine sediment, digital stores images of the constituents and displays the images in an organized manner to aid technologists in performing an Urine Sediment Analysis procedure. The MICRO21 process is substantially equivalent to the manual microscopic process.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study details for the MICRO21® with Urine Sediment Analysis device, based on the provided text:

Acceptance Criteria and Device Performance

The provided document describes categories of testing rather than explicit numerical acceptance criteria. The "Conclusion" section summarizes that the device met the implicit acceptance criteria for each test.

Acceptance Criteria CategoryReported Device Performance (Summary)
PrecisionNo significant variation demonstrated.
ReproducibilityNo significant variation demonstrated.
LinearityNo significant variation demonstrated.
CorrelationDemonstrated for RBC, WBC, Squamous Epithelial cells, Hyaline Casts, Amorphous, Calcium Oxalate, and Triple Phosphate Crystals, Mucous, Sperm and Yeast. For quantitative results, the average value from each range was used for computing regression analysis values (R values). For qualitative results, correlation/equivalence was determined to be within one reporting range.

Study Details

2. Sample Size Used for the Test Set and Data Provenance

  • Sample Size (Test Set): 182 stained samples. An additional 31 stained samples were created using serial dilution and enrichment to generate a wider range of urinary constituents.
  • Data Provenance: Not explicitly stated regarding country of origin. The study appears to be retrospective in that existing samples were processed and then compared to manual methods. The generation of additional samples via serial dilution and enrichment suggests a controlled laboratory setting.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications

  • Number of Experts: Three.
  • Qualifications of Experts: Certified Medical Technologists.

4. Adjudication Method for the Test Set

The text states, "Using blinded experimental methods, the stained samples were reviewed manually, and processed by the MCRO21 and resultant images reviewed by the technologists." It doesn't explicitly describe an adjudication method (like 2+1 or 3+1) for resolving disagreements among the three technologists when establishing the manual ground truth. It implies their manual review was the ground truth.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

The study describes a comparison between the MICRO21 system and the "manual urine microscopic reference method using standard correlation statistics." This is a comparative study, and it involved multiple readers (three certified medical technologists) reviewing both the manual slides and the MICRO21 images.

  • Effect Size of Human Readers with AI vs. Without AI Assistance: The document does not provide a specific "effect size" or quantitative measure of how much human readers improve with AI assistance. Instead, it aims to demonstrate that the MICRO21 system's results correlate well with the manual method, suggesting the device is "safe and effective for its intended use of locating, digitally storing and displaying microscopic fields of view from urine sediments in a urine slide for examination by a qualified individual for use in reporting a urine microscopic result." The phrasing "the MICRO21 process is substantially equivalent to the manual microscopic process" and the conclusion of correlation across various elements implies that performance with the device is comparable to human-only assessment.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

The MICRO21 is described as an "automated microscopic system that locates formed elements...digital stores images...and displays the images...to aid technologists in performing an Urine Sediment Analysis procedure." Crucially, item 8 of the process workflow states, "The technologist reviews the images and quantifies the results." This clearly indicates that the device is designed for human-in-the-loop operation, not standalone algorithmic interpretation. Therefore, a standalone performance study of the algorithm without human review was not performed or intended according to this document.

7. The Type of Ground Truth Used

Expert Consensus (Manual Method): The ground truth was established by three certified medical technologists performing the "manual urine microscopic reference method." This serves as the benchmark against which the MICRO21 results were compared.

8. The Sample Size for the Training Set

The document does not explicitly mention a separate "training set" or its sample size. The description of testing focuses on "performance testing" to assess precision, accuracy, linearity, and correlation, which typically refers to evaluation on a test set.

9. How the Ground Truth for the Training Set Was Established

Since a separate training set is not described, the method for establishing its ground truth is not provided.

§ 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).