(80 days)
The Yellow IRIS is used by a competent human operator to produce a complete urinalysis profile, including chemistry, sediment microscopy and specific gravity determinations.
It is capable of detecting and reporting all types of formed urine sediment elements and of quantitating such elements, when desired, based on observed proportion of total particulate count.
The Yellow IRIS is intended to replace the conventional intensive manipulatively manual complete urinalysis procedure as well as the abbreviated.
The Yellow IRIS urinalysis workstation, an already existing commercial in-vitro diagnostic device
Here's an analysis of the provided text, focusing on the acceptance criteria and the study details:
1. Table of Acceptance Criteria and Reported Device Performance
| Device Performance Metric | Acceptance Criteria (Implied) | Reported Performance (Yellow IRIS vs. Urine Test Strips) |
|---|---|---|
| Sensitivity: Microscopic detection of Red Blood Cells (hematuria) | Improved sensitivity over existing methods | 37.9% greater sensitivity |
| Sensitivity: Microscopic detection of White Blood Cells (pyuria or leukocyturia) | Improved sensitivity over existing methods | 80.8% greater sensitivity |
| Sensitivity: Microscopic detection of Bacteria (bacteriuria) | Improved sensitivity over existing methods | 555.5% greater sensitivity |
| Detection of abnormal compositions of RBCs, WBCs, and/or bacteria (compared to 3-part dipstick) | Improved detection over existing methods | 29.4% more specimens detected |
| Detection of abnormal compositions of RBCs, WBCs, and/or bacteria (compared to 6-part dipstick) | Improved detection over existing methods | 13.4% more specimens detected |
Explanation of Acceptance Criteria: The document implies that the acceptance criterion for the Yellow IRIS urinalysis workstation was to demonstrate increased sensitivity in the detection of abnormal microscopic content compared to traditional urine test strips and popular screening algorithms. While specific numerical targets are not explicitly stated as "acceptance criteria," the reported performance metrics clearly aimed to prove superiority in sensitivity.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: More than 18,000 abnormal urine specimens.
- Data Provenance: The study was carried out among more than 100 clinical laboratories. This suggests a multi-site, potentially nationwide or regional, collection effort. The data appears to be retrospective, as it describes "comparisons of detection...by dipstick screening and by visual observation of flow microscopy using The Yellow IRIS" in a population of specimens where both methods were already in use for "complete routine urinalysis."
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
The document does not explicitly state the number of experts used or their specific qualifications for establishing ground truth. However, it mentions "visual observation of flow microscopy using The Yellow IRIS" which implies that trained laboratory personnel or medical professionals were performing the visual assessments. Given it's a urinalysis workstation, these would typically be clinical laboratory scientists, medical technologists, or pathologists. Specific experience (e.g., "radiologist with 10 years of experience") is not provided.
4. Adjudication Method for the Test Set
The document does not provide details on any specific adjudication method (e.g., 2+1, 3+1, none) used for the test set. The comparison is described as "comparative measures...carried out among more than 100 clinical laboratories," suggesting that the performance of each method (dipstick vs. Yellow IRIS) was assessed against each other, rather than against a single, independently adjudicated "gold standard" truth for each specimen.
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 a comparison between a device (Yellow IRIS) and traditional methods (urine test strips), not a study explicitly evaluating human reader improvement with AI assistance. The Yellow IRIS is described as an "urinalysis workstation" that utilizes "flow microscopy" for visual observation, which could involve an automated component for image capture and analysis, but it is still overseen by a "competent human operator."
- Therefore, an MRMC comparative effectiveness study as typically defined in the context of AI assistance to human readers was not explicitly conducted or reported here. The device itself (Yellow IRIS) is being compared to the existing standard of care, not human performance with and without the device.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
The document explicitly states that "The Yellow IRIS is used by a competent human operator to produce a complete urinalysis profile, including chemistry, sediment microscopy and specific gravity determinations." This indicates that the device operates with a human-in-the-loop, and therefore, a standalone (algorithm only) performance study was not conducted or reported.
7. The Type of Ground Truth Used
The ground truth for the comparison was essentially the visual observation of flow microscopy using The Yellow IRIS itself, compared against the results from urine test strips. It's a comparison between two different diagnostic methods rather than against a completely independent "gold standard" such as pathology or outcomes data. The document states its goal is to show increased sensitivity of the Yellow IRIS compared to dipstick screening.
8. The Sample Size for the Training Set
The document does not provide any information regarding a training set sample size. The description focuses solely on the performance comparison study. This implies that if there was any machine learning or algorithm development, the details of its training and validation are not included in this summary.
9. How the Ground Truth for the Training Set Was Established
Since no information is provided about a training set, there is no information on how its ground truth might have been established.
§ 862.2900 Automated urinalysis system.
(a)
Identification. An automated urinalysis system is a device intended to measure certain of the physical properties and chemical constituents of urine by procedures that duplicate manual urinalysis systems. This device is used in conjunction with certain materials to measure a variety of urinary analytes.(b)
Classification. Class I (general controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to § 862.9.