K Number
K171083
Date Cleared
2017-05-12

(31 days)

Regulation Number
862.1340
Panel
CH
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The iChem® VELOCITY™ automated urine chemistry system is an in vitro diagnostic device used to automate the urine chemistry analysis profile using iChem® VELOCITY ™ Urine Chemistry Strips. The iChemVELOCITY can be used as a stand-alone system, as well as in an iQ®200 Series system, a configuration given the proprietary name iRICELL™ as it is designed to be hardware and software compatible with iQ200 Series systems. It produces quantitative results for specific gravity; semi-quantitative results for glucose, blood, leukocyte esterase, bilirubin, urobilingen, pH, protein, ketones and ascorbic acid; and qualitative results for nitrites, color and clarity.

iChemVELOCITY strips are intended for use only with the iChem Velocity analyzer. In particular, they are not intended for visual reading. The iChemVELOCITY is not intended to be used as a Point of Care (POC) analyzer.

These measurements are used to aid in the diagnosis of metabolic disorders, kidney function anomalies, urinary tract infections, and liver function. Tests performed using the iChemVELOCITY are intended for clinical laboratory and in vitro diagnostic use only.

Device Description

The iChemVELOCITY is an automated urine chemistry system performing measurements of defined physical and chemical constituents in urine. The system utilizes iChemVELOCITY urine chemistry test strips which are read in the Strip Reader Module (SRM) by measuring light reflectance, in addition the iChemVELOCITY measures color and clarity using light transmittance through Color/Clarity Module (CCM) and specific gravity using refractive index through Specific Gravity Module (SGM).

The subject of this submission is a design change to the Color/Clarity Module (CCM) of the Color/Clarity/Specific Gravity Module (CGM) subassembly of the iChemVELOCITY. The CCM measures the color and clarity of a urine sample using transmitted and scattered light, incident on a color sensor. An algorithm then converts the output of the different channels of the sensor into semi-quantitative colors. The CCM is being changed to replace end-of-life components (color sensor and scatter light source) and update the color detection algorithm.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Device: iChem®VELOCITY™ Automated Urine Chemistry System with redesigned Color/Clarity Module (CCM)

1. A table of acceptance criteria and the reported device performance

The document doesn't explicitly state "acceptance criteria" with numerical targets for the redesigned CCM. Instead, it aims to demonstrate substantial equivalence to the predicate device (iChemVELOCITY with the original CCM). Therefore, the reported performance is compared to the predicate's expected performance, with the implicit criterion being that the redesigned CCM performs at least as well as, or is in agreement with, the predicate.

Here's an interpretation of the performance data in the context of implied acceptance:

Feature/MetricAcceptance Criteria (Implied for Substantial Equivalence to Predicate)Reported Device Performance (Redesigned CCM vs. Predicate)
Color AgreementHigh percentage of exact match and ±1 block agreement with predicate device's color readings.Refer to "Method Comparison Results Summary" and "Precision Results Summary" below for detailed numbers. All ±1 block agreement is 100% or 99.6%. Exact match ranges from 36% (Straw) to 100%.
Clarity AgreementHigh percentage of exact match and ±1 block agreement with predicate device's clarity readings.Refer to "Method Comparison Results Summary" and "Precision Results Summary" below for detailed numbers. All ±1 block agreement is 100% or 97.2%. Exact match ranges from 29.2% (Slightly Cloudy) to 100%.
FitThe redesigned CCM must remain unchanged in fit within the iChemVELOCITY system."All testing successfully passed the acceptance criteria, and the test results demonstrated equivalence to the predicate." "The testing results confirmed that the redesigned CCM was fit..."
FunctionThe redesigned CCM must produce equivalent results to the predicate design."All testing successfully passed the acceptance criteria, and the test results demonstrated equivalence to the predicate." "The testing results confirmed that the redesigned CCM was...functionally compatible and equivalent to the original CCM."
New HazardsNo new hazards introduced by the design change."no new hazards were introduced with the implementation of this change and therefore safety associated with the operation of this device remains unchanged."
User ExperienceThe design change should not negatively impact the user experience."did not negatively impact the user experience."

Detailed Performance Tables from the Document:

Method Comparison Results Summary (Page 8):

Redesigned CCM / ComparatorColorlessStrawYellowAmberRedBlue
Color
Blue18
Red318
Amber518
Yellow11619
Straw13
Colorless1812
Exact match:100.0%36%92%60.0%100.0%100.0%
± 1 Block:100.0%100.0%100.0%100.0%100.0%100.0%
Redesigned CCM / ComparatorClearSlightly CloudyCloudyTurbid
Clarity
Turbid32
Cloudy1221
Slightly Cloudy713
Clear87161
Exact match:100.0%29.2%61.1%97.0%
± 1 Block:100.0%100.0%97.2%100.0%

Precision Results Summary (Page 9):

Color/ClarityTest levelNumber (Total)Exact agree±1 block agree% Exact agreement% ±1 block agreement
ColorColorless240240240100%100%
Straw24023824099.2%100%
Yellow240240240100%100%
Amber240240240100%100%
Red24023723998.8%99.6%
Blue240240240100%100%
ClarityClear240240240100%100%
Slightly Cloudy24022824095.0%100%
Cloudy240240240100%100%
Turbid240240240100%100%

2. Sample size used for the test set and the data provenance

  • Sample Size: The "Precision Results Summary" table on page 9 indicates that for each color and clarity level category, 240 samples were tested.
  • Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or prospective. It only states that "Performance testing of the iChemVELOCITY with the redesigned CCM was conducted."

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

The document does not specify the number of experts used or their qualifications for establishing ground truth. The "Method Comparison" results compare the "Redesigned CCM" to a "Comparator." Given the context of a design change to an existing device, the "Comparator" likely refers to the predicate iChemVELOCITY device with the original CCM. The ground truth, in this case, would be the results generated by the predicate device, not necessarily external human experts.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

The document does not mention any adjudication method, as the comparison is primarily machine-to-machine (redesigned CCM vs. predicate CCM).

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

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This device is an automated urine chemistry system, and the study focuses on the performance of the redesigned CCM against its predicate, not on human reader performance or AI assistance.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

Yes, a standalone performance study was done. The entire study focuses on the performance of the automated iChemVELOCITY system with the redesigned CCM. There is no mention of human-in-the-loop performance evaluation for the color and clarity measurements. The device is intended "for clinical laboratory and in vitro diagnostic use only" and "is not intended for visual reading."

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

The primary ground truth for the performance study is the predicate device's performance. The study aims to show that the redesigned CCM produces results equivalent to the iChemVELOCITY with the original CCM, which was previously cleared.

8. The sample size for the training set

The document does not specify a separate training set size. The study describes a design change to existing hardware/software components, including an updated algorithm. It's possible that the "new firmware has been written and installed on the CCM's microprocessor... to update the CCM algorithm" implies some form of development/training, but the specifics and size are not provided in this regulatory summary.

9. How the ground truth for the training set was established

Since no specific training set and its size are explicitly mentioned, the method for establishing its ground truth is also not described. If algorithm development involved training, the ground truth would likely have been established using reference methods during the design phase of the original or updated algorithm, but this is not detailed in the provided text. The document focuses on the verification that the redesigned component performs equivalently to the existing, cleared device.

§ 862.1340 Urinary glucose (nonquantitative) test system.

(a)
Identification. A urinary glucose (nonquantitative) test system is a device intended to measure glucosuria (glucose in urine). Urinary glucose (nonquantitative) measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, hypoglycemia, and hyperglycemia.(b)
Classification. Class II.