The Bayer ADVIA® IMS™ AFP assay is an in vitro diagnostic device intended to quantitatively measure afetoprotein (AFP) in human serum on the Bayer ADVIA IMS system as an aid in the management of nonseminomatous testicular cancer. AFP values obtained using the Bayer ADVIA IMS assay method must be interpreted in conjunction with all other available clinical and laboratory data before a medical decision is determined. AFP testing is not recommended as a screening procedure to detect cancer in the general population.

Device Description

The Bayer ADVIA® IMS™ AFP assay is an in vitro diagnostic device intended to quantitatively measure afetoprotein (AFP) in human serum on the Bayer ADVIA IMS system.

AI/ML Overview

Acceptance Criteria and Study for Bayer ADVIA® IMS™ AFP Assay

This document summarizes the acceptance criteria and the study conducted to demonstrate the safety and effectiveness of the Bayer ADVIA® IMS™ AFP Assay.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the ADVIA IMS AFP Assay are primarily established by demonstrating substantial equivalence to the predicate device, Immuno 1 AFP Assay, across various performance metrics. The specific quantitative acceptance criteria are implicitly defined by the reported performance metrics of the predicate device and the observed performance of the new device.

Performance Metric	Acceptance Criteria (Implicit, based on predicate performance)	Reported Device Performance (ADVIA IMS AFP Assay)
Imprecision (Total CV%)	Comparable to Immuno 1	Level 4.6 ng/mL: 2.3%
		Level 18.97 ng/mL: 2.7%
		Level 93.52 ng/mL: 2.6%
Correlation: Regression Equation (Y=ADVIA IMS, X=Immuno 1)	Close to Y=X (slope ~1, intercept ~0)	Y = 1.06 * X - 3.18
Correlation: Syx	Low Syx, indicating good agreement	5.82 ng/mL
Correlation: R (correlation coefficient)	High (close to 1)	0.998
Interfering Substances (Effect % change)	Effect within acceptable limits (typically < 10% or clinically insignificant)	Hemoglobin (1000 mg/dL): 5.6%
		Lipids (1000 mg/dL): 7.5%
		Bilirubin (25 mg/dL): -4.5%
		IgG (6.0 g/dL): 8.3%
		Albumin (6.5 g/dL): 4.8%
Analytical Range	Comparable to predicate or clinically appropriate	0.08 - 400 ng/mL
Minimum Detectable Concentration (MDC)	Comparable to predicate or clinically appropriate	0.08 ng/mL

Note on Acceptance Criteria: For this type of diagnostic device, formal, explicit numerical acceptance criteria often aren't stated as "must be less than X" or "must be greater than Y." Instead, the criteria are often qualitative, such as "comparable to the predicate device," "within clinically acceptable limits," or "demonstrates substantial equivalence." The reported performance of the predicate device serves as the benchmark. The study's "conclusion" explicitly states "Performance...is equivalent to the performance of the AFP Assay on the predicate device (Immuno 1) and is within proposed specifications," indicating these metrics were met.

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

Correlation Study (Regression Analysis):
- Sample Size: 50 serum specimens.
- Data Provenance: Not explicitly stated, but clinical specimens are implied for a correlation study comparing two assay methods. The country of origin and retrospective/prospective nature are not specified in the provided text.
Imprecision Study:
- Sample Size: Not explicitly stated for the number of replicates or days tested, but typically involves multiple replicates tested over several days. The data provided includes "Level" and "Total CV(%)".
- Data Provenance: Not specified.
Interfering Substances Study:
- Sample Size: Various AFP concentrations (10.2, 19.8, 21.3, 16.4, 14.8 ng/mL) were tested in the presence of specified concentrations of interfering substances. The number of individual samples tested for each substance is not explicitly stated.
- Data Provenance: Not specified.
Expected Values (Reference Range Study):
- Sample Size: 250 healthy individuals.
- Data Provenance: Not specified, but likely sourced from a local population or established clinical labs.
Patient Population Distribution Study:
- Sample Size:
  - Healthy Subjects: 350
  - Testicular Cancer (nonseminomatous): 100
  - Testicular Cancer (mixed germ cell tumor): 46
  - Testicular Cancer (seminomatous): 8
  - Prostate Cancer / Bladder Cancer: 40
  - Lung Cancer: 29
  - Colorectal Cancer: 38
  - Liver Cancer: 67
  - Breast Cancer: 10
  - Cirrhosis: 50
  - Hepatitis: 50
  - Benign Genito-urinary disease: 29
  - Other nonmalignant: 37
- Data Provenance: "Immuno 1 data on file" is noted for these expected values, suggesting this data was likely pre-existing from studies conducted with the predicate device, or was generated with the predicate and then confirmed with the new device. The country of origin and retrospective/prospective nature are not specified.

3. Number of Experts and Qualifications for Ground Truth

No "experts" in the traditional sense (e.g., radiologists interpreting images) were used to establish ground truth for the performance studies described. This is a quantitative diagnostic assay, where "ground truth" is typically established by physical measurements, reference methods, or clinical diagnoses.

4. Adjudication Method for the Test Set

Not applicable. Adjudication methods (like 2+1 or 3+1) are typically used for subjective assessment of images or clinical reports by multiple human readers. This submission describes a quantitative assay where results are numerical measurements.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No MRMC comparative effectiveness study was done. This study focuses on the analytical performance of a quantitative assay, comparing it to a predicate device, rather than assessing the performance of human readers with or without AI assistance.

6. Standalone Performance Study

Yes, a standalone study of the algorithm (assay method) was done. The entire submission details the performance of the ADVIA IMS AFP Assay as a standalone device, directly measuring AFP levels in serum samples. The performance characteristics (imprecision, correlation, interfering substances, analytical range, MDC) are all measurements of the device's inherent analytical capability without human interpretation being part of the primary performance metric being evaluated. The "monitoring data" also shows the device's output over time for individual patients.

7. Type of Ground Truth Used

The "ground truth" for the various studies can be categorized as follows:

Imprecision: Internal consistency of the device, measured against its own repeated results.
Correlation: Reference values established by the predicate device (Immuno 1 Assay). The predicate device's measurements serve as the comparator "truth" against which the new device's measurements are compared.
Interfering Substances: Presence of known concentrations of specific substances in the sample. The "effect" is the deviation from the expected measurement in the absence of the interferent.
Analytical Range & Minimum Detectable Concentration: Determined through analytical experiments using known concentrations of AFP standards.
Expected Values/Patient Population Distribution: Clinical outcomes/diagnoses (e.g., healthy subjects, testicular cancer, liver cancer, cirrhosis) were used to characterize patient populations and establish reference ranges. These clinical diagnoses serve as the "ground truth" for understanding the assay's utility in different disease states.

8. Sample Size for the Training Set

Not applicable. This document describes a traditional in-vitro diagnostic (IVD) assay, not a machine learning or AI-based device that typically requires a large "training set" for model development. The assay's performance is based on chemical reactions and detection methods, calibrated using standards.

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

Not applicable. As the device is not an AI/ML product, there is no "training set" in that context. The "ground truth" for establishing the assay's analytical characteristics (like analytical range and MDC) is derived from using known concentrations of AFP standards and calibrators. For the clinical utility data (expected values in different patient populations), the ground truth is the established clinical diagnosis of the patients in those cohorts.

Summary

{0}------------------------------------------------

OCT 01 2002

510(k) SUMMARY OF SAFETY AND EFFECTIVENESS AFP Assay for Bayer ADVIA® Integrated Modular System (IMS)™

This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of the Safe Medical Device Act of 1990 and 21 CFR 807.92.

The assigned 510(k) number is:

1. Intended Use

2. Predicate Device

Product Name	Reagent Part #	Calibrator Part #
Immuno 1 AFP Assay	T01-3100-51	T03-3187-01

3. Device / Method

Product Name	Reagent Part # / BANNumber	Calibrator Part # /BAN Number
ADVIA IMS AFP Assay	B42-3890-23 /	B43-3923-01 /
	09750523 (100 tests)	09022137
	01440029 (250 tests)

Imprecision

ADVIA IMS		Immuno 1
Level(ng/mL)	TotalCV(%)	Level(ng/mL)	TotalCV(%)
4.6	2.3	20	2.1
18.97	2.7	50	2.2
93.52	2.6	200	3.6

Correlation (Y= ADVIA IMS, X=comparison system)

Specimen type	Comparison System (X)	N	Regression Equation	Syx (ng/mL)	R	Sample Range (ng/mL)
Serum	Immuno 1	50	Y=1.06 * X -3.18	5.82	0.998	0.71 - 338.92

Interfering Substances

InterferingSubstance	Interfering SubstanceConcentrationmg/dL	AFPConcentration(ng/mL)	Effect(% change)
Hemoglobin	1000	10.2	5.6
Lipids (Triglycerides)	1000	19.8	7.5
Bilirubin	25	21.3	-4.5
IgG	6.0	16.4	8.3
Albumin	6.5	14.8	4.8

{1}------------------------------------------------

Expected values'

As with all tests, each laboratory should establish its own reference range. In a group of 250 healthy people, 97.5% of the serum AFP values were found to be 0.8 ng/mL (0.66 IU/mL) to 8.9 ng/mL (7.35 IU/mL). The distribution of the AFP values for these 250 patient samples is shown in Figure 1. Substantially higher values are often found when malignant disease is present, particularly in patients with nonseminomatous turnors. However, low AFP values do not rule out the presence of malignant disease.

Image /page/1/Figure/2 description: The image is a bar graph showing the frequency of AFP values in ng/mL. The x-axis represents the AFP values, ranging from 1 to >11, while the y-axis represents the frequency, ranging from 0 to 100. The bar for AFP value 3 has the highest frequency, reaching approximately 93, while the bar for AFP value 2 has a frequency of approximately 65.

DISTRIBUTION OF SERUM AFP ASSAY VALUES

PATIENTPOPULATION	N	AFP ASSAY VALUES (ng/mL)				MEDIAN
		0 - 8.9(%)	>8.9 - 100(%)	>100-400(%)	>400(%)
Healthy Subjects	350	98.3	1.7	0.0	0.0	2.5
Testicular Cancernonseminomatous	100	36.0	40.0	14.0	10.0	20.2
Testicular Cancermixed germ cell tumor	46	43.5	45.7	6.5	4.3	11.6
Testicular Cancerseminomatous	8	75.0	25.0	0.0	0.0	2.5
Prostate Cancer /Bladder Cancer	40	97.5	2.5	0.0	0.0	3.4
Lung Cancer	29	96.6	0.0	0.0	3.4	3.8
Colorectal Cancer	38	89.5	10.5	0.0	0.0	4.5
Liver Cancer	67	0.0	31.3	20.9	47.8	310.9
Breast Cancer	10	80.0	20.0	0.0	0.0	4.8
Cirrhosis	50	88.0	12.0	0.0	0.0	4.0
Hepatatis	50	88.0	12.0	0.0	0.0	3.9
Benign Genito-urinarydisease	29	93.1	6.9	0.0	0.0	3.1
Other nonmalignant	37	100.0	0.0	0.0	0.0	2.3

' Immuno 1 data on file

{2}------------------------------------------------

Monitoring data

Two examples of serial patient monitoring studies using Bayer ADVIA IMS assay results in comparison to results obtained for another marketed device are shown in the following figures.

Image /page/2/Figure/2 description: The image contains two line graphs that compare AFP levels over time between ADVIA IMS and a marketed device. The left graph shows a significant increase in AFP levels around 12/10/01, reaching a peak of approximately 160-180 ng/mL by 02/03/02. The right graph shows a smaller increase in AFP levels around 11/05/01, reaching a peak of approximately 60-70 ng/mL. Both graphs show a decline in AFP levels towards the end of the plotted time period.

Analytical Range

0.08 - 400 ng/mL

Minimum Detectable Concentration

ADVIA IMS(ng/mL)	Immuno 1(ng/mL)
0.08	0.1

4. Conclusion

Performance of the ADVIA IMS AFP Assay on a Bayer ADVIA® IMS™ is equivalent to the performance of the AFP Assay on the predicate device (Immuno 1) and is within proposed specifications. No safety and effectiveness issues have been raised

Kenneth T. Edds Director Regulatory Affairs Bayer Corporation 511 Benedict Avenue Tarrytown, New York 10591-5097 Date

{3}------------------------------------------------

Image /page/3/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo features the department's name in a circular arrangement around a symbol. The symbol is a stylized representation of three human profiles facing right, with flowing lines beneath them. The profiles are meant to represent the department's focus on people and their well-being.

Food and Drug Administration 2098 Gaither Road Rockville MD 20850

Kenneth T. Edds, Ph.D. Regulatory Affairs Baver Corporation 511 Benedict Avenue Tarrytown, NY 10591-5097

OCT 01 2002

Re: K020807

Trade/Device Name: AFP (α-Fetoprotein) Assay for the ADVIA® IMS™ Regulation Number: 21 CFR 866.6010 Regulation Name: Tumor-associated antigen immunological test system Regulatory Class: Class II Product Code: LOJ Dated: August 29, 2002 Received: September 3, 2002

Dear Dr. Edds:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food. Drug. and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. The general controls provisions of the Act include requirements for annual registration. Ilsting of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to such additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

{4}------------------------------------------------

Page 2 -

This letter will allow you to begin marketing your device as described in your 510(k) premarket notification. The FDA finding of substantial equivalence of your device to a legally marketed predicate device results in a classification for your device and thus, permits your device to proceed to the market.

If you desire specific advice for your device on our labeling regulation (21 CFR Part 801 and additionally 809.10 for in vitro diagnostic devices), please contact the Office of Compliance at (301) 594-4588. Additionally, for questions on the promotion and advertising of your device, please contact the Office of Compliance at (301) 594-4639. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21CFR 807.97). Other general information on your responsibilities under the Act may be obtained from the Division of Small Manufacturers International and Consumer Assistance at its toll-free number (800) 638-2041 or (301) 443-6597 or at its internet address "http://www.fda.gov/cdrl/dsmaldsmamain.html".

Sincerely yours,

Steven Sutman

Steven I. Gutman, M.D., M.B.A. Director Division of Clinical Laboratory-Devices Office of Device Evaluation Center for Devices and Radiological Health

Enclosure

{5}------------------------------------------------

K020807 510(k) Number:

Device Name: AFP (α-Fetoprotein) Assay for the ADVIA® IMS™

Indications for Use:

The Bayer ADVIA® IMS™AFP assay is an in vitro diagnostic device intended to quantitatively measure orfetoprotein (AFP) in human serum on the Bayer ADVIA IMS system as an aid in the management of nonseminomatous testicular cancer. AFP values obtained using the Bayer ADVIA IMS assay method must be interpreted in conjunction with all other available clinical and laboratory data before a medical decision is determined. AFP testing is not recommended as a screening procedure to detect cancer in the general population.

(PLEASE DO NOT WRITE BELOW THIS LINE - CONTINUE ON ANOTHER PAGE IF NEEDED)

Concurrence of CDRH, Office of Device Evaluation (ODE)

Deborah M. Moore

(Division Sign-O Division of Clinical Labor 510jk) Number _

Prescription Use (Per 21 CFR 801.109)

Over-The-CounterUse

(Optional Format 1-2-96)

Regulation Number and Section

§ 866.6010 Tumor-associated antigen immunological test system.

(a)
Identification. A tumor-associated antigen immunological test system is a device that consists of reagents used to qualitatively or quantitatively measure, by immunochemical techniques, tumor-associated antigens in serum, plasma, urine, or other body fluids. This device is intended as an aid in monitoring patients for disease progress or response to therapy or for the detection of recurrent or residual disease.(b)
Classification. Class II (special controls). Tumor markers must comply with the following special controls: (1) A guidance document entitled “Guidance Document for the Submission of Tumor Associated Antigen Premarket Notifications (510(k)s) to FDA,” and (2) voluntary assay performance standards issued by the National Committee on Clinical Laboratory Standards.