The COULTER® LH 500 is a quantitative, automated hematology analyzer For In Vitro Diagnostic Use in clinical laboratories. The LH 500 System provides automated complete blood count and leukocyte differential. The product also provides semi- automated reticulocyte analysis.

Device Description

LH 500 hematology analyzer is designed For In Vitro Diagnostic Use in clinical laboratories. The LH 500 provides automated complete blood count and leukocyte differential and semiautomated reticulocyte analysis. The purpose of the LH 500 hematology analyzer is to separate the normal patient, with all normal system-generated parameters, from the patient who needs additional studies of any of these parameters. These studies might include further measurements of cell size and platelet distribution, manual WBC differential or any other definitive test that helps diagnose the patient's condition.

AI/ML Overview

The provided text describes a 510(k) premarket notification for a software modification to the COULTER® LH 500 Hematology Analyzer, not a study presenting detailed acceptance criteria and performance data in the typical sense for a new AI/ML device. This submission focuses on demonstrating substantial equivalence to a previously cleared device. Therefore, a direct mapping to all requested elements (like sample size for training, number of experts for ground truth, MRMC study, etc.) is not fully possible given the nature of the document.

However, I can extract the relevant information and present what is available, inferring acceptance criteria and performance based on the context of a hematology analyzer.

Acceptance Criteria and Device Performance (Inferred from a Hematology Analyzer Context):

For a hematology analyzer, performance is typically assessed by its ability to accurately count and differentiate various blood cell types. The "acceptance criteria" for a modified version would generally relate to maintaining or improving the performance characteristics of the predicate device, especially for the parameters affected by the software change (e.g., differential counts and reticulocyte analysis).

Given the document is a 510(k) for a software modification to allow cyanide-free reagents and to mitigate observed anomalies of earlier versions, the primary performance assessment would involve demonstrating that the device with the new software and reagents performs comparably to the predicate device with its original reagents and software for key hematological parameters. Specific quantitative acceptance criteria are not explicitly listed in this summary, but would typically involve metrics like:

Accuracy/Bias: Comparison of counts and differentials to a reference method or predicate device.
Precision/Reproducibility: Consistency of measurements.
Correlation: Statistical correlation of results with a reference or predicate device.
Carryover: Minimal transfer of cells/material between samples.
Linearity: Accurate measurement across a range of cell concentrations.

Since the document mentions "various corrections, clarifications and minor performance testing results were added to operator labeling," this implies that some performance testing was conducted, likely demonstrating that the modifications did not negatively impact the device's accuracy or reliability for its intended use.

Table of Acceptance Criteria and Reported Device Performance (Inferred/Generic for Hematology Analyzers):

Acceptance Criteria Category (Inferred)	Specific Metric (Inferred)	Acceptance Threshold (Typical for Hema Analyzer)	Reported Device Performance (Based on "substantially equivalent")
Accuracy of CBC Parameters	White Blood Cell (WBC) Count Bias	Within +/- 5% of reference	Deemed substantially equivalent to predicate
	Red Blood Cell (RBC) Count Bias	Within +/- 3% of reference	Deemed substantially equivalent to predicate
	Hemoglobin (Hgb) Bias	Within +/- 2% of reference	Deemed substantially equivalent to predicate
	Platelet (Plt) Count Bias	Within +/- 15% of reference (at low counts)	Deemed substantially equivalent to predicate
Accuracy of Differential Counts	Neutrophil % Bias	Within +/- 5% of reference	Deemed substantially equivalent to predicate
	Lymphocyte % Bias	Within +/- 5% of reference	Deemed substantially equivalent to predicate
	Monocyte % Bias	Within +/- 3% of reference	Deemed substantially equivalent to predicate
	Eosinophil % Bias	Within +/- 2% of reference	Deemed substantially equivalent to predicate
	Basophil % Bias	Within +/- 1% of reference	Deemed substantially equivalent to predicate
Reticulocyte Analysis	Reticulocyte % Bias	Within +/- 20% of reference (at low counts)	Deemed substantially equivalent to predicate
Reproducibility/Precision	%CV for various parameters	Typically < 5%	Deemed substantially equivalent to predicate
Functional Equivalence	Ability to use new cyanide-free reagents	Successful and accurate operation	Successful (Implied by clearance)

Detailed Study Information (Based on the Provided Text):

Sample size used for the test set and the data provenance:
- Sample Size: Not explicitly stated in the provided text. The document mentions "performance testing results were added to operator labeling," which suggests a test set was used, but the size is not specified.
- Data Provenance: Not explicitly stated. For a 510(k) submission, data is typically from internal manufacturer testing or external clinical sites. The country of origin is not mentioned, and it's most likely prospective data collection for the validation of the new software/reagent combination.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not specified. For hematology analyzers, ground truth often involves manual microscopy differential counts performed by trained medical technologists or pathologists, or comparison to established reference methods using samples with known characteristics. The number and qualifications of such experts are not detailed here.
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not specified. If manual microscopy was used to establish ground truth, adjudication (e.g., by a second expert in case of disagreement) would be a standard practice, but the method is not mentioned.
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, an MRMC comparative effectiveness study was not done in the context of human readers improving with AI assistance. This device is an automated hematology analyzer, not an AI-assisted diagnostic tool that aids human interpretation of images. Its purpose is to automate cell counting and differentiation, reducing or replacing the need for manual review for normal samples. The "AI" mentioned in the prompt often refers to advanced machine learning for image interpretation, which is not the primary function or innovation described for this type of hematology analyzer in 2004. The "algorithm changes" mentioned are for internal signal processing and classification, not for assisting human readers in traditional image interpretation.
If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
- Yes, a standalone performance assessment was done. The entire operation of a hematology analyzer, including its differential cell counting, is inherently "standalone" in this context. The device directly provides results (CBC and differential) without requiring human real-time interpretation for each case. The "software algorithm changes" and "performance testing results" refer to the standalone performance of the instrument. The device aims to "separate the normal patient... from the patient who needs additional studies," implying that its standalone performance is used to flag samples for further manual human review or specialized testing.
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Not explicitly stated, but for hematology analyzers, ground truth is typically established through:
  - Manual microscopy differential counts by experienced medical technologists or pathologists.
  - Reference methods using highly characterized blood samples or certified reference materials.
  - Comparison to a predicate device that has already established acceptable accuracy against such reference methods. Given this is a 510(k) for a modification, comparison to the predicate (older software version) would be a primary method, implicitly relying on the predicate's established ground truth.
The sample size for the training set:
- Not applicable / Not specified. The document describes a software modification to an existing device, not the development of a de novo AI/ML model that typically requires a distinct "training set" in the modern sense. While the original software algorithms would have been developed using some form of data, the text does not refer to a training set for this specific Version 2A software update. The "algorithm changes" likely involved refinements based on observed performance with the original reagents or for addressing anomalies, rather than a re-training of a complex AI model.
How the ground truth for the training set was established:
- Not applicable / Not specified for the reasons mentioned above. If there were data used to refine the algorithms (rather than a formal "training set"), the ground truth would have been established using similar methods to the test set (manual microscopy, reference methods, or predicate device comparison).

Summary

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

OCT 2 9 2004

K042724

Section 1 D: Summary of Safety and Effectiveness for COULTER® LH 500 Hematology Analyzer with Version 2A Software

1.0 General Information

Device Generic Name(s):	Automated differential cell counter
Device Trade Name(s):	COULTER® LH 500 Hematology Analyzer
Device Classification:	The COULTER® LH 500 Hematology Analyzer is a Class IIImedical device.
Applicant Name and Address:	Beckman Coulter, Inc.
	Cellular Analysis Division
	11800 SW 147 Avenue
	Miami, FL 33196-2500
Date:	September 30, 2004

2.0 Legally Marketed Device(s)

The modified COULTER® LH 500 Hematology Analyzer with Version 2A Software claims substantial equivalence to the previously cleared COULTER® LH 500 Hematology Analyzer with Version 1A software.

FDA 510(k) Number(s): K032000

3.0 Device Description

4.0 Principle of Method:

CBC (Complete Blood Count) Analysis (Whole Blood)

CBC analysis is based on the established Coulter principle method of automated cell counting and spectrophotometric hemoglobin determination. The Coulter method counts and sizes cells by detecting and measuring changes in electrical resistance when a particle (such as a cell) in a conductive liquid goes through a small aperture,

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

Each cell suspended in a conductive liquid (diluent) acts as an insulator. As each cell goes through the aperture, it momentarily increases the resistance of the electrical path between two submerged electrodes, one located on each side of the aperture. This causes an electrical pulse that can be counted and sized. While the number of pulses indicates particle count, the size of the electrical pulse is proportional to the cell volume.

Differential and Reticulocyte Analysis (Whole Blood)

Differential and reticulocyte Analysis is based on the Coulter volume, conductivity and light scatter technology (VCS). Differential analysis and classification and reticulocyte analysis occur in the flow cell, where:

Low-frequency current measures volume.

High-frequency current senses cellular internal content through measuring changes in conductivity,

Light from the laser scattered off the individual cells characterizes cellular surface, shape and reflectivity.

5.0 Indications for Use:

6.0 Description of the modification:

The currently marketed COULTER LH 500 hematology analyzer with Version 1A software release was modified with software algorithm changes to allow use of cyanide-free reagents (ISOTON 4 diluent /LYSE S 4 lytic agent). Additional software modifications were made to mitigate observed anomalies of earlier versions and various corrections, clarifications and minor performance testing results were added to operator labeling.

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

DEPARTMENT OF HEALTH & HUMAN SERVICES

Image /page/2/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo consists of two main elements: a circular seal with the text "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" arranged around the perimeter, and a stylized symbol resembling three abstract human figures or waves. The symbol is positioned to the right of the circular seal.

2098 Gaither Road Rockville MD 20850

Food and Drug Administration

Stan Sugrue, Ph.D. Senior Regulatory Affairs Specialist Premarket Product Regulatory Compliance Beckman Coulter, Inc. 11800 SW 147 Avenue Miami, Florida 33196-2500

Re: K042724

Trade/Device Name: COULTER® LH 500 Hematology Analyzer with Version 2A Software Regulation Number: 21 CFR § 864.5220 Regulation Name: Automated differential cell counter Regulatory Class: II Product Code: GKZ, GKL Dated: October 18, 2004 Received: October 19, 2004

OCT 2 9 2004

Dear Dr. Sugrue:

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, listing 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 Title 21, Code of Federal Regulations (CFR), Parts 800 to 895. 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 Parts 801 and 809); and good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820). This letter will allow you to begin marketing your device as described in your Section 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.

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

Page 2

If you desire specific information about the application of labeling requirements to your device, or questions on the promotion and advertising of your device, please contact the Office of In Vitro Diagnostic Device Evaluation and Safety at (301) 594-3084. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21CFR Part 807.97). You may obtain other general information on your responsibilities under the Act 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/cdrh/dsma/dsmamain.html.

Sincerely yours,

Robert L. Becker Jr.

Robert L. Becker, Jr., M.D., Ph.D. Director Division of Immunology and Hematology Devices Office of In Vitro Diagnostic Device Evaluation and Safety Center for Devices and Radiological Health

Enclosure

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

Section 1C:

INDICATIONS FOR USE

K042724
~~Not assigned~~

510(k) Number (if known):

COULTER® LH 500 Hematology Analyzer Device:

Intended use:

21 CFR 864.5220 Automated differential cell counter

An automated differential cell counter is a device used to identify and classify one or more of the formed elements of blood.

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

Concurrence of CDRH, Office of Device Evaluation (ODE)

Prescription Use Use (Per 21 CFR 801.109) OR

Over-The-Counter

Division Sign-Off

Office of In Vitro Diagnostic Device Evaluation and Safet

510(k) K042724

Regulation Number and Section

§ 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.”