The GEM® Premier 3000 is a portable system for use by health care professionals to rapidly analyze whole blood samples that was originally cleared for the U.S. market by K992834, with glucose and lactate parameters added by K010520.

Intelligent Quality Management (iQM") is being introduced on the GEM® Premier 3000 as an active quality process control program designed to provide continuous monitoring of the analytical process with real-time, automatic error detection, automatic correction of the system and automatic documentation of all corrective actions, replacing the use of traditional external quality controls.

As part of this program, GEM® CVP (Calibration Validation Product) is intended for the external verification of the iQM" cartridge calibration after initial warm-up to ensure its integrity. The reported values for the four levels of GEM® CVP (two levels for pH, blood gases, electrolytes and metabolites; two levels for hematocrit) must meet specifications before the iQM" cartridge can be used for patient sample measurements. Once the cartridge calibration is verified, the internal iOM "program monitors the status of the system during the cartridge use life.

To ensure that a total quality management system is adhered to, laboratories should follow local, state and federal regulatory guidelines. As with any analytical device or computer software, there is always the potential for software failure. However, IL conducts rigorous testing and extensive software validation prior to releasing a software revision. If the user encounters a rare software error code, it should be reported to your local IL Technical Support Representative.

Device Description

AI/ML Overview

Here's a breakdown of the acceptance criteria and the studies performed for the GEM® Premier 3000 with iQM™ and GEM® CVP, based on the provided document:

Acceptance Criteria and Device Performance

The document does not explicitly present a table of acceptance criteria in the sense of predefined thresholds for performance metrics. Instead, it presents the results of performance studies (precision and method comparison) that indicate the device's capabilities and statistical similarity to a reference instrument.

For the GEM® CVP Precision study, the reported performance is the Day-to-Day %CV (or SD) and Total %CV (or SD) for various parameters across different CVP levels. The acceptance is implicitly assumed if these values are considered acceptable for clinical use, or comparable to existing methods.

For the GEM® Premier 3000 with iQM™ Method Comparison study, the reported performance includes the slope, intercept, and correlation coefficient (r) when compared to a reference instrument (IL Synthesis). The acceptance is stated as being "statistically similar to the reference instrument."

Table of Reported Performance Data (Excerpted from the document):

GEM® CVP Precision Study Results:

Parameter	Mean	Day-to-Day %CV (or SD)	Total %CV (or SD)
GEM® CVP Level 1
pH	7.200	0.005 (SD)	0.007 (SD)
pCO2 (mmHg)	70.8	1.39	1.63
pO2 (mmHg)	54.5	4.97	5.16
Na+ (mmol/L)	129.3	0.46	0.55
K+ (mmol/L)	2.90	0.25	0.70
Ca++ (mmol/L)	1.493	0.95	1.26
Glucose (mg/dL)	46.1	2.23	2.99
Lactate (mmol/L)	0.93	4.73	4.87
GEM® CVP Level 2
pH	7.640	0.002 (SD)	0.003 (SD)
pCO2 (mmHg)	29.9	1.78	1.91
pO2 (mmHg)	148.2	1.33	1.93
Na+ (mmol/L)	158.7	0.44	0.56
K+ (mmol/L)	6.46	0.75	0.98
Ca++ (mmol/L)	0.486	1.15	2.06
Glucose (mg/dL)	192.8	1.67	1.78
Lactate (mmol/L)	5.54	1.85	2.19
GEM® CVP Level 3
Hematocrit (%)	23.4	2.14	2.11
GEM® CVP Level 4
Hematocrit (%)	43.8	1.21	1.23

GEM® Premier 3000 with iQM™ Method Comparison Study Results:

Analyte	N	Slope	Intercept	r	Sample Range
pH	281	1.0802	-0.5810	0.9917	7.129-7.559
pCO2 (mmHg)	282	1.0674	-2.3800	0.9839	25.3-87.5
pO2 (mmHg)	282	0.9715	6.9900	0.9988	26-489
Na+ (mmol/L)	271	0.9801	2.9300	0.9584	119-148
K+ (mmol/L)	271	0.9743	-0.0600	0.9871	3.2-7.4
Ca++ (mmol/L)	271	0.9196	0.1270	0.9590	0.82-1.40
Glucose (mg/dL)	283	1.0111	8.8700	0.9860	66-389
Lactate (mmol/L)	280	0.9323	0.1730	0.9958	0.49-16.67
Hct (%)	284	0.9983	-0.7999	0.9600	17-56

Study Information:

1. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

GEM® CVP Precision Study:
- Test Set Size: 15 replicates for each of 4 CVP levels on each of 9 different GEM® Premier 3000 instruments (N=135 total measurements per CVP level/parameter combination).
- Data Provenance: Not explicitly stated, but implied to be from internal lab studies. It's likely a controlled, prospective study.
GEM® Premier 3000 with iQM™ Method Comparison Study:
- Test Set Size (N): Varies per analyte, ranging from 271 to 284 samples (e.g., 281 for pH, 282 for pCO2, 271 for Na+, etc.).
- Data Provenance: "arterial, venous, heart bypass and liver transplant blood samples from hospital patients." This indicates human patient samples. The country of origin is not specified, but the submission is for the U.S. market, so it typically implies U.S. data or data relevant to its approval. It's a retrospective analysis of prospectively collected patient samples, as they were analyzed on both the test device and a reference instrument.
iQM™ (Intelligent Quality Management) Evaluation - Evaluation of Cartridge Malfunction Detection:
- Test Set Size: Data from 79 GEM® Premier 3000 cartridges that demonstrated a QC failure.
- Data Provenance: Not explicitly stated, but implies real-world usage data where QC failures occurred. This would be considered retrospective analysis of field data.
Field Evaluation: External QC vs. iQM™:
- Test Set Size: 304 blood samples.
- Data Provenance: During an external field evaluation at a U.S. hospital. This is prospective real-world data collection.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

The document describes device performance validation against instrument measurements and quality control materials. It does not involve human expert interpretation of results to establish ground truth in the way a medical imaging study might.
GEM® CVP Precision: Ground truth is the actual concentration of the assayed quality control materials.
GEM® Premier 3000 with iQM™ Method Comparison: Ground truth is established by the IL Synthesis reference instrument. No human experts are mentioned for establishing ground truth directly for this comparison.
iQM™ (Intelligent Quality Management) Evaluation: Ground truth for a malfunction detection study would be the confirmed presence or absence of a malfunction in the cartridge. This was determined by analysis of "system parameters" and the nature of the QC failures. "No identifiable cartridge malfunction" and "All system parameters were within specifications" implies instrument-derived ground truth.
Field Evaluation: Ground truth for analyte failures came from the observation of "transient drift failures," "Benzalkonium exposure," and "Thiopental Sodium exposure."

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

Adjudication methods like 2+1 or 3+1 are typically used when human interpretation (e.g., by experts) is involved to resolve discrepancies in ground truth establishment. Since these studies primarily involve comparing instrument readings or detecting malfunctions based on predefined parameters, no such adjudication method is mentioned or appears applicable.

4. 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 MRMC comparative effectiveness study was done. This device is an analytical instrument and an associated quality control program, not a diagnostic aid that assists human readers in interpreting images or complex data as in AI applications. The focus is on automated measurement accuracy and malfunction detection.

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

Yes, the performance of the GEM® Premier 3000 with iQM™ and GEM® CVP is evaluated entirely in a standalone manner. The iQM™ system itself is an "active quality process control program designed to provide continuous monitoring of the analytical process with real-time, automatic error detection, automatic correction of the system and automatic documentation of all corrective actions, replacing the use of traditional external quality controls." Its evaluation, therefore, is its performance as a standalone automated system. The studies assess its precision, agreement with a reference instrument, and its ability to detect malfunctions automatically.

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

GEM® CVP Precision: Assayed values of the quality control materials.
GEM® Premier 3000 with iQM™ Method Comparison: Readings from a reference analytical instrument (IL Synthesis).
iQM™ (Intelligent Quality Management) Evaluation - Evaluation of Cartridge Malfunction Detection: Instrument-based parameters and previous QC failure data. The conclusion that "no identifiable cartridge malfunction" existed for the unflagged failures suggests thorough investigation of instrument internal states.
Field Evaluation: Identified causes of analytical interference (Benzalkonium exposure, Thiopental Sodium exposure) and comparison to a reference instrument (IL Synthesis) and a GEM® 3000 without iQM.

7. The sample size for the training set

The document does not explicitly state the sample size for a "training set." This type of device relies on established analytical principles and algorithms. While the iQM™ system uses "Failure Pattern Recognition (FPR) checks," it's not described as a system that undergoes machine learning training in the contemporary sense. The "training" in this context would likely refer to internal development and validation data, not a distinct "training set" as in typical AI/ML development. The "79 GEM® Premier 3000 cartridges that demonstrated a QC failure" were part of an evaluation to test the FPR checks, not necessarily to train them.

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

As a conventional analytical instrument and its QC system, there isn't a "training set" with ground truth established in the same way as an AI/ML model for image recognition or diagnosis. The underlying principles for analysis and quality control are based on established chemistry, physics, and engineering. The "ground truth" for the device's operational parameters would have been established through extensive engineering, chemical assays, and calibration procedures during the device's development.

Summary

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

Section 3

GEM® Premier 3000: Introduction of iQM™ and GEM® CVP 510(k) Summary (Summary of Safety and Effectiveness)

Submitted by:

Instrumentation Laboratory Company 113 Hartwell Avenue Lexington, MA 02421 Phone: 781-861-4467 781-861-4207 Fax:

Contact Person:

Carol Marble, Regulatory Affairs Manager Phone: 781-861-4467 / Fax: 781-861-4207

Summary Prepared:

July 1, 2002

Name of the device:

GEM® Premier 3000: Introduction of iQM™ and GEM® CVP

Classification name(s):

75JJS	Controls for Blood-Gases (Assayed and Unassayed)
75JJR	Electrolyte Controls (Assayed and Unassayed)
862.1660	Quality Control Material (Assayed and Unassayed)	Class I
81GLK	Hematocrit Control
864.8625	Hematology Quality Control Mixture	Class II

Identification of predicate device(s):

K010520	ContrIL ® 9 (FDA cleared as a blood gas/electrolyte/metabolite quality control with theintroduction of glucose and lactate on the GEM® Premier 3000)
K992834	GEM® critCheck (FDA cleared as a hematocrit quality control with the introduction ofthe GEM® Premier 3000)

Description of the device/intended use(s):

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

Section 3 (Cont.) GEM® Premier 3000: Introduction of iQM™ and GEM® CVP 510(k) Summary (Summary of Safety and Effectiveness)

Statement of Technological Characteristics of the Device Compared to Predicate Device:

The use of Intelligent Quality Management (iQM") in conjunction with GEM® CVP (Calibration Validation Product) on the GEM® Premier 3000 is not materially different from the use of external controls in performance, safety and effectiveness or intended use.

Summary of performance data:

GEM® CVP Precision

A precision study was performed on the GEM® Premier 3000 using the four levels of GEM® CVP (two levels for pH, blood gases, electrolytes and metabolites; two levels for hematocrit). Each level of the verification material was run in singlet once a day for 14 days (twice on Day 1) for a total of 15 replicates on each of 9 different GEM® Premier 3000 instruments (N=135).

	Parameter	Mean	Day-to-Day%CV (or SD)	Total%CV (or SD)
GEM® CVPLevel 1	pH	7.200	0.005 (SD)	0.007 (SD)
	pCO2 (mmHg)	70.8	1.39	1.63
	pO2 (mmHg)	54.5	4.97	5.16
	Na+ (mmol/L)	129.3	0.46	0.55
	K+ (mmol/L)	2.90	0.25	0.70
	Ca++ (mmol/L)	1.493	0.95	1.26
	Glucose (mg/dL)	46.1	2.23	2.99
	Lactate (mmol/L)	0.93	4.73	4.87
GEM® CVPLevel 2	pH	7.640	0.002 (SD)	0.003 (SD)
	pCO2 (mmHg)	29.9	1.78	1.91
	pO2 (mmHg)	148.2	1.33	1.93
	Na+ (mmol/L)	158.7	0.44	0.56
	K+ (mmol/L)	6.46	0.75	0.98
	Ca++ (mmol/L)	0.486	1.15	2.06
	Glucose (mg/dL)	192.8	1.67	1.78
	Lactate (mmol/L)	5.54	1.85	2.19
GEM® CVPLevel 3	Hematocrit (%)	23.4	2.14	2.11
GEM® CVPLevel 4	Hematocrit (%)	43.8	1.21	1.23

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

Section 3 (Cont.) GEM® Premier 3000: Introduction of iQM™ and GEM® CVP 510(k) Summary (Summary of Safety and Effectiveness)

Summary of performance data (Cont.):

GEM® Premier 3000 with iQM™ Method Comparison

In addition, a method comparison study was performed to verify the performance of the GEM® Premier 3000 cartridge with iQM" (Intelligent Quality Management). The method comparison data included arterial, venous, heart bypass and liver transplant blood samples from hospital patients using heparinized syringes. All samples were analyzed on the GEM® Premier 3000 with iQM versus an IL Synthesis as the reference instrument. The GEM® Premier 3000 with iQM " was shown to be statistically similar to the reference instrument:

Analyte	N	Slope	Intercept	r	Sample Range
pH	281	1.0802	-0.5810	0.9917	7.129-7.559
pCO2 (mmHg)	282	1.0674	-2.3800	0.9839	25.3-87.5
pO2 (mmHg)	282	0.9715	6.9900	0.9988	26-489
Na+ (mmol/L)	271	0.9801	2.9300	0.9584	119-148
K+ (mmol/L)	271	0.9743	-0.0600	0.9871	3.2-7.4
Ca++ (mmol/L)	271	0.9196	0.1270	0.9590	0.82-1.40
Glucose (mg/dL)	283	1.0111	8.8700	0.9860	66-389
Lactate (mmol/L)	280	0.9323	0.1730	0.9958	0.49-16.67
Hct (%)	284	0.9983	-0.7999	0.9600	17-56

iQM™ (Intelligent Quality Management) Evaluation

Evaluation of Cartridge Malfunction Detection .

Data from 79 GEM® Premier 3000 cartridges that demonstrated a QC failure during their cartridge use life were extensively analyzed. The Failure Pattern Recognition (FPR) checks were applied to these data to determine if iQM" could detect any malfunction.

The Failure Pattern Recognition (FPR) checks were able to detect malfunction in 74 out of 79 reported QC failures. In most cases, iQM" would have flagged the failure immediately after the sample that caused the malfunction, while with conventional controls, the user would only be aware of a problem when the external control is run again, which may be up to hours after the event occurred. Furthermore, no false positive flags were generated by the FPR checks in any of the 79 investigated cartridges.

Resolution of 5 Unflagged QC Failures:

For the 5 reported QC failures that iQM" did not detect, there was no identifiable cartridge malfunction. All system parameters were within specifications. There were no error flags and no failure patterns. There were no unusual blood values for the parameter with reported QC failure and the customer did not report any concern about blood results. In all five cases, the reported QC failures were marginal and at one level only. It was concluded that the reported QC failures in these five cartridges could not represent a serious cartridge malfunction. The failures could be considered as a false positive QC failure.

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

Section 3 (Cont.) GEM® Premier 3000: Introduction of iQM™ and GEM® CVP 510(k) Summary (Summary of Safety and Effectiveness)

Field Evaluation: External QC vs. iQM™

During an external field evaluation at a U.S. hospital, a side-by-side comparison was performed on a GEM® Premier 3000 using iQM™ versus two reference instruments, IL Synthesis and GEM® 3000 without iQM using traditional external quality controls. This study was conducted over a 3-week period with the external quality controls run during each day's shift: contrIL" 9 on all three analyzers and GEM® critCheck on the GEM® analyzers only. Each GEM® instrument used a single 450 sample capacity cartridge (1 instrument with and 1 instrument without iQM"). A total number of 304 blood samples were tested.

During this field evaluation, there were no instances of external failure on any instrument. However, the instruments experienced transient drift failures caused by interference as noted below:

. There were 4 instances of Benzalkonium exposure, which caused analyte failures on all three instruments.
. There were 8 instances of Thiopental Sodium* exposure, which caused analyte failures on both the GEM® instruments, with and without iQM™.

*NOTE: The IL Synthesis is not affected by Thiopental Sodium.

In all of the above cases, the GEM® Premier 3000 using iQM™ successfully detected and flagged the failed analytes and identified the cause as interference. All three systems self-corrected by the next sample run and therefore, the interference went undetected by external quality controls.

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

DEPARTMENT OF HEALTH & HUMAN SERVICES

Image /page/4/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo consists of a circular seal with the words "DEPARTMENT OF HEALTH & HUMAN SERVICES USA" around the perimeter. Inside the circle is an abstract image of an eagle with its wings spread.

Food and Drug Administration 2098 Gaither Road Rockville MD 20850

SEP 1 0 2002

Ms. Carol Marble Regulatory Affairs Manager Instrumentation Laboratory Company 101 Hartwell Avenue Lexington, MA 02421-3125

Re: K022158

Trade/Device Name: GEM® Premier 3000-iOM™ (Intelligent Ouality Management) AND GEM® CVP (Calibration Validation Product)

Regulation Number: 21 CFR 862.1345 Regulation Name: Glucose test system Regulatory Class: Class II Product Code: CGA; GFS; JJY Dated: July 1, 2002 Received: July 2, 2002

Dear Ms. Marble:

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. Iisting 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 (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

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

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 v 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/dsma/dsmamain.html".

Sincerely yours,

Steven Butman

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

{6}------------------------------------------------

Indications for Use Statement

510(k) Number (if known):

Device Name: GEM® Premier 3000 –iQM™ (Intelligent Quality Management) AND GEM® CVP (Calibration Validation Product)

Indications for Use:

As part of this program, GEM® CVP (Calibration Validation Product) is intended for the external verification of the iQM" cartridge calibration after initial warm-up to ensure its integrity. The reported values for the four levels of GEM® CVP (two levels for pH, blood gases, electrolytes and metabolites; two levels for hematocrit) must meet specifications before the iQM" cartidge can be used for patient sample measurements. Once the cartridge calibration is verified, the internal iOM" program monitors the status of the system during the cartridge use life.

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

Concurrence of CDRH, Office of Device Evaluation (ODE)

	Jean Cooper
(Division Sign-Off)
Division of Clinical Laboratory Devices
510(k) Number	K022158

Prescription Use (Per 21 CFR 801.019)	X	OR	Over-The-Counter Use
---------------------------------------	---	----	----------------------

Section 2

GEM® Premier 3000: iQM™ and GEM® CVP 510(k)

Regulation Number and Section

§ 862.1345 Glucose test system.

(a)
Identification. A glucose test system is a device intended to measure glucose quantitatively in blood and other body fluids. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, neonatal hypoglycemia, and idiopathic hypoglycemia, and of pancreatic islet cell carcinoma.(b)
Classification. Class II (special controls). The device, when it is solely intended for use as a drink to test glucose tolerance, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 862.9.