The Tosoh Automated Glycohemoglobin Analyzer HLC-723G8 is intended for in vitro diagnostic use for the measurement of % hemoglobin A1c (HbA1c) (DCCT/NGSP) and mmol/mol hemoglobin A1c (IFCC) in venous whole blood specimens using ion-exchange high-performance liquid chromatography (HPLC). This test is to be used as an aid in diagnosis of diabetes and identifying patients who may be at risk for developing diabetes, and for monitoring of long-term blood glucose control in individuals with diabetes mellitus.
Device Story
Automated HPLC system for quantitative measurement of stable HbA1c in venous whole blood. Input: whole blood samples. Operation: ion-exchange chromatography using non-porous cation exchange column; step gradient elution separates hemoglobin fractions based on ionic charge. Output: %HbA1c (NGSP) and mmol/mol (IFCC) values. Used in clinical laboratory settings; operated by trained laboratory personnel. System includes sampling unit, liquid pump, degasser, column, detector, microprocessors, and printer. Results aid clinicians in diabetes diagnosis and glucose monitoring. Device detects hemoglobin variants to ensure HbA1c result validity, though variant-specific performance is not FDA-cleared.
Clinical Evidence
Bench testing only. Precision/repeatability study (CLSI EP05-A3) across 4 concentrations (5.0-12.0%) showed total CVs ≤ 1.28%. Method comparison (CLSI EP09c) against Trinity Biotech Premier Hb9210 using 220 patient samples demonstrated strong correlation (Deming slope 1.013, intercept 0.1336). Interference studies (CLSI EP07-A2) confirmed no clinically significant interference from endogenous substances (albumin, ascorbic acid, bilirubin, lipemia, rheumatoid factor) or common hemoglobin variants (HbC, HbD, HbE, HbS, HbF, HbA2) using software v5.24.
Technological Characteristics
Automated ion-exchange HPLC system. Uses TSKgel G8 Variant HSi column. Detection via flow cell absorbance at 415nm with 500nm background correction. Measuring range 4.0-16.9% HbA1c. Traceable to DCCT/NGSP and IFCC. Connectivity via bi-directional interface. Software-controlled via smart media card. Components include sampling unit, liquid pump, degasser, detector, and printer.
Indications for Use
Indicated for in vitro diagnostic measurement of HbA1c in venous whole blood to aid in diabetes diagnosis, identify patients at risk for diabetes, and monitor long-term glycemic control in individuals with diabetes mellitus.
Regulatory Classification
Identification
A hemoglobin A1c test system is a device used to measure the percentage concentration of hemoglobin A1c in blood. Measurement of hemoglobin A1c is used as an aid in the diagnosis of diabetes mellitus and as an aid in the identification of patients at risk for developing diabetes mellitus.
Special Controls
(b) Classification. Class II (special controls). Hemoglobin A1c test systems must comply with the following special controls: 1) The device must have initial and annual standardization verification by a certifying glycohemoglobin standardization organization deemed acceptable by FDA. 2) The premarket notification submission must include performance testing to evaluate precision, accuracy, linearity and interference, including the following: i) Performance testing of device precision must, at a minimum, use blood samples with concentrations near 5.0%, 6.5%, 8.0% and 12% hemoglobin A1c. This testing must evaluate precision over a minimum of 20 days using at least 3 lots of the device and 3 instruments, as applicable. ii) Performance testing of device accuracy must include a minimum of 120 blood samples that span the measuring interval of the new device and compare results of the new device to results of the standardized test method. Results must demonstrate little or no bias versus the standardized method. iii) Total error of the new device must be evaluated using single measurements by the new device compared to results of the standardized test method, and this evaluation must demonstrate a total error less than or equal to 6%. iv) Performance testing must demonstrate that there is little to no interference from common hemoglobin variants, including Hemoglobin C, Hemoglobin D, Hemoglobin E, Hemoglobin A2 and Hemoglobin S. 3) When assay interference from Hemoglobin F or interference with other hemoglobin variants with low frequency in the population is observed, a warning statement must be placed in a black box and must appear in all labeling material for these devices describing the interference and any affected populations.
*Classification.* Class II (special controls). The special controls for this device are:(1) The device must have initial and annual standardization verification by a certifying glycohemoglobin standardization organization deemed acceptable by FDA.
(2) The premarket notification submission must include performance testing to evaluate precision, accuracy, linearity, and interference, including the following:
(i) Performance testing of device precision must, at a minimum, use blood samples with concentrations near 5.0 percent, 6.5 percent, 8.0 percent, and 12 percent hemoglobin A1c. This testing must evaluate precision over a minimum of 20 days using at least three lots of the device and three instruments, as applicable.
(ii) Performance testing of device accuracy must include a minimum of 120 blood samples that span the measuring interval of the device and compare results of the new device to results of a standardized test method. Results must demonstrate little or no bias versus the standardized method.
(iii) Total error of the new device must be evaluated using single measurements by the new device compared to results of the standardized test method, and this evaluation must demonstrate a total error less than or equal to 6 percent.
(iv) Performance testing must demonstrate that there is little to no interference from common hemoglobin variants, including Hemoglobin C, Hemoglobin D, Hemoglobin E, Hemoglobin A2, and Hemoglobin S.
(3) When assay interference from Hemoglobin F or interference with other hemoglobin variants with low frequency in the population is observed, a warning statement must be placed in a black box and must appear in all labeling material for these devices describing the interference and any affected populations.
Predicate Devices
Variant II Turbo Hba1c Kit-2.0 Variant II Turbo Hemoglobin Testing System (K122472, K142448)
Reference Devices
Trinity Biotech Ultra2
Trinity Premier Hb9210 system
Submission Summary (Full Text)
{0}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
K200904
B Applicant
Tosoh Bioscience, Inc.
C Proprietary and Established Names
Automated Glycohemoglobin Analyzer HLC-723G8
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| PDJ | Class II | 21 CFR 862.1373 - Hemoglobin A1c Test System | CH - Clinical Chemistry |
## II Submission/Device Overview:
A Purpose for Submission:
Modification of existing device to minimize hemoglobin variant interference
B Measurand:
Whole Blood Glycosylated Hemoglobin (HbA1c)
C Type of Test:
Quantitative Ion-exchange High Performance Liquid Chromatography (HPLC)
## III Intended Use/Indications for Use:
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
A Intended Use(s):
See Indications for Use below.
B Indication(s) for Use:
The Tosoh Automated Glycohemoglobin Analyzer HLC-723G8 is intended for in vitro diagnostic use for the measurement of % hemoglobin A1c (HbA1c) (DCCT/NGSP) and mmol/mol hemoglobin A1c (IFCC) in venous whole blood specimens using ion-exchange high-performance liquid chromatography (HPLC). This test is to be used as an aid in diagnosis of diabetes and identifying patients who may be at risk for developing diabetes, and for monitoring of long-term blood glucose control in individuals with diabetes mellitus.
C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
Hemoglobin A1c should not be used to diagnose Diabetes Mellitus in patients with iron deficiency and hemolytic anemia, various hemoglobinopathies, thalassemias, hereditary spherocytosis, malignancies and severe chronic hepatic and renal disease.
Hemoglobin A1c should not be used in pregnant patients, patients with heterozygous sickle cell trait, hemolytic diseases and recent significant or chronic blood loss.
Hemoglobin A1c should not be used in the diagnosis of gestational diabetes.
In cases of rapidly evolving type 1 diabetes the increase of HbA1c values might be delayed compared to the acute increase in glucose concentrations. In these conditions diabetes mellitus must be diagnosed based on plasma glucose concentration and/or the typical clinical symptoms.
Only the percent HbA1c values measured by this device should be reported to the health care provider. The test report displays %HbF and other detected hemoglobin variants; however, the performance characteristics of the hemoglobin variants detected by this device have not been reviewed or cleared by the FDA and therefore should not be reported to the healthcare provider. The hemoglobin variants detected by this device are only to ensure the validity of the HbA1c results because increased levels of hemoglobin variants may interfere with the percent HbA1c measurement. If a hemoglobinopathy is suspected, an FDA cleared test system for their measurement should be used
Hemoglobin A1c testing should not replace glucose testing for type 1 diabetes, in pediatric patients and pregnant women.
D Special Instrument Requirements:
All performance data was collected using the Tosoh Automated Glycohemoglobin Analyzer HLC-723G8.
K200904 - Page 2 of 10
{2}
K200904 - Page 3 of 10
# IV Device/System Characteristics:
## A Device Description:
The Tosoh Automated Glycohemoglobin Analyzer HLC-723G8 is an automated High-Performance Liquid Chromatography (HPLC) system that separates and reports stable hemoglobin A1c (sA1c) percentage in whole blood. The operational portion of the G8 is composed of a sampling unit, liquid pump, degasser, column, detector, microprocessors, sample loader, smart media card, operation panel, and a printer.
The Tosoh Automated Glycohemoglobin Analyzer HLC-723G8 system consists of the following components:
- G8 Variant Elution Buffer HSi No. 1 (S), No. 2 (S), No. 3 (S)
- TSKgel® G8 Variant HSi (column)
- Hemoglobin A1c Controls Levels 1 and 2
- 21 CFR 862.1660, Product Code JJX
- Hemoglobin A1c Calibrator Set
- 21 CFR 862.1150, Product Code JIT
- Hemolysis and Wash Solution
- 21 CFR 864.8540, Product Code GGK
## B Principle of Operation:
The Tosoh Automated Glycohemoglobin Analyzer HLC-723G8 uses ion-exchange HPLC to separate the stable form of HbA1c (sA1c) from other hemoglobin fractions. The G8 uses a non-porous cation exchange column and separates the hemoglobin components in the blood. Separation is achieved by utilizing differences in ionic interactions between the cation and exchange group on the column resin surface and the hemoglobin components in a step gradient elution. If a sample contains a hemoglobin variant, the column elutes the fraction depending upon its charge.
# V Substantial Equivalence Information:
## A Predicate Device Name(s):
Variant II Turbo Hba1c Kit-2.0 Variant II Turbo Hemoglobin Testing System
VARIANT II TURBO HbA1c Kit - 2.0
## B Predicate 510(k) Number(s):
K122472, K142448
## C Comparison with Predicate(s):
| Device & Predicate Device(s): | K200904 | K122472 | K142448 |
| --- | --- | --- | --- |
| Device Trade Name | Tosoh Automated Glycohemoglobin Analyzer HLC-723G8, v5.24 | Bio-Rad VARIANT II TURBO HbA1c Kit – 2.0 on VARIANT II TURBO Hemoglobin | Bio-Rad VARIANT II TURBO HbA1c Kit – 2.0 on VARIANT II TURBO Hemoglobin |
{3}
| | | Testing System | Testing System |
| --- | --- | --- | --- |
| General Device Characteristic Similarities | | | |
| Intended Use/Indications For Use | This test is to be used as an aid in diagnosis of diabetes and identifying patients who may be at risk for developing diabetes, and for monitoring of long-term blood glucose control in individuals with diabetes mellitus. | Same (for Monitoring) | Same (for Diagnosis) |
| Assay Principle | Ion-Exchange HPLC | Same | Same |
| Traceability and Standardization | Traceable to the Diabetes Control and Complications Trial (DCCT) reference method and IFCC. Certified via the National Glycohemoglobin Standardization Program (NGSP). | Same | Same |
| General Device Characteristic Differences | | | |
| Measuring Range | 4.0% to 16.9% HbA1c | 3.4% to 20.6% HbA1c | 3.4% to 20.6% HbA1c |
VI Standards/Guidance Documents Referenced:
21 CFR 862.1373 – Special controls for Hemoglobin A1c test system
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
1. Precision/Reproducibility:
Precision was evaluated for the Automated Glycohemoglobin Analyzer HLC-723G8 v5.24 based on CLSI EP05-A3 using four K2 EDTA venous whole blood samples containing approximately 5%, 6.5%, 8%, and 12% HbA1c. Samples were analyzed at two sites on three Automated Glycohemoglobin Analyzer HLC-723G8 v5.24 instruments using three lots of reagents on each instrument. Each sample was analyzed in two runs per day, two replicates per run, for 20 days. The results are shown below:
K200904 - Page 4 of 10
{4}
Analyzer 1
| Mean % HbA1c | Repeatability (error) | | Between-Run | | Between-Day | | Between-Lot | | Intermediate Precision (total) | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | SD | CV(%) | SD | CV(%) | SD | CV(%) | SD | CV(%) | SD | CV(%) |
| Sample 1 5.43% | 0.0178 | 0.33 | 0.0146 | 0.27 | 0.0230 | 0.42 | 0.0145 | 0.27 | 0.0356 | 0.66 |
| Sample 2 6.32% | 0.0204 | 0.32 | 0.0109 | 0.17 | 0.0252 | 0.40 | 0.0061 | 0.10 | 0.0348 | 0.55 |
| Sample 3 7.51% | 0.0218 | 0.29 | 0.0204 | 0.27 | 0.0276 | 0.37 | 0.0203 | 0.27 | 0.0454 | 0.60 |
| Sample 4 11.89% | 0.0288 | 0.24 | 0.0254 | 0.21 | 0.0509 | 0.43 | 0.0154 | 0.13 | 0.0656 | 0.55 |
Analyzer 2
| Mean % HbA1c | Repeatability (error) | | Between-Run | | Between-Day | | Between-Lot | | Intermediate Precision (total) | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | SD | CV(%) | SD | CV(%) | SD | CV(%) | SD | CV(%) | SD | CV(%) |
| Sample 1 5.48% | 0.0202 | 0.37 | 0.0151 | 0.28 | 0.0204 | 0.37 | 0.0402 | 0.73 | 0.0517 | 0.94 |
| Sample 2 6.41% | 0.0231 | 0.36 | 0.0* | 0.0* | 0.0199 | 0.31 | 0.0480 | 0.75 | 0.0569 | 0.89 |
| Sample 3 7.64% | 0.0217 | 0.28 | 0.0141 | 0.18 | 0.0278 | 0.36 | 0.0720 | 0.94 | 0.0814 | 1.07 |
| Sample 4 11.93% | 0.0266 | 0.22 | 0.0146 | 0.12 | 0.0558 | 0.47 | 0.1228 | 1.03 | 0.1383 | 1.16 |
* Negative variance component values have been sent to zero.
Analyzer 3
| Mean % HbA1c | Repeatability (error) | | Between-Run | | Between-Day | | Between-Lot | | Intermediate Precision (total) | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | SD | CV(%) | SD | CV(%) | SD | CV(%) | SD | CV(%) | SD | CV(%) |
| Sample 1 5.47% | 0.0184 | 0.34 | 0.0092 | 0.17 | 0.0317 | 0.58 | 0.0312 | 0.57 | 0.0489 | 0.89 |
| Sample 2 6.40% | 0.0201 | 0.31 | 0.0099 | 0.15 | 0.0292 | 0.46 | 0.0300 | 0.47 | 0.0475 | 0.74 |
| Sample 3 7.64% | 0.0156 | 0.20 | 0.0050 | 0.06 | 0.0395 | 0.52 | 0.0475 | 0.62 | 0.0640 | 0.84 |
| Sample 4 11.90% | 0.0277 | 0.23 | 0.0* | 0.0* | 0.0602 | 0.51 | 0.0678 | 0.57 | 0.0948 | 0.80 |
* Negative variance component values have been sent to zero.
Analyzers Combined
| Mean % HbA1c | Repeatability (error) | | Between-Run | | Between-Day | | Between-Lot | | Between-Device | | Intermediate Precision (total) | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | SD | CV (%) | SD | CV (%) | SD | CV (%) | SD | CV (%) | SD | CV (%) | SD | CV (%) |
K200904 - Page 5 of 10
{5}
K200904 - Page 6 of 10
| Sample 1
5.46% | 0.0188 | 0.35 | 0.0132 | 0.24 | 0.0266 | 0.49 | 0.0291 | 0.53 | 0.0272 | 0.50 | 0.0532 | 0.97 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Sample 2
6.38% | 0.0212 | 0.33 | 0.0084 | 0.13 | 0.0288 | 0.45 | 0.0280 | 0.44 | 0.0478 | 0.75 | 0.0665 | 1.04 |
| Sample 3
7.60% | 0.0199 | 0.26 | 0.0146 | 0.19 | 0.0386 | 0.51 | 0.0441 | 0.58 | 0.0737 | 0.97 | 0.0973 | 1.28 |
| Sample 4
11.91% | 0.0277 | 0.23 | 0.0167 | 0.14 | 0.0666 | 0.56 | 0.0684 | 0.57 | 0.0239 | 0.20 | 0.1036 | 0.87 |
2. **Linearity:**
Linearity was previously evaluated for this device in k071132.
3. **Analytical Specificity/Interference:**
Endogenous and exogenous interference as well as cross-reactivity with acetylated hemoglobin, carbamylated hemoglobin, labile HbA1c, and aldehyde hemoglobin was previously evaluated in k131580 and k071132.
**Hemoglobin Variant Interference:**
A hemoglobin variant study was performed using a total of 130 K3 EDTA venous whole blood samples known to contain hemoglobin variants HbS, HbC, HbE, HbD, HbA2, and HbF. Testing of the samples containing hemoglobin variants were performed using the Automated Glycohemoglobin Analyzer HLC-723G8 and compared to results obtained by a comparator method that has been demonstrated to be free from interference by these hemoglobin variants (Trinity Biotech Ultra2 for HbS, HbC, HbD, HbE and Bio-Rad Variant II Turbo 2.0 for HbF and HbA2).
Samples tested:
| Hemoglobin Variant | n | % Content of Variant in sample | Range in %HbA1c |
| --- | --- | --- | --- |
| HbC | 26 | 30.8-37.8 | 4.8-9.8 |
| HbD | 24 | 22.6-40.7 | 5.3-9.35 |
| HbE | 26 | 20.0-30.9 | 4.8-9.7 |
| HbS | 29 | 28.2-38.9 | 4.9-10.05 |
| HbA2 | 20 | 2.7-5.5 | 5.85-10.1 |
| HbF | 21 | 0.4-43.35 | 4.36-8.9 |
{6}
| Hemoglobin Variant | Percent Relative Bias from Reference Method at Low and High Concentrations of HbA1c Samples | |
| --- | --- | --- |
| | ~6.5 % HbA1c | ~8.0 % HbA1c |
| HbC | 0.03 to 0.17 | 0.06 to 0.34 |
| HbD | 0.08 to 0.30 | -0.04 to 0.36 |
| HbE | 0.001 to 0.27 | -0.10 to 0.49 |
| HbS | -0.04 to 0.13 | -0.14 to 0.21 |
| HbA2 | -0.17 to 0.06 | -0.37 to 0.12 |
| HbF | 0.10 to 0.25 | -0.01 to 0.34 |
4. Assay Reportable Range:
The reportable range for this device is 4.0-16.9% HbA1c.
5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
The assigned HbA1c values of the Automated Glycohemoglobin Analyzer HLC-723G8 are certified by The National Glycohemoglobin Standardization Program (NGSP). See the NGSP website for current certification at http://www.ngsp.org.
The final reportable result is traceable to both the International Federation of Clinical Chemistry (IFCC) and the Diabetes Control and Complications Trial (DCCT). The International Federation of Clinical Chemistry (IFCC) units of mmol/mol are calculated using the Master Equation NGSP (%) = 0.09148 × IFCC (mmol/mol) + 2.152. HbA1c results are provided to the customers using two different units: NGSP equivalent units (%) and IFCC equivalent units (mmol/mol).
6. Detection Limit:
Not applicable.
7. Assay Cut-Off:
Not applicable.
B Comparison Studies:
1. Method Comparison with Predicate Device:
A method comparison study was conducted at two sites (one external, one internal). A total of 220 K2-EDTA venous whole blood samples ranging from 4.7% to 15.4% HbA1c were evaluated. Results obtained on the Tosoh Automated Glycohemoglobin Analyzer HLC-723G8 v5.24 were compared to results from the same samples tested on the Trinity Premier Hb9210 system.
K200904 - Page 7 of 10
{7}
The distribution of samples used in the study is summarized below:
| %HbA1c | # Samples Tested |
| --- | --- |
| <5% | 4 |
| 5.0 – 6.0% | 30 |
| 6.0 – 6.5% | 25 |
| 6.5 – 7.0% | 33 |
| 7.0 – 8.0% | 38 |
| 8.0 – 9.0% | 18 |
| >9.0% | 72 |
| Total | 220 |
The sponsor provided scatter plots demonstrating both Deming and Passing-Bablok regression between the candidate device and the Trinity Premier. The tables below summarize the bias between the Tosoh Automated Glycohemoglobin Analyzer HLC-723G8 and the Trinity Biotech reference method.
| | y-Intercept | Slope |
| --- | --- | --- |
| Deming | 0.1336 | 1.013 |
| | 95% CI: -0.0331 to 0.3005 | 95% CI: 0.9894 to 1.036 |
| Passing-Bablok | 0.0754 | 1.020 |
| | 95% CI: -0.0472 to -0.1819 | 95% CI: 1.007 to 1.037 |
The predicted bias at HbA1c concentrations near clinical decision points, as determined by Passing-Bablok regression and Deming regression, are described below:
Passing-Bablok:
| Decision Level | Bias | % Bias |
| --- | --- | --- |
| 5.0% | 0.1753 | 3.5% |
| 6.5% | 0.2068 | 3.2% |
| 8.0% | 0.2383 | 3.0% |
| 12.0% | 0.3224 | 2.7% |
Deming:
| Decision Level | Bias | % Bias |
| --- | --- | --- |
| 5.0% | 0.1979 | 4.0% |
| 6.5% | 0.2172 | 3.3% |
| 8.0% | 0.2366 | 3.0% |
| 12.0% | 0.2884 | 2.4% |
Total Error:
Total error (%TE) was calculated using the following equation:
$$
\% \mathrm{TE} = \left| \% \text{Bias} \right| + 1.96 \times \% \mathrm{CV} \times (1 + \% \text{Bias}/100)
$$
K200904 - Page 8 of 10
{8}
The %Bias component was generated during the method comparison studies using the Deming regression data for decision levels 5.0% and 6.5% and using the Passing-Bablok regression data for decision levels 8.0% and 12.0% and is the %Bias shown in the table below. The variance component (%CV) was generated during the precision studies and represents the total reproducibility shown in the table below:
| Sample [%HbA1c] | Passing Bablok | | Deming | | Precision (%CV) |
| --- | --- | --- | --- | --- | --- |
| | %TE | %Bias | %TE | %Bias | |
| Sample1 [5%] | 5.48 | 3.5 | 5.99 | 4.0 | 0.97 |
| Sample2 [6.5%] | 5.31 | 3.2 | 5.41 | 3.3 | 1.04 |
| Sample3 [8%] | 5.59 | 3.0 | 5.48 | 2.9 | 1.28 |
| Sample4 [12%] | 4.45 | 2.7 | 4.15 | 2.4 | 0.87 |
## 2. Matrix Comparison:
The effect on Hemoglobin A1c determination, with the HbA1c assay, in the presence of anticoagulants was determined on the Tosoh Automated Glycohemoglobin Analyzer HLC-723G8 by comparing values obtained from samples drawn into K₂-EDTA to results obtained from samples in K₃-EDTA.
47 samples of each anticoagulant were evaluated, with %HbA1c concentrations for the sample sets ranging from 5.12% to 12.86%. The sample tubes were from a total of 47 donors. Two tubes, one with each anticoagulant, were drawn from each donor. The following are results from least-squares regression analysis:
$$
y = 1.004x - 0.02021 \quad R^2 = 0.999999
$$
The results support the use of the HbA1c assay with samples collected in K₂-EDTA and K₃-EDTA.
## C Clinical Studies:
1. Clinical Sensitivity:
Not applicable.
2. Clinical Specificity:
Not applicable.
3. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):
Not applicable.
K200904 - Page 9 of 10
{9}
D Clinical Cut-Off:
Not applicable.
E Expected Values/Reference Range:
Reference Ranges (non-diabetic): HbA1c 4.0-6.0 % (mean 5.0 %, SD 0.5 %)
Ref: American Diabetes Association. 2. Classification and diagnosis of diabetes: Standards of Medical Care in Diabetes—2020. Diabetes Care 2020;43(Suppl. 1):S14–S31.
The diagnosis of diabetes and identification of persons at increased risk of developing diabetes follows the ADA Guideline of 6.5% for the cut-off and values between 5.7% and 6.4% as being at increased risk.
VIII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
IX Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K200904 - Page 10 of 10
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.
