UNICEL DXC SYNCHRON SYSTEMS GLUCOSE REAGENT (GLUH)
Applicant
Beckman Coulter, Inc.
Product Code
CFR · Clinical Chemistry
Decision Date
Apr 17, 2014
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1345
Device Class
Class 2
Attributes
Pediatric
Indications for Use
UniCel DxC SYNCHRON Systems Glucose reagent (GLUH), when used in conjunction with UniCel® DxC 600/800 SYNCHRON System(s) and SYNCHRON Systems AQUA CAL 1 and 3, is intended for the quantitative determination of glucose concentration in human serum. plasma, urine or cerebrospinal fluid (CSF). Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, neonatal hypoglycemia, idiopathic hypoglycemia, and pancreatic islet cell carcinoma.
Device Story
In vitro diagnostic reagent kit for quantitative glucose measurement in human serum, plasma, urine, or CSF. Operates on UniCel DxC 600/800 SYNCHRON analyzers using a timed endpoint spectrophotometric method. Reagent contains hexokinase, glucose-6-phosphate dehydrogenase, ATP, and NAD+. Hexokinase catalyzes phosphorylation of glucose to glucose-6-phosphate; G6PDH oxidizes this to 6-phosphogluconate, reducing NAD+ to NADH. NADH production is measured spectrophotometrically. Used in clinical laboratory settings by trained personnel. Output is glucose concentration (mg/dL), used by clinicians to diagnose and manage carbohydrate metabolism disorders. Benefits include accurate, automated glucose quantification for patient monitoring and diagnostic decision-making.
Clinical Evidence
Bench testing only. Precision studies (within-run and total imprecision) conducted per CLSI EP5-A2 using serum, urine, and CSF pools (n=80 per sample type). Linearity verified per CLSI EP6-A (5-700 mg/dL). Method comparison against predicate (k883181) showed high correlation (R=1.000) across all sample types. Interference testing confirmed no significant bias (<10%) for common substances (hemoglobin, bilirubin, etc.). No clinical trials performed.
Technological Characteristics
Spectrophotometric, timed endpoint assay. Reagents: Hexokinase (2.0 KIU/L), G6PDH (3.0 KIU/L), ATP (3.8 mmol/L), NAD+ (2.7 mmol/L). Analytical range: 5-700 mg/dL. Automated system integration with UniCel DxC 600/800 analyzers. Calibration traceable to NIST SRM 917a. Complies with CLSI guidelines for precision (EP5-A2), linearity (EP6-A), and interference (EP7-A2).
Indications for Use
Indicated for quantitative glucose determination in human serum, plasma, urine, or CSF to aid in diagnosis/treatment of carbohydrate metabolism disorders, including diabetes mellitus, neonatal/idiopathic hypoglycemia, and pancreatic islet cell carcinoma. Prescription use only.
Regulatory Classification
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.
Special Controls
*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.
Predicate Devices
SYNCHRON Systems LX and UniCel DxC GLU reagent (k883181)
Reference Devices
SYNCHRON Systems AQUA CAL 1 and 3 (k965240)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k131189
B. Purpose for Submission:
Modification of a previously cleared glucose assay (k883181)
C. Measurand:
Glucose
D. Type of Test:
Quantitative, Spectrophotometric method
E. Applicant:
Beckman Coulter, Inc.
F. Proprietary and Established Names:
UniCel DxC SYNCHRON Systems Glucose reagent (GLUH)
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| CFR | Class II | Glucose test system (21CFR 862.1345) | 75-Chemistry |
H. Intended Use:
1. Intended use(s):
See indications for use below.
2. Indication(s) for use:
UniCel DxC SYNCHRON Systems Glucose Reagent (GLUH), when used in conjunction with UniCel DxC 600/800 SYNCHRON System(s) and SYNCHRON Systems AQUA CAL 1 and 3, is intended for the quantitative determination of glucose concentration in human serum, plasma, urine or cerebrospinal fluid (CSF).
Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, neonatal hypoglycemia, idiopathic hypoglycemia, and pancreatic islet cell carcinoma.
{1}
3. Special conditions for use statement(s):
For prescription use only
4. Special instrument requirements:
UniCel® DxC 600/800 SYNCHRON Analyzer(s)
I. Device Description:
The UniCel DxC SYNCHRON Systems GLUH reagent kit contains a single reagent (comes in a 104 mL bottle) and must be used with the SYNCHRON Systems AQUA CAL 1 and 3, which has been previously cleared in k965240.
The reagent consists of the following components:
- UniCel DxC SYNCHRON Systems GLUH reagent
| Reagents | Concentration |
| --- | --- |
| Adenosine Triphosphate | 3.8 mmol/L |
| NAD+ | 2.7 mmol/L |
| Glucose-6-phosphate dehydrogenase | 3.0 KIU/L |
| Hexokinase | 2.0 KIU/L |
J. Substantial Equivalence Information:
1. Predicate device name(s):
SYNCHRON Systems LX and UniCel DxC GLU reagent
2. Predicate 510(k) number(s):
k883181
3. Comparison with predicate:
| Similarities and Differences | | |
| --- | --- | --- |
| Item | Candidate device | Predicate device |
| | UniCel DxC SYNCHRON Systems GLUH Reagent (New Device) | SYNCHRON Systems LX and UniCel DxC GLU reagent (K883181) |
| Intended Use | For the quantitative determination of glucose concentration in human serum, plasma, urine, or cerebrospinal fluid (CSF). | Same |
| Methodology | Timed endpoint method | Same |
| Fundamental Technology | Spectrophotometric detection | Same |
| Analytic Range | 5-700 mg/dL | Same |
| Reagent | REAGENT CONSTITUENTS: | Same |
{2}
| Similarities and Differences | | |
| --- | --- | --- |
| Item | Candidate device | Predicate device |
| | Adenosine Triphosphate, 3.8 mmol/L; NAD+, 2.7 mmol/L; Hexokinase, 2.0 KIU/L; Glucose-6- phosphate dehydrogenase, 3.0 KIU/L; Also non-reactive chemicals necessary for optimal system performance. | |
| Sample Storage and Stability | Serum/plasma
1. 8 hours at 20 to 25°C
2. 48 hours at 2°to 8°C
3. > 48 hours at ≤ -15 to -20°C
Serum/plasma
One freeze/thaw cycle (when stored at -15 to -20°C) | Same |
| Linearity | Analytical range: 5-700mg/dL | Same |
| Sample type | Serum, plasma, CSF, urine | Same |
| On Board Stability | 30 days | Same |
| Calibration stability | 14 days | Same |
| Calibrator used | SYNCHRON Systems AQUA CAL | SYNCHRON MultiCal |
| Calibrator Stability (opened) | 30 days | 20 days |
| Anticoagulant | Lithium Heparin, Sodium Heparin, Potassium Oxalate/Sodium Fluoride | Ammonium Heparin, Lithium Heparin, Sodium Heparin, Potassium Oxalate/Sodium Fluoride |
K. Standard/Guidance Document Referenced (if applicable):
- CLSI C28-A3, Defining, Establishing, and Verifying Reference Intervals in the Clinical Laboratory
- CLSI EP14-A2, Evaluation of Matrix Effects; Approved Guideline - Second Edition
- CLSI EP-17A Protocols for Determination of Limits of Detection and Limits of Quantitation
- CLSI EP25-A, Evaluation of Stability of In Vitro Diagnostic Reagents; Approved Guideline
- CLSI EP5-A2, Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline.
- EP6-A Evaluation of the Linearity of Quantitative Measurement Procedures: A Statistical Approach; Approved Guideline
- CLSI EP 7-A2, Interference Testing in Clinical Chemistry; Approved Guideline
- EP9-A2, Method Comparison and Bias Estimation Using Patient Samples
{3}
4
L. Test Principle:
GLUH reagent is used to measure the glucose concentration by a timed endpoint method. In the reaction, hexokinase (HK) catalyzes the transfer of a phosphate group from adenosine triphosphate (ATP) to glucose to form adenosine diphosphate (ADP) and glucose-6-phosphate. The glucose-6-phosphate is then oxidized to 6-phosphogluconate with the concomitant reduction of nicotinamide adenine dinucleotide (NAD) to reduced - nicotinamide adenine dinucleotide (NADH) by the catalytic action of glucose-6-phosphate dehydrogenase (G6PDH). The signal is measured by spectrophotometric detection.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
Within-run (repeatability) and total imprecision (Intermediate precision) studies for the UniCel DxC SYNCHRON Systems Glucose (GLUH) assay were performed in accordance to CLSI Guideline EP5- A2, "Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline – Second Edition."
Precision studies were performed using 3 serum based controls, 3 serum pools, 3 urine pools, and 3 CSF pools. Samples were analyzed in duplicate, twice daily, over the course of twenty working days. Precision studies were conducted on both UniCel DxC 600 and 800 analyzers. The precision results are summarized in the tables below:
UniCel® DxC 600 SYNCHRON System
| Analyzer | SAMPLE TYPE | | No. Data Points | Test Mean Value (mg/dL) | SD | %CV |
| --- | --- | --- | --- | --- | --- | --- |
| Within-run (DxC600) | Serum | Control | 80 | 43 | 0.7 | 1.6 |
| | Serum | Control | 80 | 219 | 2.3 | 1.0 |
| | Serum | Control | 80 | 390 | 5.7 | 1.5 |
| | Serum | Pool 1 | 80 | 9 | 0.3 | 3.6 |
| | Serum | Pool 2 | 80 | 101 | 1.1 | 1.1 |
| | Serum | Pool 3 | 80 | 660 | 6.4 | 1.0 |
| | Urine | Pool 1 | 80 | 10 | 0.3 | 3.2 |
| | Urine | Pool 2 | 80 | 95 | 0.9 | 1.0 |
| | Urine | Pool 3 | 80 | 670 | 5.2 | 0.8 |
| | CSF | Pool 1 | 80 | 11 | 0.3 | 3.0 |
| | CSF | Pool 2 | 80 | 109 | 1.3 | 1.2 |
| | CSF | Pool 3 | 80 | 677 | 7.0 | 1.0 |
{4}
| Analyzer | SAMPLE TYPE | | No. Data Points | Test Mean Value (mg/dL) | SD | %CV |
| --- | --- | --- | --- | --- | --- | --- |
| Total precision (DxC600) | Serum | Control | 80 | 43 | 0.8 | 1.9 |
| | Serum | Control | 80 | 219 | 2.6 | 1.2 |
| | Serum | Control | 80 | 390 | 6.5 | 1.7 |
| | Serum | Pool 1 | 80 | 9 | 0.6 | 5.9 |
| | Serum | Pool 2 | 80 | 101 | 1.6 | 1.6 |
| | Serum | Pool 3 | 80 | 660 | 8.4 | 1.3 |
| | Urine | Pool 1 | 80 | 10 | 0.6 | 5.7 |
| | Urine | Pool 2 | 80 | 95 | 1.4 | 1.5 |
| | Urine | Pool 3 | 80 | 670 | 6.1 | 0.9 |
| | CSF | Pool 1 | 80 | 11 | 0.6 | 5.3 |
| | CSF | Pool 2 | 80 | 109 | 1.6 | 1.5 |
| | CSF | Pool 3 | 80 | 677 | 8.6 | 1.3 |
UniCel® DxC 800 SYNCHRON System
| Analyzer | SAMPLE TYPE | | No. Data Points | Test Mean Value (mg/dL) | SD | %CV |
| --- | --- | --- | --- | --- | --- | --- |
| Within-run (DxC800) | Serum | Control 1 | 80 | 43 | 0.5 | 1.2 |
| | Serum | Control 2 | 80 | 219 | 2.7 | 1.2 |
| | Serum | Control 3 | 80 | 389 | 6.3 | 1.6 |
| | Serum | Pool 1 | 80 | 9 | 0.3 | 3.2 |
| | Serum | Pool 2 | 80 | 101 | 1.1 | 1.1 |
| | Serum | Pool 3 | 80 | 662 | 7.5 | 1.1 |
| | Urine | Pool 1 | 80 | 10 | 0.3 | 3.0 |
| | Urine | Pool 2 | 80 | 94 | 1.2 | 1.2 |
| | Urine | Pool 3 | 80 | 668 | 7.9 | 1.2 |
| | CSF | Pool 1 | 80 | 11 | 0.3 | 2.3 |
| | CSF | Pool 2 | 80 | 108 | 1.1 | 1.0 |
| | CSF | Pool 3 | 80 | 680 | 6.7 | 1.0 |
{5}
| Analyzer | SAMPLE TYPE | | No. Data Points | Test Mean Value (mg/dL) | SD | %CV |
| --- | --- | --- | --- | --- | --- | --- |
| Total precision (DxC800) | Serum | Control 1 | 80 | 43 | 0.7 | 1.7 |
| | Serum | Control 2 | 80 | 219 | 3.5 | 1.6 |
| | Serum | Control 3 | 80 | 389 | 7.2 | 1.9 |
| | Serum | Pool 1 | 80 | 9 | 0.3 | 3.6 |
| | Serum | Pool 2 | 80 | 101 | 1.2 | 1.2 |
| | Serum | Pool 3 | 80 | 662 | 9.4 | 1.4 |
| | Urine | Pool 1 | 80 | 10 | 0.4 | 3.7 |
| | Urine | Pool 2 | 80 | 94 | 1.3 | 1.3 |
| | Urine | Pool 3 | 80 | 668 | 8.1 | 1.2 |
| | CSF | Pool 1 | 80 | 11 | 0.4 | 3.6 |
| | CSF | Pool 2 | 80 | 108 | 1.7 | 1.6 |
| | CSF | Pool 3 | 80 | 680 | 8.1 | 1.2 |
# b. Linearity/assay reportable range:
Linearity studies were designed in accordance with CLSI Guideline EP6-A: Evaluation of the Linearity of Quantitative Measurement Procedures. Samples were prepared by splitting two pools for each of the three sample types: serum, urine and CSF. One of the pools for each of the sample types were spiked with a glucose stock solution and then intermixed with the second pool to create 16 samples spanning the assay range. 4 replicates were tested for each of the 16 glucose samples created. Samples range tested was between $5 - 700\mathrm{mg / dL}$ . The results from regression analysis between the target values and the measured values are summarized below:
UniCel® DxC 600 SYNCHRON System
| Urine | Y = 1.00x + 0.446, R²=0.999 |
| --- | --- |
| CSF | Y = 1.01x + 1.516, R²=0.999 |
| Serum | Y = 1.01x + 1.088, R²=0.999 |
UniCel® DxC 800 SYNCHRON System
| Urine | Y = 0.991x + 2.198, R²=0.999 |
| --- | --- |
| CSF | Y = 1.008x + 1.578, R²=0.999 |
| Serum | Y = 1.004x + 2.197, R²=0.999 |
{6}
The results of the linearity study support the claimed measuring range of 5-700 mg/dL for glucose on the UniCel® DxC 600/800 SYNCHRON System analyzers.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Traceability:
The SYNCHRON Systems AQUA CAL 1 and 3 calibrators are traceable to NIST SRM 917a reference material and have been previously cleared in k965240.
d. Detection limit:
The Limit of Blank (LoB), Limit of Detection (LoD) and Limit of Quantitation (LoQ) of UniCel DxC SYNCHRON Systems Glucose reagent (GLUH) were determined according to CLSI EP17-A- Protocols for Determination of Limits of Detection and Limits of Quantitation. Studies were performed in the following manner:
To calculate the Limit of Blank (LoB), 4 blank samples were measured in triplicate for 5 days using 2 instrument lots on both UniCel® DxC 600 and 800 SYNCHRON System analyzers.
To estimate the LoD, 4 samples containing low levels of glucose were measured in triplicate for 5 days using 2 instrument lots on both UniCel® DxC 600 and 800 SYNCHRON System analyzers.
To estimate the LoQ, 4 samples containing low levels of glucose were measured in triplicate for 5 days using 2 instrument lots on both UniCel® DxC 600 and 800 SYNCHRON System analyzers.
Based on the study results, the following detection limit claims were made for both UniCel® DxC 600 and 800 SYNCHRON System analyzers.
| | Serum mg/dL | CSF mg/dL | Urine mg/dL |
| --- | --- | --- | --- |
| LoB | 0.19 | 0.17 | 0.19 |
| LoD | 1.74 | 1.68 | 1.78 |
| LoQ | 3.78 | 3.67 | 3.69 |
The detection limit studies support the claimed measuring range of 5-700 mg/dL.
e. Analytical specificity:
Interference studies were performed by evaluating 8 potential interfering substances spiked into patient serum pools at three different glucose levels, 40 to 60 mg/dL, 166 to 210 mg/dL and 400 to 480 mg/dL. Potential interferences were spiked into patient
{7}
serum pools to assess which substance would interfere with the UniCel DxC SYNCHRON Systems Glucose (GLUH) assay. Bias greater than +/- 10% between the spiked and unspiked samples defines significant interference. The following substances produced less than 10% difference when tested on the UniCel® DxC 600 and 800 SYNCHRON System analyzers at levels equal to the concentrations listed below.
| Substances | Highest Concentration Tested that showed non-significant interference |
| --- | --- |
| Hemoglobin | 500 mg/dL |
| Bilirubin | 24 mg/dL |
| Ascorbic Acid | 6.0 mg/dL |
| Urea | 500 mg/dL |
| Uric Acid | 40 mg/dL |
| EDTA | 16 mg/dL |
| Creatinine | 40 mg/dL |
| Lipemia | 200 mg/dL |
f. Assay cut-off:
Not applicable.
2. Comparison studies:
a. Method comparison with predicate device:
Serum:
A total of 120 serum samples spanning the measuring range were analyzed on the UniCel® DxC 600 and 800 SYNCHRON Systems using the candidate method and compared against the predicate method. A total of 20 samples were altered (10 samples were diluted and 10 samples were spiked). The linear regression analysis is as follows:
UniCel® DxC 600 SYNCHRON System:
Y = 0.982x - 1.02, R = 1.000, sample range tested of 5-697 mg/dL.
UniCel® DxC 800 SYNCHRON System:
Y = 0.999x - 1.60, R = 1.000, sample range tested of 5-691 mg/dL.
CSF:
A total of 100 CSF samples spanning the measuring range were analyzed on the UniCel® DxC 600 and 800 SYNCHRON Systems using the candidate method and compared against the predicate method. A total of 20 samples were altered (8 samples were diluted and 12 samples were spiked). The linear regression analysis is as follows:
{8}
UniCel® DxC 600 SYNCHRON System:
Y = 0.978x + 1.25, R = 1.000, sample range tested 8-693 mg/dL.
UniCel® DxC 800 SYNCHRON System:
Y = 1.002x - 0.61, R = 1.000, sample range tested 8-675 mg/dL.
**Urine:**
A total of 117 urine samples spanning the measuring range were analyzed on the UniCel® DxC 600 and 800 SYNCHRON Systems using the candidate method and compared against the predicate method. A total of 23 samples were altered (6 samples were diluted and 17 samples were spiked). The linear regression analysis is as follows:
UniCel® DxC 600 SYNCHRON System:
Y = 0.989x + 2.08, R = 1.000, sample range tested 12-689 mg/dL.
UniCel® DxC 800 SYNCHRON System:
Y = 0.973x + 2.86, R = 1.000, sample range tested 11-694 mg/dL.
**b. Matrix comparison:**
Matrix comparison studies were performed using 79 matched serum/plasma (Sodium Heparin, Lithium Heparin, and Sodium Fluoride/Potassium Oxalate) samples and tested on the UniCel® DxC 600 SYNCHRON System and 58 matched serum/plasma samples (Sodium Heparin, Lithium Heparin, and Sodium Fluoride/Potassium Oxalate) were analyzed on the UniCel® DxC 800 SYNCHRON System.
The following table summarizes the matrix comparison studies:
| UniCel®DxC600 SYNCHRON System | | |
| --- | --- | --- |
| Anticoagulant | N | Deming Regression Analysis |
| Sodium Heparin | 79 | y= 0.983x + 0.849, R= 0.999 |
| Lithium Heparin | 79 | y= 0.994x + 0.393, R= 0.999 |
| Sodium Fluoride/Potassium Oxalate | 79 | y= 0.995x + 1.007, R= 0.999 |
| UniCel®DxC800 SYNCHRON System | | |
| Anticoagulant | N | Deming Regression Analysis |
| Sodium Heparin | 58 | y= 0.998x - 0.172, R= 0.999 |
| Lithium Heparin | 58 | y= 1.02x - 2.476, R= 1.000 |
| Sodium Fluoride/Potassium Oxalate | 58 | y= 1.012x - 0.302, R= 0.999 |
The sponsor concluded that lithium heparin, sodium heparin and sodium fluoride/potassium oxalate plasma are acceptable to be used with the device on the
{9}
UniCel® DxC 600 and 800 SYNCHRON System.
3. Clinical studies:
a. Clinical Sensitivity: Not applicable.
b. Clinical specificity: Not applicable.
c. Other clinical supportive data (when a. and b. are not applicable): Not applicable.
4. Clinical cut-off: Not applicable.
5. Expected values/Reference range:
Expected values are based on literature as follows:
| | SAMPLE TYPE | CONVENTIONAL | S.I. UNITS |
| --- | --- | --- | --- |
| Literature 1,2 | Serum or Plasma | 74- 106 mg/dL | 4.1 - 5.9 mmol/L |
| | Urine | 1 - 15 mg/dL | 0.06 - 0.83 mmol/L |
| | Urine (timed) | < 0.5 g/24 hrs | < 2.8 mmol/24 hrs |
| | CSF | 40- 70 mg/dL | 2.2 - 3.9 mmol/L |
1 Tietz, N.W., ed., Fundamentals of Clinical Chemistry, 6th edition, W.B. Saunders, Philadelphia, PA (2007)
2 Pagana, KD and Pagana, T J, Mosby's Manual of Diagnostic and Laboratory Tests 3rd Edition, Mosby Inc., St Louis, MO (2006)
N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
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.