Patient samples were used in method comparison studies to evaluate the performance of the ELITech Clinical Systems GLUCOSE HK SL reagent against a predicate device (Cobas C111) and to establish matrix equivalence.
ELITech Clinical Systems GLUCOSE HK SL is intended for the quantitative in vitro diagnostic determination of glucose in human serum, plasma and urine using ELITech Clinical Systems Selectra Pro Series Analyzers. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus and idiopathic hypoglycemia, and of pancreatic diseases. ELITech Clinical Systems ELICAL 2 is a multi-parametric calibrator for in vitro diagnostic use in the calibration of quantitative ELITech Clinical Systems methods on ELITech Clinical Systems Analyzers. ELITech Clinical Systems ELITROL II are multiparametric control sera for in vitro diagnostic use in quality control of quantitative ELITech Clinical Systems methods on ELITech Clinical Systems Analyzers.
Device Story
Device is an in vitro diagnostic reagent kit (GLUCOSE HK SL) used with ELITech Clinical Systems Selectra Pro Series Analyzers. It utilizes an enzymatic hexokinase/G-6-PDH UV end-point method; glucose reacts with ATP to form glucose-6-phosphate, which is then oxidized by NAD+ to produce NADH; the resulting increase in absorbance is directly proportional to glucose concentration. The system includes multi-parametric calibrators (ELICAL 2) and control sera (ELITROL I/II). Operated by laboratory technicians in clinical settings; output is a quantitative glucose concentration (mg/dL). Results assist healthcare providers in diagnosing and monitoring carbohydrate metabolism disorders and pancreatic diseases. Benefits include standardized, automated glucose quantification for clinical decision-making.
Clinical Evidence
Bench testing only. Precision evaluated per CLSI EP05-A2 (n=80 per level, total CV% 1.7-2.0%). Linearity established per CLSI EP06-A (range 20-720 mg/dL for serum, 10-720 mg/dL for urine). Method comparison (n=100 serum, n=40 urine) against predicate showed high correlation (r=1.000). Interference testing per CLSI EP07-A2 confirmed no significant interference for common substances up to specified concentrations. No clinical studies performed.
Indicated for quantitative in vitro diagnostic determination of glucose in human serum, plasma, and urine to aid in diagnosis and treatment of carbohydrate metabolism disorders (diabetes mellitus, idiopathic hypoglycemia) and pancreatic diseases. Prescription use only; not for Point of Care settings.
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
Roche Diagnostics Cobas C111 Glucose HK (k951595)
Roche Calibrator for Automated Systems (C.f.a.s.) (k033501)
Roche Diagnostics Precinorm U and Precipath U (k041227)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k153644
B. Purpose for Submission:
New device
C. Measurand:
Glucose
D. Type of Test:
Quantitative, Enzymatic (Hexokinase) end point, UV
E. Applicant:
ELITechGroup, Inc.
F. Proprietary and Established Names:
ELITech Clinical Systems GLUCOSE HK SL
ELITech Clinical Systems ELICAL 2
ELITech Clinical Systems ELITROL I and ELITROL II
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| CFR | II | 862.1345, Glucose Test System | 75-Chemistry |
| JIX | II | 862.1150, Calibrators | 75- Chemistry |
| JJY | I, reserved | 826.1660, Multi-analyte Controls | 75- Chemistry |
H. Intended Use:
1. Intended use(s):
See Indications for Use below
{1}
2. Indication(s) for use:
ELITech Clinical Systems GLUCOSE HK SL is intended for the quantitative in vitro diagnostic determination of glucose in human serum, plasma and urine on ELITech Clinical Systems Selectra Pro Series Analyzers. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus and idiopathic hypoglycemia, and of pancreatic diseases.
ELITech Clinical Systems ELICAL 2 is a multi-parametric calibrator for in vitro diagnostic use in the calibration of quantitative ELITech Clinical Systems methods on ELITech Clinical Systems Analyzers.
ELITech Clinical Systems ELITROL I and ELITROL II are multi-parametric control sera for in vitro diagnostic use in quality control of quantitative ELITech Clinical Systems methods on ELITech Clinical Systems Analyzers.
3. Special conditions for use statement(s):
This device is intended for prescription use and in vitro diagnostic use only. It is not intended for use in Point of Care settings.
4. Special instrument requirements:
ELITech Clinical Systems Selectra ProM Analyzer
I. Device Description:
ELITech Clinical Systems GLUCOSE HK SL is available as a kit only. It consists of 8x20ml of R1 and 8x5ml of R2, sufficient for 8x57 tests:
Reagent 1 (R1): Pipes buffer, pH 7.60 80 mmol/L, NAD 4.1 mmol/L, ATP 2.2 mmol/L, Sodium azide < 0.1 %.
Reagent 2 (R2): Hexokinase ≥ 8500 U/L, G-6-PDH ≥ 8500 U/L, Magnesium salt 20 mmol/L, Sodium azide < 0.1 % mmol/L.
ELITech Clinical Systems ELICAL2 is a lyophilized calibrator based on human serum containing constituents to ensure optimal calibration. ELICAL 2 must be used to calibrate the ELITech Clinical Systems GLUCOSE HK SL assay. ELICAL 2 is sold separately.
ELITech Clinical Systems ELITROL I and ELITROL II are two-level quality control products consisting of a lyophilized human serum containing constituents at desired levels. ELITROL I and ELITROL II should be used with the ELITech Clinical Systems GLUCOSE HK SL assay. ELITROL I and ELITROL II are sold separately.
ELICAL 2, ELITROL I and ELITROL II are prepared exclusively from the blood of donors
{2}
tested individually and found to be negative for HbsAg and to antibodies to HCV and HIV according to FDA-approved methods.
## J. Substantial Equivalence Information:
1. Predicate device name(s):
Roche Diagnostics Cobas C111 Glucose HK
Roche Calibrator for Automated Systems (C.f.a.s.)
Roche Diagnostics Precinorm U and Precipath U
2. Predicate 510(k) number(s):
k951595
k033501
k041227
3. Comparison with predicate:
Glucose assay:
| Item | Candidate Device | Predicate Device |
| --- | --- | --- |
| Characteristics | ELITech Clinical Systems GLUCOSE HK SL (k153644) | ROCHE DIAGNOSTICS GLUCOSE HK (k951595) |
| Similarities | | |
| Intended Use | For the quantitative determination of glucose in human serum, plasma and urine. It is not intended for use in Point of Care settings. | Same |
| Test Principle | Enzymatic (hexokinase). | Same |
| Reagent Format | Liquid form, ready to use | Same |
| Same Type | Serum, Plasma, Urine | Same |
| Differences | | |
| Assay Range | Serum, Plasma: 20-720 mg/dL
Urine: 10-720 mg/dL | Serum, Plasma, Urine: 1.98-720 mg/dL |
| Recommended Controls (not included in the kit) | ELITech Clinical Systems ELITROL I (Normal)
ELITech Clinical Systems ELITROL II (Pathologic control) | Precinorm U or Precinorm U plus and
Precipath U or Precipath U plus |
| Recommended Calibrators (not included in the kit) | ELITech Clinical Systems ELICAL 2 | Calibrator C.f.a.s |
{3}
ELITech Clinical Systems ELITROL I and ELITROL II (Quality controls):
| Item | Candidate Device | Predicate Device |
| --- | --- | --- |
| Characteristics | ELITech Clinical Systems
ELITROL I / ELITROL II
(k153644) | Roche Diagnostics
Precinorm U / Precipath U
(k041227) |
| Similarities | | |
| Intended Use | Multi-parametric control
sera for in vitro diagnostic
use in quality control of
respective quantitative
method/analyzer systems | Same |
| Levels | 2 | Same |
| Format | Lyophilized human sera
with constituents
added as required to obtain
defined
component levels | Same |
| Stability | Lyophilized:
To store at 2-8°C and
protected from light until
the expiry date
After reconstitution, the
stabilities are :
- 12 hours between 15-25
°C.
- 5 days between 2-8 °C.
- 4 weeks between -25 and -
15 °C (when frozen once) | Same |
| Differences | | |
| Intended Analyzers | ELITech Clinical Systems
Analyzers | Roche/Hitachi
MODULAR, cobas c and
COBAS INTEGRA
analyzers |
4
{4}
ELITech Clinical Systems ELICAL 2 (Calibrator):
| Item | Candidate Device | Predicate Device |
| --- | --- | --- |
| Characteristics | ELITech Clinical Systems
ELICAL 2
(k153644) | Roche Calibrator for Automated Systems
(C.f.a.s.) (k033501) |
| Similarities | | |
| Intended Use | Multi-parametric calibrator for in vitro diagnostic use | Same |
| Levels | Single level | Same |
| Format | Lyophilized calibrator based on human serum with constituents added as requires to obtain desired component levels | Same |
| Stability | Lyophilized:
To store at 2-8°C and protected from light until the expiry date
After reconstitution, the stabilities are :
- 8 hours between 15-25 °C.
- 2 days between 2-8 °C.
- 4 weeks between -25 and -15 °C (when frozen once) | Same |
| Differences | | |
| Intended Analyzers | ELITech Clinical Systems Analyzers | Roche/Hitachi MODULAR, cobas c and COBAS INTEGRA analyzers |
K. Standard/Guidance Document Referenced (if applicable):
CLSI - EP05-A2, Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline-Second Edition.
CLSI - EP06-A, Evaluation of the Linearity of Quantitative Measurement Procedures: A Statistical Approach; Approved Guideline.
CLSI - EP07-A2, Interference Testing in Clinical Chemistry; Approved Guideline-Second Edition.
CLSI EP9-A2, Method Comparison and Bias Estimation Using Patient Samples; Approved Guideline-Second Edition.
CLSI - EP17-A, Protocols for the Determination of Limits of Detection and Limits of Quantification; Approved Guideline.
{5}
6
L. Test Principle:
The reaction of glucose with ATP produces Glucose-6-phosphate which in presence of NAD⁺ will produce D-Gluconate-6-phosphate + NADH + H⁺
The increase of absorbance is directly proportional to the glucose concentration.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
ELITech Clinical Systems Selectra ProM Analyzers were used to conduct the performance studies below.
a. Precision/Reproducibility:
The precision of the device was determined in accordance to CLSI EP05-A2 protocol.
Within-run and total precision results were obtained by performing two runs per day, two measurements per run, for 4 levels of serum samples and 3 levels of urine samples on two Selectra ProM analyzers during twenty operating days. The results are presented in the table below:
Serum samples precision*:
| | | | Precision (CV %) | |
| --- | --- | --- | --- | --- |
| Level | N | Mean (mg/dL) | Within Run | Total |
| 1 | 80 | 45.5 | 1.1 | 2.0 |
| 2 | 80 | 119.5 | 0.9 | 1.7 |
| 3 | 80 | 251.5 | 0.9 | 2.0 |
| 4 | 80 | 522.5 | 0.4 | 1.8 |
*Level 1 is a natural human serum pool, level 2 and 4 are spiked human serum pool and level 3 is a control sera (ELITROL II).
Urine samples precision*:
| | | | Precision (CV %) | |
| --- | --- | --- | --- | --- |
| Level | N | Mean (mg/dL) | Within Run | Total |
| 1 | 80 | 18.0 | 0.9 | 2.0 |
| 2 | 80 | 204.4 | 0.7 | 1.7 |
| 3 | 80 | 497.4 | 0.6 | 1.7 |
* Level 1 is a natural human urine pool, level 2 and level 3 are spiked human urine pool.
{6}
b. Linearity/assay reportable range:
The linearity of the assay for serum and urine matrix was evaluated respectively by mixing a spiked patient serum and urine pool with high glucose and a diluted patient serum and urine pool with low glucose (diluted with Albumin 6 g/dL / NaCl 0.9%) to obtain 11 equidistant concentrations (10% increase each level). The glucose concentration of each level was measured in triplicates using one lot of ELITech Clinical Systems GLUCOSE HK SL reagent on one Selectra ProM analyzer. The mean of the triplicates was used in the regression analysis. Results are summarized below.
Serum:
High sample: 726.6 mg/dL; Low sample: 20.0 mg/dL
y = 1.025x - 1.9618, R² = 0.9999
Claimed measuring range: 20-720 mg/dL
Urine:
High sample: 726.6 mg/dL; Low sample: 10.1 mg/dL
y=1.0155x - 1.596, R²=0.9998
Claimed measuring range: 10-720 mg/dL
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Traceability:
ELITech Clinical Systems GLUCOSE HK SL method is traceable to NIST SRM 965b reference material.
Stability:
ELITROL I and II serum control material is purchased from a commercial vendor (previously cleared under k041227). The following is claimed for stability: Before reconstitution, the shelf-life of the ELITROL I and ELITROL II is 24 months at 2-8°C. After reconstitution the stability is 12 hours when stored at 15-25°C, 5 days when stored at 2-8°C or 4 weeks (when frozen once) at -25° and -15°C.
ELICAL 2 calibrator material is purchased from a commercial vendor (previously cleared under k033501). The following is claimed for stability: Before reconstitution, the shelf-life of ELICAL 2 is stable 24 months at 2-8°C. After reconstitution the stability is 8 hours when stored at 15-25°C, 2 days at 2-8°C or 4 weeks (when frozen once) at -25° and -15°C. The labeling states that the ELICAL 2 should be stored tightly capped and protected from light when not in use.
7
{7}
# Value Assignment:
Each lot of ELITROL I and II are value assigned using the median of the observed values (at least 48 measurements in total: 2 analyzers x 2 reagent lots x 3 vials per test lot x 4 measurements per vial). The lot release criteria is that the assigned value should be within $\pm 15\%$ of the supplier's value, and the CV should be $\leq 2.4\%$ for ELITROL I, and $\leq 1.8\%$ for ELITROL II. The control ranges are lot specific, an example of one lot of control ranges is provided below:
ELITROL I: mean $= 95.1\mathrm{mg / dL}$ , control range $= 80.8$ to $109.4\mathrm{mg / dL}$
ELITROL II: mean $= 252.8\mathrm{mg / dL}$ , control range $= 214.9$ to $290.7\mathrm{mg / dL}$
For each lot of ELICAL 2, the calibrator concentration on the supplier's certificate of analysis is verified by testing the released lot of ELITRO I, ELITROL II and ELICAL 2 tested in triplicate on one instrument using two reagent lots. The release criteria are that the mean analyte values of ELITRO I, ELITROL II and ELICAL 2 are within $\pm 7.5\%$ of the target value. The calibrator value is lot specific, an example of one lot of calibrator is provided below:
ELICAL 2: Target value $= 196\mathrm{mg / dL}$
# d. Detection limit:
Limit of Blank (LoB), Limit of Detection (LoD) and Limit of Quantitation (LoQ) was determined according to the CLSI EP-17A guideline on Selectra ProM Analyzers.
Limit of Blank (LoB) was determined using 60 measurements of blank sample (Solution of Albumin $6\mathrm{g / dL}$ /NaCl $0.9\%$ ). Limit of Detection (LoD) was determined using 15 measurements of 4 samples with a low concentration of glucose (approximately $4\times \mathrm{LoB}\approx 0.4\mathrm{mg / dL}$ ). For the determination of the Limit of Quantification (LoQ), four (4) diluted sample pools are prepared from 4 different patient sample pools of known concentrations (measured by the test method) in order to obtain a concentration close to the expected LoQ target of $5\mathrm{mg / dL}$ . The sponsor validated the LoQ claim of $5\mathrm{mg / dL}$ ; the $\% \mathrm{CV}$ of serum samples at the target LoQ of $5.0\mathrm{mg / dL}$ is $<3.5\%$ , and the $\% \mathrm{CV}$ of urine samples at the target LoQ of $5.0\mathrm{mg / dL}$ is $<3\%$ . Results are summarized in the table below.
| Measurand | LoB | LoD | LoQ |
| --- | --- | --- | --- |
| Glucose (Serum) (mg/dL) | 0.1 | 0.3 | 5.0 |
| Glucose (Urine) (mg/dL) | 0.1 | 0.2 | 5.0 |
The claimed measuring range of the candidate device is 20 to $720\mathrm{mg / dL}$ for serum sample, and is 10 to $720\mathrm{mg / dL}$ for urine sample.
{8}
# e. Analytical specificity:
Various concentrations of potential interferents were spiked into two sample pools with low and high glucose levels in serum and urine, respectively, to support the specificity claim of each matrix. Testing was performed on Selectra ProM Analyzers and the mean of triplicate measurements of each sample was used to calculate the difference between the spiked and the control samples. The sponsor states that interference is considered to be non-significant if the bias between the tested and control samples are within $\pm 10\%$ . For each interferent, 6-9 levels were tested and the highest concentration tested that shows non-significant interference are summarized below:
Serum (Low sample pool at $50\mathrm{mg / dL}$ , high sample pool at $120\mathrm{mg / dL}$ of Glucose)
| Interferents | Test range up to | Highest level tested with no interference |
| --- | --- | --- |
| Triglycerides | 3000 mg/dL | 622 mg/dL |
| Unconjugated bilirubin | 30 mg/dL | 30 mg/dL |
| Conjugated bilirubin | 29.5 mg/dL | 29.5 mg/dL |
| Hemoglobin | 500 mg/dL | 500 mg/dL |
| Uric Acid | 20 mg/dL | 20 mg/dL |
| L-Dopa | 30 mg/dL | 30 mg/dL |
| Ascorbic acid | 20 mg/dL | 20 mg/dL |
| Methyl dopa | 2.0 mg/dL | 2.0 mg/dL |
| Tolazamide | 50 mg/dL | 50 mg/dL |
| Acetaminophen | 30 mg/dL | 30 mg/dL |
Urine (Low sample pool at $18.0\mathrm{mg / dL}$ , high sample pool at $200\mathrm{mg / dL}$ of Glucose)
| Interferents | Test range up to | Highest level tested with no interference |
| --- | --- | --- |
| Conjugated bilirubin | 29.5 mg/dL | 29.5 mg/dL |
| Hemoglobin | 500 mg/dL | 500 mg/dL |
| Uric Acid | 100 mg/dL | 100 mg/dL |
| Urea | 6000 mg/dL | 6000 mg/dL |
| pH | pH from 2.5 to 12.0 | pH 12.0 |
| Specific Gravity | 1.000 to 1.030 | 1.030 |
{9}
Sponsor has the following conclusions based on their triglycerides interference and included this information in the labeling:
“Triglycerides at a concentration of ~1300 mg/dL decreased glucose result in serum at 50 mg/dL by 32% and at 120 mg/dL by 19%.”
Sponsor also has the following limitations in the labeling:
1. Do not use hemolyzed samples.
2. Do not use lipemic samples.
3. Urine collected over 24 hours in a dark bottle, adding 5mL of glacial acetic acid before sample collection.
4. In addition, the sponsor also states the following in their labeling:
Other compounds may interfere. Users should refer to the following literature references:
- Young, D. S., Effects of preanalytical variables on clinical laboratory tests, 2nd Ed., AACC Press, (1997).
- Young, D. S., Effects of drugs on clinical laboratory tests, 4th Ed., AACC Press, (1995).
- Berth, M. & Delanghe, J. Protein precipitation as a possible important pitfall in the clinical chemistry analysis of blood samples containing monoclonal immunoglobulins: 2 case reports and a review of literature, Acta Clin Belg., (2004), 59, 263.
f. Assay cut-off:
Not Applicable
2. Comparison studies:
a. Method comparison with predicate device:
Method comparison was performed between the predicate method and ELITech Clinical Systems GLUCOSE HK SL reagent on a Selectra ProM analyzer. The results for serum and urines samples are summarized below. A single test result using the proposed candidate method, and the mean of triplicate measurements using the comparative method, were used in the regression analysis. The altered samples used for each matrix are no more than 10%. Results are summarized in the table below.
10
{10}
| Matrix | N | Linear regression | Candidate Device Sample range (mg/dL) |
| --- | --- | --- | --- |
| Serum | 100 | y=1.008x + 0.430
R²=1.000 | 20.5 to 707.5 |
| Urine
(24-hr., collected
with glacial acetic
acid as a
preservative) | 40 | y= 0.996x - 0.4
R² = 1.000 | 10.1 to 703.9 |
b. Matrix comparison:
The sponsor performed a matrix comparison study by comparing 40 lithium heparin samples ranging from 25.2 to 704.5 mg/dL and 40 sodium fluoride/ oxalate samples ranging from 21.0 to 719.7 mg/dL to serum samples on the Selectra ProM analyzer. Regression analysis of the results yielded the following:
Lithium heparin vs Serum: y=1.001x - 0.7 mg/dL, r= 1.000
Sodium fluoride/ oxalate vs Serum: y= 1.016x- 0.9 mg/dL, r= 0.999
The matrix comparison study results support the use of lithium heparin and sodium fluoride/ oxalate samples in addition to serum samples for glucose measurement using the ELITech Clinical Systems GLUCOSE HK SL assay.
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
{11}
5. Expected values/Reference range:
Serum/ Plasma*:
74 - 106 mg/dL (4.1 - 5.9 mmol/L)
Urine (24 hours collection)*:
<0.5 g/day (1-15 mg/dL)
<2.78 mmol/day (0.1 - 0.8 mmol/L)
*These reference values are from:
Wu, A. H. B., Clinical guide to laboratory tests, 4th Ed., (W.B. Saunders eds. Philadelphia USA), (2006), 444
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.
12
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.