The sponsor used 80 clinical urine samples to perform a method comparison between the subject device and a reference method (GC/MS) to demonstrate clinical performance and substantial equivalence.
Method comparison; Clinical samples; Urine
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Method comparison study
Clinical unaltered human urine samples; Sample Size: 80
GC/MS (Gas or liquid chromatography/mass spectrometry)
Agreement with positive and negative samples
Indications for Use
The Cocaine Metabolite Enzyme Immunoassay is intended for the qualitative and semiquantitative determination of benzoylecgonine in human urine, at a cutoff value of 150 ng/mL. The assay is designed for professional use with a number of automated clinical chemistry analyzers. The semi-quantitative mode is for purposes of (1) enabling laboratories to determine an appropriate dilution of the specimen for confirmation by a confirmatory method such as GCMS or (2) permitting laboratories to establish quality control procedures. The Cocaine Metabolite Drugs of Abuse (DAU) Calibrators are for use as calibrators in the qualitative and semi-quantitative calibration of the Cocaine Metabolite Enzyme Immunoassay at a cutoff value of 150 ng/mL. The Cocaine Metabolite Drugs of Abuse (DAU) Controls are for use as assayed quality control materials to monitor the precision of the Cocaine Metabolite Enzyme Immunoassay at a cutoff value of 150 ng/mL. The assay provides only a preliminary analytical result. A more specific alternative chemical method must be used in order to obtain a confirmed analytical result. Gas or liquid chromatography/mass spectrometry (GC/MS or LC/MS) is the preferred confirmatory method). Clinical consideration and professional judgment should be exercised with any drug of abuse test result, particularly when the preliminary test result is positive.
Device Story
Homogeneous enzyme immunoassay for benzoylecgonine in human urine; utilizes competition between sample drug and G6PDH-labeled drug for fixed antibody. Enzyme activity inversely proportional to drug concentration; active enzyme converts NAD to NADH, measured spectrophotometrically at 340 nm. Used in clinical laboratories on automated chemistry analyzers by professional staff. Provides preliminary screening results; requires confirmatory testing via GC/MS or LC/MS. Assists clinicians in identifying potential drug use; supports laboratory quality control and specimen dilution for confirmation.
Clinical Evidence
Bench testing only. Precision evaluated with 88 determinations per concentration level; linearity confirmed (0-1000 ng/mL, r=0.9992). Method comparison with 80 clinical samples showed 90% positive agreement and 95-98% negative agreement compared to confirmatory methods.
Indicated for qualitative and semi-quantitative detection of benzoylecgonine in human urine at 150 ng/mL cutoff. For professional use in clinical laboratories using automated chemistry analyzers. Not for patient self-testing.
Regulatory Classification
Identification
A cocaine and cocaine metabolite test system is a device intended to measure cocaine and a cocaine metabolite (benzoylecgonine) in serum, plasma, and urine. Measurements obtained by this device are used in the diagnosis and treatment of cocaine use or overdose.
Special Controls
*Classification.* Class II (special controls). A cocaine and cocaine metabolite test system is not exempt if it is intended for any use other than employment or insurance testing or is intended for Federal drug testing programs. The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 862.9, provided the test system is intended for employment and insurance testing and includes a statement in the labeling that the device is intended solely for use in employment and insurance testing, and does not include devices intended for Federal drug testing programs (*e.g.,* programs run by the Substance Abuse and Mental Health Services Administration (SAMHSA), the Department of Transportation (DOT), and the U.S. military).
Predicate Devices
Lin-Zhi International Inc., Cocaine Metabolite Enzyme Immunoassay (k020763)
Lin-Zhi International Inc., Cocaine Metabolite calibrators and controls (k020769)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k113139
B. Purpose for Submission:
New device
C. Measurand:
Cocaine
D. Type of Test:
Qualitative and semi-quantitative enzyme immunoassay
E. Applicant:
Lin-Zhi International, Inc.
F. Proprietary and Established Names:
Cocaine Metabolite Enzyme Immunoassay
Cocaine Metabolite Drugs of Abuse (DAU) Calibrators
Cocaine Metabolite Drugs of Abuse (DAU) Controls
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| DIO – Cocaine and cocaine metabolite test system | II | 862.3250 | 91-Toxicology |
| DLJ -Clinical toxicology calibrator | II | 862.3200 | 91- Toxicology |
| LAS -Clinical toxicology control material | I, reserved | 862.3280 | 91- Toxicology |
{1}
H. Intended Use:
1. Intended use(s):
See indications for use below
2. Indication(s) for use:
The Cocaine Metabolite Enzyme Immunoassay is intended for the qualitative and semi-quantitative determination of benzoylecgonine in human urine, at a cutoff value of 150 ng/mL. The assay is designed for professional use with a number of automated clinical chemistry analyzers.
The semi-quantitative mode is for purposes of (1) enabling laboratories to determine an appropriate dilution of the specimen for confirmation by a confirmatory method such as GCMS or (2) permitting laboratories to establish quality control procedures.
This assay provides only a preliminary analytical test result. A more specific alternative chemical method must be used in order to obtain a confirmed analytical result. Gas or Liquid Chromatograph/Mass Spectrometry (GC/MS or LC/MS) is the preferred confirmatory method. Clinical consideration and professional judgment should be exercised with any drug of abuse test result, particularly when the preliminary result is positive.
The Cocaine Metabolite Drugs of Abuse (DAU) Calibrators are for use as calibrators in the qualitative and semi-quantitative calibration of the Cocaine Metabolite Enzyme Immunoassay at a cutoff value of 150 ng/mL.
The Cocaine Metabolite Drugs of Abuse (DAU) Controls are for use as assayed quality control materials to monitor the precision of the Cocaine Metabolite Enzyme Immunoassay at a cutoff value of 150 ng/mL.
3. Special conditions for use statement(s):
For professional use only
4. Special instrument requirements:
Clinical chemistry analyzers capable of maintaining a constant temperature, pipetting sample, mixing reagent, measuring enzymatic rates at 340 nm and timing the reaction accurately can be used to perform this homogeneous immunoassay.
Performance testing was conducted on the Roche Diagnostics Hitachi 717 analyzer.
2
{2}
I. Device Description:
The assay consists of ready-to-use liquid reagents. Reagent 1 contains a mouse monoclonal anti-benzoylecgonine antibody, glucose-6-phosphate (G6P) nicotinamide adenine dinucleotide (NAD), stabilizers and sodium azide (0.09%) as a preservative. Reagent 2 contains glucose-6-phosphate dehydrogenase (G6PDH) labeled with benzoylecgonine in buffer with sodium azide (0.09%) as a preservative.
The calibrators and controls are sold separately. The calibrator has 5 levels and the control has 2 levels. They consist of human urine samples containing benzoylecgonine with sodium azide (0.09%) as a preservative.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Lin-Zhi International Inc., Cocaine Metabolite Enzyme Immunoassay
Lin-Zhi International Inc., Cocaine Metabolite calibrators and controls
2. Predicate 510(k) number(s):
k020763 and k020769, respectively
3. Comparison with predicate:
| Similarities/Differences | | |
| --- | --- | --- |
| Item | Device | Predicates |
| Intended Use | Intended for the qualitative and semi-quantitative determination of benzoylecgonine in human urine.
The Calibrators are for use as calibrators in the qualitative and semi-quantitative calibration of the Cocaine Metabolite Enzyme Immunoassay.
The Controls are for use as assayed quality control materials to monitor the precision of the Cocaine Metabolite Enzyme Immunoassay. | Same |
| Analyte | Benzoylecgonine | Same |
| Cutoff | 150 ng/mL | 300 ng/mL |
| Matrix | Urine | Same |
| Calibrators | 5 levels | 5 levels |
{3}
| Similarities/Differences | | |
| --- | --- | --- |
| Item | Device | Predicates |
| | (0, 75, 150, 300, 1000 ng/mL) | (0, 150,300,1000, 3000 ng/mL) |
| Controls | 2 levels
(112.5 ng/mL, 187.5 ng/mL) | 2 levels
(225 ng/mL, 375 ng/mL) |
| Storage | 2-8 °C until expiration date | 2-8 °C until expiration date |
## K. Standard/Guidance Document Referenced (if applicable):
CLSI EP5-A, Evaluation of Precision Performance of Clinical Chemistry Devices
## L. Test Principle:
The Cocaine Metabolite assay is a homogenous enzyme immunoassay with ready-to-use liquid reagent. The assay is based on competition between drug in the sample and dug labeled with enzyme glucose-6-phosphate dehydrogenase (G6PDH) for a fixed amount of antibody in the reagent.
Enzyme activity decreases upon binding to the antibody, and the drug concentration in the sample is measured in terms of enzyme activity. In the absence of drug in the sample, benzoylecgonine-labeled G6PDH conjugate is bound to antibody, and the enzyme activity is inhibited. On the other hand, when free drug is present in the sample, antibody would bind to free drug, the unbound benzoylecgonine-labeled G6PDH then exhibits its maximal enzyme activity. Active enzyme converts nicotinamide adenine dinucleotide (NAD) to NADH resulting in an absorbance change that can be measured spectrophotometrically at 340 nm.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
Precision was determined by spiking benzoylecgonine into drug free urine at various concentrations (zero, -75%, -50%, -25%, at the cutoff, 125%, 150%, 175% and 200% of the cutoff). Concentrations were confirmed by GC/MS. Testing for both the with-in run and between-run studies were performed by testing each sample in replicate, with two runs per day, for 22 days. The qualitative and semi-quantitative results are presented below:
{4}
Qualitative:
| | | Within Run | | Between Run |
| --- | --- | --- | --- | --- |
| Sample concentration (ng/mL) | No. Observations | | No. Observations | |
| | | # Neg/#Pos | | # Neg/#Pos |
| 0 (negative) | 22 | 22/0 | 88 | 88/0 |
| 37.5 (-75% c/o) | 22 | 22/0 | 88 | 88/0 |
| 75 (-50% c/o) | 22 | 22/0 | 88 | 88/0 |
| 112.5 (-25% c/o) | 22 | 22/0 | 88 | 88/0 |
| 150 (cutoff) | 22 | 19/3 | 88 | 73/15 |
| 187.5 (+25% c/o) | 22 | 0/22 | 88 | 0/88 |
| 225 (+50% c/o) | 22 | 0/22 | 88 | 0/88 |
| 267.5 (+50% c/o) | 22 | 0/22 | 88 | 0/88 |
| 300 (+100% c/o) | 22 | 0/22 | 88 | 0/88 |
Semi-Quantitative:
| | | Within Run | | Between Run |
| --- | --- | --- | --- | --- |
| Sample concentration (ng/mL) | No. Observations | | No. Observations | |
| | | # Neg/#Pos | | # Neg/#Pos |
| 0 (negative) | 22 | 22/0 | 88 | 88/0 |
| 37.5 (-75% c/o) | 22 | 22/0 | 88 | 88/0 |
| 75 (-50% c/o) | 22 | 22/0 | 88 | 88/0 |
| 112.5 (-25% c/o) | 22 | 22/0 | 88 | 88/0 |
| 150 (cutoff) | 22 | 18/4 | 88 | 59/29 |
| 187.5 (+25% c/o) | 22 | 0/22 | 88 | 0/88 |
| 225 (+50% c/o) | 22 | 0/22 | 88 | 0/88 |
| 267.5 (+50% c/o) | 22 | 0/22 | 88 | 0/88 |
| 300 (+100% c/o) | 22 | 0/22 | 88 | 0/88 |
b. Linearity/assay reportable range:
Linearity across the range was confirmed by serially diluting a spiked urine pool containing $1000\mathrm{ng / mL}$ of benzoylecgonine in to concentration levels listed in the table below. Each sample was assayed in the semi-quantitative mode. The results were averaged and compared to the expected result and the percent recovery was calculated. Results are presented in the table below:
{5}
| Expected Concentration (ng/mL) | Mean Observed Concentration (ng/mL) | Recovery (%) |
| --- | --- | --- |
| Negative | 4.0 | not applicable |
| 48.1 | 58.1 | 120.8 |
| 96.2 | 96.6 | 100.4 |
| 144.3 | 151.4 | 104.9 |
| 192.4 | 200.5 | 104.2 |
| 288.6 | 312.1 | 108.1 |
| 384.8 | 403.1 | 104.8 |
| 481 | 488.3 | 101.5 |
| 577.2 | 588.2 | 101.9 |
| 673.4 | 694.8 | 103.2 |
| 769.6 | 812 | 105.5 |
| 865.8 | 917.5 | 106 |
| 962 | 1017.8 | 105.8 |
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Five levels of calibrators (0, 75, 150, 300, 1000 ng/mL) and two levels of control material (112.5 ng/mL, 187.5 ng/mL) are available for use with the Cocaine Metabolite Enzyme Immunoassay. A commercially available benzoylecgonine standard solution from Cerilliant Analytical Reference Standards is used and traceable to NIST standard. This standard solution is made into a secondary (lower concentration) stock solution. The secondary stock solution is then spiked into the calibrators and controls to the desired concentration. The concentrations are confirmed by GC/MS.
Stability Studies:
Real time and accelerated studies for both controls and calibrators have been conducted. Protocols and acceptance criteria were described and found to be acceptable. The manufacturer claims the following expiration date for both controls and calibrators:
When stored at 2-8 °C unopened product is stable until expiration date which is 18 months.
On board stability is good for 14 days when stored at 2-8 °C.
d. Detection limit:
Performance at low drug concentrations in the semi-quantitative assay was
{6}
characterized by determination of recovery (see section b above).
# e. Analytical specificity:
Cross-reactivity was established by spiking various concentrations of structurally related into drug-free urine. Results are expressed as a minimum concentration of metabolite or compound required to produce a response approximately equivalent to the cutoff concentration of the assay. The percent cross-reactivity of those compounds are presented below:
Structurally related
| Compound | Equivalent to 150 ng/mL | % Cross reactivity |
| --- | --- | --- |
| Benzoylecgonine | 150 | 96.03% |
| Cocaethylene | 4,000 | 4.58% |
| Cocaine | 25,000 | 0.62% |
| Ecgonine | 400,000 | 0.03% |
| Ecgonine, Methyl Ester | 500,000 | 0% |
| Norcocaine | 30,000 | 0.68% |
| Atropine | 500,000 | 0% |
Structurally unrelated
| Compound | Tested concentrations ng/mL | -25% Benzoylecgonine | +25% Benzoylecgonine |
| --- | --- | --- | --- |
| Acetaminophen | 500,000 | Negative | Positive |
| Acetylsalicylic Acid | 500,000 | Negative | Positive |
| Amobarbital | 500,000 | Negative | Positive |
| Amoxicillin | 500,000 | Negative | Positive |
| Amphetamine | 500,000 | Negative | Positive |
| Bupropion | 500,000 | Negative | Positive |
| Catptopril | 500,000 | Negative | Positive |
| Caffeine | 500,000 | Negative | Positive |
| Chlordiazepoxide | 500,000 | Negative | Positive |
| Chlorpheniramine | 500,000 | Negative | Positive |
| Chlorpomazine | 500,000 | Negative | Positive |
| Codeine | 500,000 | Negative | Positive |
| Dextromethorphan | 500,000 | Negative | Positive |
| Diazepam | 500,000 | Negative | Positive |
| Digoxin | 500,000 | Negative | Positive |
| Enalapril | 500,000 | Negative | Positive |
| Fluoxetine | 100,000 | Negative | Positive |
| Glyburide | 500,000 | Negative | Positive |
| Ibuprofen | 500,000 | Negative | Positive |
| Lidocaine | 500,000 | Negative | Positive |
{7}
| Compound | Tested concentrations ng/mL | -25% Benzoylecgonine | +25% Benzoylecgonine |
| --- | --- | --- | --- |
| Meperidine | 500,000 | Negative | Positive |
| Methadone | 100,000 | Negative | Positive |
| Methamphetamine | 500,000 | Negative | Positive |
| Methaqualone | 500,000 | Negative | Positive |
| Morphine | 500,000 | Negative | Positive |
| Nicodine | 500,000 | Negative | Positive |
| Nifedipine | 100,000 | Negative | Positive |
| Oxazepam | 100,000 | Negative | Positive |
| Phencyclidine | 500,000 | Negative | Positive |
| Phenobarbital | 500,000 | Negative | Positive |
| Propoxyphene | 100,000 | Negative | Positive |
| Ranitidine | 500,000 | Negative | Positive |
| Salicyluric acid | 500,000 | Negative | Positive |
| Secobarbital | 500,000 | Negative | Positive |
| 11-nor-THC-COOH | 500,000 | Negative | Positive |
| Valproic Acid | 500,000 | Negative | Positive |
| Verapamil | 500,000 | Negative | Positive |
# Endogenous Compounds
The following endogenous compounds were added into drug-free urine, urine sample spiked to $-25\%$ of benzoylecgonine and one urine spiked to $+25\%$ of benzoylecgonine at various concentrations. The substances listed in the table below were determined not to interfere at the concentration shown:
| Interfering Substance | Concentration Tested mg/dL | -25% Benzoylecgonine | +25% Benzoylecgonine |
| --- | --- | --- | --- |
| Acetone | 1000 | Negative | Positive |
| Ascorbic Acid | 400 | Negative | Positive |
| Creatinine | 500 | Negative | Positive |
| Ethanol | 1000 | Negative | Positive |
| Galactose | 10 | Negative | Positive |
| r-Globulin | 500 | Negative | Positive |
| Glucose | 1500 | Negative | Positive |
| Hemoglobin | 300 | Negative | Positive |
| Human Serum Albumin | 500 | Negative | Positive |
| Oxalic Acid | 100 | Negative | Positive |
| Sodium Chloride | 3000 | Negative | Positive |
| Urea | 2000 | Negative | Positive |
{8}
There is the possibility that other substances and/or factors not listed above may interfere with the test and cause false results, e.g., technical or procedural errors.
## pH and Specific Gravity
To test for possible positive and/or negative interference from pH urine samples having pH from 3, 4, 5, 7, 8, 9, 10 and 11 were used. Each of these samples were divided into two aliquots for each drug and spiked to -25% of the cutoff and +25% of the cutoff. No positive or negative interference due to pH was observed.
To test for possible positive and/or negative interference from specific gravity urine samples having specific gravity from 1.000, 1.002, 1.005, 1.007, 1.010, 1.015, 1.017, 1.025 and 1.030 were used. Each of these samples were divided into two aliquots for each drug and spiked to -25% of the cutoff and 125% of the cutoff. No positive or negative interference due to specific gravity was observed.
## f. Assay cut-off:
Analytical performance of the device around the claimed cutoff is described in precision section (1 a.) above
## 2. Comparison studies:
### a. Method comparison with predicate device:
Eighty unaltered clinical urine samples (40 negative and 40 positive) were evaluated by the Lin-Zhi Cocaine Metabolite Enzyme Immunoassay and compared to LC/MS. Results from the study are presented below:
Qualitative
| Candidate Device Results | Negative | Less than half the cutoff concentration by GC/MS analysis | Near Cutoff Negative (Between 50% below the cutoff and the cutoff concentration) | Near Cutoff Positive (Between the cutoff and 50% above the cutoff concentration) | High Positive (greater than 50% above the cutoff concentration) |
| --- | --- | --- | --- | --- | --- |
| Positive | 0 | 0 | 2 | 5 | 31 |
| Negative | 20 | 4 | 14 | 4 | 0 |
% Agreement among positives is 90% (36/40)
% Agreement among negatives is 95% (38/40)
{9}
10
Discordant
| Cutoff Value (ng/mL) | LZI Cocaine Assay (POS/NEG) | Drug/Metabolite LC/MS value (ng/mL) |
| --- | --- | --- |
| 150 | Positive | 141 |
| 150 | Positive | 147 |
| 150 | Negative | 150 |
| 150 | Negative | 152 |
| 150 | Negative | 167 |
| 150 | Negative | 176 |
Semi-quantitative
| Candidate Device Results | Negative | Less than half the cutoff concentration by GC/MS analysis | Near Cutoff Negative (Between 50% below the cutoff and the cutoff concentration) | Near Cutoff Positive (Between the cutoff and 50% above the cutoff concentration) | High Positive (greater than 50% above the cutoff concentration) |
| --- | --- | --- | --- | --- | --- |
| Positive | 0 | 0 | 1 | 5 | 31 |
| Negative | 20 | 4 | 15 | 4 | 0 |
% Agreement among positives is 90% (36/40)
% Agreement among negatives is 98% (39/40)
Discordant
| Cutoff Value (ng/mL) | LZI 6-Acetylmorphine Assay (POS/NEG) | Drug/Metabolite LC/MS value (ng/mL) |
| --- | --- | --- |
| 150 | Positive | 141 |
| 150 | Negative | 150 |
| 150 | Negative | 167 |
| 150 | Negative | 167 |
| 150 | Negative | 176 |
b. Matrix comparison:
Test is for urine samples only
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable
b. Clinical specificity:
{10}
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:
Not applicable
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.
11
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.