K192299 · Lin-Zhi International, Inc. · MKU · Nov 21, 2019 · Clinical Toxicology
Device Facts
Record ID
K192299
Device Name
LZI Cotinine II Enzyme Immunoassay
Applicant
Lin-Zhi International, Inc.
Product Code
MKU · Clinical Toxicology
Decision Date
Nov 21, 2019
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.3220
Device Class
Class 1
Indications for Use
The LZI Cotinine II Enzyme Immunoassay is intended for the qualitative and semi-quantitative determination of cotinine in human urine at the cutoff value of 200 ng/mL when calibrated against cotinine. The assay is intended as an aid in the detection of cotinine after use or exposure to tobacco products. The assay is designed for prescription 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 gas or liquid chromatography/mass spectrometry (GC/MS or LC/MS) or (2) permitting laboratories to establish quality control procedures. The assay provides only a preliminary analytical result. A more specific alternative chemical method (e.g., gas or liquid chromatography and mass spectrometry) must be used in order to obtain a confirmed analytical result. 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
LZI Cotinine II Enzyme Immunoassay is a homogeneous enzyme immunoassay for urine cotinine detection. Input: human urine sample. Principle: competitive binding between sample cotinine and cotinine-labeled G6PDH enzyme for fixed antibody; drug presence inhibits antibody binding, allowing G6PDH to remain active. Active enzyme converts NAD to NADH, measured spectrophotometrically at 340 nm. Output: qualitative or semi-quantitative cotinine concentration. Used in clinical laboratories; operated by trained personnel (technicians/medical technologists). Results are preliminary; require confirmation by GC/MS or LC/MS. Clinical decision-making relies on professional judgment; aids in identifying tobacco use/exposure.
Clinical Evidence
Bench testing only. Precision/reproducibility evaluated over 22 days (N=88) on AU480 analyzer. Linearity confirmed across 0-1000 ng/mL range. Method comparison performed on 104 clinical samples against LC/MS reference method; demonstrated 96.4% positive agreement and 98.7% negative agreement. Interference studies evaluated endogenous compounds, pH (3-11), and specific gravity (1.005-1.028). Cross-reactivity tested against various drugs and metabolites.
Indicated for the qualitative and semi-quantitative detection of cotinine in human urine at a 200 ng/mL cutoff to aid in identifying tobacco use or exposure. For prescription use in clinical laboratories using automated chemistry analyzers. Requires confirmation by GC/MS or LC/MS.
Regulatory Classification
Identification
A carbon monoxide test system is a device intended to measure carbon monoxide or carboxyhemoglobin (carbon monoxide bound to the hemoglobin in the blood) in blood. Measurements obtained by this device are used in the diagnosis and treatment of or confirmation of carbon monoxide poisoning.
Predicate Devices
Niccheck I (k963733)
Submission Summary (Full Text)
{0}
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
k192299
B Applicant
Lin-Zhi International, Inc.
C Proprietary and Established Names
LZI Cotinine II Enzyme Immunoassay
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| MKU | Class I | 21 CFR 862.3220 - Carbon Monoxide Test System | TX - Clinical Toxicology |
## II Submission/Device Overview:
A Purpose for Submission:
New Device
B Measurand:
Cotinine
C Type of Test:
Immunoassay
K192299 - Page 1 of 11
{1}
III Intended Use/Indications for Use:
A Intended Use(s):
See Indications for Use below
B Indication(s) for Use:
The LZI Cotinine II Enzyme Immunoassay is intended for the qualitative and semi-quantitative determination of cotinine in human urine at the cutoff value of 200 ng/mL when calibrated against cotinine. The assay is intended as an aid in the detection of cotinine after use or exposure to tobacco products. The assay is designed for prescription 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 gas or liquid chromatography/mass spectrometry (GC/MS or LC/MS) or (2) permitting laboratories to establish quality control procedures.
The assay provides only a preliminary analytical result. A more specific alternative chemical method (e.g., gas or liquid chromatography and mass spectrometry) must be used in order to obtain a confirmed analytical result. Clinical consideration and professional judgment should be exercised with any drug of abuse test result, particularly when the preliminary test result is positive.
C Special Conditions for Use Statement(s):
Prescription use only
D Special Instrument Requirements:
Validation studies were conducted using the AU480 Chemistry Analyzer.
IV Device/System Characteristics:
A Device Description:
The LZI Cotinine Enzyme Immunoassay is a homogeneous enzyme immunoassay with ready-to use liquid reagents. The LZI Cotinine Enzyme Immunoassay is a kit comprised of two reagents, an R1 and R2, which are bottled separately but sold together within the kit. The R1 solution contains mouse monoclonal anti-cotinine antibody, glucose-6-phosphate (G6P) nicotinamide adenine dinucleotide (NAD), stabilizers, and sodium azide (0.09 %) as a preservative. The R2 solution contains glucose-6-phosphate dehydrogenase (G6PDH) labeled with cotinine in buffer with sodium azide (0.09 %) as a preservative.
B Principle of Operation:
The assay is based on competition between drug in the sample and drug labeled with the 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, cotinine-
K192299 - Page 2 of 11
{2}
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 cotinine-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.
V Substantial Equivalence Information:
A Predicate Device Name(s):
Niccheck I
B Predicate 510(k) Number(s):
k963733
C Comparison with Predicate(s):
| Device & Predicate Device(s): | k192299 | k963733 |
| --- | --- | --- |
| Device Trade Name | LZI Cotinine II Enzyme Immunoassay | NicCheckI |
| General Device Characteristic Similarities | | |
| Analyte | Cotinine | same |
| Matrix | Urine | same |
| Cutoff | 200 ng/mL | same |
| Intended Use/Indications For Use | For the qualitative and semi-quantitative determination of cotinine in human urine at the cutoff value of 200 ng/mL when calibrated against cotinine. The assay is intended as an aid in the detection of cotinine after use or exposure to tobacco products. | same |
| General Device Characteristic Differences | | |
| Storage | 2-8°C until expiration date | 2-8°C until 2 years from date of manufacture. Test strips are susceptible to conditions of high humidity, the canister must be kept tightly closed after removal of the required number of strips. |
K192299 - Page 3 of 11
{3}
VI Standards/Guidance Documents Referenced:
CLSI EP05-A3, Evaluation of Precision of Quantitative Measurement Procedures
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
1. Precision/Reproducibility:
Cotinine samples (cotinine spiked negative urine pools) were run in replicates of 2, two runs per day (one in the morning and one in the afternoon) for 22 days on one AU480 automatic clinical analyzer for a total of 88 runs, in both qualitative and semi-quantitative modes. One single lot of reagents and calibrators and controls were used. Cotinine was spiked into samples at the concentrations shown in the tables below, and all sample cotinine concentrations were confirmed by LC/MS.
Semi-Quantitative Positive/Negative Results:
| 200 ng/mL Cutoff Result: | | Within Run (N=22) | | Total Precision (N=88) | |
| --- | --- | --- | --- | --- | --- |
| Cotinine Concentration | % of Cutoff | # of Determinatio n | EIA Result | # of Determinatio n | EIA Result |
| 0 ng/mL | 0.0 % | 22 | 22 Negative | 88 | 88 Negative |
| 50 ng/mL | 25.0 % | 22 | 22 Negative | 88 | 88 Negative |
| 100 ng/mL | 50.0 % | 22 | 22 Negative | 88 | 88 Negative |
| 150 ng/mL | 75.0 % | 22 | 22 Negative | 88 | 88 Negative |
| 200 ng/mL | 100.0 % | 22 | 14 Neg/8 Pos | 88 | 55 Neg/33 Pos |
| 250 ng/mL | 125.0 % | 22 | 22 Positive | 88 | 88 Positive |
| 300 ng/mL | 150.0 % | 22 | 22 Positive | 88 | 88 Positive |
| 350 ng/mL | 175.0 % | 22 | 22 Positive | 88 | 88 Positive |
| 400 ng/mL | 200.0 % | 22 | 22 Positive | 88 | 88 Positive |
Qualitative Positive/Negative Results:
| 200 ng/mL Cutoff Result: | | Within Run (N=22) | | Total Precision (N=88) | |
| --- | --- | --- | --- | --- | --- |
| Cotinine Concentration | % of Cutoff | # of Determinatio n | EIA Result | # of Determinatio n | EIA Result |
| 0 ng/mL | 0.0 % | 22 | 22 Negative | 88 | 88 Negative |
| 50 ng/mL | 25.0 % | 22 | 22 Negative | 88 | 88 Negative |
| 100 ng/mL | 50.0 % | 22 | 22 Negative | 88 | 88 Negative |
| 150 ng/mL | 75.0 % | 22 | 22 Negative | 88 | 88 Negative |
| 200 ng/mL | 100.0 % | 22 | 10 Neg/12 Pos | 88 | 51 Neg/37 Pos |
| 250 ng/mL | 125.0 % | 22 | 22 Positive | 88 | 88 Positive |
| 300 ng/mL | 150.0 % | 22 | 22 Positive | 88 | 88 Positive |
| 350 ng/mL | 175.0 % | 22 | 22 Positive | 88 | 88 Positive |
| 400 ng/mL | 200.0 % | 22 | 22 Positive | 88 | 88 Positive |
K192299 - Page 4 of 11
{4}
K192299 - Page 5 of 11
2. Linearity:
A recovery/linearity study was performed by spiking cotinine into a pool of negative urine to create a 1000 ng/mL high concentration. The high concentration was then diluted to reach the final concentrations listed in the table below. Each sample was run in 10 replicates on the AU480 automated clinical analyzer in semi-quantitative mode with a calibration curve established with the five Cotinine calibrators (0, 100, 200, 400, and 1000 ng/mL). Recovery values (expected value divided by average observed value) were calculated and are presented in the table below.
| Target Concentration (ng/mL) | Determined (ng/mL) | % Recovery |
| --- | --- | --- |
| 1000 | 978.9 | 97.9% |
| 900 | 919.6 | 102.2% |
| 800 | 851.7 | 106.5% |
| 700 | 766.0 | 109.4% |
| 600 | 664.8 | 110.8% |
| 500 | 539.1 | 107.8% |
| 400 | 395.0 | 98.8% |
| 300 | 302.4 | 100.8% |
| 200 | 199.9 | 100.0% |
| 100 | 109.0 | 109.0% |
| 20 | 33.5 | 167.5% |
| 0 | 19.3 | N/A |
3. Analytical Specificity/Interference:
The compounds listed below were spiked into urine to the desired concentrations. These solutions were then split into three portions; one without cotinine, and the remaining two that were further spiked with cotinine standards obtained from Cerilliant to a final cotinine concentration of 150 ng/mL or 250 ng/mL (as negative or positive controls, ±25 % Cutoff Concentration, respectively). Samples were then evaluated against the assay's calibration curve in both qualitative and semi-quantitative modes, and the results are as shown below (results were identical for both qualitative and semi-quantitative modes). Results indicated that there is interference from boric acid at 1 % w/v and citric acid. No other compounds showed interference concentrations at the concentrations tested. Data collected on the AU480 automated clinical analyzer is summarized in the following table:
Endogenous Compounds Interference
| Endogenous Substance | Concentration Tested (ng/mL) | Spiked Cotinine Concentration | | |
| --- | --- | --- | --- | --- |
| | | 0 ng/mL | 150 ng/mL Control | 250 ng/mL Control |
| Acetone | 1000 | Neg | Neg | Pos |
| Ascorbic Acid | 1500 | Neg | Neg | Pos |
| Bilirubin | 2 | Neg | Neg | Pos |
| Boric Acid | 1000 | Neg | Neg | Neg |
| Calcium Chloride (CaCl2) | 300 | Neg | Neg | Pos |
| Citric Acid (pH 3) | 800 | Neg | Neg | Neg |
| Creatinine | 500 | Neg | Neg | Pos |
| Ethanol | 1000 | Neg | Neg | Pos |
| Galactose | 10 | Neg | Neg | Pos |
| γ-Globulin | 500 | Neg | Neg | Pos |
{5}
K192299 - Page 6 of 11
| Glucose | 3000 | Neg | Neg | Pos |
| --- | --- | --- | --- | --- |
| Hemoglobin | 300 | Neg | Neg | Pos |
| β-hydroxybutyric Acid | 100 | Neg | Neg | Pos |
| HAS | 500 | Neg | Neg | Pos |
| Oxalic Acid | 100 | Neg | Neg | Pos |
| Potassium Chloride | 6000 | Neg | Neg | Pos |
| Riboflavin | 0.3 | Neg | Neg | Pos |
| Urea | 6000 | Neg | Neg | Pos |
| Uric Acid | 10 | Neg | Neg | Pos |
| Sodium Azide | 1000 | Neg | Neg | Pos |
| Sodium Chloride | 6000 | Neg | Neg | Pos |
| Sodium Fluoride | 1000 | Neg | Neg | Pos |
| Sodium Phosphate | 300 | Neg | Neg | Pos |
| Endogenous Substance | Concentration Tested (ng/mL) | Spiked Cotinine Concentration | | |
| --- | --- | --- | --- | --- |
| | | 0 ng/mL | 100 ng/mL Control | 300 ng/mL Control |
| Boric Acid | 1000 | Neg | Neg | Neg |
| Citric Acid (pH 3) | 800 | Neg | Neg | Neg |
## pH Interference Study
Drug free urine and urine spiked with cotinine to the final cotinine concentration of either 150 ng/mL or 250 ng/mL (as negative or positive controls, ±25% cutoff concentration, respectively) were adjusted to the pH levels reported in the table below and tested by the assay. The pH adjusted solutions were evaluated against the cutoff calibrator. No major interference between pH 3 to pH 11. Results are summarized in the table below.
| pH | Spiked Cotinine Concentration | | |
| --- | --- | --- | --- |
| | 0 ng/mL | 150 ng/mL Control | 250 ng/mL Control |
| pH 3 | Neg | Neg | Pos |
| pH 4 | Neg | Neg | Pos |
| pH 5 | Neg | Neg | Pos |
| pH 6 | Neg | Neg | Pos |
| pH 7 | Neg | Neg | Pos |
| pH 8 | Neg | Neg | Pos |
| pH 9 | Neg | Neg | Pos |
| pH 10 | Neg | Neg | Pos |
| pH 11 | Neg | Neg | Pos |
## Specific Gravity Interference Study
Samples ranging in specific gravity from 1.005 to 1.028 were split into three portions each and either left un-spiked or further spiked to a final cotinine concentration of either 150 ng/mL or 250 ng/mL (as negative or positive controls, ±25% cutoff concentration, respectively). These samples were then evaluated in qualitative mode. No interference was observed at any specific gravity.
{6}
# Cross-Reactivity Study
The cross-reactivity of various potentially interfering drugs were tested by spiking various concentrations of each substance listed in the table below into drug free urine and then evaluating the sample against the assay. The results are summarized in the tables below.
Cotinine
| Compound | Target Concentration (ng/mL) | % Cross-reactivity |
| --- | --- | --- |
| (-)-Cotinine | 200 | 100.00% |
Cotinine Metabolites
| Compound | Target Concentration (ng/mL) | % Cross-reactivity |
| --- | --- | --- |
| (+)-Anabasine | 250,000 | 0.08% |
| S(-)-Nicotine | 25,000 | 0.80% |
| Nicotinic Acid (Niacin) | 100,000 | 0.20% |
| (-) Norcotinine | 1000 | 20.00% |
| (+) Norcotinine | 100,000 | 0.20% |
| (R, S)-Norcotinine | 850 | 23.53% |
| (±)-Nornicotine | 250,000 | 0.08% |
| trans-3'-hydroxycotinine | 10,000 | 2.00% |
Cross-reactivity of various potentially interfering drugs were tested by spiking 100,000 ng/mL (or as listed in the table below) of each substance into drug free urine. These solutions were then split into three portions; one without Cotinine, and two that were further spiked with Cotinine to a final Cotinine concentration of 150 ng/mL or 250 ng/mL (as negative or positive controls, ±25 % Cutoff Concentration, respectively). Samples were then evaluated with the assay. The results are as shown below.
Structurally Unrelated Pharmacological Compounds
| Cross-reactant | Spiked [ ] (ng/mL) | Spiked Cotinine Concentration | | |
| --- | --- | --- | --- | --- |
| | | 0 ng/mL | 150 ng/mL Control | 250 ng/mL Control |
| Acetaminophen | 100,000 | ND | Neg | Pos |
| 6-Acetylmorphine | 100,000 | ND | Neg | Pos |
| Amitriptyline | 100,000 | ND | Neg | Pos |
| Amlodipine Besylate | 100,000 | ND | Neg | Pos |
| Amoxicillin | 100,000 | ND | Neg | Pos |
| Azelastine | 100,000 | ND | Neg | Pos |
| d-Amphetamine | 100,000 | ND | Neg | Pos |
| Atorvastatin | 20,000 | ND | Neg | Pos |
| Benzoylecgonine | 100,000 | ND | Neg | Pos |
K192299 - Page 7 of 11
{7}
Structurally Unrelated Pharmacological Compounds, continued
| Cross-reactant | Spiked [ ] (ng/mL) | Spiked Cotinine Concentration | | |
| --- | --- | --- | --- | --- |
| | | 0 ng/mL | 150 ng/mL Control | 250 ng/mL Control |
| Loratidine | 100,000 | ND | Neg | Pos |
| MDA (3,4-methylenedioxyamphetamine) | 100,000 | ND | Neg | Pos |
| MDEA | 100,000 | ND | Neg | Pos |
| MDMA (3,4-methylenedioxymethamphetamine) | 100,000 | ND | Neg | Pos |
K192299 - Page 8 of 11
{8}
| Cross-reactant | Spiked [ ] (ng/mL) | Spiked Cotinine Concentration | | |
| --- | --- | --- | --- | --- |
| | | 0 ng/mL | 150 ng/mL Control | 250 ng/mL Control |
| Meperidine | 100,000 | ND | Neg | Pos |
| Metformin | 100,000 | ND | Neg | Pos |
| Methapyrilene | 100,000 | ND | Neg | Pos |
| Metoprolol | 100,000 | ND | Neg | Pos |
| Methadone | 100,000 | ND | Neg | Pos |
| d-Methamphetamine | 100,000 | ND | Neg | Pos |
| Morphine | 100,000 | ND | Neg | Pos |
| Nortriptyline | 100,000 | ND | Neg | Pos |
| Omeprazole | 100,000 | ND | Neg | Pos |
| Oxazepam | 100,000 | ND | Neg | Pos |
| Oxycodone | 100,000 | ND | Neg | Pos |
| Oxymorphone | 100,000 | ND | Neg | Pos |
| Phenobarbital | 100,000 | ND | Neg | Pos |
| Promethazine | 100,000 | ND | Neg | Pos |
| (1S,2S)-(+)Pseudoephedrine | 100,000 | ND | Neg | Pos |
| Quetiapine | 100,000 | ND | Neg | Pos |
| Ranitidine | 100,000 | ND | Neg | Pos |
| Salbutamol (Albuterol) | 100,000 | ND | Neg | Pos |
| Sertraline | 100,000 | ND | Neg | Pos |
| Terfenadine | 100,000 | ND | Neg | Pos |
| THC-COOH (11-Nor-Delta-9-THC-9-carboxylic acid) | 1,000 | ND | Neg | Pos |
| l-Thyroxine | 10,000 | ND | Neg | Pos |
| Tramadol | 100,000 | ND | Neg | Pos |
| Triprolidine | 100,000 | ND | Neg | Pos |
| Zolpidem | 10,000 | ND | Neg | Pos |
4. Assay Reportable Range:
Not Applicable.
5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
The device is traceable to certified Cerilliant Cotinine, verified by HPLC and GC/MS. Purity determination and gravimetric preparation using balances calibrated with NIST traceable weights ensured the accuracy of the stock standard solution.
6. Detection Limit:
See section VII.A.1 above
K192299 - Page 9 of 11
{9}
7. Assay Cut-Off:
See section VII.A.1 above
B Comparison Studies:
1. Method Comparison with Predicate Device
A total of one-hundred and four (104) unaltered clinical samples were tested with the LZI Cotinine II Enzyme Immunoassay on the AU480 automated clinical analyzer. Samples were evaluated against the assay's calibration curve in both qualitative and semi-quantitative modes. All samples were tested in singlet. All samples were confirmed with LC/MS for cotinine concentrations, and the accuracy of the assay to LC/MS is provided in the table below.
Semi-Quantitative Results
| Candidate Device Results 200 ng/mL Cutoff | Negati ve | < 50 % of 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) | % Agreement t |
| --- | --- | --- | --- | --- | --- | --- |
| Positive | 0 | 0 | 1* | 11 | 16 | 96.4 % |
| Negati ve | 20 | 32 | 23 | 1** | 0 | 98.7 % |
| Sample # | GC/MS Cotinine (ng/mL) | Pos/ Neg Result |
| --- | --- | --- |
| 57* | 128.6 | - |
| 78** | 204.2 | + |
Qualitative Results
| Candidate Device Results 200 ng/mL Cutoff | Negati ve | < 50 % of 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) | % Agreement t |
| --- | --- | --- | --- | --- | --- | --- |
| Positive | 0 | 0 | 1* | 11 | 16 | 96.4 % |
| Negati ve | 20 | 32 | 23 | 1** | 0 | 98.7 % |
K192299 - Page 10 of 11
{10}
| Sample # | GC/MS Cotinine (ng/mL) | Pos/ Neg Result |
| --- | --- | --- |
| 57* | 128.6 | - |
| 78** | 204.2 | + |
2. Matrix Comparison:
Not applicable.
C Clinical Studies:
Not Applicable.
D Clinical Cut-Off:
See section VII.A.1. above
E Expected Values/Reference Range:
Not Applicable.
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.
K192299 - Page 11 of 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.