AMEDICA DRUG SCREEN THC/COC, OP1300, PPX, OXY, BAR/BZO TEST
K040464 · Amedica Biotech, Inc. · LDJ · May 17, 2004 · Clinical Toxicology
Device Facts
Record ID
K040464
Device Name
AMEDICA DRUG SCREEN THC/COC, OP1300, PPX, OXY, BAR/BZO TEST
Applicant
Amedica Biotech, Inc.
Product Code
LDJ · Clinical Toxicology
Decision Date
May 17, 2004
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.3870
Device Class
Class 2
Indications for Use
The Amedica Drug Screen THC/COC, OPI300, PPX, OXY, BAR/BZO Test is an in vitro diagnostic test for the rapid detection of THC, benzoylecgonine, morphine, propoxyphene, oxycodone, secobarbital and oxazepam in human urine at the following cut-off concentration THC 11-nor-Δ⁹-THC-9-COOH 50 ng/ml COC benzoylecgonine 300 ng/ml OPI morphine 300 ng/ml PPY propoxyphene 300 ng/ml OXY oxycodone 100 ng/ml BAR secobarbital 300 ng/ml BZO oxazepam 300 ng/ml This test kit is used to obtain a visual, qualitative result and is intended for use in laboratories and workplaces by trained users. It is not intended for over the counter sale. For in vitro diagnostic use Minimum training for operators is defined as those individuals who have received instructions for drugs of abuse testing from a physician or medical review officer. Operators may be lay users with no prior experience in running laboratory tests, but who are expected to perform at least 5 tests per week. Training should cover a variety of topics such as the value of confirmation testing, how to obtain confirmation testing, false positive results, false negative results, and quality control procedures. The sponsor recommends that operators take a written and practical exam before performing any testing and that employers keep documentation of the testing.
Device Story
Lateral flow immunochromatographic assay; detects seven drugs of abuse in human urine. Input: urine sample applied to dipstick, cassette, or cup format. Principle: competitive binding between drug in sample and drug-labeled conjugate for antibody binding sites on nitrocellulose strip. Output: visual presence or absence of colored test line; internal process control line confirms sample volume and strip integrity. Used in laboratories and workplaces; operated by trained personnel. Results are preliminary; require confirmation via GC/MS. Affects clinical/workplace decision-making by identifying potential drug presence; benefits patient/employer by providing rapid screening.
Clinical Evidence
No clinical studies performed. Evidence consists of analytical performance data: precision/reproducibility studies (n=180 per concentration), analytical sensitivity (detection limits validated at cutoff), and method comparison studies against GC/MS and predicate devices. Method comparison included 74-115 samples per analyte group, showing high agreement (90-100%) with GC/MS and predicate results.
Technological Characteristics
Lateral flow immunochromatographic assay. Nitrocellulose strip in dipstick, cassette, or cup formats. Sensing principle: competitive antibody-antigen binding. Internal process control: goat anti-rabbit antibodies/rabbit antibody gold complex. Visual readout. No external energy source required. Single-use.
Indications for Use
Indicated for rapid, qualitative detection of THC, benzoylecgonine, morphine, propoxyphene, oxycodone, secobarbital, and oxazepam in human urine. Intended for use in laboratory and workplace settings by trained personnel. Not for OTC use.
Regulatory Classification
Identification
A cannabinoid test system is a device intended to measure any of the cannabinoids, hallucinogenic compounds endogenous to marihuana, in serum, plasma, saliva, and urine. Cannabinoid compounds include delta-9-tetrahydrocannabinol, cannabidiol, cannabinol, and cannabichromene. Measurements obtained by this device are used in the diagnosis and treatment of cannabinoid use or abuse and in monitoring levels of cannabinoids during clinical investigational use.
Special Controls
*Classification.* Class II (special controls). A cannabinoid 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).
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY DEVICE ONLY TEMPLATE
A. 510(k) Number:
K040464
B. Purpose for Submission:
New Device
C. Analytes:
THC (marijuana metabolite), benzoylecgonine, morphine, propoxyphene, oxycodone, secobarbital, and oxazepam
D. Type of Test:
Qualitative enzyme immunoassay
E. Applicant:
Amedica Biotech, Inc.
F. Proprietary and Established Names:
Amedica Drug Screen THC/COC, OPI300, PPX, OXY, BAR/BZO Test
G. Regulatory Information:
1. Regulation section:
21 CFR § 862.3870
21 CFR § 862.3250
21 CFR § 862.3650 (opiates)
21 CFR § 862.3700
21 CFR § 862.3650 (oxycodone)
21 CFR § 862.3150
21 CFR § 862.3170
2. Classification:
II
3. Product Code:
LDJ (Cannabinoid Test System)
DIO (Cocaine and Cocaine Metabolite Test System)
DJG (Opiate Test System)
JXN (Propoxyphene Test System)
DJG (Opiate Test System - oxycodone)
DIS (Barbiturate Test System)
JXM (Benzodiazepine Test System)
4. Panel:
{1}
Toxicology (91)
## H. Intended Use:
1. Intended use(s):
Refer to Indications for use.
2. Indication(s) for use:
The Amedica Drug Screen THC/COC, OPI300, PPX, OXY, BAR/BZO Test is an in vitro diagnostic test for the rapid detection of THC, benzoylecgonine, morphine, propoxyphene, oxycodone, secobarbital and oxazepam in human urine at the following cut-off concentration
| THC | 11-nor-Δ⁹-THC-9-COOH | 50 ng/ml |
| --- | --- | --- |
| COC | benzoylecgonine | 300 ng/ml |
| OPI | morphine | 300 ng/ml |
| PPY | propoxyphene | 300 ng/ml |
| OXY | oxycodone | 100 ng/ml |
| BAR | secobarbital | 300 ng/ml |
| BZO | oxazepam | 300 ng/ml |
This test kit is used to obtain a visual, qualitative result and is intended for use in laboratories and workplaces by trained users. It is not intended for over the counter sale. For in vitro diagnostic use
Minimum training for operators is defined as those individuals who have received instructions for drugs of abuse testing from a physician or medical review officer. Operators may be lay users with no prior experience in running laboratory tests, but who are expected to perform at least 5 tests per week. Training should cover a variety of topics such as the value of confirmation testing, how to obtain confirmation testing, false positive results, false negative results, and quality control procedures. The sponsor recommends that operators take a written and practical exam before performing any testing and that employers keep documentation of the training.
3. Special condition for use statement(s):
The Amedica Drug Screen THC/COC, OPI300, PPX, OXY, BAR/BZO Test provides only a preliminary analytical test result. A more specific alternative chemical method must be used to obtain a confirmed analytical result. Gas chromatography/Mass spectrometry is the preferred confirmatory method. Other chemical confirmation methods are available. Clinical consideration and professional judgment should be applied to any drug of abuse test result, particularly when preliminary positive results are used.
{2}
Page 3 of 27
Tests for barbiturates, benzodiazepines, and opiates cannot distinguish between abused drugs and certain prescribed medications.
Certain foods or medications may interfere with tests for opiates and cause false positive results.
4. Special instrument Requirements:
Not applicable. The device is a visually read single-use device.
I. Device Description:
The Amedica Drug Screen THC/COC, OPI300, PPX, OXY, BAR/BZO Test uses a nitrocellulose strip in a dip test, cassette (test card) test, and cup test formats. The only difference between the three strips is the length, where the dip test is 84 mm, the cassette test 59 mm, and the cup test 56 mm.
In the dipstick format, operators dip the test strip into the urine and the reaction is initiated by movement of the sample through the test strip.
In the cassette format, operators add several drops of the sample to the sample well. The test reaction is initiated by movement of the sample through the test strip.
In the cup format, test strips are incorporated into the sides of the test cup. Addition of the urine to the test cup brings the test strips in contact with the sample and the sample begins migrating up the test strip. The sponsor recommends a minimum urine volume of 30 mL.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Amedica Drug Screen THC Test
Amedica Drug Screen Cocaine Test
Rapid Opiates Test
Instant-View Propoxyphene Test
Branan Oxycodone Test
Amedica Drug Screen MDMA, BAR, BZO, MTD, TCA Test
2. Predicate K number(s):
k022955
k022954
k020716
k022915
k030113
k031497
{3}
# 3. Comparison with predicate:
When compared to the predicates, the candidate device is for the qualitative determination of the same seven analytes in the same matrix, and utilizes the same cutoff concentrations. All of the predicates and the candidate device are visually-read single use devices.
The reagent formulations vary between the predicates and the candidate device.
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Type of Test | Single-Use, Qualitative Immunochromatographic Assay | Same |
| Cutoffs | THC: 50 ng/mL Cocaine Metab: 300 ng/mL Opiates: 300 ng/mL Propox: 300 ng/mL Oxycod: 100 ng/mL Barb: 300 ng/mL Benz: 300 ng/mL | Same |
| Number of Analytes | THC Cocaine Metab Opiates Propox Oxycod | Predicate measures THC Only Predicate measures Cocaine Metab Only Predicate measures Opiates Only Predicate measures Propoxyphene Only Predicate measures Oxycodone Only |
| Differences | | |
| Item | Device | Predicate |
| Number of Analytes | Barbs plus six other analytes Benz plus six other analytes | Predicate measures only Barbs and Benzos Predicate measures only Barbs and Benzos |
| Test Formats | Dipstick, Cassette, and Cup | Dipstick and/or Cassette and/or Cup |
# K. Standard/Guidance Document Referenced (if applicable):
The sponsor referenced the following guidance document(s) in their submission:
Premarket Submission and Labeling Recommendations for Drugs of Abuse Screening Tests, published December 2003.
The sponsor indicated deviation from this guidance in regards to interference testing.
{4}
Page 5 of 27
L. Test Principle:
The test employs lateral flow immunochromatographic technology.
Drug in the sample and drug-labeled conjugate (containing a chromagen) compete for antibody binding sites in the test area of the test strip. Binding of drug in the sample causes the absence of a line at the test area, i.e., a positive result. When drug is not present in the sample, the drug-labeled conjugate binds at the test line, resulting in formation of a line, i.e., a negative result. The absence or presence of the line is determined visually by the operator.
The test region of the strips contains protein conjugated to THC, benzoylecgonine, morphine, propoxyphene, oxycodone, barbiturates, and benzodiazepines. The coated pad below the test region contains antibodies to THC, benzoylecgonine, morphine, propoxyphene, oxycodone, barbiturates, and benzodiazepines.
The device also has an internal process control which indicates that an adequate volume of sample has been added and that the immunochromatographic strip is intact. Goat anti-rabbit antibodies in the control region combine with a rabbit antibody gold complex to produce a colored product.
The user is instructed in the Package Insert that a very faint line in the test region is to be interpreted as a negative result.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
Samples used for the precision study consisted of drug free urine spiked with 11-nor-Δ⁹-THC-9-COOH, benzoylecgonine, morphine, propoxyphene, oxycodone, secobarbital, and oxazepam. The sponsor states that the drug concentration was confirmed by GC-MS by the vendor. The testing was done on-site in the sponsor's laboratory. Three operators, who are from the manufacturer's staff, performed the testing over 20 days using three lots of the assay. Two replicates were run per day.
{5}
Results of the study are presented below:
Cannabinoid (THC) Precision Study Results
| Concentration of sample, ng/mL | Number of determinations | Results # Neg/ #Pos |
| --- | --- | --- |
| 25 | 180 | 180/0 |
| 37.5 | 180 | 180/0 |
| 50 | 180 | 77/103 |
| 62.5 | 180 | 39/141 |
| 75 | 180 | 0/180 |
Cocaine Precision Study Results
| Concentration of sample, ng/mL | Number of determinations | Results # Neg/ #Pos |
| --- | --- | --- |
| 150 | 180 | 180/0 |
| 225 | 180 | 180/0 |
| 300 | 180 | 94/86 |
| 375 | 180 | 58/122 |
| 450 | 180 | 0/180 |
Opiates Precision Study Results
| Concentration of sample, ng/mL | Number of determinations | Results # Neg/ #Pos |
| --- | --- | --- |
| 150 | 180 | 180/0 |
| 225 | 180 | 180/0 |
| 300 | 180 | 94/86 |
| 375 | 180 | 53/127 |
| 450 | 180 | 0/180 |
Propoxyphene Precision Study Results
| Concentration of sample, ng/mL | Number of determinations | Results # Neg/ #Pos |
| --- | --- | --- |
| 150 | 180 | 180/0 |
| 225 | 180 | 180/0 |
| 300 | 180 | 94/86 |
| 375 | 180 | 55/125 |
| 450 | 180 | 0/180 |
{6}
Page 7 of 27
## Oxycodone Precision Study Results
| Concentration of sample, ng/mL | Number of determinations | Results # Neg/ #Pos |
| --- | --- | --- |
| 50 | 180 | 180/0 |
| 75 | 180 | 180/0 |
| 100 | 180 | 95/85 |
| 125 | 180 | 37/143 |
| 150 | 180 | 0/180 |
## Barbiturates Precision Study Results
| Concentration of sample, ng/mL | Number of determinations | Results # Neg/ #Pos |
| --- | --- | --- |
| 150 | 180 | 180/0 |
| 225 | 180 | 180/0 |
| 300 | 180 | 101/79 |
| 375 | 180 | 57/123 |
| 450 | 180 | 0/180 |
## Benzodiazepines Precision Study Results
| Concentration of sample, ng/mL | Number of determinations | Results # Neg/ #Pos |
| --- | --- | --- |
| 150 | 180 | 180/0 |
| 225 | 180 | 180/0 |
| 300 | 180 | 112/68 |
| 375 | 180 | 57/123 |
| 450 | 180 | 0/180 |
The sponsor also provided precision data collected at three workplace sites in order to support a workplace claim. A different operator collected the data at each site and each operator completed the study in one day. Combined results were as follows:
## Cannabinoid (THC) Precision Study Results
| Concentration of sample, ng/mL | Number of determinations | Results # Neg/ #Pos |
| --- | --- | --- |
| 25 | 30 (10 per site) | 28/2 |
| 37.5 | 30 (10 per site) | 23/7 |
| 50 | 30 (10 per site) | 18/12 |
| 62.5 | 30 (10 per site) | 4/26 |
| 75 | 30 (10 per site) | 0/30 |
{7}
Page 8 of 27
## Cocaine Precision Study Results
| Concentration of sample, ng/mL | Number of determinations | Results # Neg/ #Pos |
| --- | --- | --- |
| 150 | 30 (10 per site) | 29/1 |
| 225 | 30 (10 per site) | 21/9 |
| 300 | 30 (10 per site) | 19/11 |
| 375 | 30 (10 per site) | 6/24 |
| 450 | 30 (10 per site) | 0/30 |
## Opiates Precision Study Results
| Concentration of sample, ng/mL | Number of determinations | Results # Neg/ #Pos |
| --- | --- | --- |
| 150 | 30 (10 per site) | 30/0 |
| 225 | 30 (10 per site) | 23/7 |
| 300 | 30 (10 per site) | 22/8 |
| 375 | 30 (10 per site) | 5/25 |
| 450 | 30 (10 per site) | 0/30 |
## Propoxyphene Precision Study Results
| Concentration of sample, ng/mL | Number of determinations | Results # Neg/ #Pos |
| --- | --- | --- |
| 150 | 30 (10 per site) | 30/0 |
| 225 | 30 (10 per site) | 25/5 |
| 300 | 30 (10 per site) | 24/8 |
| 375 | 30 (10 per site) | 6/24 |
| 450 | 30 (10 per site) | 0/30 |
## Oxycodone Precision Study Results
| Concentration of sample, ng/mL | Number of determinations | Results # Neg/ #Pos |
| --- | --- | --- |
| 50 | 30 (10 per site) | 30/0 |
| 75 | 30 (10 per site) | 26/4 |
| 100 | 30 (10 per site) | 24/6 |
| 125 | 30 (10 per site) | 2/28 |
| 150 | 30 (10 per site) | 0/30 |
{8}
Page 9 of 27
Barbiturates Precision Study Results
| Concentration of sample, ng/mL | Number of determinations | Results # Neg/ #Pos |
| --- | --- | --- |
| 150 | 30 (10 per site) | 30/0 |
| 225 | 30 (10 per site) | 28/2 |
| 300 | 30 (10 per site) | 29/1 |
| 375 | 30 (10 per site) | 6/24 |
| 450 | 30 (10 per site) | 3/27 |
Benzodiazepines Precision Study Results
| Concentration of sample, ng/mL | Number of determinations | Results # Neg/ #Pos |
| --- | --- | --- |
| 150 | 30 (10 per site) | 30/0 |
| 225 | 30 (10 per site) | 21/9 |
| 300 | 30 (10 per site) | 24/6 |
| 375 | 30 (10 per site) | 5/25 |
| 450 | 30 (10 per site) | 0/30 |
b. Linearity/assay reportable range:
Not applicable. The assay is intended for qualitative use.
c. Traceability (controls, calibrators, or method):
Control materials are required but are not specifically identified in the labeling.
The device has an internal process control which indicates that an adequate volume of sample has been added and that the immunochromatographic strip is intact. Users are instructed to follow federal, state, and local guidelines when determining when to run external controls.
{9}
# d. Detection limit:
Sensitivity of this assay is characterized by validating performance around the claimed cutoff concentration of the assay, including a determination of the lowest concentration of drug that is capable of producing a positive result.
To determine the analytical sensitivity, 25 replicates were run at drug concentrations from negative to 3X cutoff. NOTE: for the purposes of this experiment, a very faint line in the test region was interpreted as a borderline result near the cutoff. The user is instructed in the Package Insert that a very faint line in the test region is to be interpreted as negative when testing clinical samples.
| THC Conc. (ng/ml) | # Tested | # Negative | # Cut-Off (borderline) | # Positive |
| --- | --- | --- | --- | --- |
| 0 | 25 | 25 | 0 | 0 |
| 25 | 25 | 25 | 0 | 0 |
| 37.5 | 25 | 10 | 15 | 0 |
| 50 | 25 | 0 | 13 | 12 |
| 62.5 | 25 | 0 | 5 | 20 |
| 75 | 25 | 0 | 0 | 25 |
| 150 | 25 | 0 | 0 | 25 |
{10}
| COC Conc. (ng/ml) | # Tested | # Negative | # Cut-Off (borderline) | # Positive |
| --- | --- | --- | --- | --- |
| 0 | 25 | 25 | 0 | 0 |
| 150 | 25 | 25 | 0 | 0 |
| 225 | 25 | 9 | 16 | 0 |
| 300 | 25 | 0 | 14 | 11 |
| 375 | 25 | 0 | 8 | 17 |
| 450 | 25 | 0 | 0 | 25 |
| 900 | 25 | 0 | 0 | 25 |
| OPI Conc. (ng/ml) | # Tested | # Negative | # Cut-Off (borderline) | # Positive |
| --- | --- | --- | --- | --- |
| 0 | 25 | 25 | 0 | 0 |
| 150 | 25 | 25 | 0 | 0 |
| 225 | 25 | 12 | 13 | 0 |
| 300 | 25 | 0 | 14 | 11 |
| 375 | 25 | 0 | 7 | 18 |
| 450 | 25 | 0 | 0 | 25 |
| 900 | 25 | 0 | 0 | 25 |
| PPY Conc. (ng/ml) | # Tested | # Negative | # Cut-Off (borderline) | # Positive |
| --- | --- | --- | --- | --- |
| 0 | 25 | 25 | 0 | 0 |
| 150 | 25 | 25 | 0 | 0 |
| 225 | 25 | 11 | 14 | 0 |
| 300 | 25 | 0 | 15 | 10 |
| 375 | 25 | 0 | 5 | 20 |
| 450 | 25 | 0 | 0 | 25 |
| 900 | 25 | 0 | 0 | 25 |
{11}
| BAR Conc. (ng/ml) | # Tested | # Negative | # Cut-Off (borderline) | # Positive |
| --- | --- | --- | --- | --- |
| 0 | 25 | 25 | 0 | 0 |
| 50 | 25 | 25 | 0 | 0 |
| 75 | 25 | 9 | 16 | 0 |
| 100 | 25 | 0 | 10 | 15 |
| 125 | 25 | 0 | 8 | 17 |
| 150 | 25 | 0 | 0 | 25 |
| 300 | 25 | 0 | 0 | 25 |
| BZO Conc. (ng/ml) | # Tested | # Negative | # Cut-Off (borderline) | # Positive |
| --- | --- | --- | --- | --- |
| 0 | 25 | 25 | 0 | 0 |
| 150 | 25 | 25 | 0 | 0 |
| 225 | 25 | 8 | 17 | 0 |
| 300 | 25 | 0 | 14 | 11 |
| 375 | 25 | 0 | 9 | 16 |
| 450 | 25 | 0 | 0 | 25 |
| 900 | 25 | 0 | 0 | 25 |
| BZO Conc. (ng/ml) | # Tested | # Negative | # Cut-Off (borderline) | # Positive |
| --- | --- | --- | --- | --- |
| 0 | 25 | 25 | 0 | 0 |
| 150 | 25 | 25 | 0 | 0 |
| 225 | 25 | 9 | 16 | 0 |
| 300 | 25 | 0 | 14 | 11 |
| 375 | 25 | 0 | 8 | 17 |
| 450 | 25 | 0 | 0 | 25 |
{12}
Page 13 of 27
| 900 | 25 | 0 | 0 | 25 |
| --- | --- | --- | --- | --- |
Based on this data, the sensitivity of the assay to the seven analytes is as follows:
THC: 50 ng/ml
COC: 300 ng/ml
OPI: 300 ng/ml
PPY: 300 ng/ml
OXY: 100 ng/ml
BAR: 300 ng/ml
BZO: 300 ng/ml
{13}
Page 14 of 27
e. Analytical specificity:
Cross-reactivity was established by spiking various concentrations of similarly structured drug compounds into drug-free urine /a negative control. By analyzing various concentration of each compound the sponsor determined the concentration of the drug that produced a response approximately equivalent to the cutoff concentration of the assay. Results of those studies appear in the table(s) below:
Cannabinoids (THC)
| Compound | Response equivalent to cutoff in ng/mL |
| --- | --- |
| 11-Hydroxy-Δ⁹-Tetrahydrocannabinol | 2,500 |
| 11-Nor-Δ⁸-Tetrahydrocannabinol carboxylic acid | 50 |
| 11-Nor-Δ⁹-Tetrahydrocannabinol carboxylic acid | 50 |
| Δ⁸-Tetrahydrocannabinol | 8,000 |
| Δ⁹-Tetrahydrocannabinol | 10,000 |
| Cannabinol | 10,000 |
| Cannabidiol | 100,000 |
Cocaine
| Compound | Response equivalent to cutoff in ng/mL |
| --- | --- |
| Benzoylecogonine | 300 |
| Cocaine | 50,000 |
| Ecgonine | >100,000 |
| Ecgonine Methyl Ester | >100,000 |
Opiates
| Drug compound | Response equivalent to cutoff in ng/mL |
| --- | --- |
| 6-monoacetylmorphine | 300 |
| Codeine | 300 |
| Hydrocodone | 3,000 |
| Hydromorphone | 3,000 |
| Morphine | 300 |
| Ethylmorphine | 2,000 |
Propoxyphene
| Drug compound | Response equivalent to cutoff in ng/mL |
| --- | --- |
| Propoxyphene | 300 |
| Norpropoxyphene | 20,000 |
{14}
Page 15 of 27
## Oxycodone
| Drug compound | Response equivalent to cutoff in ng/mL |
| --- | --- |
| Oxycodone | 100 |
| Oxymorphone | 80,000 |
## Barbiturates
| Compound | Response equivalent to cutoff in ng/mL |
| --- | --- |
| Secobarbital | 300 |
| Phenobarbital | 300 |
| Butalbital | 3000 |
| Pentobarbital | 400 |
| Alphenal | 400 |
| Amobarbital | 2000 |
| Aprobarbital | 300 |
| Barbital | 300 |
| Butabarbital | 300 |
## Benzodiazepines
| Compound | Response equivalent to cutoff in ng/mL |
| --- | --- |
| Alprazolam | 200 |
| Chlordiazepoxide | 500 |
| Diazepam | 300 |
| Oxazepam | 300 |
| Clonazepam | 50,000 |
| Flunitrazepam | 1500 |
| Nitrazepam | 20,000 |
| Bromazepam | 1500 |
| Clobazam | 400 |
| Estazolam | 500 |
| Flurazepam | 1000 |
| Lorazepam | 3000 |
| Lometazepam | 10,000 |
| Medazepam | 50,000 |
| Nordiazepam | 400 |
| Prazepam | 5000 |
| Temazepam | 3000 |
| Triazolam | 50,000 |
{15}
The following compounds were evaluated for potential positive and/or negative interference with the assay.
The compounds were dissolved in $50\%$ cutoff samples to the concentration of $100~\mathrm{ug / ml}$ to evaluate any positive interference effects. An unaltered sample was used as a control. Results are listed below
| Compound | THC | COC | OPI | PPX | OXY | BAR | BZO |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Control | - | - | - | - | - | - | - |
| Acetaminophen | - | - | - | - | - | - | - |
| Acetone | - | - | - | - | - | - | - |
| Albumin | - | - | - | - | - | - | - |
| Ampicillin | - | - | - | - | - | - | - |
| Amitriptyline | - | - | - | - | - | - | - |
| Aspartame | - | - | - | - | - | - | - |
| Aspirin | - | - | - | - | - | - | - |
| Atropine | - | - | - | - | - | - | - |
| Benzocaine | - | - | - | - | - | - | - |
| Bilirubin | - | - | - | - | - | - | - |
| Caffeine | - | - | - | - | - | - | - |
| Chloroquine | - | - | - | - | - | - | - |
| Chlorpheniramine | - | - | - | - | - | - | - |
| Creatine | - | - | - | - | - | - | - |
| Dexbrompheniramine | - | - | - | - | - | - | - |
| Dextromethorphan | - | - | - | - | - | - | - |
| 4-Dimethylamino antipyrine | - | - | - | - | - | - | - |
| Dopamine | - | - | - | - | - | - | - |
| (+/-)-Ephedrine | - | - | - | - | - | - | - |
| Erythromycin | - | - | - | - | - | - | - |
| Ethanol | - | - | - | - | - | - | - |
| Furosemide | - | - | - | - | - | - | - |
| Guaiacol Glyceryl Ether | - | - | - | - | - | - | - |
| Glucose | - | - | - | - | - | - | - |
| Hemoglobin | - | - | - | - | - | - | - |
| Isoproterenol | - | - | - | - | - | - | - |
| Lidocaine | - | - | - | - | - | - | - |
| Methylphenidate | - | - | - | - | - | - | - |
| N-Methyl-Ephedrine | - | - | - | - | - | - | - |
| (+)-Naproxen | - | - | - | - | - | - | - |
| Oxalic acid | - | - | - | - | - | - | - |
| Penicillin-G | - | - | - | - | - | - | - |
| Pheniramine | - | - | - | - | - | - | - |
| Phenothiazine | - | - | - | - | - | - | - |
| L-Phenylephrine | - | - | - | - | - | - | - |
| β-phenylethylamine | - | - | - | - | - | - | - |
| Procaine | - | - | - | - | - | - | - |
| Quinidine | - | - | - | - | - | - | - |
| Ranitidine | - | - | - | - | - | - | - |
| Sodium Chloride | - | - | - | - | - | - | - |
{16}
The compounds were dissolved in $150\%$ cutoff samples to the concentration of $100~\mathrm{ug / ml}$ to evaluate any negative interference effects. An unaltered sample was used as a control. Results are listed below
| Compound | THC | COC | OPI | PPX | OXY | BAR | BZO |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Control | + | + | + | + | + | + | + |
| Acetaminophen | + | + | + | + | + | + | + |
| Acetone | + | + | + | + | + | + | + |
| Albumin | + | + | + | + | + | + | + |
| Ampicillin | + | + | + | + | + | + | + |
| Amitriptyline | + | + | + | + | + | + | + |
| Aspartame | + | + | + | + | + | + | + |
| Aspirin | + | + | + | + | + | + | + |
| Atropine | + | + | + | + | + | + | + |
| Benzocaine | + | + | + | + | + | + | + |
| Bilirubin | + | + | + | + | + | + | + |
| Caffeine | + | + | + | + | + | + | + |
| Chloroquine | + | + | + | + | + | + | + |
| Chlorpheniramine | + | + | + | + | + | + | + |
| Creatine | + | + | + | + | + | + | + |
| Dexbrompheniramine | + | + | + | + | + | + | + |
| Dextromethorphan | + | + | + | + | + | + | + |
| 4+Dimethylamino antipyrine | + | + | + | + | + | + | + |
| Dopamine | + | + | + | + | + | + | + |
| (+/+) +Ephedrine | + | + | + | + | + | + | + |
| Erythromycin | + | + | + | + | + | + | + |
| Ethanol | + | + | + | + | + | + | + |
| Furosemide | + | + | + | + | + | + | + |
| Guaiacol Glyceryl Ether | + | + | + | + | + | + | + |
| Glucose | + | + | + | + | + | + | + |
| Hemoglobin | + | + | + | + | + | + | + |
| Isoproterenol | + | + | + | + | + | + | + |
| Lidocaine | + | + | + | + | + | + | + |
| Methylphenidate | + | + | + | + | + | + | + |
| N+Methyl+Ephedrine | + | + | + | + | + | + | + |
| (+) +Naproxen | + | + | + | + | + | + | + |
| Oxalic acid | + | + | + | + | + | + | + |
| Penicillin+G | + | + | + | + | + | + | + |
| Pheniramine | + | + | + | + | + | + | + |
| Phenothiazine | + | + | + | + | + | + | + |
| L+Phenylephrine | + | + | + | + | + | + | + |
| β+phenylethylamine | + | + | + | + | + | + | + |
{17}
Page 18 of 27
| Procaine | + | + | + | + | + | + | + |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Quinidine | + | + | + | + | + | + | + |
| Ranitidine | + | + | + | + | + | + | + |
| Sodium Chloride | + | + | + | + | + | + | + |
| Sulindac | + | + | + | + | + | + | + |
| Thioridazine | + | + | + | + | + | + | + |
| Trifluoperazine | + | + | + | + | + | + | + |
| Tyramine | + | + | + | + | + | + | + |
| Vitamin C | + | + | + | + | + | + | + |
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.
To test for potential positive/and or negative interference from endogenous conditions the following studies were performed:
To evaluate any possible positive interference of pH, acid or base was added to 50% cutoff samples to obtain samples with pH values from 3 to 9. An unaltered sample was used as a control. Results were as follows.
| pH | THC | COC | OPI | PPX | OXY | BAR | BZO |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 7 (Control) | - | - | - | - | - | - | - |
| 3 | - | - | - | - | - | - | - |
| 4.5 | - | - | - | - | - | - | - |
| 5.5 | - | - | - | - | - | - | - |
| 8 | - | - | - | - | - | - | - |
| 9 | - | - | - | - | - | - | - |
To evaluate any possible negative interference of pH, acid or base was added to 150% cutoff samples to obtain samples with pH values from 3 to 9. An unaltered sample was used as a control. Results were as follows.
| pH | THC | COC | OPI | PPX | OXY | BAR | BZO |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 7 (Control) | + | + | + | + | + | + | + |
| 3 | - | - | - | - | - | - | - |
| 4.5 | + | + | + | + | + | + | + |
| 5.5 | + | + | + | + | + | + | + |
| 8 | + | + | + | + | + | + | + |
| 9 | + | + | + | + | + | + | + |
{18}
To evaluate any possible positive interference of specific gravity, distilled water or sodium chloride was added to $50\%$ cutoff sample to obtain samples with specific gravity values from 1.002 to 1.03. An unaltered sample was used as a control. Results were as follows.
| Specific gravity | THC | COC | OPI | PPX | OXY | BAR | BZO |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 1.01 (Control) | - | - | - | - | - | - | - |
| 1.002 | - | - | - | - | - | - | - |
| 1.02 | - | - | - | - | - | - | - |
| 1.03 | - | - | - | - | - | - | - |
To evaluate any possible negative interference of specific gravity, distilled water or sodium chloride was added to $150\%$ cutoff sample to obtain samples with specific gravity values from 1.002 to 1.03. An unaltered sample was used as a control. Results were as follows.
| Specific gravity | THC | COC | OPI | PPX | OXY | BAR | BZO |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 1.01 (Control) | + | + | + | + | + | + | + |
| 1.002 | + | + | + | + | + | + | + |
| 1.02 | + | + | + | + | + | + | + |
| 1.03 | + | + | + | + | + | + | + |
The sponsor did not evaluate the effects of albumin on the assay.
# f. Assay cut-off:
The identified cutoff concentration of the assays for THC and cocaine metabolite are recommended for use by the Substance Abuse and Mental Health Services Administration (SAMHSA). The cutoff chosen for the opiates assay is different than that recommended by SAMHSA. No recommendations have been made by SAMHSA for propoxyphene, oxycodone, barbiturates, or benzodiazepines.
Characterization of how the device performs analytically around the claimed cutoff concentration appears in the precision and sensitivity sections, above.
{19}
Page 20 of 27
2. Comparison studies:
a. Method comparison with predicate device:
Forty presumed negative samples were collected from volunteer donors at the sponsor’s facility and tested for all seven analytes by the candidate device and the predicate devices. All forty samples were negative for all analytes using the candidate device and the predicate devices. In a separate study, seven drug groups were evaluated by the candidate device, GC/MS and the predicate devices. The groups consisted of the following:
THC group: 95 samples (21 neg, 74 pos)
COC group: 86 samples (22 neg, 64 pos)
OPIA group: 101 samples (31 neg, 70 pos)
PPX group: 115 samples (31 neg, 84 pos)
OXY group: 74 samples (21 neg, 53 pos)
BAR group: 83 samples (21 neg, 62 pos)
BZO group: 79 samples (37 neg, 42 pos)
Sample description: Unaltered clinical urine samples were evaluated. An additional 267 diluted samples were also included in the study. The samples were prepared by diluting clinical samples with high drug concentrations with drug-free urine. This was done in order to obtain samples near the cutoff concentration of the assay, because the sponsor was not able to obtain unaltered samples near the cutoff.
{20}
Page 21 of 27
Samples previously analyzed by GC-MS were selected to be analyzed by the candidate device and the predicate. Results were grouped according to GC-MS concentration. NOTE: the sponsor states that samples were run in duplicate on the candidate device. If there was a discrepancy between the two results the sample was run a third time in order to obtain the final result. The number of times where a third result was required is as follows:
THC group: 1/95 samples with GC-MS concentration of 54 ng/mL
COC group: 2/86 samples with GC-MS concentrations of 305 and 313 ng/mL
OPIA group: none
PPX group: 1/115 samples with GC-MS concentration of 284 ng/mL
OXY group: none
BAR group: none
BZO group: none
In three of the four cases where a third replicate was run, the final result reported was in agreement with the GC-MS concentration.
The study included an adequate number of samples that contained drugs near to the cutoff concentration of the assay. More than 10% of the study samples are evenly distributed between plus and minus 50% of the claimed cutoff concentration for all analytes.
The study was performed at the manufacturer's facility by one member of the manufacturer's staff.
Candidate Device Results vs. Predicate Device Results - THC
| | Positive by Predicate Device | Negative by Predicate Device |
| --- | --- | --- |
| Positive by Candidate Device | 71 | 0 |
| Negative by Candidate Device | 1 | 63 |
% Agreement among positives is 100%
% Agreement among negatives is 98%
{21}
Page 22 of 27
Candidate Device Results vs. stratified GC/MS Values - THC
| Candidate Device Results | 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 | 1 | 8 | 63 |
| Negative | 12 | 9 | 2 | 0 |
GC/MS values used to categorize samples in this table are based on the concentration of THC found in the sample.
% Agreement among positives is 97%
% Agreement among negatives is 95%
NOTE: one sample was run in triplicate to obtain a final result
Candidate Device Results vs. Predicate Device Results - COC
| | Positive by Predicate Device | Negative by Predicate Device |
| --- | --- | --- |
| Positive by Candidate Device | 64 | 1 |
| Negative by Candidate Device | 0 | 61 |
% Agreement among positives is 98%
% Agreement among negatives is 100%
{22}
Page 23 of 27
# Candidate Device Results vs. stratified GC/MS Values - COC
| Candidate Device Results | 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 | 2 | 8 | 54 |
| Negative | 11 | 9 | 1 | 0 |
GC/MS values used to categorize samples in this table are based on the concentration of BE found in the sample.
% Agreement among positives is 98%
% Agreement among negatives is 91%
NOTE: two samples were run in triplicate to obtain a final result
# Candidate Device Results vs. Predicate Device Results - OP
| | Positive by Predicate Device | Negative by Predicate Device |
| --- | --- | --- |
| Positive by Candidate Device | 69 | 1 |
| Negative by Candidate Device | 1 | 70 |
% Agreement among positives is 99%
% Agreement among negatives is 99%
# Candidate Device Results vs. stratified GC/MS Values - OP
| Candidate Device Results | 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 | 2 | 9 | 59 |
| Negative | 15 | 14 | 2 | 0 |
GC/MS values used to categorize samples in this table are determined by adding together codeine and morphine values.
% Agreement among positives is 97%
% Agreement among negatives is 94%
{23}
Page 24 of 27
# Candidate Device Results vs. Predicate Device Results - PPX
| | Positive by Predicate Device | Negative by Predicate Device |
| --- | --- | --- |
| Positive by Candidate Device | 81 | 2 |
| Negative by Candidate Device | 4 | 68 |
% Agreement among positives is 98%
% Agreement among negatives is 94%
# Candidate Device Results vs. stratified GC/MS Values - PPX
| Candidate Device Results | 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 | 2 | 7 | 74 |
| Negative | 20 | 9 | 3 | 0 |
GC/MS values used to categorize samples in this table are based on the concentration of propoxyphene found in the sample.
% Agreement among positives is 96%
% Agreement among negatives is 94%
NOTE: one sample was run in triplicate to obtain a final result
# Candidate Device Results vs. Predicate Device Results - OXY
| | Positive by Predicate Device | Negative by Predicate Device |
| --- | --- | --- |
| Positive by Candidate Device | 52 | 1 |
| Negative by Candidate Device | 2 | 59 |
% Agreement among positives is 98%
% Agreement among negatives is 97%
{24}
Page 25 of 27
# Candidate Device Results vs. stratified GC/MS Values - OXY
| Candidate Device Results | 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 | 2 | 8 | 43 |
| Negative | 11 | 8 | 2 | 0 |
GC/MS values used to categorize samples in this table are based on the concentration of oxycodone found in the sample.
% Agreement among positives is 96%
% Agreement among negatives is 90%
# Candidate Device Results vs. Predicate Device Results - BAR
| | Positive by Predicate Device | Negative by Predicate Device |
| --- | --- | --- |
| Positive by Candidate Device | 62 | 1 |
| Negative by Candidate Device | 1 | 59 |
% Agreement among positives is 98%
% Agreement among negatives is 98%
# Candidate Device Results vs. stratified GC/MS Values - BAR
| Candidate Device Results | 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 | 2 | 10 | 51 |
| Negative | 10 | 9 | 1 | 0 |
GC/MS values used to categorize samples in this table are based on the concentration of butabarbital found in the sample.
% Agreement among positives is 98%
% Agreement among negatives is 90%
{25}
Page 26 of 27
# Candidate Device Results vs. Predicate Device Results - BZO
| | Positive by Predicate Device | Negative by Predicate Device |
| --- | --- | --- |
| Positive by Candidate Device | 44 | 0 |
| Negative by Candidate Device | 0 | 75 |
% Agreement among positives is 100%
% Agreement among negatives is 100%
# Candidate Device Results vs. stratified GC/MS Values - BZO
| Candidate Device Results | 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 | 3 | 9 | 32 |
| Negative | 25 | 9 | 1 | 0 |
GC/MS values used to categorize samples in this table are based on the concentration of oxazepam found in the sample.
% Agreement among positives is 98%
% Agreement among negatives is 92%
b. Matrix comparison:
Not applicable. The assay is intended for only one sample matrix.
3. Clinical studies:
a. Clinical sensitivity:
Not applicable. Clinical studies are not typically submitted for this device type.
b. Clinical specificity:
Not applicable. Clinical studies are not typically submitted for this device type.
c. Other clinical supportive data (when a and b are not applicable):
4. Clinical cut-off:
Not applicable.
5. Expected values/Reference range:
Not applicable.
{26}
Page 27 of 27
N. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
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.