PROFILE-V MEDTOXSCAN DRUGS OF ABUSE TEST SYSTEM AND 12 DRUGS TEST SYSTEM
Applicant
Medtox Diagnostics, Inc.
Product Code
DJG · Clinical Toxicology
Decision Date
Apr 5, 2010
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.3650
Device Class
Class 2
Attributes
Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K100023 · Apr 5, 2010
PROFILE-V MEDTOXSCAN DRUGS OF ABUSE TEST SYSTEM AND 12 DRUGS TEST SYSTEM
Medtox Diagnostics, Inc.
Clinical urine samples from MEDTOX Laboratories
The sponsor used a panel of clinical urine samples to evaluate the accuracy of the device by comparing test results against GC/MS or LC/MS/MS reference methods.
Accuracy study; Clinical urine samples; Retrospective clinical data
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Accuracy study of PROFILE-V MEDTOXScan Drugs of Abuse Test System; Retrospective accuracy evaluation using clinical samples
Clinical urine samples; Sample Size: Not explicitly stated (total count of samples across categories); Number of Sites: 1 (MEDTOX Laboratories)
GC/MS or LC/MS/MS
Accuracy (percent agreement) compared to reference methods
Indications for Use
The PROFILE®-V MEDTOXScan® Drugs of Abuse Test System consists of the PROFILE®-V MEDTOXScan® Test Devices and the MEDTOXScan® Reader. The PROFILE®-V MEDTOX Scan® Test Devices are one-step immunochromatographic tests for the rapid, qualitative detection of one or more of the following in human urine: Amphetamines, Barbiturates, Benzodiazepines, Buprenorphine, Cocaine, Methamphetamine, Opiates, Oxycodone, Phencyclidine, Propoxyphene, THC (Cannabinoids), and Tricyclic Antidepressants or their metabolites. The PROFILE®-V MEDTOXScan® Test Devices can only be used with the MEDTOXScan® Reader. The MEDTOX Scan® Reader is an instrument used to interpret and report the results of the PROFILE®-V MEDTOXScan® Test Device. PROFILE®-V MEDTOXScan® Test Devices cannot be visually read. The PROFILE®-V MEDTOXScan® Drugs of Abuse Test System is for in vitro diagnostic use and is intended for professional use only. It is not intended for use in point-of-care settings.
Device Story
System comprises single-use immunochromatographic test cassettes and MEDTOXScan® Reader. Urine sample applied to cassette; membrane strip contains drug-conjugates and antibody-colloidal gold. Reader uses contact imaging sensor (CIS) to scan test lines; software interprets line presence/absence to determine qualitative positive/negative results. Used by professionals in clinical settings; not for point-of-care. Output provided via LCD screen or printout. Provides preliminary analytical results; requires confirmatory testing (GC/MS, HPLC, or LC/MS/MS) for clinical decision-making. Benefits include rapid screening for multiple drug classes.
Clinical Evidence
No clinical studies performed. Performance validated via method comparison study using 172 unaltered clinical urine samples compared against GC/MS or LC/MS/MS reference methods. Precision evaluated with 45 replicates per concentration level across 3 readers and 8 operators. Analytical specificity, cross-reactivity, and interference (pH, specific gravity, common drugs) were assessed via bench testing.
Technological Characteristics
Single-use immunochromatographic lateral flow test cassettes; gold-conjugated reagents. Reader utilizes contact imaging sensor (CIS) for optical signal detection. System includes QC and cleaning cassettes for sensor maintenance. Software-based interpretation of line intensity. Standalone instrument with display and printout capability.
Indications for Use
Indicated for professional, in vitro diagnostic use in clinical settings (not point-of-care) for the rapid, qualitative detection of drugs of abuse or their metabolites in human urine. Target analytes include Amphetamines, Barbiturates, Benzodiazepines, Buprenorphine, Cocaine, Methadone, Methamphetamine, Opiates, Oxycodone, Phencyclidine, Propoxyphene, THC, and Tricyclic Antidepressants. Results are preliminary; confirmatory testing via GC/MS, HPLC, or LC/MS/MS is required.
Regulatory Classification
Identification
An opiate test system is a device intended to measure any of the addictive narcotic pain-relieving opiate drugs in blood, serum, urine, gastric contents, and saliva. An opiate is any natural or synthetic drug that has morphine-like pharmocological actions. The opiates include drugs such as morphine, morphine glucoronide, heroin, codeine, nalorphine, and meperedine. Measurements obtained by this device are used in the diagnosis and treatment of opiate use or overdose and in monitoring the levels of opiate administration to ensure appropriate therapy.
Special Controls
*Classification.* Class II (special controls). An opiate 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
PROFILE®-V MEDTOXScan® Drugs of Abuse Test System (K091454)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k100023
B. Purpose for Submission:
Addition of 2 new drugs of abuse tests (buprenorphine and opiates 2000) to an already cleared reader (MEDTOXScan® Reader, k080635). Amphetamines, Barbiturates, Benzodiazepines, Cocaine, Methadone, Methamphetamine, Opiates 100, Oxycodone, Phencyclidine, Propoxyphene, THC and Tricyclics antidepressants assays were previously cleared on the reader.
C. Measurand:
Buprenorphine and Opiates 2000
D. Type of Test:
Qualitative immunochromatographic test for drugs of abuse in urine performed on a reader.
E. Applicant:
Medtox Diagnostics, Inc.
F. Proprietary and Established Names:
PROFILE®-V MEDTOXScan®
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| DJG – Opiate Test System | II | 862.3650 | 91- Toxicology |
H. Intended Use:
1. Intended use(s):
See indications for use below.
{1}
2
2. Indication(s) for use:
The PROFILE®-V MEDTOXScan® Drugs of Abuse Test System consists of the PROFILE®-V MEDTOXScan® Test Devices and the MEDTOXScan® Reader. The PROFILE®-V MEDTOX Scan® Test Devices are one-step immunochromatographic tests for the rapid, qualitative detection of one or more of the following in human urine: Amphetamines, Barbiturates, Benzodiazepines, Buprenorphine, Cocaine, Methadone, Methamphetamine, Opiates, Oxycodone, Phencyclidine, Propoxyphene, THC (Cannabinoids), and Tricyclic Antidepressants or their metabolites. The PROFILE®-V MEDTOXScan® Test Devices can only be used with the MEDTOXScan® Reader. The MEDTOX Scan® Reader is an instrument used to interpret and report the results of the PROFILE®-V MEDTOXScan® Test Device. PROFILE®-V MEDTOXScan® Test Devices cannot be visually read. The PROFILE®-V MEDTOXScan® Drugs of Abuse Test System is for in vitro diagnostic use and is intended for professional use only. It is not intended for use in point-of-care settings. The PROFILE®-V MEDTOXScan® Drugs of Abuse Test System detects drug classes at the following cutoff concentrations:
| AMP Amphetamine (d-Amphetamine) | 500 ng/mL | OPI Opiates (Morphine) | 100 ng/mL or 2000 ng/mL |
| --- | --- | --- | --- |
| BAR Barbiturates (Butalbital) | 200 ng/mL | OXY Oxycodone (Oxycodone) | 100 ng/mL |
| BUP Buprenorphine (Nordiazepam) | 10 ng/mL | PCP Phencyclidine (Phencyclidine) | 25 ng/mL |
| COC Cocaine (Benzoylecgonine) | 150 mg/mL | PPX Propoxyphene (Norpropoxyphene) | 300 ng/mL |
| MAMP Methamphetamine (d-Methamphetamine) | 500 ng/mL | THC (Cannabinoids 11-nor-9-carboxy-r9-THC) | 50 ng/mL |
| MTD Methadone (Methadone) | 200 ng/mL | TCA Tricyclic Antidepressants (Desipramine) | 300 ng/mL |
Configurations of the PROFILE®-V MEDTOXScan® Test Devices may consist of any combination of the above listed and previously cleared drug. Test Devices will have an opiate cutoff of either 100 ng/mL or 2000 ng/mL. Refer to specific product labeling for the combination of drug tests included on that test device.
The PROFILE®-V MEDTOXScan® DRUGS OF ABUSE TEST SYSTEM PROVIDES ONLY A PRELIMINARY ANALYTICAL TEST RESULT. A MORE SPECIFIC ALTERNATE CHEMICAL METHOD MUST BE USED IN ORDER TO OBTAIN A CONFIRMED ANALYTICAL RESULT. GAS CHROMATOGRAPHY / MASS SPECTROMETRY (GC/MS), HIGH
{2}
PERFORMANCE LIQUID CHROMATOGRAPHY (HPLC) OR LIQUID CHROMATOGRAPHY / TANDEM MASS SPECTROMETRY (LC/MS/MS) ARE THE PREFERRED CONFIRMATORY METHODS. CLINICAL CONSIDERATION AND PROFESSIONAL JUDGMENT SHOULD BE APPLIED TO ANY DRUG OF ABUSE TEST RESULT, PARTICULARLY WHEN PRELIMINARY POSITIVE RESULTS ARE OBTAINED.
The MEDTOXScan® Reader includes a Positive QC Test Device, a Negative QC Test Device and a Cleaning Cassette. The MEDTOXScan® Positive and Negative QC Test Devices are intended to detect errors associated with the MEDTOXScan® Reader and a contaminated contact imaging sensor (CIS), and to verify that the CIS cleaning procedure using the MEDTOXScan® Cleaning Cassette effectively removed any contamination.
3. Special conditions for use statement(s):
The device is for in vitro diagnostic prescription use.
The assay is not designated for use in the point-of-care settings.
The PROFILE®-V MEDTOXScan® Tes devices cannot be visually read.
The PROFILE®-V MEDTOXScan® Drugs of Abuse Test System provides only a preliminary analytical test result. A more specific alternate chemical method must be used in order to obtain a confirmation analytical result. Gas chromatography/mass spectrometry (GC/MS), high performance liquid chromatography (HPLC) or liquid chromatography/tandem mass spectrometry (LC/MS/MS) are the preferred confirmatory methods. Clinical consideration and professional judgment should be applied to any drug of abuse test result, particularly when preliminary positive results are obtained.
The positive and negative QC test devices should not be used to replace performing QC using external liquid quality control materials.
4. Special instrument requirements:
PROFILE®-V MEDTOXScan®
I. Device Description:
The PROFILE®-V MEDTOXScan® Drugs of Abuse Test System kit contains PROFILE®-V MEDTOXScan® Test Devices for use with the MEDTOXScan® Reader.
3
{3}
- Each test device has all the reagents necessary to test one urine sample for one or more drugs simultaneously on the MEDTOXScan® Reader.
- Each test device holds one or more test strips composed of a membrane strip coated with drug conjugate and a pad coated with antibody-colloidal gold in a protein matrix.
Kit Contents:
1. Twenty-five (25) test devices in individual foil packages
2. Twenty-five (25) disposable pipette tips
3. One Quick Reference guide
MEDTOXScan® Reader Contents:
1. Positive and Negative QC Test Devices
2. Cleaning Cassette
3. MiniPet pipettor
4. Quick Set Up guide
5. User Manual
## J. Substantial Equivalence Information:
1. Predicate device name(s):
PROFILE®-V MEDTOXScan®
2. Predicate 510(k) number(s):
k091454
3. Comparison with predicate:
The device and the predicate device have the same intended use and test the same sample type (urine). The similarities and differences are presented below.
| Item
Intended use | Similarities/Differences | |
| --- | --- | --- |
| | Device
Determines qualitative positive or negative result from drug of abuse immunoassay screens. | Predicate
Same |
| System Procedure Measurement Method
Output | Sample is added to a single use test cassette, which is then read by instrument. Instrument is designed to read multiple single use test cassettes, one at a time. Scans the single-use test cassette with contact imaging sensor (CIS) to detect a single Outputs “positive,” “negative,” and “invalid” test results on | Same |
{4}
5
| paper printout or LCD screen; stores and uploads results. | | |
| --- | --- | --- |
| Analytes | Amphetamines, Barbiturates, Benzodiazepines, Buprenorphine, Cocaine Methadone, Methamphetamine, Opiates, Oxycodone, Phencyclidine, Propoxyphene, THC (Cannabinoids) and Tricyclic Antidepressants | Amphetamines, Barbiturates, Benzodiazepines, Cocaine Methadone, Methamphetamine, Opiates, Oxycodone, Phencyclidine, Propoxyphene, THC (Cannabinoids) and Tricyclic Antidepressants |
K. Standard/Guidance Document Referenced (if applicable):
None were referenced
L. Test Principle:
The PROFILE®-V MEDTOXScan® Drugs of Abuse Test System includes a competitive, membrane-based immunochromatographic PROFILE®-V MEDTOXScan® Test Device and the MEDTOXScan® Reader.
Antibody-Colloidal Gold: Mouse monoclonal antibodies bind to the drug being tested.
Drug-Conjugates: Each drug to be tested was individually conjugated to bovine serum albumin (BSA) or IgG. Each drug conjugate is immobilized on a test line at a designated position on the membrane strip.
Control Line: Each test strip has anti-mouse antibody immobilized at the Control (C) position of the membrane strip. The anti-mouse antibody will bind excess antibody-colloidal gold, indicating that the reagents are working properly. When the urine sample is placed in the sample well of a test strip, the dried antibody-colloidal gold under the sample pad dissolves and the urine wicks up the white strips carrying the reddish-purple antibody-colloidal gold with it.
The MEDTOXScan® Reader scans the test device and utilizes a contact imaging sensor (CIS) to capture relative line intensities. Software algorithms and barcodes are used to identify the test device, the drug tests associated with the test device and whether the presence or absence of a line is associated with a negative or positive result, respectively.
{5}
6
# Negative Samples
When no drug(s) is present in the urine sample, the reddish purple antibody-colloidal gold solutions migrate along the strip and bind to the respective drug conjugate(s) immobilized on the membrane. Each strip has up to 4 drug test lines. Labeled T1-T4. The binding of the antibody-colloidal gold to the drug conjugate generates a line at the corresponding test position on the strip. The MEDTOXScan® Reader will scan each test position and if a line is detected it will return “NEG” on the display screen (or print out) next to the abbreviation for the drug test, indicating a negative result.
# Positive Samples
When drug(s) is present in the urine sample the antibody-colloidal gold binds to the drug(s) before it migrates along the strip. When the antibody-colloidal gold binds to the drug(s) in the urine, it cannot bind to the drug conjugate immobilized on the membrane and no line is generated at the drug specific position in the result window. The MEDTOXScan® Reader will scan each test position and if no line is detected it will return “POS” on the display screen (or print out) next to the abbreviation for the drug test, indicating a preliminary positive result.
# Control Line (Valid or Invalid results)
Each test strip has an internal procedural control. A line must form at the Control (C) position in the result window to indicate that sufficient sample was applied and that the reagents are migrating properly. If a Control line does not form, the test is invalid. The MEDTOXScan® Reader scans each control line and returns “VALID” to the right of the drug test result to confirm that the control line was detected. If no control line is detected it will return “INVALID” on the display screen (or print out) next to the abbreviation for the invalid drug test, and no result will be given for that drug test.
# M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
Urine stock solutions were prepared for each test compound by spiking standard solution of known concentrations into negative pool urine. Each stock solution concentration was confirmed by GC/MS or LC/MS/MS. The stock solution was serially diluted into negative urine to obtain concentrations of 50%, 75%, 125% and 150% of the cutoff. The prepared sample concentrations were confirmed by GC/MS or LC/MS/MS. A total of 45 results (3 readers x 3 aliquots for 5 days and one strip lot) were obtained for each level. Testing was rotate between 8 operators. The results are presented in the tables below:
{6}
| Buprenorphine Cutoff=10 ng/mL | | | | |
| --- | --- | --- | --- | --- |
| Conc. (ng/mL) | % of Cutoff | Number Tested | Positive | Negative |
| Negative | Negative | 45 | 0 | 45 |
| 5 | 50% | 45 | 0 | 45 |
| 7.5 | 75% | 45 | 15 | 30 |
| 12.5 | 125% | 45 | 45 | 0 |
| 15 | 150% | 45 | 45 | 0 |
| Opiate (Morphine) Cutoff = 2000 ng/mL | | | | |
| --- | --- | --- | --- | --- |
| Conc. (ng/mL) | % of Cutoff | Number Tested | Positive | Negative |
| Negative | Negative | 45 | 0 | 45 |
| 1000 | 50% | 45 | 0 | 45 |
| 1500 | 75% | 45 | 14 | 31 |
| 2500 | 125% | 45 | 45 | 0 |
| 3000 | 150% | 45 | 45 | 0 |
b. Linearity/assay reportable range:
Not applicable. This is a qualitative test.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Profile V quality control materials were previously cleared and are sold separately. The sponsor specifies the quality control product in the "materials required but not provided" section of the labeling.
No calibrators are required. The device is calibrated during the manufacturing process.
d. Detection limit:
Analytical performance of the device around the cutoff is described in the precision section 1.a above.
e. Analytical specificity:
Cross-reactivity was established by spiking various concentrations of similarly structured drug compounds 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 re-activities of those compounds are presented below:
{7}
| Opiates (OPI) (Morphine) 2000 ng/mL | | |
| --- | --- | --- |
| Compound | Result | % Cross Reactive |
| Codeine | Positive at 900 ng/mL | 222% |
| Diacetylmorphine | Positive at 2500 ng/mL | 80% |
| Dihydrocodeine | Positive at 3800 ng/mL | 53% |
| Ethylmorphine | Positive at 600 ng/mL | 333% |
| Hydrocodone | Positive at 1400 ng/mL | 143% |
| Hydromorphine | Positive at 1900 ng/mL | 105% |
| Levorphanol | Positive at 5000 ng/mL | 40% |
| 6-Monoacetylmorphine | Positive at 3800 ng/mL | 53% |
| Morphine 3-β-D-Glucuronide | Positive at 5000 ng/mL | 40% |
| Morphine 6-β-D-Glucuronide | Positive at 6000 ng/mL | 33% |
| Norcodeine | Positive at 40,000 ng/mL | 5% |
| Thebaine | Positive at 2500 ng/mL | 80% |
| Apomorphine | Negative at 100,000 ng/mL | None Detected |
| Nalorphine | Negative at 100,000 ng/mL | None Detected |
| Naloxone | Negative at 100,000 ng/mL | None Detected |
| Naltrexone | Negative at 100,000 ng/mL | None Detected |
| Oxycodone | Negative at 100,000 ng/mL | None Detected |
| Oxymorphone | Negative at 100,000 ng/mL | None Detected |
{8}
Non Cross-reactive endogenous compounds
The following compounds were evaluated for reactivity with the Profile V device at 100 ug/mL (albumin was evaluated at 20 mg/mL and bilirubin was evaluated at 200 ug/mL). Samples were evaluated in triplicate by in-house operators. None of the listed compounds affected the expected results.
| Acetaldehyde | Creatinine | Hemoglobin, Human |
| --- | --- | --- |
| Acetone | Epinephrine | Sodium Chloride |
| Albumin, Human | b-Estradiol | Tetrahydrocortisone |
| Bilirubin | Estriol | D, l-Thyroxine |
| Cholesterol | Glucose Std. | Uric Acid |
Unrelated Compounds, Prescription and Over-the-Counter Medication
Common compounds were evaluated for reactivity at 100 ug/mL. Samples were evaluated in triplicate by in-house operators. The list of compounds tested can be found in the package insert.
Common Drugs
Drug free urine samples were spiked with the Profile V targeted drugs to the concentrations of 50% and 125% of the cutoff concentrations. An amount of 100,000 ng/mL of each common drug was added to the preparation and assayed. Evaluations were performed in triplicate by in-house operators. None of the common drugs listed affected the expected results.
| Acetylsalicylic Acid | Chorpheniramine | Morphine – OPI, OXY |
| --- | --- | --- |
| Acetaminophen | Cocaine | Phenobarbital |
| Brompheniramine Maleate | Dextromethorphan | Phenytoin |
| Caffeine | Doxylamine | d-Pseudoephedrine |
| Carbamazepine | Ibuprofen | Salicylic Acid |
There is the possibility that other substances and/or factors not listed above may interfere with the test and cause false results.
pH and Specific Gravity
To test for possible positive and/or negative interference drug free urine was divided into three aliquots and adjusted to the following pH
{9}
concentrations 4.0, 7.0, and 9.0. Each of these samples was spiked to 50% of the cutoff and 125% of the cutoff for each drug. Each sample was assayed in triplicate. No negative interference due to pH was observed.
To test for possible positive and/or negative interference from specific gravity drug free urine samples having specific gravity from 1.003, 1.015 and 1.030 were used. Each of these samples were divided into two aliquots for each drug and spiked to 50% of the cutoff and 125% of the cutoff. No negative interference due to specific gravity was observed.
f. Assay cut-off:
Characterization of how the device performs around the claimed cutoff concentration appears in the precision section 1.a., above.
2. Comparison studies:
a. Method comparison with predicate device:
Performance was evaluated by 2 operators who tested a total of 172 unaltered clinical samples, 88 samples for OPI and 84 samples for BUP. The samples were compared to the GC/MS or LC/MS/MS. The results are presented in the table below:
| Durg ng/mL | Candidate Device Results | Negative | Less than half the cutoff concentration by GC/MS or LC/MS/MS | 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) |
| --- | --- | --- | --- | --- | --- | --- |
| BUP (10) | Positive | 0 | 0 | 0 | 4 | 36 |
| | Negative | 40 | 0 | 4 | 0 | 0 |
| OPI (2000) | Positive | 0 | 0 | 1 | 4 | 36 |
| | Negative | 40 | 4 | 3 | 0 | 0 |
The summary of discordant results is listed in the table below:
| Assay | Cutoff Value (ng/mL) | Profile V Assay Pos/Neg | GC/MS or LC/MS/MS value (ng/mL) |
| --- | --- | --- | --- |
| OPI | 2000 | Positive | Morphine at 1375 ng/mL |
{10}
b. Matrix comparison:
Not applicable. The assay is intended for use with urine samples only.
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable
b. Clinical specificity:
Not applicable
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
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.
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.