IMPACT TEST SYSTEM; SALIVA TEST MODULE-OPIATE (PRESCRIPTION USE)
Applicant
Lifepoint,Inc
Product Code
DJG · Clinical Toxicology
Decision Date
Nov 23, 2004
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.3650
Device Class
Class 2
Indications for Use
For in vitro diagnostic point-of-care prescription use. The LifePoint® IMPACT® Test System Saliva Test Module (STM) for Opiate is a professional use singledrug test for the rapid determination of Opiate in human saliva. It provides qualitative screening results for Opiate at a cut-off value of 40 ng/mL. The disposable STM is used exclusively with the LifePoint IMPACT Test System instrument. This assay provides only a preliminary result. Clinical consideration and professional judgment must be applied to any drug of abuse test result, particularly in evaluating a preliminary positive result. In order to obtain a confirmed analytical result, a more specific alternate chemical method is needed. Gas Chromatography/Mass Spectroscopy (GC/MS) is the preferred confirmation method.
Device Story
The IMPACT Test System is a point-of-care diagnostic platform for drug abuse screening. It utilizes a disposable Saliva Test Module (STM) to analyze human saliva samples. The system performs rapid, qualitative detection of Opiates at a 40 ng/mL threshold. Designed for professional use in clinical settings, the device provides preliminary screening results to healthcare providers. These results assist in clinical decision-making but require confirmation by more specific analytical methods, such as Gas Chromatography/Mass Spectroscopy (GC/MS), before final diagnosis or action. The system streamlines the initial screening process, allowing for immediate assessment of potential opiate presence in a clinical environment.
Clinical Evidence
No clinical data provided; bench testing only.
Technological Characteristics
The device consists of a disposable Saliva Test Module (STM) used with the LifePoint IMPACT Test System instrument. It functions as an in vitro diagnostic immunoassay for the qualitative detection of opiates in saliva. The system is designed for professional point-of-care use.
Indications for Use
Indicated for professional point-of-care, prescription-only, in vitro qualitative screening of Opiate in human saliva at a 40 ng/mL cut-off. Intended for use with the LifePoint IMPACT Test System instrument. Preliminary results require confirmation via alternate chemical methods like GC/MS.
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).
Submission Summary (Full Text)
{0}
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DATA SUMMARY
A. 510(k) Number:
k041746
B. Purpose of the Submission:
New 510(k). This is the first assay cleared for use on the instrument, therefore the instrument is reviewed with this submission.
C. Analyte:
Opiates
D. Type of Test:
Qualitative immunoassay and instrumentation
E. Applicant:
LifePoint, Inc.
F. Proprietary and Established Names:
IMPACT Test System; Saliva Test Module (STM)- Opiate
G. Regulatory Information:
1. Regulation section:
862.3650, Opiate test system.
862.2560, Fluorometer for clinical use.
2. Classification:
II and I, respectively.
(The instrument is being reviewed as it is analyzing a class II assay.)
3. Product Code:
DJG and KHO respectively.
4. Panel:
Toxicology (91), and Chemistry (75), respectively.
H. Intended Use:
1. Intended use(s):
Refer to Indications for use.
2. Indication(s) for use:
For in vitro diagnostic point-of-care prescription use. The LifePoint IMPACT Test System Saliva Test Module (STM) for Opiate is a professional use
{1}
Page 2 of 11
single-drug test for the rapid determination of Opiate in human saliva. It provides qualitative screening results for Opiate as a cut-off value of 40 ng/mL. The disposable STM is used exclusively with the LifePoint IMPACT Test System instrument. The device is for in vitro diagnostic use.
The LifePoint IMPACT Quality Check is to be used for quality control of the IMPACT Test System and Saliva Test Modules (STM). It is labeled only as a positive and negative control and is therefore exempt from review.
3. Special condition for use statement(s):
The assay 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.
The assay is for Rx use and is intended for use in point-of-care settings.
4. Special instrument Requirements: IMPACT instrument.
I. Device Description:
The IMPACT Test System is a saliva-based, on-site drugs of abuse system. It automatically collects saliva and analyzes up to 10 drugs simultaneously in about 5 minutes. The system has two main components: 1) A single-use saliva test module (SMT) that consists of a mouthpiece, tubing and self-contained test cassette, and 2) an automated, transportable instrument or reader.
The system aspirates a small sample of saliva that is distributed to chambers inside the cassette for analysis. The reader has electronic checks. All functions are managed by the instrument through its software.
The five components to the reader are:
- Reader base assembly
- Reader mounted keypad and display
- Electro-mechanical assembly for processing STM
- Upper housing assembly
- Internal printer, imbedded processor, and interface electronics
The SMT is a single-use, disposable device that performs immunochemical and enzymatic assays. The module is constructed primarily of injection molded plastics. It is designed to align the optical components within the STM to the reader optical assemblies. It has a two-dimensional bar code that contains all the
{2}
lot specific data for the tests contained within it.
The test sequence is:
- Cassette loading
- Sample aspiration/preparation
- Reader scanning and data acquisition
- Cassette unloading
# J. Substantial Equivalence Information:
1. Predicate device name(s):
OraSure Technologies Intercept Saliva Opiates Assay
2. Predicate K number(s):
k981341
3. Comparison with predicate:
Both devices are for the qualitative determination of the same analyte(s) in the same matrix. Both are instrument-read devices.
The predicate device is a competitive EIA utilizing a horseradish peroxidase tracer and a cutoff of $5\mathrm{ng / mL}$ . It calculates the concentration using a change in absorbance via a microplate reader at $450\mathrm{nm}$ . The candidate device is a continuous flow immunoassay utilizing an opiate/CY5 tracer at a cutoff of $40\mathrm{ng / mL}$ . It calculates the concentration via fluorescence intensity at $670\mathrm{nm}$ by the IMPACT test system.
# K. Standard/Guidance Document Referenced (if applicable):
The sponsor referenced the following guidance document(s) in their submission: Guidance for Prescription Use Drugs of Abuse Assays Premarket Notifications, published November 2000. They indicated that they referred to this document while designing their studies.
# L. Test Principle:
The instrument uses a technology which the sponsor calls Continuous Flow Immunoassay. The assay employs fluorescent-labeled individual drugs bound to a solid-phase monoclonal antibody specific for each drug in an individual column. There is competitive binding for limited antibody binding sites between drug in the saliva and a fluorescent-labeled antigen. When the sample is introduced into an individual micro-column containing the specific drug reagent, the fluorescent labeled tracer is displayed from the immobilized antibody and flows into a small detection cell where it is detected using a laser/detector optical system at the appropriate wavelength. The fluorescence intensity (relative fluorescence units or RFU) is proportional to the drug level in the sample. Results are reported as either negative (if RFUs of the unknown are greater than the RFU of the cut-off calibrator) or presumptive positive (if they are greater or equal to the RFU of the cut-off calibrator).
{3}
The antibody utilized in this test is a monoclonal (mouse) antibody against morphine.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
The precision of the IMPACT assay was assessed by testing 10 normal saliva samples spiked with morphine-3-glucuronide to varied concentrations. The precision at each drug concentration level is described in the following table, along with the number of replicate measurements. The cut-off concentration is 40 ng/mL at an RFU value of 1.10.
MORPHINE-3-GLUCURONIDE IMPACT RAW DATA PERFORMANCE STUDY Relative Fluorescence Units (RFU)
| ng/mL | 0.0 | 30.0 | 35.0 | 37.5 | 40.0 | 42.5 | 45.0 | 50.0 | 60.0 | 70.0 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| % Cut-off | 0 | 75 | 87.50 | 93.75 | Cut-off 100% | 106.25 | 112.50 | 125 | 150 | 175 |
| Mean | 0.10 | 0.42 | 0.67 | 0.93 | 1.08 | 1.22 | 1.65 | 2.12 | 3.25 | 3.77 |
| Std Dev | 0.03 | 0.10 | 0.22 | 0.29 | 0.27 | 0.31 | 0.21 | 0.25 | 0.64 | 0.25 |
| N | 28 | 22 | 25 | 24 | 30 | 21 | 30 | 23 | 26 | 30 |
Summary of IMPACT Raw Data Test Results for Saliva Spiked Samples
| Sample ID | Concentration (ng/mL) | Number of Samples Tested | Number of Samples with Positive Tests Results (RFU ≥ 1.10) | Number of Samples with Negative Tests Results (RFU < 1.10) | Mean RFU* | Std Deviation |
| --- | --- | --- | --- | --- | --- | --- |
| Negative control | 0 | 28 | 0 | 28 | 0.10 | 0.03 |
| 25% below Cut-off | 30 | 22 | 0 | 22 | 0.42 | 0.10 |
| 12.5% below Cut-off | 35 | 25 | 5 | 24 | 0.67 | 0.22 |
| 6.25% below Cut-off | 37.5 | 24 | 14 | 19 | 0.93 | 0.29 |
| Cut-off | 40 | 30 | 16 | 16 | 1.08 | 0.27 |
{4}
| Sample ID | Concentration (ng/mL) | Number of Samples Tested | Number of Samples with Positive Tests Results (RFU ≥ 1.10) | Number of Samples with Negative Tests Results (RFU < 1.10) | Mean RFU* | Std Deviation |
| --- | --- | --- | --- | --- | --- | --- |
| 6.25% above Cut-off | 42.5 | 21 | 13 | 5 | 1.22 | 0.31 |
| 12.5% above Cut-off | 45 | 30 | 30 | 0 | 1.65 | 0.21 |
| 25% above Cut-off | 50 | 23 | 23 | 0 | 2.12 | 0.25 |
| 50% above Cut-off | 60 | 26 | 25 | 1 | 3.25 | 0.64 |
| 75% above Cut-off | 70 | 30 | 30 | 0 | 3.77 | 0.25 |
* IMPACT test results expressed in Relative Fluorescence Units. At a cut-off concentration of 40 ng/mL the RFU is 1.10. Samples with RFU values less than 1.10 are negative. Samples with RFU values greater than or equal to 1.10 are positive.
# b. Linearity/assay reportable range:
Not applicable. The assay is intended for qualitative use.
# c. Traceability (controls, calibrators, or method):
The assay is calibrated during the manufacturing process using four calibrators. A calibration response curve is constructed by plotting RFUs against the known drug concentrations of morphine-3-glucuronide. This information is included in the bar code reader of the SMT. The concentrations of the calibrators are 20, 40, 80, and $120\mathrm{ng / mL}$ . Each concentration is assayed 21 times using 12 different STMs on different IMPACT instruments. Each is calibrated against one another, and normalized to yield the same output signal as all manufactured instruments.
Stability claims for the calibrator are not applicable. Stability is a function of the reagent stability.
# d. Detection limit:
The LOD was calculated by assaying 20 replicates of drug free oral fluid specimens, calculating the mean fluorescence signal of those replicates, then adding 3 standard deviations to the mean. The concentration of this reading was extrapolated from the standard curve. The LOD is $12.0\mathrm{ng / mL}$ .
{5}
Page 6 of 11
Sensitivity of this assay can also be 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. This information appears in the precision section, above.
e. Analytical specificity:
Cross Reactivity to Structurally Related Compounds:
The following compounds, structurally similar to opiates, were tested for cross-reactivity using the IMPACT Test System Opiates Test. Each tested compound was prepared in human saliva. Morphine was used as the standard and represents 100% activity at the cut-off concentration at 40 ng/ml. The percent cross-reactivity of a compound in the assay is defined as the apparent morphine concentration divided by the spiked concentration times 100.
Cross Reactivity of the IMPACT Immunoassay Saliva Test to Compounds Structurally Related to Morphine
| Compound | Concentration Tested (ng/ml) | Cross-reactivity (%) |
| --- | --- | --- |
| Morphine (Control) | 40 | 100 |
| 6-Acetylmorphine | 200 | 97 |
| 3,6-Diacetylmorphine (Heroin HCl) | 200 | 92 |
| Hydrocodone | 200 | 71 |
| Hydromorphone | 200 | 57 |
| Meperidine | 200 | 22 |
| Morphine-3-beta-d-glucuronide(M3G) | 200 | 85 |
| Morphine-6-beta-d-glucuronide(M6G) | 200 | 52 |
| Nalorphine | 200 | 42 |
| Norcodeine | 200 | <1 |
| Oxycodone | 200 | 23 |
| Thebaine | 200 | 51 |
| Rifampicin | 400 | 35 |
| Codeine | 100 | 116 |
Cross Reactivity of non-structurally related compounds:
Compounds were spiked into pooled normal human saliva at the described concentrations and tested for cross-reactivity by measuring the RFU signal and comparing the signal strength to that of the control (morphine-3-glucuronide). None of the samples at the test concentrations were found to produce an RFU signal higher or equal to that of the cut-off control solution. A complete listing of all the compounds tested appears in the package insert.
{6}
Page 7 of 11
Cross Reactivity of the IMPACT Immunoassay Opiate Saliva Test
| Cross Reactant | Test Concentration (μg/ml) |
| --- | --- |
| Acetaminophen | 10 |
| Albumin, human | 4,000 |
| (d) - Amphetamine | 20 |
| Benzoylecgonine | 20 |
| l-Ascorbic acid | 50 |
| Cocaine | 20 |
| (+) – Methamphetamine | 20 |
| Phencyclidine | 20 |
| Δ9 – THCA: (+/-)-11-nor-delta 9-THC-COOH | 4 |
| Aspirin | 30 |
| Aspartame | 47 |
| Butalbital | 10 |
| Caffeine | 1,000 |
| Dextrose, USP | 40,000 |
| Diazepam | 10 |
| Ibuprofen | 10 |
| Naproxen, USP | 50 |
| Niacinamide, USP | 30 |
| (-)-Nicotine | 10 |
| Saccharin, USP | 100 |
**Interferents**
For all assays, the following compounds were tested and gave a negative result in human saliva. The compounds were spiked into pooled normal human saliva containing the control material (morphine-3-glucuronide) and the RFU signal strength of the mixture was measured. The signal strength (RFU) was compared to the signal strength of the control (morphine-3-glucuronide) containing no interferent. None of the interferents in the presence of (morphine-3-glucuronide) was found to produce a signal (RFU) that was lower than that of the cut-off control solution alone.
{7}
Page 8 of 11
## Tested Interferents
| Amylase | Listerine Mouthwash | Cranberry Juice | Crest Toothpaste |
| --- | --- | --- | --- |
| Cholesterol | Scope Mouthwash | Grape juice | Advance White Toothpaste |
| Hemoglobin | Chap Stick | Chewing gum | Seven-Up |
| Albumin | Revlon Lipstick | Chewing tobacco | Orange Juice |
| Sucrose | Yuban Coffee | Vick’s 44 M Cough Syrup | |
| Saccharin | Coca-Cola | Mint Tea | |
| Aspartame | Whole Milk | Peppermint Candy | |
## f. Assay cut-off:
To date the Substance Abuse and Mental Health Services Administration (SAMHSA) has not accepted the use of oral fluids into the Federal Workplace Program.
Characterization of how the device performs analytically around the claimed cutoff concentration appears in the precision section, above.
## 2. Comparison studies:
a. Method comparison with predicate device:
Performance of the IMPACT assay was evaluated in two separate clinical studies. In each study, subjects who were either known or suspected drug users were asked to provide information on their recent drug use. Subjects provided a sample for analysis by the IMPACT system, and a second sample to be analyzed by GC/MS. Samples to be tested by GC/MS were collected within 30 minutes of the sample analyzed by the IMPACT system. IMPACT test results were compared to self-reported drug use and to GC/MS test results.
The IMPACT drug assay was performed on-site by four different operators at three different point-of-care locations. Operators had little or no laboratory testing experience or training prior to the study.
Results from the studies are presented below. The table describes the agreement between IMPACT results and GC/MS results, and are separated according to whether donors indicated they had (or had not) used an opiate within 48 hours. Nine-nine donors indicated they had not used opiates within the past 48 hours, and 105 indicated that they had. (Of the 105 individuals indicating they had used opiates,
{8}
Page 9 of 11
97 % of them indicated they used the drug within the previous 24 hours.) GC/MS results are stratified according to the concentration of morphine-3-glucoronide in the sample.
Results of Those Indicating No Opiate Use within the Previous 48 hours
| Number of Test Subjects | GC/MS M3G Concentration Range in the Sample * (ng/mL) | IMPACT Test Result | |
| --- | --- | --- | --- |
| | | Number of Negative Samples | Number of Presumed Positive Samples |
| 92 | No Drug | 92** | 0 |
| 5 | 4-28 | 4 | 1 |
| 2 | 131-181 | 0 | 2 |
* The determination of M3G content in saliva is an accepted marker of opiate drug (Cone, E. J. Saliva Testing for Drugs of Abuse-see reference 2). The cut-off concentration is 40 ng/mL of M3G.
** A portion of these samples were tested a second time, and two samples produced a presumed positive result.
Results of Those Indicating Opiate Use within the Previous 48 hours
| Number of Test Subjects | GC/MS M3G Concentration Range in the Sample * (ng/mL) | IMPACT Test Result | |
| --- | --- | --- | --- |
| | | Number of Negative Samples | Number of Presumed Positive Samples |
| 26 | No Drug | 25 | 1 |
| 8 | 6-26 | 6 | 2 |
| 10 | 40-60 | 4 | 6 |
| 15 | 69-220 | 0 | 15 |
| 23 | 221-423 | 5** | 18 |
| 23 | 427-1056 | 0 | 23 |
** It is believed that these negative test results were a result of inadequate volume of sample tested during the study. The system was later modified to detect short samples. When the samples were tested, all rendered Presumed Positive results.
GC/MS analysis was performed in-house by LifePoint, Inc.
{9}
Page 10 of 11
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.
N. Instrument Name: IMPACT Test System
O. System Descriptions:
1. Modes of Operation:
See the Test Description (I) and Test Principle (L) sections, above.
2. Software:
FDA has reviewed applicant’s Hazard Analysis and software development processes for this line of product types:
Yes ☑ or No ☐
3. Sample Identification:
Saliva
4. Specimen Sampling and Handling:
The collection and handling of saliva samples for testing and for confirmation testing are specified in the package insert. Test samples are aspirated directly from the subject’s mouth. A second sample is to be collected for confirmation testing by the user. A collection container and buffer for this process is identified in the package insert.
5. Assay Types:
See the Test Description (I) and Test Principle (L) sections, above.
6. Reaction Types:
See the Test Description (I) and Test Principle (L) sections, above.
{10}
Page 11 of 11
7. Calibration:
See the Traceability (M, 1c) and Device Descriptions sections (I), above for a description of instrument calibration processes.
8. Quality Control:
Liquid unassayed control materials are recommended for use on the instrument. They are run just as test samples are run, except they are aspirated from a container instead of the subject’s mouth.
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The “Performance Characteristics” Section Of The SE Determination Decision Summary.
The sponsor demonstrated that the collection tube being recommended for use for confirmation testing adequately stored oral fluids to be tested for the presence of morphine. The collection container is identified, but is not provided by the sponsor and is not sold by the sponsor. The buffer recommended for use during sample collection is identified and is sold separately.
An extensive discussion of the biocompatibility of the collection tubing, which is placed in the donor’s mouth, was presented in the file.
They presented information to support the safety of the laser portion of their device.
Q. 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.