Clinical research facility patient samples (self-reported drug users)
The sponsor used clinical patient samples to verify that drug concentrations collected by the device are analytically comparable to neat oral fluid collected by expectoration and to demonstrate equivalence between the device's two collection pads.
Self-reported drug user patients; Sample Size: 60; Number of Sites: 1
Neat oral fluid collected by expectoration
Analytical comparability of drug concentrations (linear regression)
Method comparison study
Self-reported drug user patients; Sample Size: At least 80 (40 negative, 40 positive); Number of Sites: 1
Not applicable for this study
Equivalence of collection pads A and B (linear regression)
Indications for Use
The Quantisal II Oral Fluid Collection Device is intended for the collection, preservation and transport of oral fluid specimens for tetrahydrocannabinol (THC), benzoylecgonine, cocaine, oxycodone, hydrocodone, bacetylmorphine, phencyclidine, amphetamine, buprenorphine, methadone, benzodiazepines and tramadol. This device is for prescription use only.
Device Story
Device collects oral fluid for drug testing; consists of two cellulose pads on polypropylene stems and two transport tubes with preservative buffer. Operator places pads under tongue until volume adequacy indicator (blue color) appears in stem window. Device collects 1 mL neat oral fluid per pad, diluted 1:4 in buffer. Two-pad design allows split-specimen collection for screening and confirmation/retain. Used in clinical/testing settings; operated by healthcare professionals. Output is preserved oral fluid specimen in tubes for laboratory analysis via LC-MS/MS or GC-MS. Facilitates accurate drug detection/quantification; enables split-sample testing for verification.
Clinical Evidence
Bench testing only. Study of 125 subjects verified collection volume (mean 0.997-1.001 mL) and collection time (mean 3m 54s). Drug recovery studies for 15 analytes showed mean recoveries 87-100%. Stability studies confirmed analyte recovery after refrigerated and room temperature storage. Clinical comparison study (N=60) comparing Quantisal II to expectoration showed high correlation (R2 0.982-0.999) across all analytes. Pad A vs. Pad B equivalence confirmed via linear regression (R2 0.994-0.999).
Technological Characteristics
Materials: cellulose pads, polypropylene stems, polypropylene transport tubes. Principle: passive absorption of oral fluid until volume saturation indicated by color change. Energy: none (mechanical). Connectivity: none. Sterilization: not specified. Software: none.
Indications for Use
Indicated for the collection, preservation, and transport of oral fluid specimens for drug testing in patients. Prescription use only.
Regulatory Classification
Identification
A blood specimen collection device is a device intended for medical purposes to collect and to handle blood specimens and to separate serum from nonserum (cellular) components prior to further testing. This generic type device may include blood collection tubes, vials, systems, serum separators, blood collection trays, or vacuum sample tubes.
Predicate Devices
Saliva Sampler (k942435)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION MEMORANDUM ASSAY ONLY TEMPLATE
A. 510(k) Number:
k183048
B. Purpose for Submission:
New device
C. Measurand:
Not applicable.
D. Type of Test:
Collection, preservation, and transport of oral fluid specimens with drugs of abuse testing for tetrahydrocannabinol (THC), benzoylecgonine, cocaine, morphine, codeine, oxycodone, hydrocodone, 6-acetylmorphine, phencyclidine, amphetamine, methamphetamine, buprenorphine, methadone, benzodiazepines and tramadol.
E. Applicant:
Immunalysis Corporation
F. Proprietary and Established Names:
Quantisal II Oral Fluid Collection Device
G. Regulatory Information:
| Regulation | Classification | Product Code | Panel |
| --- | --- | --- | --- |
| 21 CFR 862.1675, Blood specimen collection device | Class II | PJD, Oral Fluid Drugs of Abuse and Alcohol Test Specimen Collection Device | Clinical Chemistry (75) |
H. Intended Use:
1. Intended use:
See Indications for use.
{1}
2. Indications for use:
The Quantisal II Oral Fluid Collection Device is intended for the collection, preservation and transport of oral fluid specimens for tetrahydrocannabinol (THC), benzoylecgonine, cocaine, morphine, codeine, oxycodone, hydrocodone, 6-acetylmorphine, phencyclidine, amphetamine, methamphetamine, buprenorphine, methadone, benzodiazepines and tramadol. This device is for prescription use only.
3. Special conditions for use statements:
For prescription use only.
4. Special instrument requirements:
Not applicable.
I. Device Description:
The Quantisal II Oral Fluid Collection Device is intended for the collection, preservation and transport of oral fluid. An oral fluid specimen is collected by placing two cellulose pads affixed to a polypropylene stem collector under the tongue of an individual until a defined volume of saliva has saturated the cellulose pads. When sufficient volume is collected a blue color is shown in a window on the stem. The collector is then separated into two pads A and B, then transferred into two separate polypropylene tubes, both containing a volume of preservative buffer. The tubes are stoppered with caps. The design with two pads and two tubes allows for one aliquot to be used for screening and confirmation testing, and the other aliquot to be stored in reserve in cases where re-testing by the confirmation method is required. The Quantisal II Oral Fluid Collection System collects 1 mL of neat oral fluid and is diluted with 3 mL of preservative buffer.
J. Substantial Equivalence Information:
1. Predicate device name:
Saliva Sampler
2. Predicate 510(k) number:
k942435
{2}
3
3. Comparison with predicate:
| Similarities and differences | | |
| --- | --- | --- |
| Item | Subject device, Quantisal II Oral Fluid Collection Device k183045 | Predicate device, Saliva Sampler k942435 |
| Intended use | Intended for the collection, preservation and transport of oral fluid specimens for drug testing. | Same |
| Collection type / Specimen collection site | Two absorbent pads for under tongue collection. | One absorbent pad for under tongue collection. |
| Collection volume | 1 mL with built-in sample volume adequacy window. | Same |
| Collection tube | Tube for 1 to 4 dilution with preservation fluid. | Tube for 1 to 2 dilution with preservation fluid. |
K. Standard/Guidance Document Referenced:
None referenced.
L. Test Principle:
Not applicable.
M. Performance Characteristics:
1. Analytical performance:
a. Precision/Reproducibility:
Not applicable.
b. Linearity/assay reportable range:
Not applicable.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Sample Volume
A sample volume study was conducted to verify the consistency of oral fluid volume collected by the Quantisal II Oral Fluid Collection Device. In the study, oral fluid samples were collected from a total of 125 subjects (including 75 drug users) following the instructions for use. Prior to collection, each stem (A and B) was
{3}
weighed. After the volume adequacy indicator turned blue on both A and B collector stems, each stem was weighed again. The volume was calculated from the weight change and using the specific gravity for saliva based on scientific literature references. The study found the mean ± standard deviation volume collected was 0.997 ± 0.05 mL (range 0.860 – 1.103) and 1.001 ± 0.05 (range 0.902 – 1.093) mL for collectors A and B, respectively.
## Sample Collection Time
A sample collection time study was conducted to verify the collection time range for Quantisal II Oral Fluid Collection Device. The product labeling states that the collection time may take from 2 to 10 minutes, and if the indicator has not turned blue within 15 minutes, the pad should be removed from the mouth and discarded. In the study, oral fluid samples were collected from a total of 125 subjects (including 75 drug users) following the instructions for use. The timer started when the collector was placed into subject’s mouth, and stopped when the volume adequacy indicator turned blue on both A and B collector stems. The sponsor reported that 99.2% (124 of 125) subjects were able to provide sufficient oral fluid within the recommended 10 minute collection. The mean time required for collection was 3 minutes and 54 seconds. The maximum time required for collection was reported as 11 minutes.
## Drug Recovery
A drug recovery study was conducted to verify adequate analytical recovery of 15 drugs from oral fluid collected by the Quantisal II Oral Fluid Collection Device. The samples under test for each drug (THC, benzoylecgonine, cocaine, morphine, codeine, oxycodone, hydrocodone, 6-acetylmorphine, phencyclidine, amphetamine, methamphetamine, buprenorphine, methadone, nordiazepam, and tramadol) were prepared by spiking the drug into negative oral fluid at ±25% and +50% from the concentrations listed in the table below. The sample concentrations were assayed by LC/MS/MS or GC/MS prior to introduction into the collector. For each sample, three Quantisal II Oral Fluid Collection Devices were sequentially dipped and removed after the volume adequacy indicator turned blue. The collectors (pad A and B) were then placed into the collection tubes, sealed with the cap, and stored overnight at room temperature. The next day the liquids in the tubes were assayed by LC/MS/MS or GC/MS in replicates of three per pad for each collection device for a total of 18 replicates at each concentration.
| Analyte | Concentration (ng/mL) |
| --- | --- |
| THC | 4 |
| Benzoylecgonine | 15 |
| Cocaine | 15 |
| Morphine | 30 |
| Codeine | 30 |
| Oxycodone | 30 |
| Hydrocodone | 30 |
| 6-acetylmorphine | 4 |
{4}
| Analyte | Concentration (ng/mL) |
| --- | --- |
| Phencyclidine | 10 |
| Amphetamine | 50 |
| Methamphetamine | 50 |
| Buprenorphine | 3 |
| Methadone | 20 |
| Nordiazepam | 5 |
| Tramadol | 50 |
The recovery results are summarized in the following table:
| Analyte | Mean | Min. | Max. |
| --- | --- | --- | --- |
| THC | 87% | 80% | 96% |
| Benzoylecgonine | 98% | 89% | 108% |
| Cocaine | 98% | 92% | 108% |
| Morphine | 95% | 86% | 109% |
| Codeine | 97% | 84% | 107% |
| Oxycodone | 97% | 86% | 105% |
| Hydrocodone | 98% | 90% | 108% |
| 6-acetylmorphine | 98% | 88% | 103% |
| Phencyclidine | 95% | 86% | 106% |
| Amphetamine | 99% | 93% | 104% |
| Methamphetamine | 100% | 94% | 107% |
| Buprenorphine | 96% | 80% | 107% |
| Methadone | 95% | 82% | 105% |
| Nordiazepam | 98% | 88% | 104% |
| Tramadol | 98% | 83% | 107% |
## Oral Fluid Sample Stability
Sample stability studies were conducted to verify the stability of 15 drugs in human oral fluid under the claimed storage stability conditions in the product labeling when diluted with preservative buffer and stored in the Quantisal II Oral Fluid Collection Device polypropylene tube. The product labeling identifies that certain drugs in oral fluid specimens collected with pad A of the Quantisal II Oral Fluid Collector are stable for 10 days if stored refrigerated (2-8°C; 36-46°F) and stable for 5 or 10 days (depending on the drug type) if stored at room temperature (8-25°C; 46-77°F). For pad B specimens, certain drugs in oral fluid are stable for 1 month if stored refrigerated. The product labeling also identifies that samples should be stored diluted for a minimum of 4 hours at room temperature prior to testing to allow sufficient time for any drug(s) present to be extracted from the pad into the preservation buffer. The transportation claims were also supported by the specimen stability studies.
## Pad A refrigerated storage
To verify the claimed refrigerated storage conditions, a study was conducted by
{5}
testing samples stored for 5 and 10 days using three collection devices at each condition and time point. Samples were drug-free oral fluid spiked with the drug (THC, benzoylecgonine, cocaine, morphine, codeine, oxycodone, hydrocodone, 6-acetylmorphine, phencyclidine, amphetamine, methamphetamine, buprenorphine, methadone, nordiazepam, or tramadol) at $+50\%$ above the concentrations listed in table under Drug Recovery. The samples were each applied into the collection device per the required volume and then diluted with buffer. At each time point, an aliquot was taken from the storage tube and assayed in replicates of 3 by LC/MS/MS or GC/MS. The analyte recovery results after storage for 10 days support the claimed refrigerated storage conditions and are given in the following table.
| Analyte | Mean | Min. | Max. |
| --- | --- | --- | --- |
| THC | 100% | 98% | 103% |
| Benzoylecgonine | 110% | 104% | 109% |
| Cocaine | 95% | 90% | 95% |
| Morphine | 98% | 95% | 102% |
| Codeine | 98% | 93% | 100% |
| Oxycodone | 98% | 96% | 100% |
| Hydrocodone | 100% | 98% | 102% |
| 6-acetylmorphine | 100% | 97% | 102% |
| Phencyclidine | 107% | 100% | 107% |
| Amphetamine | 99% | 96% | 100% |
| Methamphetamine | 97% | 93% | 100% |
| Buprenorphine | 102% | 98% | 107% |
| Methadone | 97% | 97% | 100% |
| Nordiazepam | 100% | 97% | 103% |
| Tramadol | 103% | 100% | 104% |
# Pad A room temperature storage
To verify the claimed room temperature storage conditions, a study was conducted by testing samples stored for 5 and 10 days at room temperature using three collection devices at each condition and time point. Samples were drug-free oral fluid spiked with the drug (THC, benzoylecgonine, cocaine, morphine, codeine, oxycodone, hydrocodone, 6-acetylmorphine, phencyclidine, amphetamine, methamphetamine, buprenorphine, methadone, nordiazepam, or tramadol) at a $+50\%$ above the concentrations listed in table under Drug Recovery. The samples were each applied into the collection device per the required volume and then diluted with buffer. At each time point an aliquot was taken from the storage tube and assayed in replicates of 3 by LC/MS/MS or GC/MS. The analyte recovery results after storage at room temperature for 5 days (for cocaine) and 10 days (for the other 14 drugs) support the claimed room temperature storage conditions and are given in the following table.
| Analyte | Mean | Min. | Max. |
| --- | --- | --- | --- |
| THC | 98% | 98% | 100% |
| Benzoylecgonine | 105% | 100% | 109% |
| Cocaine * | 95% | 95% | 100% |
| Morphine | 98% | 98% | 100% |
| Codeine | 98% | 98% | 100% |
| Oxycodone | 98% | 98% | 100% |
| Hydrocodone | 100% | 98% | 100% |
| 6-acetylmorphine | 100% | 98% | 100% |
| Phencyclidine | 100% | 98% | 100% |
| Amphetamine | 99% | 98% | 100% |
| Methamphetamine | 97% | 98% | 100% |
| Buprenorphine | 100% | 98% | 100% |
| Methadone | 97% | 97% | 100% |
| Nordiazepam | 100% | 97% | 100% |
| Tramadol | 100% | 97% | 100% |
{6}
| Analyte | Mean | Min. | Max. |
| --- | --- | --- | --- |
| Morphine | 100% | 95% | 102% |
| Codeine | 98% | 93% | 100% |
| Oxycodone | 96% | 93% | 100% |
| Hydrocodone | 100% | 96% | 102% |
| 6-acetylmorphine | 100% | 97% | 103% |
| Phencyclidine | 100% | 100% | 107% |
| Amphetamine | 97% | 95% | 100% |
| Methamphetamine | 99% | 93% | 101% |
| Buprenorphine | 102% | 98% | 107% |
| Methadone | 97% | 97% | 100% |
| Nordiazepam | 100% | 99% | 103% |
| Tramadol | 101% | 97% | 105% |
* 5 days at room temperature for cocaine. The sponsor identified that cocaine is unstable in samples stored greater than 5 days at room temperature and converts to benzoylecgonine. Benzoylecgonine is the metabolite of cocaine and is found only in samples from subjects who have taken cocaine.
# Pad B refrigerated storage
To verify the claimed long term refrigerated storage conditions for pad B, a study was conducted by testing samples stored for 1 month using three collection devices at each condition and time point. Samples were drug-free oral fluid spiked with the drug (THC, benzoylecgonine, cocaine, morphine, codeine, oxycodone, hydrocodone, 6-acetylmorphine, phencyclidine, amphetamine, methamphetamine, buprenorphine, methadone, nordiazepam, or tramadol) at $+50\%$ above the concentrations listed under Drug Recovery. The samples were each applied into the collection device per the required volume and then diluted with buffer. At each time point an aliquot was taken from the storage tube and assayed in replicates of 3 by LC/MS/MS or GC/MS. The analyte recovery results support the claimed one month storage stability at refrigerated conditions for specimen B and are given in the following table.
| Analyte | Mean | Min. | Max. |
| --- | --- | --- | --- |
| THC | 92% | 91% | 93% |
| Benzoylecgonine | 101% | 100% | 102% |
| Cocaine | 97% | 96% | 98% |
| Morphine | 97% | 93% | 101% |
| Codeine | 110% | 109% | 110% |
| Oxycodone | 97% | 96% | 97% |
| Hydrocodone | 103% | 99% | 107% |
| 6-acetylmorphine | 107% | 102% | 111% |
| PCP | 98% | 97% | 98% |
| Amphetamine | 95% | 92% | 96% |
| Methamphetamine | 102% | 101% | 103% |
| Buprenorphine | 99% | 98% | 100% |
| Methadone | 96% | 94% | 97% |
{7}
| Analyte | Mean | Min. | Max. |
| --- | --- | --- | --- |
| Benzodiazepines | 94% | 92% | 95% |
| Tramadol | 101% | 99% | 105% |
# Clinical Specimens Testing
# Quantisal II Oral Fluid Collection Device versus expectoration
A study was conducted to verify that drug concentrations in oral fluid samples collected by Quantisal II Oral Fluid Collection Device are analytically comparable to the neat oral fluid samples collected by expectoration. The samples used in the study were collected from self-reported drug user patients at a clinical research facility. For each patient, a single neat oral fluid sample was collected by expectoration into a borosilicate glass vial. An aliquot of each sample was subsequently processed through the Quantisal II Oral Fluid Collection Device by dipping the collection pad into the oral fluid until the volume adequacy indicator turned blue. The expectoration samples and Quantisal II samples were assayed by LC-MS/MS or GC-MS. The assay results from expectoration samples and for Quantisal II (pad A) were compared by linear regression. The results are given in the following table.
| Analyte | Slope | Intercept | R2 | N |
| --- | --- | --- | --- | --- |
| THC | 0.939 | 0.9 | 0.992 | 60 |
| Benzoylecgonine | 0.901 | 1.5 | 0.988 | 60 |
| Cocaine | 0.908 | 2.1 | 0.990 | 60 |
| Morphine | 0.914 | 3.1 | 0.992 | 60 |
| Codeine | 0.919 | 0.6 | 0.992 | 60 |
| Oxycodone | 0.978 | 0.4 | 0.993 | 60 |
| Hydrocodone | 0.918 | 2.0 | 0.992 | 60 |
| 6-acetylmorphine | 0.900 | 5.6 | 0.992 | 60 |
| Phencyclidine | 1.005 | 0.6 | 0.998 | 60 |
| Amphetamine | 0.958 | 2.1 | 0.992 | 60 |
| Methamphetamine | 0.930 | 3.9 | 0.982 | 60 |
| Buprenorphine | 0.910 | 2.9 | 0.999 | 60 |
| Methadone | 0.962 | 0.4 | 0.994 | 60 |
| Nordiazepam | 0.971 | 0.2 | 0.986 | 60 |
| Tramadol | 0.985 | 4.7 | 0.991 | 60 |
The sponsor also provided a study demonstrating that the borosilicate glass vials used to collect expectoration samples were analytically fit for purpose because of high analyte recovery properties of the vial material. In the study, samples were prepared in the subject vial by spiking drug free expectorated oral fluid with the drug analytes (THC, benzoylecgonine, cocaine, morphine, codeine, oxycodone, hydrocodone, 6-acetylmorphine, phencyclidine, amphetamine, methamphetamine, buprenorphine, methadone, nordiazepam, or tramadol) at $+50\%$ above the concentrations listed in table under Drug Recovery. The initial concentration of each sample was assayed by LC-MS/MS or GC-MS. For each sample, three aliquots were subsequently taken from the vial and dispensed into three vials. The vialed samples were stored at $25^{\circ}\mathrm{C}$
{8}
for 48 hours and then tested in replicates of three for each vial using the same analytical method. The recovery for all test samples in the subject vial was within $100 \pm 10\%$ .
# Pad A versus pad B
A second study was conducted to demonstrate that both collection pads on the Quantisal II Oral Fluid Collection Device are equivalent when used under real world conditions. In the study, samples were collected from self-reported drug user patients at a clinical research facility using the Quantisal II Oral Fluid Collection Device. At least 40 unaltered drug negative oral fluid samples and 40 unaltered oral fluid samples containing analyte from each drug class were collected. The samples were assayed by LC-MS/MS or GC-MS. The assay results from samples for pad A and pad B were compared by linear regression. The results are given in the following table.
| Analyte | Slope | Intercept | R2 |
| --- | --- | --- | --- |
| THC | 1.047 | -3.4 | 0.995 |
| Benzoylecgonine | 0.990 | 0.2 | 0.999 |
| Cocaine | 0.976 | 3.2 | 0.994 |
| Morphine | 1.039 | 5.2 | 0.998 |
| Codeine | 1.008 | 0.5 | 0.999 |
| Oxycodone | 0.989 | 0.8 | 0.999 |
| Hydrocodone | 1.018 | 0.3 | 0.999 |
| 6-acetylmorphine | 1.015 | 4.5 | 0.997 |
| Phencyclidine | 1.033 | -6.2 | 0.996 |
| Amphetamine | 0.989 | 7.6 | 0.999 |
| Methamphetamine | 0.982 | 48.1 | 0.997 |
| Buprenorphine | 1.006 | 11.2 | 0.998 |
| Methadone | 1.024 | -8.9 | 0.997 |
| Nordiazepam | 1.024 | -0.2 | 0.997 |
| Tramadol | 0.947 | 51.1 | 0.997 |
In the study, the patient samples included 40 drug negative oral fluid samples that were collected using the Quantisal II Oral Fluid Collection Device and also collected by expectoration into a borosilicate glass vial. A comparison of the expectoration samples and Quantisal II samples was conducted by assaying for drugs using LC-MS/MS or GC-MS. To remove bias, the sequence of collection between expectoration and the Quantisal II Oral Fluid Collection Device was randomized. The assay results across all drugs were negative for both the expectoration samples and samples collected by the Quantisal II Oral Fluid Collection Device.
# Biocompatibility
The Quantisal II Oral Fluid Collection Device has short term contact (up to 15 minutes) with the patient's mouth during oral fluid collection. The materials comprising the Quantisal II Oral Fluid Collection Device are the same as those of the Quantisal I Oral Fluid Collection Device (cleared under k942435 with tradename Saliva Sampler), and therefore no new biocompatibility testing was performed.
{9}
d. Detection limit:
Not applicable.
e. Analytical specificity:
Not applicable.
f. Assay cut-off:
Not applicable.
2. Comparison studies:
a. Method comparison with predicate device:
Not applicable.
b. Matrix comparison:
Not applicable.
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable.
b. Clinical specificity:
Not applicable.
c. Other clinical supportive data:
Not applicable.
4. Clinical cut-off:
Not applicable.
5. Expected values/Reference range:
Not applicable.
10
{10}
N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Parts 801 and 809, as applicable.
O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
11
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.