100 patient urine samples were analyzed to evaluate the accuracy and concordance of the DRI Hydrocodone Assay compared to LC-MS/MS reference method results.
Accuracy; Concordance; Patient samples; Urine
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Retrospective accuracy/concordance study
Patient urine samples; Sample Size: 100
LC-MS/MS
Overall concordance between LC-MS/MS and the DRI Hydrocodone Assay
Indications for Use
The DRI® Hydrocodone Assay is intended for the qualitative and semi-quantitative detection and estimation of Hydrocodone and its metabolites in human urine at a cutoff of 300 ng/mL. The semi-quantitative mode is for purposes of enabling laboratories to determine an appropriate dilution of specimen for confirmatory method such as LC-MS/MS or GC-MS and permitting laboratories to establish quality control measures. This assay provides a preliminary analytical test result. A more specific alternative chemical method must be used in order to confirm an analytical result. Gas chromatography/mass spectrometry (GC/MS) and 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 used. The DRI® Hydrocodone Assay Calibrators are intended for the calibration of the DRI® Hydrocodone Assay. For In Vitro Diagnostic Use Only. The DRI® Hydrocodone Controls are unassayed quality control material intended for use in the DRI Hydrocodone Assay to detect and monitor systematic deviations from accuracy resulting from reagent or instrument defects. For In Vitro Diagnostics Use Only
Device Story
Homogeneous enzyme immunoassay for hydrocodone detection in human urine; utilizes competition between drug-labeled G6PDH and free drug in sample for fixed antibody binding sites. Absence of drug allows antibody binding to G6PDH, decreasing enzyme activity; presence of drug allows G6PDH to interact with substrate, increasing activity. Enzyme activity measured spectrophotometrically at 340 nm via NAD to NADH conversion. Used in clinical laboratories on automated chemistry analyzers (e.g., Beckman Coulter AU680) by trained technicians. Provides preliminary analytical results; requires confirmation by LC-MS/MS or GC-MS. Semi-quantitative mode assists in determining specimen dilution for confirmation and quality control. Results support clinical decision-making regarding drug use.
Clinical Evidence
Bench testing only. Precision (n=80) demonstrated accurate recovery at 300 ng/mL cutoff. Accuracy study (n=100) compared to LC-MS/MS showed 93% overall concordance. Linearity (r2=0.9965) confirmed across calibration range. Specificity/cross-reactivity tested against various opiates; interference testing (pH, endogenous substances, specific gravity) showed no significant impact on assay performance.
Technological Characteristics
Liquid, ready-to-use homogeneous enzyme immunoassay. Reagents: mouse monoclonal anti-hydrocodone antibody, G6PDH, G6P, NAD, Tris buffer, sodium azide preservative. Sensing principle: spectrophotometric measurement of NAD to NADH conversion at 340 nm. Form factor: kit for automated clinical chemistry analyzers. Storage: 2-8°C. Standards: CLSI EP5-2A, EP7-A2, EP9-A3.
Indications for Use
Indicated for qualitative and semi-quantitative detection of hydrocodone and metabolites in human urine at 300 ng/mL cutoff. For prescription use only.
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).
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
K150502
B. Purpose for Submission:
New Device
C. Measurand:
Hydrocodone
D. Type of Test:
Qualitative and semi-quantitative homogeneous immunoassay
E. Applicant:
Microgenics Corporation
F. Proprietary and Established Names:
DRI Hydrocodone Assay
DRI Hydrocodone Calibrator
DRI Hydrocodone Control
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| DJG | II | 21 CFR § 862.3650
Opiate test system | Toxicology (91) |
| DLJ | II | 21 CFR § 862.3200
Clinical toxicology calibrator | Toxicology (91) |
| LAS | I, reserved | 21 CFR § 862.3280
Clinical toxicology control material | Toxicology (91) |
H. Intended Use:
1. Intended use(s):
See indications for use below.
2. Indication(s) for use:
The DRI Hydrocodone assay is intended for the qualitative and semi-quantitative detection and estimation of Hydrocodone and its metabolites in human urine at a cutoff of 300 ng/mL.
{1}
The semi-quantitative mode is for purposes of enabling laboratories to determine an appropriate dilution of the specimen for confirmation by a confirmatory method such as LC-MS/MS or GC-MS and permitting laboratories to establish quality control procedures.
This assay provides a preliminary analytical test result. A more specific alternative chemical method must be used in order to confirm an analytical result. Gas chromatography/mass spectrometry (GC/MS) and 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 used.
The DRI Hydrocodone assay calibrators are intended for the calibration of the DRI Hydrocodone assay. For in vitro diagnostic use only.
The DRI Hydrocodone assay controls are unassayed quality control material intended for the use in the DRI Hydrocodone assay to detect and monitor systematic deviations from accuracy resulting from reagent or instrument defects. For in vitro diagnostic use only.
3. Special conditions for use statement(s):
For prescription use only.
4. Special instrument requirements:
Beckman Coulter AU 680 chemistry analyzer was used to generate data for this submission.
I. Device Description:
The DRI Hydrocodone assay is supplied as a liquid ready-to-use homogeneous enzyme immunoassay.
The DRI Hydrocodone Assay is a kit comprised of two reagents, Reagent A and Reagent E, which are bottled separately but sold together within the same kit.
The Reagent A solution contains: mouse monoclonal anti-hydrocodone antibody, glucose-6-phosphate (G6P) and nicotinamide adenine dinucleotide (NAD) in Tris buffer with Sodium Azide (≤0.09%) as a preservative).
The Reagent E solution contains: glucose-6-phosphate dehydrogenase (G6PDH) in Tris buffer with Sodium Azide (≤0.09%) as preservative.
The DRI Hydrocodone Enzyme Immunoassay calibrators designated for use at the 300 ng/mL cutoff contain 0 (negative), 100, 300, 500, and 1,000 ng/mL of hydrocodone in human urine with sodium azide (≤0.09%) as preservative. The calibrators are provided in liquid ready to use form as a separate kit, and are to be stored at 2° to 8° C until the expiration date on the label.
The controls are provided at a concentration of 225 and 375 ng/mL. The controls are provided in liquid ready to use form as a separate kit, and are to be stored at 2° to 8° C until the expiration date on the label.
2
{2}
J. Substantial Equivalence Information:
1. Predicate device name(s):
LZI Hydrocodone Enzyme Immunoassay
2. Predicate 510(k) number(s):
K141055
3. Comparison with predicate:
| Item | DRI Hydrocodone Assay, Calibrator and Control (Candidate Device) | LZI Hydrocodone Enzyme Immunoassay, k141055 (Predicate Device) |
| --- | --- | --- |
| Intended use | For the qualitative and semi-quantitative determination of the presence of hydrocodone in human urine. For in vitro diagnostic use. | Same |
| Assay cutoff | 300 ng/mL of Hydrocodone | 100 or 300 ng/mL of Hydrocodone |
| Assay calibrated against | Hydrocodone | Same |
| Test system type | Homogenous enzyme immunoassay | Same |
| Storage conditions | 2 - 8°C until expiration date | Same |
| Calibrator form | Liquid | Same |
| Control set levels | 300 ng/mL Cutoff: Two levels (225 ng/mL and 375 ng/mL) | 100 ng/mL Cutoff: Two levels (75 ng/mL and 125 ng/mL).
300 ng/mL Cutoff: Two levels (225 ng/mL and 375 ng/mL). |
| Calibrator set levels | 300 ng/mL Cutoff: Five levels (0, 100, 300, 500 and 1000 ng/mL) | 100 ng/mL Cutoff: Five levels (0, 50, 100, 150 and 300 ng/mL).
300 ng/mL Cutoff: Five levels (0, 150, 300, 500 and 800 ng/mL). |
3
{3}
4
K. Standard/Guidance Document Referenced (if applicable):
- CLSI EP5-2A, Evaluation of Precision Performance of Quantitative Measurement Methods; Second Edition, 2004.
- CLSI EP7-A2: Interference Testing in Clinical Chemistry, 2005.
- CLSI EP9-A3; Method Comparison and Bias Estimation Using Patient Samples; Approved Guideline – Third Edition, 2013.
L. Test Principle:
The DRI® Hydrocodone Assay is a homogeneous enzyme immunoassay. The assay uses specific antibodies that can detect Hydrocodone and its metabolites without any significant cross-reactivity to other opiate compounds. The assay is based on competition between a drug labeled with glucose-6-phosphate dehydrogenase (G6PDH) and free drug from the urine sample, for a fixed amount of specific antibody binding sites. In the absence of free drug from the sample, mouse monoclonal anti-hydrocodone antibody binds to the drug labeled with G6PDH and causes a decrease in enzyme activity. In the presence of free drug, the free drug occupies the antibody binding sites, allowing the drug bound G6PDH to interact with the substrate, resulting in enzyme activity. This phenomenon creates a direct proportional relationship between the drug concentration in urine and enzyme activity. The enzyme activity is determined spectrophotometrically at 340 nm by measuring the conversion of nicotinamide adenine dinucleotide (NAD) to NADH.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
A precision study was performed by one trained operator following the CLSI (EP5-A2) precision guidelines. Drug free urine samples were spiked with hydrocodone at 0, 75, 150, 225, 300, 375, 450, 525 and 600 ng/mL, representing 0, 25, 50, 75, 100, 125, 150, 175 and 200% of the device cutoff (300 ng/mL). Each level sample was tested in duplicates per run, two runs per day for twenty consecutive days (total N= 80/level/reagent lot) using 2 lots on the Beckman Coulter AU680 chemistry analyzer. The results of one representative lot are shown below:
{4}
Qualitative Precision Result:
| Concentration as % of the Cutoff Level | Target Hydrocodone concentration (ng/mL) | DRI Hydrocodone Assay # Neg / # Pos |
| --- | --- | --- |
| 0 | 0 | 80 Neg / 0 Pos |
| 25 | 75 | 80 Neg / 0 Pos |
| 50 | 150 | 80 Neg / 0 Pos |
| 75 | 225 | 80 Neg / 0 Pos |
| 100 | 300 | 46 Neg / 34 Pos |
| 125 | 375 | 0 Neg / 80 Pos |
| 150 | 450 | 0 Neg / 80 Pos |
| 175 | 525 | 0 Neg / 80 Pos |
| 200 | 600 | 0 Neg / 80 Pos |
Semi-Quantitative Precision Result:
| Concentration as % of the Cutoff Level | Target Hydrocodone concentration (ng/mL) | DRI Hydrocodone Assay # Neg / # Pos |
| --- | --- | --- |
| 0 | 0 | 80 Neg / 0 Pos |
| 25 | 75 | 80 Neg / 0 Pos |
| 50 | 150 | 80 Neg / 0 Pos |
| 75 | 225 | 80 Neg / 0 Pos |
| 100 | 300 | 40 Neg / 40 Pos |
| 125 | 375 | 0 Neg / 80 Pos |
| 150 | 450 | 0 Neg / 80 Pos |
| 175 | 525 | 0 Neg / 80 Pos |
| 200 | 600 | 0 Neg / 80 Pos |
b. Linearity/assay reportable range:
Linearity study in the semi-quantitative mode was conducted by spiking drug free urine pool with hydrocodone (serial dilutions of a high concentration hydrocodone in negative urine pool) to achieve concentrations ranging from 0ng/mL to 1000ng/mL, and testing each level on two reagent lots in replicates of five on the Beckman
{5}
Coulter AU680 clinical chemistry analyzer. The results of one representative lot are summarized below:
| Hydrocodone (ng/mL) | Recovery (ng/mL) | % Recovery |
| --- | --- | --- |
| 0 | N/A | N/A |
| 50 | 47 | 94 |
| 75 | 76 | 101 |
| 100 | 108 | 108 |
| 150 | 171 | 114 |
| 225 | 250 | 111 |
| 300 | 302 | 101 |
| 375 | 398 | 106 |
| 450 | 472 | 105 |
| 500 | 527 | 105 |
| 750 | 844 | 113 |
| 1000 | 1014 | 101 |
Traceability, Stability, Expected values (controls, calibrators, or methods):
Traceability
The primary controls and calibrators are traceable to the 1 mg/mL Hydrocodone stock solution purchased from a commercial source which is established at 99.9% purity. The concentration of the primary control and calibrator stocks is confirmed by LC-MS/MS from three independent laboratories.
Value Assignment – Calibrators and Controls
The primary controls and calibrators are used to prepare secondary controls and calibrators and the performance testing is performed on AU680 analyzers against the primary controls and calibrators, in replicates of five. The testing required two passing runs on two different AU680 analyzers. The preset acceptance criteria is that replicates have less than or equal to 5% rate (mA/min) difference between the secondary and the primary controls and calibrators. The concentration of the controls and calibrators are further corroborated with validated LC-MS/MS and the values should be within 10% of the nominal values.
{6}
7
# Calibrators and Controls Stability Studies
Accelerated a stability studies in the qualitative and semi-quantitative modes were conducted on three lots of DRI Hydrocodone Controls and DRI Hydrocodone Calibrators. Real time stability studies are ongoing. The stability protocols and acceptance criteria for open and closed vial were reviewed and found acceptable. The open vial and closed vial study results support the open vial stability claim of 60 days and closed vial stability claim of thirteen months when stored at 2 to 8 °C for the DRI Hydrocodone Controls and DRI Hydrocodone Calibrators.
d. Detection limit:
Not applicable.
e. Analytical specificity:
An analytical specificity study to evaluate interference from non-structurally and structurally related compounds was performed in the qualitative and semi-quantitative mode. The study design and results are described below. Results were the same for each mode (qualitative and semi-quantitative modes).
# Structurally Related Compounds and Other Opiates
To evaluate potential cross-reactivity for the DRI Hydrocodone assay, structurally similar compounds were spiked into drug free urine at concentrations that will yield a result that is equivalent to the 300 ng/mL cutoff. Non-cross-reacting compounds were titrated to the highest levels yielding negative results in the assay. The percent cross-reactivity is presented in the table below.
| Compounds | Tested Concentration (ng/mL) | % Cross-Reactivity |
| --- | --- | --- |
| Hydrocodone | 300 | 102 |
| Hydromorphone | 250 | 122 |
| Hydromorphone 3β-D-Glucuronide | 250 | 122 |
| NorHydrocodone | 10,000 | 3.1 |
| Dihydrocodeine | 12,000 | 2.7 |
| 6-Acetyl Morphine | 1000,000 | < 0.3 |
| Buprenorphine | 1000,000 | < 0.3 |
| Buprenorphine 3β-D-Glucuronide | 100,000 | < 0.3 |
| Codeine | 150,000 | < 0.2 |
| Dextromethorphan | 250,000 | < 0.2 |
| EDDP | 150,000 | < 0.2 |
| Fentanyl | 100,000 | < 0.3 |
| Heroin | 100,000 | < 0.3 |
| Levorphanol | 12,000 | 1.7 |
{7}
Non-Structurally Related Compounds
Potential interference from non-structurally related drugs and metabolites was evaluated in the qualitative and semi-quantitative modes, by spiking these compounds at high concentrations in drug free urine spiked with hydrocodone at $\pm 25\%$ of the cutoff (225 and $375~\mathrm{ng / mL}$ ). Results obtained with the two reagent lots are the same.
| Cross Reactants | Spiked Concentration (ng/mL) | Spiked Hydrocodone Concentration | | |
| --- | --- | --- | --- | --- |
| | | 0 ng/mL | -25% Cutoff (225 ng/mL) | +25% Cutoff (375 ng/mL) |
| Acetaminophen | 500,000 | Negative | Negative | Positive |
| Acetylsalicylic acid | 500,000 | Negative | Negative | Positive |
| Amitryptyline | 100,000 | Negative | Negative | Positive |
| Amoxicillin | 100,000 | Negative | Negative | Positive |
| Amphetamine | 1,000,000 | Negative | Negative | Positive |
| Benzoylecgonine | 1,000,000 | Negative | Negative | Positive |
| Caffeine | 100,000 | Negative | Negative | Positive |
| Carbamazepine | 500,000 | Negative | Negative | Positive |
| Chlorpromazine | 100,000 | Negative | Negative | Positive |
| Clomipramine | 100,000 | Negative | Negative | Positive |
| Cimetidine | 500,000 | Negative | Negative | Positive |
| Desipramine | 100,000 | Negative | Negative | Positive |
| Dexamethasone | 100,000 | Negative | Negative | Positive |
| Doxorubicin | 100,000 | Negative | Negative | Positive |
| Doxorubicin + 5-FU | 100,000 | Negative | Negative | Positive |
| Doxorubicin + 5-FU + 5-FU + 5-FU + 5-FU + 5-FU + 5-FU + 5-FU + 5-FU + 5-FU + 5-FU + 5-FU + 5-FU + 5-FU | 100,000 | Negative | Negative | Negative |
{8}
9
| Diphenhydramine | 100,000 | Negative | Negative | Positive |
| --- | --- | --- | --- | --- |
| Doxepine | 100,000 | Negative | Negative | Positive |
| Ephedrine | 1,000,000 | Negative | Negative | Positive |
| Fluoxethine | 100,000 | Negative | Negative | Positive |
| Fluphenazine | 100,000 | Negative | Negative | Positive |
| Ibuprofen | 500,000 | Negative | Negative | Positive |
| Imipramine | 100,000 | Negative | Negative | Positive |
| Maprotiline | 100,000 | Negative | Negative | Positive |
| Nortryptiline | 100,000 | Negative | Negative | Positive |
| Oxazepam | 250,000 | Negative | Negative | Positive |
| Phencyclidine | 100,000 | Negative | Negative | Positive |
| Phenobarbital | 100,000 | Negative | Negative | Positive |
| Ranitidine | 500,000 | Negative | Negative | Positive |
| Secobarbital | 100,000 | Negative | Negative | Positive |
| Thioridazine | 100,000 | Negative | Negative | Positive |
## Endogenous Compounds
Potential interference from endogenous compounds commonly found in urine was evaluated in the qualitative and semi-quantitative modes, by spiking these compounds into drug free urine containing hydrocodone at $\pm 25\%$ of the $300~\mathrm{ng/mL}$ cutoff (225 and $375~\mathrm{ng/mL}$). Results obtained with the two reagent lots are the same.
| Compounds | Concentration tested (mg/dL) | -25% Cutoff (225ng/mL) | +25% Cutoff (375ng/mL) |
| --- | --- | --- | --- |
| No added compound | N/A | Negative | Positive |
| Acetaminophen | 10 | Negative | Positive |
| Acetone | 500 | Negative | Positive |
| Acetyl Salicylic Acid | 10 | Negative | Positive |
| Ascorbic Acid | 150 | Negative | Positive |
| Caffeine | 10 | Negative | Positive |
| Creatinine | 400 | Negative | Positive |
| Ethanol | 10 | Negative | Positive |
| Galactose | 5 | Negative | Positive |
| Glucose | 1000 | Negative | Positive |
| Hemoglobin | 150 | Negative | Positive |
| Human Serum Albumin (HSA) | 200 | Negative | Positive |
| Ibuprophen | 10 | Negative | Positive |
| Oxalic acid | 50 | Negative | Positive |
| Riboflavin | 3 | Negative | Positive |
| Sodium Chloride | 1000 | Negative | Positive |
| Urea | 1000 | Negative | Positive |
{9}
pH and Specific Gravity
For potential interference from the pH of urine, device performance in the qualitative and semi-quantitative modes was tested using a range of urine pH values (4.0, 5.0, 6.0, 7.0, 8.0, 9.0 and 10.0). All test samples were prepared in drug free urine containing hydrocodone at ± 25% of the cutoff (225 ng/mL and 375 ng/mL hydrocodone concentrations). No positive or negative interference was observed at urine pH values ranging from 4.0 to 10.0 for each test mode.
For potential interference from the specific gravity of urine, device performance in the qualitative and semi-quantitative modes was tested using a range of urine specific gravity values (1.000, 1.006, 1.007, 1.010, 1.013, 1.018, 1.021, 1.025, 1.028, 1.034 and 1.036). All test samples were prepared in drug free urine containing hydrocodone at ± 25% of the cutoff (225 ng/mL and 375 ng/mL hydrocodone concentrations). No positive or negative interference was observed at urine specific gravity values ranging from 1.000 to 1.036 for each test mode.
f. Assay cut-off:
Characterization of how the device performs analytically around the claimed cutoff concentration of 300 ng/mL hydrocodone is described in the precision section, M.1.a. above.
2. Comparison studies:
a. Method comparison with predicate device:
A total of 100 unaltered urine samples from pain management laboratories were analyzed by two lots of the candidate device in the qualitative and semi-quantitative modes on the Beckman Coulter AU680 clinical chemistry analyzer and the comparative mass spectrometry based quantitative method (LC-MS/MS). LC-MS/MS and immunoassay qualitative results are based on a 300 ng/mL cutoff. The results from the study in the two modes were same and are summarized below:
Qualitative and Semi-quantitative Mode
| Candidate Device Results | Negative | <50% of cutoff concentration by LC/MS (< 150ng/mL) | Near Cutoff Negative (Between 50% below the cutoff and the cutoff concentration by LC/MS) (150 ~ 299 ng/mL) | Near Cutoff Positive (Between the cutoff and 50% above the cutoff concentration by LC/MS) (300 ~ 450 ng/mL) | High Positive (Greater than 50% above the cutoff concentration by LC/MS) > 450 ng/mL |
| --- | --- | --- | --- | --- | --- |
| Positive | 0 | 1* | 5** | 10 | 39 |
| Negative | 31 | 6 | 7 | 1 | 0 |
* and ** are oxycodone positive samples that contained 41,240 ng/mL and 37,000 ng/mL oxycodone respectively.
% Agreement among positives is 98%.
% Agreement among negatives is 88%.
{10}
% Overall agreement is 93%.
# Discordant Result Table for the Discrepant Samples near cutoff
| Sample # | Qualitative EIA | LC-MS/MS (ng/mL) | | |
| --- | --- | --- | --- | --- |
| | | Hydrocodone | Hydromorphone | Hydromorphone 3β-D Glucuronide |
| 33 | Positive | 143.3 | <LLOQ+ | 67.6 |
| 70* | Positive | 138.4 | <LLOQ | <LLOQ |
| 75** | Positive | 216.7 | <LLOQ | <LLOQ |
| 76 | Positive | 198.8 | <LLOQ | 42.6 |
| 83 | Positive | 78.4 | <LLOQ | 110.1 |
| 89 | Positive | 192.3 | <LLOQ | 56.2 |
| 96 | Negative | 303.3 | <LLOQ | 50.1 |
ng/mL oxycodone respectively.
+LLOQ = Lowest Limit of Quantitation is 40 ng/mL
# b. Matrix comparison:
Not applicable. Urine is the only claimed matrix for the candidate device.
# 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.
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.