K132066 · Rapid Pathogen Screening, Inc. · PFQ · Nov 21, 2013 · Clinical Chemistry
Device Facts
Record ID
K132066
Device Name
INFLAMMA DRY
Applicant
Rapid Pathogen Screening, Inc.
Product Code
PFQ · Clinical Chemistry
Decision Date
Nov 21, 2013
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1540
Device Class
Class 1
Indications for Use
InflammaDry is a rapid, immunoassay test for the visual, qualitative in vitro detection of elevated levels of the MMP-9 protein in human tears from patients suspected of having dry eye to aid in the diagnosis of dry eye in conjunction with other methods of clinical evaluation. This test is intended for prescription use at point-of-care sites. InflammaDry External Controls are QC materials used for verifying the performance of the InflammaDry test reagents and assay. These controls can also be used to assist in operator training and troubleshooting invalid results.
Device Story
InflammaDry is a lateral flow immunoassay for qualitative detection of MMP-9 protein in human tears. Device components include a sterile Dacron fleece sample collector, test cassette with membrane, and buffer vial. Operation: clinician collects tear sample from lower eyelid; sample is transferred to test strip; buffer initiates microfiltration to remove debris and transport immune complex. MMP-9 is captured between monoclonal mouse anti-MMP-9 (colloidal gold conjugate) and polyclonal goat anti-human antibody (immobilized at test line). Results are visual: red test line indicates elevated MMP-9 (>40 ng/mL); blue control line confirms test validity. Used at point-of-care; results available in 10-15 minutes. Output aids clinicians in dry eye diagnosis alongside other clinical evaluations. External controls (lyophilized recombinant MMP-9) verify reagent performance and assist operator training.
Clinical Evidence
Prospective, sequential, masked clinical trial (N=237). Compared InflammaDry results against clinical assessment (OSDI, TBUT, Schirmer, corneal staining). Positive agreement ranged 66%-97%; negative agreement 97%-98%. Analytical precision confirmed at 3 sites with 120 determinations per concentration. Specificity tested against various ocular microorganisms and cytokines; interference identified for specific medications (Iquix, Quixin, Proparacaine, Trusopt).
Indicated for patients suspected of having dry eye disease to aid in diagnosis. Requires prescription and point-of-care use. Contraindicated for patients with active intraocular inflammation (must be excluded via slit-lamp biomicroscopy).
Regulatory Classification
Identification
An osmolality test system is a device intended to measure ionic and nonionic solute concentration in body fluids, such as serum and urine. Osmolality measurement is used as an adjunct to other tests in the evaluation of a variety of diseases, including kidney diseases (e.g., chronic progressive renal failure), diabetes insipidus, other endocrine and metabolic disorders, and fluid imbalances.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k132066
B. Purpose for Submission:
New device
C. Measurand:
Matrix metalloproteinase-9 (MMP-9) in human tears
D. Type of Test:
Qualitative immunoassay
E. Applicant:
Rapid Pathogen Screening, Inc.
F. Proprietary and Established Names:
InflammaDry
InflammaDry External Controls
G. Regulatory Information:
1. Regulation section:
862.1540 Osmolality Test System
862.1660 Quality control material (assayed and unassayed)
2. Classification:
Class I, exempt; subject to limitations of exemption 21 CFR § 862.9 (b) and (c)(9)
Class I, reserved
3. Product code:
PFQ, JJX
{1}
4. Panel:
75, Chemistry
H. Intended Use:
1. Intended use(s):
See indications for use below
2. Indication(s) for use:
InflammaDry is a rapid, immunoassay test for the visual, qualitative *in vitro* detection of elevated levels of the MMP-9 protein in human tears from patients suspected of having dry eye to aid in the diagnosis of dry eye in conjunction with other methods of clinical evaluation. This test is intended for prescription use at point-of-care sites.
InflammaDry External Controls are QC materials used for verifying the performance of the InflammaDry test reagents and assay. These controls can also be used to assist in operator training and troubleshooting invalid results.
3. Special conditions for use statement(s):
- For prescription use only
- For point-of-care use
- Slit-lamp biomicroscopy is required to eliminate patients with active intraocular inflammation.
- InflammaDry requires a visual readout. Do not interpret the test result if you have color-impaired vision.
- The Dacron material used in the Sampling Fleece may cause allergic reactions for some people.
- InflammaDry should be performed prior to instilling ocular anesthetic, topical dyes, or performing Schrimer testing.
- Certain medications may cause erroneous results if used immediately before taking a sample. If ocular anesthetic or any other topical medication has been applied to the eye, wait at least 2 hrs prior to collecting a sample.
4. Special instrument requirements:
Not applicable; this is a visually read single use device
2
{2}
3
I. Device Description:
InflammaDry™ consists of three (3) parts: a sterile sample collector, an immunoassay test strip in a plastic test cassette housing, and buffer in a vial. The separately packaged and sterile sample collector has a contoured end with a dacron fleece to collect the tear sample from the inside of the lower eyelid. The plastic housing of the test cassette body protects the strip from unintended physical influence. Additionally, the housing guarantees correct sample transfer onto the lateral flow assay strip. The buffer vial contains a buffered salt solution containing: 200 mM Tris, 10% Fish 81 (sea block), 0.8% Tergitol, 100 mM NaCl, 0.1% Sodium Azide, 0.0126% Gentamycin and pH 9.5 ± 0.05. The buffer functions as the solution that initiates the test, carries antigen through a microfiltration process to remove unwanted cellular debris, and transports the immune complex and the control conjugate to the “Test” and “Control” lines on the test strip membrane.
The InflammaDry external controls are supplies as lyophilized powder in small glass vials with screw caps. A soft and pliable plastic dropper bottle filled with DI water diluent is provided with each set of external controls to reconstitute the lyophilized control materials.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Occusense Inc. TearLab Osmolarity System and TearLab Control Solutions
2. Predicate 510(k) number(s):
k083184
3. Comparison with predicate:
| Similarities/Difference | | |
| --- | --- | --- |
| Item | Candidate Device | Predicate Device |
| Indications for Use | Measurement of tear fluid from patients suspected of having dry eye to aid in the diagnosis of dry eye in conjunction with other methods of clinical evaluation. | Same |
| Materials | Plastic housings, membrane, glass fiber absorbent tip and waste pad, foil pouches, MMP-9 antibody gold conjugate, dacron fleece and buffer solution. Phenol red dye added to | The device consists of the following components and accessories: One TearLab Reader, Two TearLab Pens, Two TearLab |
{3}
| Similarities/Difference | | |
| --- | --- | --- |
| Item | Candidate Device | Predicate Device |
| | the sample collector dacron fleece. | Electronic Check Cards, Single Use TearLab Osmolarity Test cards and TearLab Control Solutions. |
| Sterile | Yes, sample collector by gamma radiation | No; test cards are hygienically clean |
| Kit composition | Sample collector and test cassette sealed in foil pouches and a vial of buffer | The device consists of the following components and accessories: One TearLab Reader, Two TearLab Pens, Two TearLab Electronic Check Cards, Single Use TearLab Osmolarity Test cards and TearLab Control Solutions. |
| Technology | Lateral Flow Immunoassay | The TearLab Osmolarity Test utilizes an impedance measurement of tear fluid to provide a calculated measurement of osmolarity |
| Form | Lyophilized | Liquid |
| Intended use of the controls | Verify performance of InflammaDry test reagent and assay; assist with operator training; troubleshoot invalid results | Monitor day-to-day test variation; lot-to-lot kit performance; assist with operator training; troubleshoot invalid results |
| Test Results | Qualitative | Quantitative |
## K. Standard/Guidance Document Referenced (if applicable):
11137-1; ANSI/AAMI/ISO Sterilization of health care products – Radiation -Part 1: Requirements for development, validation and routine control of a sterilization process for medical devices, 2006/(R) 2010
11137-2; ANSI/AAMI/ISO Sterilization of health care products – Radiation – Part 2: Establishing the Sterilization Dose 2012
14971; ISO Medical Devices – Application of Risk Management to Medical Devices
## L. Test Principle:
The InflammaDry test is based on the principle of lateral flow immunoassay using direct sampling micro-filtration technology. Matrix Metalloproteinase -9 (MMP-9) present in the tear fluid is captured between two highly specific anti-MMP-9 antibodies: a monoclonal
{4}
mouse anti-MMP-9 antibody and a polyclonal goat antihuman antibody. This antigen-antibody complex is captured by NeutrAvidin immobilized as the test line. The formation of a blue color line at the control zone line with a red color line at the test zone line is considered as a positive result, a blue color line at the control zone only is considered as a negative result, if a blue color line in the control zone does not appear the test is considered invalid.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
Precision studies were performed at three point-of-care sites using stabilizing buffer spiked to the following concentrations: negative (zero), cutoff, +/-25%, and +/-50%, of the cutoff. The samples were aliquoted, randomized and blinded, then given to each site. A total of 120 determinations were made at each concentration. Testing was performed in duplicate twice a day over 5 days by 6 intended use operators (2/site). The intended users performed the testing by following the instructions for use. Sample concentrations were confirmed by LC/MS/MS.
| | | Negative | -50% | -25% | Cutoff | +25% | +50% |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | Neg/Pos | Neg/Pos | Neg/Pos | Neg/Pos | Neg/Pos | Neg/Pos |
| Site 1 | Op 1 | 20/0 | 19/1 | 18/2 | 4/16 | 0/20 | 0/20 |
| | Op 2 | 20/0 | 19/1 | 10/10 | 4/16 | 2/18 | 0/20 |
| Site 2 | Op 1 | 20/0 | 20/0 | 17/3 | 10/10 | 3/17 | 0/20 |
| | Op 2 | 20/0 | 20/0 | 18/2 | 12/8 | 2/18 | 3/17 |
| Site 3 | Op 1 | 20/0 | 20/0 | 19/1 | 10/10 | 2/18 | 0/20 |
| | Op 2 | 20/0 | 20/0 | 18/2 | 12/8 | 2/18 | 0/20 |
| Combined | | 120/0 | 118/2 | 100/20 | 52/68 | 11/109 | 3/117 |
#### b. Linearity/assay reportable range:
Not applicable. The assay is intended for qualitative use.
#### c. Traceability, Stability, Expected values (controls, calibrators, or methods):
InflammaDry has built-in procedural controls. The appearance of the control line indicates the correct application of sample volume
InflammaDry External Controls consists of 2 levels (a positive and a negative) of QC materials: Positive controls are prepared by spiking MMP-9 in stabilizing buffer solution with known concentration of MMP-9 antigen which are traceable to a MMP-
{5}
9 monomer form of progelatinase B from human blood. The positive control concentrations are confirmed by LC/MS/MS. Negative control is recombinant MMP-9 in stabilizing buffer solution containing no drug.
External controls solutions are not supplied with this device but can be purchased separately from Rapid Screening Diagnostic Inc. Users are advised to follow federal, state and local guidelines for QC testing requirements.
Stability:
Accelerated and Real time studies have been conducted for the control material. Protocols and acceptance criteria were described and found to be acceptable. The manufacturer claims that when stored un-opened at room temperature, the product is stable until expiration date which is 24 months. Open vial stability the controls should be used on the same day they are reconstituted.
d. Detection limit:
Not applicable, this is a qualitative assay.
e. Analytical specificity:
Cross-reactivity of the test with various microorganisms and cytokines was assessed by adding 15 μl of potential cross-reactant to a sample collector fleece then running the test as per the directions. Microorganism concentrations ranged from 500,000 and 1,500,000 microorganisms (virus, bacteria) per ml of supernatant and cytokines were tested at 150 ng/mL. All isolates were cultured from human specimen. There were no positive tests observed for the following:
Microorganism (virus, bacteria) and ocular enzymes:
Adenovirus, IgE, Staphylococcus aureus, Methicillin resistant Staphylococcus aureus (MRSA), Moraxella catarrhalis, Haemophilus influenza, Staphylococcus epidermis, Streptococcus pneumonia and Pseudomonas aeroginosa.
Cytokines:
Matrix metalloproteinase: 1, 2 and 3
Tissue Inhibitor of MMP: MMP-1, MMP-2
Interference study:
The effect of different eye drops on the analytical sensitivity and specificity of the InflammaDry™ tests was determined. The eye drops were evaluated with two different MMP-9 antigen concentrations, C₅ (C₅₀ - 25%) and C₉₅ (C₅₀ + 25%) in duplicate. Influence of the relevant proteins on sensitivity and specificity is also examined. Any positive or negative interfering substance identified by this testing was re-tested using C₅₀ - 50%, and C₅₀ +50%.
6
{6}
The following eye medications were tested for interference in human tears at the cutoff level and the respective medication. The following medications did not show any interferences:
Alcaine Alcon, "Azopt"-Alcon, Econopred Alcon, "Nevanac"-Alcon, "Pataday"-Alcon, Systaine"-Alcon, Tobra Dex, "Travatan"-Alcon, Alcon, Vigamox Alcon, "Acular LS"-Allergan, Alphagan Allergan, "Combigan"-Allergan, Elastat Allergan, "FML"-Allergan Lastacaft -Allergan, Lumigan Allergan, Optive"-Allergan, Pred Forte"-Allergan, Refresh Liquigel, Refresh Tears Allergan, Zymar Allergan, "Blink Tears"-Amo, Thera Tears AVS, Alrex B&L, Lotemax B&L, "Zylet"-Bausch&Lomb, Gentamycin Sulfate-Falcon, Polymyxin B sulfate Falcon, "Timolol"-Falcon, "AzaSite"-Inspire, Bepreve-Ista, "Xibrom"-Ista, Optivar MedPDEnte, Truspot Merck, GenTeal"-Novartis, "Voltaren"-Novartis, "Zaditor"-Novartis, Visine Pfizer, Xalatan Pharmacia, human IgA (1 mg/ml), Sigma-Aldrich, human lactoferrin (1 mg/ml), Sigma-Aldrich, Transferrin (1 mg/ml), Betimol Vistakon
However, the following medications show false positive or false negative results: Vistakon, Iquix; Vistakon, Quixin; Wilson, Proparacaine; and Trusopt.
Therefore, sponsor has the following limitations in the labeling:
Patients should not be tested with InflammaDry if the following medications were administrated into the eyes within 2 hours of the testing of the ImflammaDry. Interferences medications: Vistakon, Iquix; Vistakon, Quixin; Wilson, Proparacaine; and Trusopt.
Certain medications such as systemic immunodulators, topical or oral steroids, cyclosporine, tetracycline and topical azithromycin are known to inhibit metalloproteinase activity. Use of these medications may lead to false negative results.
f. Assay cut-off:
The cutoff study performed used increments from 5 ng/mL to 70 ng/mL. The study was conducted with 10 operators testing 10 replicates using stabilizing buffer sample. The results are presented in the table below:
| Concentration (ng/mL) | Negative | Positive |
| --- | --- | --- |
| 5 | 100 | 0 |
| 10 (-75%) | 93 | 7 |
| 20 (-50%) | 97 | 3 |
| 30 (-25%) | 83 | 17 |
| 35 | 65 | 35 |
| 40 (cutoff) | 48 | 52 |
| 50 (25%) | 5 | 95 |
| 60 (50%) | 0 | 100 |
| 70 (75%) | 0 | 100 |
{7}
8
2. Comparison studies:
a. Method comparison with predicate device:
See clinical study in 3.c. below.
b. Matrix comparison:
Not applicable. The assay is intended for only one sample matrix.
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):
The InflammaDry Test underwent a clinical evaluation to determine the negative and positive agreement of the InflammaDry with clinical assessment of dry eye. The study design was a prospective, sequential, masked, clinical trial. Those patients who were clinically determined by an ophthalmic clinician to meet enrollment criteria were included in the study. The study enrolled 237 patients consisting of 164 females and 73 males between the ages of 18 and 94 years old with an average age of 53 years. Patients presented from both private practices and academic centers from various regions across the country. Although 257 patients were recruited, seventeen (17) patients were excluded for a protocol deviation.
The protocol deviation involved patients receiving topical ocular anesthetic prior to the evaluation of the tear break up time (TBUT) and corneal staining, potentially accelerating the TBUT and inducing corneal staining.
Study testing was done on the subject’s more symptomatic eye (if no difference existed symptomatically between the two eyes, the right eye was tested). Each subject underwent the following sequence of testing: Each patient had the following tests performed: InflammaDry, tear break up time (TBUT), Schirmer tear testing, and corneal staining.
The InflammaDry was compared to the clinical assessment in the table below. Derived from the DEWS criteria, the clinical assessment was developed to represent a combination of symptoms and signs. The pivotal clinical trial used the same metrics for TBUT, Schirmer tear testing, and
{8}
corneal staining as described in the DEWS criteria, however, conjunctival injection, conjunctival staining, and the presence of meibomian disease were not tested or used to characterize the severity of dry eye disease. In general, the worst severity for any sign tested determined the overall severity. Symptoms are known to be poorly correlated with signs with even the most severe dry eye patients often reporting little to no symptoms. Patients were categorized to the highest severity level at which all required criteria are satisfied. Patients who do not meet all the required clinical criteria for a given severity grade will be considered to be at the next lower grade.
| Clinical Testing | Negative Control | Mild Grade 1 | Moderate Grade 2 | Moderately Severe Grade 3 | Sever Grade 4 |
| --- | --- | --- | --- | --- | --- |
| OSDI score | ≤13 | ≥13 | ≥13 | ≥13 | ≥13 |
| TBUT (sec) | >10 | <10 | <10 | ≤5 | 0 (immediate) |
| Schirmer (mm/5 min) | >10 | <10 | <10 | ≤5 | ≤2 |
| Staining (0-5) | None | None | 1-2 | 3 | ≥4 |
Clinical Results
| Site 1 | Grade | | | | | Total |
| --- | --- | --- | --- | --- | --- | --- |
| | 4 | 3 | 2 | 1 | 0 | |
| InflammaDry + | 0 | 0 | 15 | 41 | 1 | 57 |
| InflammaDry - | 0 | 0 | 0 | 2 | 31 | 33 |
| Total | 0 | 0 | 15 | 43 | 32 | 90 |
| Site 2 | Grade | | | | | Total |
| --- | --- | --- | --- | --- | --- | --- |
| | 4 | 3 | 2 | 1 | 0 | |
| InflammaDry + | 0 | 7 | 21 | 1 | 1 | 30 |
| InflammaDry - | 0 | 0 | 0 | 7 | 47 | 55 |
| Total | 0 | 7 | 21 | 9 | 48 | 85 |
| Site 3 | Grade | | | | | Total |
| --- | --- | --- | --- | --- | --- | --- |
| | 4 | 3 | 2 | 1 | 0 | |
| InflammaDry + | 0 | 0 | 4 | 4 | 0 | 8 |
| InflammaDry - | 0 | 0 | 3 | 1 | 0 | 4 |
| Total | 0 | 0 | 7 | 5 | 0 | 12 |
| Site 4 | Grade | | | | | Total |
| --- | --- | --- | --- | --- | --- | --- |
| | 4 | 3 | 2 | 1 | 0 | |
| InflammaDry + | 1 | 11 | 20 | 1 | 0 | 33 |
| InflammaDry - | 0 | 2 | 13 | 2 | 0 | 17 |
| Total | 1 | 13 | 33 | 3 | 0 | 50 |
Grade is assessed based on OSDI, TBUT, Schirmer tear testing, and corneal staining as described
{9}
in the DEWS criteria, however, conjunctival injection, conjunctival staining, and the presence of meibomian disease were not tested or used to characterize the severity of dry eye disease.
- Grade 0 (Negative Control) is when OSDSI is ≤13, TBUT is >10 seconds, Schirmer is >10mm, Staining is none.
- Grade 1 (Mild) is when OSDI score is ≥ 13, TBUT is <10 seconds, Schirmer test is <10 mm, Staining is none.
- Grade 2 (Moderate) is when OSDSI is ≥13, TBUT is ≤10 seconds, Schirmer is ≤10 mm, Staining is 1-2.
- Grade 3 (Moderately Severe) is when OSDSI is ≥13, TBUT is <5 seconds, Schirmer is ≤5 mm, Staining is 3.
- Grade 4 (Severe) is when OSDSI is ≥13, TBUT is 0 seconds (immediate), Schirmer is ≤2 mm, Staining is ≥4.
Device Performance:
The multicenter clinical study depicted below demonstrated the following range of performance: Positive Agreement 66%-97% and Negative Agreement 97%-98%. At 2 sites Negative Agreement could not be calculated because there were no subjects without dry eye.
| N=237 | | | Clinical Assessment ODSI** + TBUT + Schirmer + Staining | | Positive % agreement 95% confidence interval | Negative % agreement 95% confidence interval |
| --- | --- | --- | --- | --- | --- | --- |
| | | | Positive | Negative | | |
| Site 1 | InflammaDry | Positive | 56 | 1 | 97% (56/58) (88%, 99%) | 97% (31/32) (84%, 99%) |
| | | Negative | 2 | 31 | | |
| Site 2 | InflammaDry | Positive | 29 | 1 | 76% (29/37) (62%, 90%) | 98% (47/48) (89%, 100%) |
| | | Negative | 8 | 47 | | |
| Site 3 | InflammaDry | Positive | 8 | 0 | 67% (8/12) (39%, 86%) | N/A* |
| | | Negative | 4 | 0 | | |
| Site 4 | InflammaDry | Positive | 33 | 0 | 66% (33/50) (51%, 79%) | N/A* |
| | | Negative | 17 | 0 | | |
*N/A = not available. Negative Agreement cannot be calculated because there were no subjects without dry eye.
** 11 patients were assessed to be positive for mild dry eye based on the OSDI (OSDI ≥ 13) without any associated positive objective test results
4. Clinical cut-off:
40 ng/mL
{10}
5. Expected values/Reference range:
Based on the literature the sponsor claims that the normal levels of MMP-9 in human tears range from 3 ng/mL to 40 ng/mL.
Literature:
1. Acera A, Rocha G, Vecino E, et al. Inflammatory markers in the tears of patients with ocular surface disease. Ophthalmic Res. 2008 Oct; 40(6):315-21.
2. Chotikavanich S, de Paiva CS, Li de Q, et al. Production and activity of matrix metalloproteinase-9 on the ocular surface increase in dysfunctional tear syndrome. Invest Ophthalmol Vis Sci. 2009 Jul; 50(7):3203-9.
3. Solomon A, Dursun D, Liu Z, et al. Pro- and anti-inflammatory forms of interleukin-1 in the tear fluid and conjunctiva of patients with dry-eye disease. Invest Ophthalmol Vis Sci. 2001;42(10):2283-92.
4. Leonardi A, Brun P, Abatangelo G, et al. Tear levels and activity of matrix metalloproteinase (MMP)-1 and MMP-9 in vernal keratoconjunctivitis. Invest Ophthalmol Vis Sci. 2003;44(7):3052-8.
5. Lema I, Sobrino T, Durán JA, et al. Subclinical keratoconus and inflammatory molecules from tears. Br J Ophthalmol. 2009;93(6):820-4.
6. Honda N, Miyai T, Nejima R, et al. Effect of latanoprost on the expression of matrix metalloproteinases and tissue inhibitor of metalloproteinase 1 on the ocular surface. Arch Ophthalmol. 2010;128(4):466-71.
N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.