Kerasave is indicated for storage of human corneas at 2-8°C for up to 14 days. It is intended for prescription (Rx) use by physicians or highly skilled personnel, such as Eye Bank operators.
Device Story
Kerasave is a corneal storage medium containing preservatives and antifungals; used to temporarily preserve human cornea tissue between harvesting and transplantation. Device maintains corneal integrity during storage at 2-8 C for up to 14 days. Operated by physicians or skilled eye bank personnel. Output is preserved corneal tissue suitable for surgical implantation. Benefits include extended storage duration while maintaining endothelial cell density, morphology, transparency, and central corneal thickness. Requires rinsing of cornea prior to transplantation and complete dissolution of preservatives.
Clinical Evidence
No clinical data. Evidence based on non-clinical performance testing, including demonstration of endothelial cell density, morphology, transparency, and central corneal thickness following storage, as well as antimicrobial activity, biocompatibility, and shelf-life stability.
Technological Characteristics
Corneal storage medium containing preservatives and antifungals. Requires demonstration of chemical activity, concentration, and dissolution of preservatives. Must be sterile, biocompatible, and non-pyrogenic. Compatible with commercial container closure systems. Performance characteristics include maintenance of endothelial cell density, morphology, transparency, and central corneal thickness.
Indications for Use
Indicated for storage of human corneas at 2-8°C for up to 14 days. Intended for prescription use by physicians or skilled personnel (e.g., Eye Bank operators).
Regulatory Classification
Identification
Kerasave is a buffered corneal storage medium with preservatives, including antibiotics (gentamicin sulfate and streptomycin sulfate) and an antifungal agent (Amphotericin B), used to temporarily preserve human cornea tissue at 2-8°C for up to 14 days between harvesting and implantation. It is intended for prescription use by physicians or highly skilled personnel, such as Eye Bank operators.
Special Controls
In combination with the general controls of the FD&C Act, the corneal storage medium with preservatives including antifungals is subject to the following special controls:
Submission Summary (Full Text)
{0}------------------------------------------------
## DE NOVO CLASSIFICATION REQUEST FOR KERASAVE
#### REGULATORY INFORMATION
FDA identifies this generic type of device as:
Corneal storage medium with preservatives including antifungals. Corneal storage medium with preservatives including antifungals is a device that is used to temporarily preserve human cornea tissue between harvesting and implantation.
NEW REGULATION NUMBER: 21 CFR 886.4320
CLASSIFICATION: Class II
PRODUCT CODE: QCW
#### BACKGROUND
DEVICE NAME: Kerasave
SUBMISSION NUMBER: DEN200063
DATE DE NOVO RECEIVED: November 10, 2020
#### SPONSOR INFORMATION:
AL.CHI.MI.A. S.r.l. Viale Austria 14 Ponte San Nicolo, Province of Padua 35020 ITALY
#### INDICATIONS FOR USE
Kerasave is indicated for storage of human corneas at 2-8°C for up to 14 days. It is intended for prescription (Rx) use by physicians or highly skilled personnel, such as Eye Bank operators.
#### LIMITATIONS
The sale, distribution, and use of Kerasave are restricted to prescription use in accordance with 21 CFR 801.109.
Prior to distribution for surgical use, the cornea should be evaluated for suitable use as there may be reduced corneal clarity during storage due to the addition of Amphotericin B.
{1}------------------------------------------------
# PLEASE REFER TO THE LABELING FOR A MORE COMPLETE LIST OF WARNINGS, PRECAUTIONS, AND CONTRAINDICATIONS.
## DEVICE DESCRIPTION
Kerasave is made of a buffered corneal storage medium, which provides basic nutrients for cell maintenance during storage of donor corneas at 2-8°C for up to 14 days, at physiological pH. The device also includes antimicrobial agents. The antibiotics are dissolved in the solution and an antifungal agent is formulated as a tablet for stability reason and constitutes integral part of the device; it shall be dissolved in the medium prior to use.
The product specifications and ingredients for the Kerasave are presented in Table 2, respectively, below.
| Parameter | Product |
|---------------------------|-------------------------------------------|
| Form | Liquid |
| Appearance | Clear orange-red solution |
| Volume/Weight | 20 mL |
| Sterilization | Filtration |
| Contents | 12 vials and 12 tablets of Amphotericin B |
| Storage temperature | 2-8°C |
| Shelf-life | 24 months |
| Temperature of actual use | 2-8 °C |
| Use-life | 14 days |
| Number of uses | Single-use |
#### Table 1: Kerasave product summary
{2}------------------------------------------------
| Ingredient | Category | Function |
|-------------------------------------------------------------------------------------|---------------|------------------------------------------------------------------------------------------------------|
| (b)(4) and (b)(4) salt solution (including amino acids, vitamins, (b)(4) and (b)(4) | Base medium | Provides basic nutrients for cell maintenance, maintains pH, and a color indicator for pH indication |
| Sodium bicarbonate | Buffer | Maintains pH |
| Gentamicin sulfate | Antibiotic | Reduces bacterial growth |
| Streptomycin sulfate | Antibiotic | Reduces bacterial growth |
| Amphotericin B | Antifungal | Reduces Fungal Growth |
| Dextran (b)(4) | Osmotic agent | Prevents swelling, preserves corneal thickness |
| Sodium pyruvate | ATP precursor | Provides energy for pumping function |
## Table 2: Kerasave ingredients and their functions
## SUMMARY OF NONCLINICAL/BENCH STUDIES
## BIOCOMPATIBILITY
Kerasave is a surface device with prolonged (> h to 30 days) contact with breached/compromised surface. The biocompatibility assessment summarized below in Table 3 was conducted in accordance with FDA's Biocompatibility Guidance Document titled "Use of International Standard ISO 10993-1, "Biological evaluation of medical devices - Part 1: Evaluation and testing within a risk management process", as well as other relevant parts of standard ISO 10993- Biological evaluation of medical devices. This assessment demonstrated that the device is biocompatible for its intended use.
## Table 3: Summary of Biocompatibility Assessment
| Biocompatibility assessment | Assessment outcome |
|-------------------------------------------------------------------------------------|--------------------|
| Cytotoxicity (MEM extraction method) (ISO 10993-5) | Non-cytotoxic |
| Sensitization (Guinea pig maximization test) (ISO 10993-10) | Non-sensitizer |
| Ocular irritation (ISO 10993-10) | Non-irritant |
| Acute systemic toxicity (FDA Biocompatibility Guidance) | Non-toxic |
| Material mediated pyrogenicity (FDA Biocompatibility<br>Guidance) | Non-pyrogenic |
| Subacute/Subchronic systemic toxicity (FDA<br>Biocompatibility Guidance) | Non-toxic |
| Biocompatibility Assessment of Primary Packaging (FDA<br>Biocompatibility Guidance) | Biocompatible |
{3}------------------------------------------------
# CHEMICAL CHARACTERIZATION
Analysis of critical properties of Amphotericin B through chemical characterization were (D)(4) performed through multiple assessments. Identification by indicated that the Amphotericin B in Kerasave is the same as the TOTAL reference Amphotericin B CRS (Chemical Reference Substance). Further testing of the Amphotericin B tablet included an impurity profile that met limits based on US Pharmacopeia (UP) and European Pharmacopoeia; a heavy metals tests that met the acceptance criterion of @pm, and a light degradation assessment which demonstrated that the Amphotericin B concentration was above 11% after Thours of light exposure and indicated Amphotericin B was stable after hours of light exposure. Testing performed after dissolution of the tablet in solution indicated that there was a uniform distribution of the Amphotericin B and that the osmolality and pH stayed within acceptance limits 14 days after dissolving amphotericin B tablet in the solution,
### SHELF-LIFE/STERILITY
Device sterility is achieved using multiple methods of sterilization, including filter sterilization of the corneal storage medium, a combination of dry heat and gamma irradiation of the device primary packaging, and gamma irradiation of the Amphotericin B tablets. The dry heat and gamma irradiation sterilization methods were demonstrated to achieve a Sterility Assurance Level of 106 (e.g., a reduction of at least 106 microorganisms). The filter sterilization method was validated to reproducibly remove viable microorganisms from the aseptic manufacturing process. Bacterial endotoxin. testing demonstrated levels below recommended limits.
A shelf-life of 24 months has been established for Kerasave corneal storage media when stored at the recommended storage temperature of 2-8℃ in its primary packaging. A shelf-life of months has been established for Amphotericin B tablets when stored at the recommended storage temperature of 4℃ in its primary packaging. These claims are supported by demonstration of Kerasave corneal storage media and Amphotericin B tablet sterility and stability in both real-time and accelerated aging studies, as well as after short term storage at high temperatures.
Relevant standards followed include: Sterilizing Filtration of Liquids (PDA TR 26-2008-). Standard Test Method for Determining Bacterial Retention of Membrane Filters Utilized for Liquid Filtration (ASTM F838)-, Sterilization of health care products (ISO 11137-1 and ISO 11137-2, and ISO 20857). Bacterial Endotoxins (USP<85>).
## PERFORMANCE TESTING - BENCH
The performance characteristics of Kerasave were assessed to ensure that the cornea was preserved while in storage. The assessment for the preservation of the cornea included the viability of the endothelial cell layer, corneal clarity, and cornea central thickness.
### CORNEAL ENDOTHELIAL CELL LAYER PRESERVATION
The performance characteristics of Kerasave were assessed in comparison with Optisol-GS, a US FDA-cleared corneal storage medium as control in preserving the corneal endothelial cell layer using a Konan specular microscope. The specular microscopy outcomes measured were:
{4}------------------------------------------------
- Endothelial cell density (ECD) .
- . Endothelial cell morphology (pleomorphism): Hexagonality (HEX)
- Endothelial cell morphology (polymegathism): Coefficient of variation (%CV) .
Twenty-seven (27) paired donor corneas were included in the study. For each paired corneas, one comea was stored in Kerasave and the contralateral cornea in Optisol-GS. Tissue and media assignments were performed randomly. The storage was performed at 2-8°C for 14 days and each cornea was tested at Day 1 and Day 14. The study demonstrated that, using a mon-inferiority margin, the corneas stored in Kerasave were non-inferior to those stored in Optisol-GS at Day 14 in terms of ECD (Table 4) and HEX (Table 5). The study failed to statistically clear the 10% noninferiority margin between Kerasave and Optisol-GS at Day 14 in terms of %CV (Table 6). However, an exploratory analysis that excluded an outlier datapoint (CV%=DM) for Kerasave (identified as a protocol deviation), showed that Kerasave was non-inferior to the Optisol-GS in terms of Coefficient of variation (Table 7).
## Table 4: Endothelial Cell Density (ECD) Results Obtained in Corneas Stored in Kerasave or Optisol-Gs at Day 1 and Day 14
| | Kerasave | | Optisol-GS | |
|---------------------------------------------------------------------------------------------|-----------|------------|------------|------------|
| | ECD Day 1 | ECD Day 14 | ECD Day 1 | ECD Day 14 |
| Mean (cells/mm) | | | | (b)(4) |
| SD (cells/mm) | | | | |
| Median (cells/mm) | | | | |
| Minimum (cells/mm) | | | | |
| Maximum(cells/mm) | | | | |
| Coefficient of variation (%) | | | | |
| d, non-inferiority limit<br>(10% of the mean ECD in Optisol-GS<br>day 14) | | | | |
| The null hypothesis<br>µs: the mean Optisol-GS treatment<br>µe: the mean Kerasave treatment | | | | |
| Alternative hypothesis | | | | |
| Statistical analysis and conclusion | | | | |
{5}------------------------------------------------
# Table 5: Pleomorphism (hexagonality, HEX) results obtained in corneas stored in Kerasave or Optisol-Gs at Day 1 and Day 14 of storage
| | Kerasave | | Optisol-<br>GS | |
|-----------------------------------------------------------------------------------------------|--------------|---------------|----------------|---------------|
| | HEX<br>Day 1 | HEX<br>Day 14 | HEX<br>Day 1 | HEX<br>Day 14 |
| Mean | | (b)(4) | | |
| SD | | | | |
| Median | | | | |
| Minimum | | | | |
| Maximum | | | | |
| Coefficient of variation<br>(%) | | | | |
| d, non-inferiority limit<br>(10% of the mean HEX<br>in Optisol- GS day 14) | | | | |
| Null hypothesis<br>μs: the mean Optisol-GS<br>treatment<br>μe: the mean Kerasave<br>treatment | | | | |
| Alternative hypothesis | | | | |
| Statistical analysis and<br>conclusion | | | | |
{6}------------------------------------------------
## Table 6: Statistical evaluation of polymegathism (%CV) results based on pre-specified analysis obtained in corneas stored in Kerasave or Optisol-Gs at Day 1 and Day 14 of storage
| | Kerasave | | Optisol-GS | |
|-------------------------------------------------------------------------------------------------------------------------------------------|----------|--------|------------|--------|
| | Day 1 | Day 14 | Day 1 | Day 14 |
| Mean | | | (b)(4) | |
| SD | | | | |
| Median | | | | |
| Minimum | | | | |
| Maximum | | | | |
| Coefficient of<br>variation | | | | |
| d, non-inferiority limit<br>(10% of the mean CV% in Optisol-GS<br>day 14) | | | | |
| Null hypothesis<br>$ μs $ : the mean Optisol-GS treatment<br>$ μe $ : the mean Kerasave treatment | | | | |
| Alternative hypothesis | | | | |
| Statistical analysis and conclusion | | | | |
## Table 7: Exploratory Analysis of polymegathism (%CV) results obtained in corneas stored in Kerasave or Optisol-Gs at Day 1 and Day 14 of storage
| | Kerasave | | Optisol-GS | |
|----------------------------------------------------------------------------------------------|----------|--------|------------|--------|
| | Day 1 | Day 14 | Day 1 | Day 14 |
| Mean | | (b)(4) | | |
| SD | | | | |
| Median | | | | |
| Minimum | | | | |
| Maximum | | | | |
| Coefficient of variation | | | | |
| d, non-inferiority limit<br>(10% of the mean CV% in Optisol- GS day 14) | | | | |
| Exploratory analysis<br>μs: the mean Optisol-GS treatment<br>μe: the mean Kerasave treatment | | | | |
# EVALUATION OF PERFORMANCE CHARACTERISTICS ON CORNEA
Corneal clarity and central corneal thickness (CCT) were evaluated at Day 1 and Day 14. The 27 paired donor corneas used in the specular microscopy measurements were also used to determine the CCT and corneal clarity through optical coherence
{7}------------------------------------------------
tomography and slit lamp examination, respectively. The results demonstrated that the CCT changes were similar between the Kerasave and Optisol-GS arms and had no statistical difference (Table 8).
# Table 8: Statistical evaluation of Corneal central thickness (CCT) by OCT obtained in corneas stored in Kerasave or Optisol-GS at Day 1 and Day 14 of storage
| | Kerasave | | | Optisol-GS | | |
|--------------------------------------------|--------------|---------------|---------------------------------|--------------|---------------|---------------------------------|
| | CCT<br>Day 1 | CCT<br>Day 14 | Change in CCT<br>(Day14 - Dayl) | CCT<br>Day 1 | CCT<br>Day 14 | Change in CCT<br>(Day14 - Dayl) |
| Mean (µm) | | | (b)(4) | | | |
| SD (µm) | | | | | | |
| Median (µm) | | | | | | |
| Minimum (µm) | | | | | | |
| Maximum (µm) | | | | | | |
| Coefficient of variation(%) | | | | | | |
| <i>p</i> value (Kerasave<br>vs Optisol-GS) | | | | | | |
In the assessment for corneal clarity, a statistical difference was not observed for the clarity scores on the Day 14 between Kerasave and the comparator arm, Optisol-GS (Table 9). It should be noted that Kerasave had 7 out of the 27 corneas that progressed from a score of '1' (mild) on Day 1 to a score of '2' (moderate) on Day 14 demonstrating an increase in opacity. Whereas the control arm had 2 out of 27 corneas that had increased opacity from Day 1 to Day 14. Additionally, increased edema and fold/striae were observed in the corneas that progressed.
# Table 9: Statistical evaluation of corneal transparency scores obtained in corneas stored in Kerasave or Optisol- GS at Day 1 and Day 14 of storage
| | Transparency score<br>Kerasave | | Transparency score<br>Optisol-GS | |
|------------------------------------------------|--------------------------------|--------|----------------------------------|--------|
| | Day 1 | Day 14 | Day 1 | Day 14 |
| Median | | (b)(4) | | |
| Minimum | | | | |
| Maximum | | | | |
| <i>p</i> value1<br>(Kerasave vs<br>Optisol-GS) | | | | |
1Day 1 (p=1.0000, Mann-Whitney test) and Day 14 (p=0.1651, Mann-Whitney test)
## ANTIMICROBIAL EVALUATION
An analysis of antimicrobial presence and activity were provided. FDA determined that the concentrations of streptomycin, gentamicin, and Amphotericin B in the Kerasave device were unlikely to contribute to antimicrobial resistance emergence, or the spread of resistant microorganisms.
{8}------------------------------------------------
Ex-vivo testing and preservative testing were provided to evaluate effectiveness of the instructions for use in reducing antimicrobial presence prior to implantation to reduce unnecessary exposure, as well as the antimicrobial effectiveness of the antimicrobial components of the device, respectively.
## EX VIVO TESTING
Assessment of Amphotericin B accumulation on the cornea grafts was nerformed to determine the residual concentration of the antifungal after storage. [[b](4] corneal grafts (n=0) were stored in Kerasave device at 2-8°C for 14 days. The grafts (with or without rinsing in @mL of of to blows) were (b)s) ======================================================================================================================================================================== and evaluated (CD)10) by I for the presence of Amphotericin B. Amphotericin B was below detection limit in rinsed corneas and between mail - mg/cornea in corneas that were not rinsed.
# PRESERVATIVE TESTING
Kerasave with streptomycin and gentamicin (antibacterials) and Amphotericin B (antifungal) were tested at appropriate concentrations in the final solution. Testing was conducted to evaluate the microbial log reduction of laboratory strains, specifically
| specifically | | and | |
|-----------------------------------------------------------------------------------------|-------------------------------------------------------------------------------|-----|--|
| | (b)(4) after incubation in Kerasave. Testing was performed at (b)(4) (e.g., t | | |
| temperature range for product storage), and conducted in accordance with standard | | | |
| ISO 18259 (Contact lens care products). | (b)(4) in the device arm was | | |
| compared to microbial growth the control arm, which involved | (b)(4) The results indicate | | |
| that the combination of streptomycin and gentamicin in Kerasave inhibited the | | | |
| growth of all | (b)(4) tested in comparison to the respective | | |
| controls and reduced the number of | (b)(4) with known | | |
| susceptibility. With the addition of Amphotericin B to the storage solution, the (b)(4) | | | |
| (b)(4) population was reduced by (b)(4) (+/- SE), while the spore-forming | | | |
| filamentous fungi (Fusarium sp.) population was reduced by -log (+/- SE). These | | | |
| results demonstrate that the device adequately inhibited the growth of laboratory | | | |
## LABELING
Device labeling satisfies the requirements of 21 CFR & 801.109 for prescription devices. The device labeling provides product description, Indications for Use, and instructions for how to use the device by the end user. The labeling also provides a summary of the cornea viability after storage. The labeling includes warnings and precautions describing limitations and risks of the device.
# RISKS TO HEALTH
The table below identifies the risks to health that may be associated with use of corneal storage medium with preservatives including antifungals and the measures necessary to mitigate these risks.
{9}------------------------------------------------
| Identified Risks to Health | Mitigation Measures |
|----------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------|
| Infection | Sterilization validation<br>Non-clinical performance testing<br>Labeling<br>Shelf life testing |
| Adverse tissue reaction | Biocompatibility evaluation<br>Non-clinical performance testing |
| Antimicrobial resistance | Antimicrobial resistance analysis<br>Non-clinical performance testing<br>Labeling |
| Worsening prognosis that may need recurring<br>or more invasive surgery due to damage to<br>cornea tissue while in storage | Non-clinical performance testing<br>Labeling |
### Table 10: Identified Risks to Health and Mitigation Measures
### SPECIAL CONTROLS
In combination with the general controls of the FD&C Act, the corneal storage medium with preservatives including antifungals is subject to the following special controls:
- (1) Non-clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use.
- (i) The following performance characteristics of the cornea following storage in the device must be demonstrated:
- (A) Endothelial cell density;
- Endothelial cell morphology; (B)
- (C) Corneal transparency; and
- (D) Central corneal thickness.
- Antimicrobial activity of the device must be demonstrated at the initial and (ii) maximum labeled storage time.
- (iii) Characterization of all preservatives, including antifungals, must include the following:
- (A) Characterization of impurities, heavy metal analysis, concentration, and dissolution; and
- Chemical activity of all preservatives over the labeled use life of the (B) device.
{10}------------------------------------------------
- (2) Performance data must demonstrate the sterility of the device.
- The device must be demonstrated to be biocompatible and non-pyrogenic. (3)
- (4) Performance data must support the claimed shelf life by demonstrating continued sterility, controlled bioburden, package integrity, and device functionality over the intended shelf life.
- (5) The device and each of its components (e.g., antifungal, antibiotic, medium) must be demonstrated to be compatible with their respective commercial container closure system/packaging.
- (6) An analysis must be provided that identifies and evaluates any contribution to the development and spread of antimicrobial resistance.
- (7) Labeling must include the following instructions:
- (i) Rinsing of cornea prior to transplantation; and
- (ii) Complete dissolution of all preservatives.
## BENEFIT-RISK DETERMINATION
The risks of the device are based on the non-clinical performance testing data collected. The data demonstrated that corneal clarity decreased with increased edema and folds/striae in some of the corneas stored in the device for 14 days. Device labeling will help ensure that the end users clearly understand the device description, indications, contraindications, precautions, warnings, and instructions for use. Specifically, the device labeling informs the end user to check the suitability of the cornea prior to distribution.
The probable benefits of the device are based on the non-clinical performance testing data collected. The non-clinical study demonstrated inhibition in the growth of microbials in the presence of preservatives, including an antifungal in the device. The endothelial cell layer was preserved in the corneas stored in the device for 14 days.
Although it is unknown whether reduced corneal clarity may occur after transplantation, the overall probable benefits of limiting infection of the cornea tissue stored in the device that includes an antifungal agent to minimize microbial growth outweighs the probable risks of decreased corneal clarity.
### Pediatric Extrapolation
In this De Novo request, existing clinical data were not leveraged to support the use of the device in a pediatric patient population.
### Patient Perspectives
This submission did not include specific information on patient perspectives for this device.
{11}------------------------------------------------
## BENEFIT/RISK CONCLUSION
In conclusion, given the available information above, for the following indication statement:
Kerasave is indicated for storage of human corneas at 2-8°C for up to 14 days. It is intended for prescription (Rx) use by physicians or highly skilled personnel, such as Eye Bank operators.
The probable benefits outweigh the probable risks for the Kerasave device. The device provides benefits, and the risks can be mitigated by the use of general controls and the identified special controls.
## CONCLUSION
The De Novo request for the Kerasave is granted and the device is classified as follows:
Product Code: QCW Device Type: Corneal storage medium with preservatives including antifungals Regulation Number: 21 CFR 886.4320 Class: II
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.