DEN230087 · Peytant Solutions, Inc. · SDB · Oct 16, 2024 · Anesthesiology
Device Facts
Record ID
DEN230087
Device Name
AMStent® Tracheobronchial Covered Stent System
Applicant
Peytant Solutions, Inc.
Product Code
SDB · Anesthesiology
Decision Date
Oct 16, 2024
Decision
DENG
Submission Type
Direct
Regulation
21 CFR 868.3721
Device Class
Class 2
Attributes
Therapeutic
Indications for Use
The AMStent® Tracheobronchial Covered Stent System (AMStent® System) is indicated for use in the treatment of tracheobronchial strictures produced by malignant neoplasms in adult patients.
Device Story
Self-expanding nitinol stent (10mm x 40mm) covered with decellularized amniotic membrane (DCAM) attached via PET sutures; preloaded on pull-back delivery catheter. Used in clinical settings by physicians under bronchoscopic/fluoroscopic guidance. Input: standard 0.035" guidewire (not included). Output: mechanical airway patency. Radiopaque markers facilitate placement. Device maintains airway lumen in patients with malignant tracheobronchial strictures, providing palliative relief of labored breathing. Single-use only; non-repositionable after deployment.
Clinical Evidence
No clinical data. Evidence based on non-clinical bench testing and two GLP-compliant large animal studies (one chronic 92-day, one acute). Animal studies evaluated safety, implantability, migration, systemic effects, and usability, demonstrating satisfactory performance.
Technological Characteristics
Self-expanding nitinol (NiTi) stent; decellularized amniotic membrane (DCAM) cover; PET suture attachment. Dimensions: 10mm diameter x 40mm length. MR Conditional (3T). Sterilization: terminal sterilization. Delivery system: pull-back catheter with radiopaque markers. Complies with ISO 10993-1 (biocompatibility), ASTM F2052-15, F2213-06, F2119-07 (MRI), and ASTM D4169, F2096-11, F88-15, F1886/F1886M-16 (packaging).
Indications for Use
Indicated for adult patients with tracheobronchial strictures caused by malignant neoplasms. Contraindicated for small bronchi impeding catheter removal, tracheobronchial obstruction with lumen diameter <4mm, and patients where bronchoscopic procedures are not recommended.
Regulatory Classification
Identification
The tracheal prosthesis with cover material derived from human sources is an expandable tubular device made of a metal material covered with a human-sourced decellularized material. It is intended to be implanted to restore the structure and/or function of the trachea or tracheobronchial tree. This device may also include a device delivery system. The AMStent® Tracheobronchial Covered Stent System is indicated for use in the treatment of tracheobronchial strictures produced by malignant neoplasms in adult patients.
Special Controls
In combination with the general controls of the FD&C Act. the tracheal prosthesis with cover material derived from human sourcesis subject to the following special controls:
Submission Summary (Full Text)
{0}------------------------------------------------
### DE NOVO CLASSIFICATION REQUEST FOR AMSTENT® TRACHEOBRONCHIAL COVERED STENT SYSTEM
#### REGULATORY INFORMATION
FDA identifies this generic type of device as:
Tracheal prosthesis with cover material derived from human sources. The tracheal prosthesis with cover material derived from human sources is an expandable tubular device made of a metal material covered with a human-sourced decellularized material. It is intended to be implanted to restore the structure and/or function of the trachea or tracheobronchial tree. This device may also include a device delivery system. This device type does not include products that are intended to promote regeneration, impede inflammatory cascades, and release growth factors.
NEW REGULATION NUMBER: 21 CFR 868.3721
CLASSIFICATION: Class II
PRODUCT CODE: SDB
#### BACKGROUND
DEVICE NAME: AMStent® Tracheobronchial Covered Stent System
SUBMISSION NUMBER: DEN230087
DATE DE NOVO RECEIVED: December 20, 2023
#### SPONSOR INFORMATION:
Peytant Solutions, Inc. 3650 Annapolis Lane North, #180 Plymouth, MN 55447
#### INDICATIONS FOR USE
The AMStent® Tracheobronchial Covered Stent System (AMStent® System) is indicated for use in the treatment of tracheobronchial strictures produced by malignant neoplasms in adult patients.
#### LIMITATIONS
The AMStent® System is contraindicated for:
- · Small bronchi which could impede catheter removal.
{1}------------------------------------------------
• Tracheobronchial obstruction with a lumen diameter which cannot be dilated and maintained at a minimum of 4mm.
· Patients for whom bronchoscopic procedures are not recommended.
### WARNINGS
- The safety and effectiveness of the AMStent® System for use in the vascular . system has not been established and can result in serious harm and/or death.
- . This product has been designed for single patient use only. Do not reuse. Do not resterilize.
- Inspect the packaging and device before use. Do not use if the packaging is damaged or the device is damaged. Do not use unless the packaging sterile barrier is intact.
- . Do not use if expiration date has been exceeded.
- The AMStent® delivery catheter is not intended for any use except AMStent® deployment.
- . Placing an AMStent® across a major bifurcation may prevent or hinder future access for other procedures.
- . Placing the AMStent® across bifurcations or side branches could impede airflow to the affected portions of the lung.
- The AMStent® cannot be repositioned in the airway after partial or full deployment.
- . If the AMStent® is partially or fully deployed, the AMStent® cannot be resheathed or remounted onto the AMStent® delivery catheter.
- . Do not place an AMStent® in a tumor stricture that is adjacent to a major vessel, as this may create a potential for fistula formation.
- . A 0.035" guidewire is required before introduction of the AMStent® delivery catheter into the body. The guidewire must remain in place during the introduction, manipulation, and eventual removal of the AMStent® delivery catheter.
- . After use, dispose of product and packaging in accordance with hospital, administrative, and/or local government policy.
- . The AMStent® contains nitinol, an alloy of nickel and titanium. Persons with allergic reactions to these metals may suffer an allergic reaction to this implant. Prior to implantation, patients should be counseled on the materials contained in the device, as well as potential for allergy/hypersensitivity to these materials.
## PLEASE REFER TO THE LABELING FOR A COMPLETE LIST OF WARNINGS, PRECAUTIONS AND CONTRAINDICATIONS.
## DEVICE DESCRIPTION
Peytant Solutions, Inc. developed the AMStent® Tracheobronchial Covered Stent System (AMStent System) to provide patency of the tracheobronchial tree in patients suffering from tracheobronchial strictures produced by malignant neoplasms. Like other nitinol devices that are also used for treating tracheobronchial strictures produced by malignant neoplasms, the AMStent System consists of a self-expanding metallic stent
{2}------------------------------------------------
(SEMS) that has a covering material over the interstices of the stent is provided preloaded on a delivery catheter (Figure 1). The difference is that the AMStent covering is made from human-sourced decellularized amniotic membrane (DCAM), while the existing stents utilize synthetic cover materials (e.g., polyurethane, ePTFE, or silicone).
The AMStent is an open-cell, self-expanding, nitinol stent (10mm diameter x 40mm length) with a DCAM cover that is attached to the stent with polyethylene terephthalate (PET) sutures. The AMStent is preloaded on a flexible, "pull-back," AMStent delivery catheter. The AMStent delivery catheter is positioned in the tracheobronchial stricture with the assistance of a standard 0.035" guidewire, that is not provided with the AMStent System, under bronchoscopic and / or fluoroscopic visualization. Radiopaque markers are located on each end of the AMStent and on the distal end of the AMStent delivery catheter to facilitate placement.
Image /page/2/Figure/2 description: The image shows a medical device and its components. The top part of the image shows a stent with radiopaque markers. The bottom part of the image shows a diagram of the device, with labels indicating the distal tip, outer sheath, Y-manifold, Tuohy-Borst, and Luer hub. The diagram also indicates the guidewire lumen, stopcock, and hypotube.
Figure 1: The AMStent system stent (above) and delivery catheter (below)
Third-party Components and Accessories: The device is delivered with a 0.035" guidewire under bronchoscopy and includes radiopaque markers for detection via fluoroscope. The guidewire and fluoroscope are not included in the device. The device also requires saline and a 10cc syringe.
### SUMMARY OF NONCLINICAL/BENCH STUDIES
{3}------------------------------------------------
The non-clinical/bench studies conducted on the Pevtant Solutions AMStent System are summarized in the sections below. Note that certain tests were conducted in DEN200047. including some of the engineering/bench testing and shelf-life testing.
### BIOCOMPATIBILITY
AMStent System materials with direct or indirect patient contact, representative of the final finished product, were tested based on ISO 10993-1: 2018 and FDA guidance "Use of International Standard ISO 10993-1, "Biological evaluation of medical devices – Part 1:Evaluation and testing within a risk management process" issued September 8, 2023. The stent related materials were tested for long-term (>30 day) duration and the delivery catheter materials were tested for a limited (≤24 hours) duration. Cytotoxicity testing of the AMStent primary package (tray with Tyvek lid) was conducted to provide additional assurance of biological safety. The results of all biological tests demonstrated that the patient contacting materials of the AMStent System device are biocompatible.
### SHELF-LIFE
All testing of the complete AMStent System including packaging, delivery catheter, and AMStent, to include independent characterization of the DCAM cover, has demonstrated continued intended function over a minimum of 90 days. As a result, the current shelf life is established at 90 days from the date of sterilization.
## MR COMPATIBILITY
The AMStent was tested for safety in the Magnetic Resonance Imaging (MRI) environment on fully finished and sterilized AMStents that had been deployed from the AMStent delivery catheter. Testing was conducted in accordance with ASTM F2052-15, ASTM 2213-06. ASTM 2119-07. Testing was conducted at 3-Tesla (magnetic field interactions, and artifacts). MRI-related heating was conducted at 1.5 Tesla/64 MHz, and 3 Tesla/128 MHz.
Testing resulted in a recommendation for the following MRI Compatibility labeling:
## MR Conditional
Magnetic Field Interactions: translational attraction was 2 degrees.
MRI-Related Heating: expected maximum temperature rise of 3.1℃ after 15 minutes of continuous scanning.
Artifacts: image artifact extends approximately 5 mm from the implant using69 gradient echo pulse sequence and a 3 Tesla System
### PACKAGING
Engineering bench testing of the AMStent System packaging was conducted in as follows:
- Distribution testing in accordance with ASTM D4169: 2016;
- · Bubble Leak testing in accordance with ASTM F2096-11;
- · Seal Strength testing in accordance with ASTM F88-15:
- · Visual inspection in accordance with ASTM F1886/F1886M-16.
{4}------------------------------------------------
In addition, due to its direct contact with the AMStent delivery catheter, cvtotoxicity testing of the PETG tray in accordance with ISO 10993-5: 2009 was conducted, as noted above. Results of this testing indicated the tray to be non-cytotoxic.
### PERFORMANCE/BENCH TESTING
Performance testing of the AMStent System on the catheter, stent, and stent cover. This included stent deployment, compression and recoil, expansion force, dimensional, fatigue, and corrosion tests, as well as puncture testing of the DCAM cover. Specific testing related to stent corrosion and Ni ion release was performed as recommended in the FDA guidance Technical Considerations for Non-Clinical Assessment of Medical Devices Containing Nitinol. The products used for testing had undergone all processing. including sterilization, and underwent simulated distribution prior to conducting the tests. These engineering bench tests were conducted on product that had not been intentionally aged, although many had been real-time aged as discussed in the individual test reports. Testing was also conducted on product and packaging that had been intentionally aged for a minimum of 90 days to ensure continued performance as intended over the labeled shelf life. The testing was satisfactory to show the device performs as intended and is safe for use.
### HUMAN TISSUE CONTROLS
The AMStent System process for obtaining and preparing human tissue for use as a stent cover is sufficient and meets regulatory requirements for the use of human cells, tissues, and cellular and tissue-based products (HCT/P's). The AMStent System includes a human-sourced decellularized amniotic membrane cover. The process of obtaining DCAM material for use in manufacture of the AMStent System includes the key steps as shown in Table 1. Each step is to be conducted in accordance with 21 CFR 1271 requirements and Current Good Tissue Practice (CGTP) requirements. To ensure adherence to 21 CFR 1271 and reduce the risk of transmitting communicable diseases, facilities involved in the processing of DCAM coupons to be used on the AMStent are required to be an FDA registered facility and approved in writing by Peytant Solutions, Inc.
Risk control measures implemented include:
- · Source material selection;
- · Processing:
- Terminal sterilization;
- · Compliance with 21 CFR 1271;
- Annual scientific review of literature and AATB bulletins to identify new and emerging diseases; and
• Labeling discloses the use of human-sourced material and residual risk of communicable disease.
{5}------------------------------------------------
Table 1: DCAM Material Recovery, Processing, Manufacturing and Release Overview
| DCAM Step | Description |
|-------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Donor eligibility<br>assessment | Evaluation of whether potential donor meets criteria including<br>maternal risk and health history, donor screening, testing, and<br>consent |
| Placenta Recovery (Birth<br>Tissue Procurement) | (b) (4) |
| Manufacturing | (b) (4) |
| Final Review for Product<br>Release | Review of documentation by trained Clinical and Quality<br>function personnel or designee to ensure all requirements have<br>been met from donor eligibility assessment through final<br>manufacturing prior to approving product for release to<br>distribution |
Prior to releasing AMStent Systems for distribution, extensive product release activities are completed. These are completed to ensure that the donated birth tissue was appropriately processed as intended. This is required to result in the intended humansourced decellularized amniotic membrane material and ensure that:
- · Donor eligibility and material processing and handling were conducted in accordance with 21 CFR 1271 requirements; and
- · The final product meets all specifications.
# MATERIAL CHARACTERIZATION AND LOT RELEASE
The AMStent is covered in a human-sourced decellularized amniotic membrane material. To characterize the composition of this material, the following tests were performed
{6}------------------------------------------------
(Table 2). Results of the material characterization activities demonstrate that the processing of the DCAM material both within and across lots is appropriately controlled to result in DCAM material that is consistently able to meet final product specifications based on user requirements. Qualitative and quantitative criteria have been identified and implemented for an acceptance and lot release evaluation to ensure the safety and effectiveness of the AMStent System is maintained across product lots.
| Characterization Attribute | Characterization Tests |
|-------------------------------------|------------------------|
| Mechanical Strength | (b) (4) |
| Nucleic Acids and Cell Debris | |
| Collagen Quality | |
| Collagen Type and Content | |
| Visual Quality | |
| Presence of Manufacturing Residuals | |
Table 2: DCAM Material Characterization Attributes Overview
### ANIMAL STUDIES
Two large animal studies were conducted that provide information to support the safety and effectiveness of the AMStent System. Both studies were conducted in compliance with Good Laboratory Practices (GLP) in accordance with 21 CFR 58. The first was a chronic (average 92 day) study to evaluate the in-vivo safety, implantability, migration, systemic effects, and usability of the AMStent compared to a control device. The second was an acute study to evaluate the in-vivo safety, implantability, removability, and usability of the AMStent following deployment. Both studies met their success criteria and study objectives, and the results support the safety and performance claims for the AMStent System.
## SUMMARY OF CLINICAL INFORMATION
Not applicable. Validation of the AMStent System did not require clinical evaluation in human subjects.
### LABELING
The labeling for the device is sufficient and consists of a package label, patient tracking card, and
{7}------------------------------------------------
the Instructions for Use. The package labeling satisfies the requirements of 21 CFR 801.109 to include a prescription use symbol, the patient tracking card satisfies the tracking requirements of 21 CFR 1271.290, and the Instructions for Use satisfies the medical device labeling requirements of 21 CFR 801 and specific human tissue labeling requirements for 21 CFR 1271.55.
Please see the Limitations section above for important contraindications, warnings, and precautions presented in the device labeling.
## RISKS TO HEALTH
The table below (Table 3) identifies the risks to health that may be associated with the tracheal prosthesis with cover material derived from human sources.
| Risks to Health | Mitigation Measures |
|-----------------------------------------------------------------------------------|-------------------------------------------------------------|
| Device mispositioning, migration,<br>erosion, and fracture | Animal performance testing |
| | Non-clinical performance testing |
| | Labeling |
| Adverse tissue reaction<br>Device repositioning or removal<br>during implantation | Biocompatibility evaluation |
| | Animal performance testing |
| | Non-clinical performance testing |
| Labeling | |
| Infection | Material characterization and infection control<br>measures |
| | Sterility testing |
| | Shelf-life testing |
| | Labeling |
Table 3: Risk/Mitigation table
## SPECIAL CONTROLS
In combination with the general controls of the FD&C Act. the tracheal prosthesis with cover material derived from human sourcesis subject to the following special controls:
- (1) Human tissue characterization and infection control measures must be provided for all human cells, tissues, and cellular and tissue-based products (HCT/P's), including documentation demonstrating:
- (i) Determination of donor eligibility, based on donor screening and testing for relevant communicable disease agents and diseases;
- (ii) Testing of all donor tissue for evidence of infection by relevant communicable disease agents, including (but not limited to): Human immunodeficiency virus type 1 and type 2. Hepatitis B and C viruses, and Treponema pallidum:
- (iii) Material sourcing from facilities that are registered for handling and processing of HCT/P materials and that incorporate the following procedures:
- The facility must monitor environmental conditions for contamination or cross-(A) contamination of HCT/Ps or equipment, or accidental exposure of HCT/Ps to
{8}------------------------------------------------
communicable disease agents:
- (B) Processing must ensure materials have undergone defined decellularization processing and demonstrate sufficient viral inactivation potency across RNA. DNA, enveloped, non-enveloped virus types, and viruses native to the tissue, and removal of residual human nucleic acids via lot-based testing:
- A distinct identification code must be affixed to the HCT/P container that (C) relates the HCT/P to the donor and to all accompanying records pertaining to the HCT/P, except for Personally Identifiable Information, and must enable tracking from the donor to the consignee or final disposition; and
- All HCT/P material must be kept in quarantine until completion of the donor-(D) eligibility determination;
- (iv) Material characterization activities demonstrating that the processing of the humanderived material both within and across lots is appropriately controlled to result in material that is consistently able to meet final product specifications.
- (2) Non-clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use. The following performance characteristics must be tested:
- Deployment testing to evaluate the accuracy and repeatability of any delivery (i) system;
- (ii) Compression and expansion forces;
- Dimensional testing: (iii)
- Fatigue and corrosion testing; and (iv)
- Compatibility of the device in a magnetic resonance (MR) environment. (v)
- Animal performance testing must demonstrate that the device performs as intended under (3) anticipated conditions of use, including an animal study with chronic time points to evaluate device migration, occlusion, and granuloma formation.
- The device must be demonstrated to be biocompatible. (4)
- (ર) Labeling must include:
- Magnetic resonance compatibility information; (i)
- Labeling must include a detailed summary of the device-related and procedure-(ii) related complications pertinent to the use of human-derived material and appropriate warnings:
- (iii) A summary of bench and in vivo testing that describes the duration of testing;
- Descriptions of claims and functionality must be limited to device functionality (iv) information demonstrated from performance testing; and
- A shelf life. (v)
- (6) Performance data must demonstrate the sterility of patient-contacting components of the device.
- Performance data must support the shelf-life of the device by demonstrating continued (7) sterility, package integrity, tissue integrity, and device functionality over the identified
{9}------------------------------------------------
### shelf life.
### BENEFIT-RISK DETERMINATION
The AMStent System is intended for use in the treatment of tracheobronchial strictures produced by malignant neoplasms (cancerous tumors). Tracheobronchial strictures may also be referred to as tracheobronchial stenosis and define a condition where the airways narrow making it harder to breathe. When the tumor is wholly within the central airway. it is often treated by mechanical removal, to the extent possible, and thermal techniques (e.g., LASER, electrocoagulation, photodynamic therapy, argon plasma and cryoextraction).1 Fully or partially covered selfexpanding metallic stents may then be used to maintain the opening of the airway. Pre-stenting treatments are less likely when the tumor is outside of the central airway. By the time patients need this type of intervention, they are typically at the end of their life. In most studies, the median life expectancy is usually less than 3 months after stent placement.2
Nitinol/metal stents have a history of palliative use providing relief to labored breathing and end of life comfort. With it, however, they also have a history of mispositioning, migration, erosion, infection, and fracture. These probable risks are greatly outweighed by the probable benefit that comes with improved breathing experienced by patients who have these implants placed. To address these risks, the performance analysis for this device included an animal study which showed less stent migration, less mucus accumulation and occlusion, and fewer obstructive granulomas relative to a marketed stent, although this was for a small sample size and not repeated in other studies. Additionally, there remains uncertainty as to the device's performance in patients living 90-days post implant as that is the extent of the tested use life assessed in the in vivo animal study.
While The AMStent® System maintains the general benefits of a tracheal stent in the palliative care setting (i.e. providing relief to labored breathing and end of life comfort), it does include a new risk of disease communication due to the use of human derived amnion tissue. This is mitigated. however, by the adherence to human tissue characterization and infection control measures. The calculated risk of disease transmission is <1:1million instances of the use of the DCAM covers. This risk is greatly outweighed by the benefit of this device for palliative care.
#### Patient Perspectives
This submission did not include specific information on patient perspectives for this device.
#### Benefit/Risk Conclusion
In conclusion, given the available information above, for the following indication statement:
The AMStent® Tracheobronchial Covered Stent System (AMStent® System) is indicated for use in the treatment of tracheobronchial strictures produced by malignant neoplasms in adult patients.
{10}------------------------------------------------
The probable benefits outweigh the probable risks for the AMStent® Tracheobronchial Covered Stent System. The device provides benefits, and the risks can be mitigated using general controls and the identified special controls.
## References
- 1. Guibert N, et al. Airway stenting: Technological advancements and its role in interventional pulmonology. Respirology. 2020 Sep; 25(9): 953-962. doi: 10.1111/resp.13801. Epub 2020 Mar 11.
- 2. Holden VK, et al. Safety and Efficacy of the Tracheobronchial Bonastent: A Single-Center Case Series. Respiration. 2020;99(4):353-359. doi: 10.1159/000506815.
## CONCLUSION
The De Novo request for the AMStent® Tracheobronchial Covered Stent System is granted, and the device is classified as follows:
Product Code: SDB Device Type: Tracheal prosthesis with cover material derived from human sources Regulation Number: 21 CFR 878.3721 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.