DEN180067 · Diversatek Healthcare, Inc. · QIS · Dec 23, 2019 · Gastroenterology, Urology
Device Facts
Record ID
DEN180067
Device Name
Mucosal Integrity Conductivity (MI) Test System
Applicant
Diversatek Healthcare, Inc.
Product Code
QIS · Gastroenterology, Urology
Decision Date
Dec 23, 2019
Decision
DENG
Submission Type
Direct
Regulation
21 CFR 876.1450
Device Class
Class 2
Indications for Use
The Mucosal Integrity Conductivity Test System is indicated for use by gastroenterologists, surgeons, and medically trained personnel during an endoscopy to obtain a real time measurement of esophageal epithelial impedance. The device is not for use as a sole diagnostic screening tool.
Device Story
Device measures esophageal epithelial impedance during endoscopy; provides real-time data to gastroenterologists or surgeons. Used in clinical settings to assist in tissue characterization. Operates by measuring electrical properties within esophageal tissue; output aids clinical decision-making as an adjunct tool. Not intended as a standalone diagnostic.
Clinical Evidence
Two prospective studies evaluated the device. Study 1 (n=69): patients with GERD, EoE, or normal EGD/pH testing. Study 2 (n=33): 23 adults with EoE and 10 controls. Device successfully measured esophageal mucosal impedance in all patients. One unrelated adverse event reported; no device-related adverse events. Evidence supports safety and effectiveness for intended use.
Technological Characteristics
System comprises balloon probe, inflator gauge box, adapter, and central unit. Probe uses electrical contact sensors. Materials evaluated for biocompatibility (cytotoxicity, sensitization, irritation) per ISO 10993-1. Electrical safety/EMC per IEC 60601-1 and IEC 60601-1-2. Software-based data processing and display. Reusable components require manual cleaning/disinfection.
Indications for Use
Indicated for use by gastroenterologists, surgeons, and medically trained personnel during endoscopy to measure esophageal epithelial impedance. Not for use as a sole diagnostic screening tool.
Regulatory Classification
Identification
An esophageal tissue characterization system is a device intended for obtaining measurements of electrical properties within esophageal tissue.
Special Controls
*Classification.* Class II (special controls). The special controls for this device are:(1) All patient contacting components of the device must be demonstrated to be biocompatible.
(2) Performance testing must demonstrate the device can accurately measure the designated electrical characteristics.
(3) Mechanical safety testing must demonstrate that the device will withstand forces encountered during use.
(4) Software verification, validation, and hazard analysis must be performed.
(5) Electromagnetic compatibility and electrical safety, mechanical safety, and thermal safety of the device must be performed.
(6) Performance data must validate the reprocessing instructions for any reusable components of the device.
(7) Labeling must include:
(i) Specific instructions regarding the proper placement and use of the device;
(ii) Instructions for reprocessing of any reusable components; and
(iii) An expiration date for single use components.
Submission Summary (Full Text)
{0}------------------------------------------------
# DE NOVO CLASSIFICATION REQUEST FOR MUCOSAL INTEGRITY CONDUCTIVITY (MI) TEST SYSTEM
## REGULATORY INFORMATION
FDA identifies this generic type of device as the following:
Esophageal tissue characterization system. An esophageal tissue characterization system is a device intended for obtaining measurement of electrical properties within esophageal tissue.
NEW REGULATION NUMBER: 21 CFR 876.1450
CLASSIFICATION: Class II
PRODUCT CODE: QIS
### BACKGROUND
DEVICE NAME: Mucosal Integrity Conductivity (MI) Test System
SUBMISSION NUMBER: DEN180067
DATE DE NOVO RECEIVED: December 20, 2018
#### CONTACT:
Diversatek Healthcare, Inc. 102 East Keefe Avenue Milwaukee, WI 53212
#### INDICATIONS FOR USE
The Mucosal Integrity Conductivity Test System is indicated for use by gastroenterologists, surgeons, and medically trained personnel during an endoscopy to obtain a real time measurement of esophageal epithelial impedance. The device is not for use as a sole diagnostic screening tool.
#### LIMITATIONS
The sale, distribution, and use of the Mucosal Integrity Conductivity (MI) System are restricted to prescription use in accordance with 21 CFR 801.109.
The MI Test System should be used as directed in the labeling to avoid adverse interaction within the esophagus.
{1}------------------------------------------------
# PLEASE REFER TO THE LABELING FOR A COMPLETE LIST OF WARNINGS, PRECAUTIONS AND CONTRAINDICATIONS.
# DEVICE DESCRIPTION
The Mucosal Integrity Conductivity (MI) Test System provides real-time measurements of alterations in esophageal evithelial integrity. The device is intended to aid in the evaluation of esophageal epithelial integrity by means of a balloon probe with direct electrical contact with the mucosal epithelium of the esophagus along with associated signal conditioning, hardware, and software for measuring and displaying information.
The patient undergoing an esophageal mucosal impedance study will first have an endoscope placed with the distal end of the scope proximal to the area under study. The MI Probe is advanced into the patient's esophagus by guiding it alongside the endoscope. The MI Probe is positioned under visual guidance using the optics of the endoscope. The probe also contains proximal markings on the catheter portion outside the patient to aid in positioning. The total time of deployment for collecting mucosal impedance values is expected to be less than 5 minutes. Figure 1 shows the MI Probe and its components along with its inflated and deflated state.
Image /page/1/Figure/4 description: The image shows three different views of a medical device. The first image shows the device inflated, with labels pointing to the distal esophagus, sensor column (10 cm), and proximal esophagus. The second image shows the device deflated, and the third image shows the device inflated again.
Figure 1. Inflated and Deflated Probe.
The impedance values are transmitted from the MI Probe to the non-patient contacting MI Adapter as standard impedance signals, measured, converted to digital data and are then transmitted to the Central Unit via the MI Cable. The Central Unit then transfers the processed data to the PC for display and analysis through the MI Software. This data is displayed through the use of a color map for easy identification of impedance values. The color map displays realtime impedance measurements for the duration of the individual study, and results are reported as both raw data and a summary.
The inflation and deflation of the probe is controlled via the MI Inflator Gauge Box, which has a pressure gauge to display the pressure within the balloon. The components are illustrated in
{2}------------------------------------------------
Figure 2 below. The impedance values are transmitted from the MI Probe to the non-patient contacting MI Adapter as standard impedance signals, measured, converted to digital data and are then transmitted to the Central Unit via the MI Cable. The Central Unit then transfers the processed data to the PC for display and analysis through the MI Software. This data is displayed through the use of a color map for identification of impedance values. The color map displays real-time impedance measurements for the duration of the individual study, and results are reported as both raw data and a summary.
Image /page/2/Figure/1 description: The image shows a medical device called an MI Inflator Gauge Box, along with its various components. The components include an inflator, a cable, an air supply line to the probe, an MI adapter module, and an MI probe. The image also shows an inflated balloon of the MI probe with the sheath removed. The MI Inflator Gauge Box appears to be the central control unit for the device.
Figure 2. The complete MI System with all components aside from the Central Unit
# SUMMARY OF NONCLINICAL/BENCH STUDIES
Non-clinical/bench studies conducted on the MI Test System to demonstrate a reasonable assurance of safety and effectiveness of the device are summarized below.
## REPROCESSING
As illustrated in Figure 3 below, the MI Probe makes direct patient contact and is connected to reusable components that do not make direct patient contact. Those reusable components will be manipulated by the user at the same time they are using the patientcontacting probe, thereby making cross-contamination between the probe and the reusable components possible. This risk was addressed by the inclusion of validated reprocessing instructions in the labeling for the reusable components.
{3}------------------------------------------------
Image /page/3/Figure/0 description: The image shows a diagram of a system with several components. The components include an MI Probe, MI Probe Cable, Inflator Gauge Box, MI Adapter for Central Unit, Cable for Central Unit, Central Unit (inSIGHT Ultima), USB, and a Computer running System software (Zvu adapted for MI). The diagram also indicates the areas of patient contact, clinician, and technician.
Figure 3. Diagram of patient contacting and non-patient contacting components. This involved the use of cleaning instructions and disinfection instructions per FDA's 2015 reprocessing guidance document, "Reprocessing Medical Devices in Health Care Settings: Validation Methods and Labeling". The instructions for the MI Test System provide step-by-step instructions for the user to first clean and then low-level disinfect the reusable components using a Sani-Cloth wipe.
The instructions indicate that reprocessing should occur immediately following use, they include the words "thoroughly clean," they provide endpoints for each step (i.e., visibly clean for cleaning and contact time of 2 minutes per wipe manufacturer's instructions for disinfection), they include a visual inspection step following cleaning and state that the user should repeat the cleaning steps if still visibly dirty, and they include drying steps post-cleaning and disinfection.
Furthermore, the reuse inspection instructions to indicate that the user should inspect the device for damage, corrosion, cuts, punctures, and cracked seals following cleaning and disinfection.
# SOFTWARE
Software documentation was provided in accordance with the FDA Guidance Document, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices," (issued May 11, 2005) for a Moderate Level of Concern (LOC). A Moderate LOC is deemed appropriate as malfunction of the device software or a latent design flaw in the device software may lead to a delay in the delivery of appropriate medical care, which would likely result in minor injury, but would likely not result in serious injury or death due to the availability of other patient vital signs.
Cybersecurity information was provided in accordance with the FDA Guidance Document, "Content of Premarket Submissions for Management of Cybersecurity in Medical Devices - Guidance for Industry and Food and Drug Administration Staff" (issued October 02, 2014).
{4}------------------------------------------------
## BIOCOMPATIBILITY/MATERIALS
The MI Test System is classified as mucosal membrane contacting for repeat, prolonged contact during clinical use (< 24 hours). The MI Probe was evaluated according to the FDA guidance (2016). "Use of International Standard ISO 10993-1. Biological evaluation of medical devices - Part 1: Evaluation and testing within a risk management process," and the following biocompatibility endpoints were assessed for the MI Test System:
- Cytotoxicity .
- Sensitization .
- Irritation .
Results support the biocompatibility of the MI Test System.
## ELECTRICAL SAFETY AND ELECTROMAGNETIC COMPATIBILITY (EMC)
The test reports address the basic safety evaluation (which includes electrical safety testing) per the FDA-recognized standard IEC 60601-1:2005 + A1:2012. In addition, the EMC testing was conducted per IEC 60601-1-2:2007 and passed the applicable clauses. The results support the electrical safety and EMC of the device.
## PERFORMANCE TESTING - BENCH
The integrity and performance of the MI Test System were evaluated with the nonclinical testing summarized in the tables below.
| Test | Acceptance Criteria | Diversatek Healthcare<br>Test Article Result |
|---------------------------------|---------------------|----------------------------------------------|
| Double Wall Thickness | .00045" +/- .00025" | (b)(4)<br>Pass |
| Compliance<br>Diameter @ 0.5atm | 20 mm +/- .65 mm | (b)(4)<br>Pass |
| Burst Pressure | 2.04 atm minimum | (b)(4)<br>Pass |
#### Table 13.1 Balloon Functionality Testing Summary
Sample size of the tests above are n=10. The double wall thickness and compliance diameter was measured using digital height gauge.
A hydraulic burst tester was used to record the balloon burst pressure (n=10), and the compliance of the diameter of the balloons at 0.5 atm was measured with a ruler.
| Table 13.3 Dimensional Design Verification Testing Summary | | |
|------------------------------------------------------------|---------------------|----------------------------------------------|
| Test | Acceptance Criteria | Diversatek Healthcare<br>Test Article Result |
{5}------------------------------------------------
| Probe Overall Length | 55.25" +/- 2.0" | (b)(4) |
|---------------------------------------|---------------------|--------|
| | | Pass |
| Probe, Balloon Diameter when Inflated | 2.0 cm +/- 0.1 cm | (b)(4) |
| | | Pass |
| Probe Weight | 2.8 oz. +/- 0.5 oz. | (b)(4) |
| | | Pass |
Dimensional verification test for the probe overall length, probe-balloon inflated diameter (n=33) were measured using a ruler, and the probe weight was measured with a digital scale.
Table 13.4 Bond between Sensors and Balloon Testing Summary
| Test | Acceptance Criteria | Diversatek Healthcare<br>Test Article Result |
|-----------------------------------------------|-------------------------------------------------------------|----------------------------------------------|
| Adhesive Strength after<br>Exposure to Saline | ≥ adhesive strength<br>without saline exposure<br>2.267 lbf | (b)(4)<br>Pass |
were prepared by (b) (4) For the Adhesive Strength test, samples(b) (4)
Table 13.5 Tensile Strength, Distal Tip to Catheter of MI Probe
| Test | Acceptance Criteria | Diversatek Healthcare<br>Test Article Result |
|-----------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------|----------------------------------------------|
| Tensile Strength Distal<br>Tip Joint MI Probe | ≥ 3.0 lbf based on<br>independent study | (b)(4)<br>Pass |
| Tensile Strength Distal<br>Tip Joint MI Probe | Added to this Submission:<br>≥ 4.5 lbf from EN 1617 (20<br>Newtons) for max break<br>force of sterile drainage<br>catheters | (b)(4)<br>Pass |
An initial pull test (ng) on the distal tip joint of the MI Probe, where a (b) (4)
acceptance criteria was used. Another test (n=4) was then conduced in accorduced in accordu was then conduced in accordance with le Drainage Catheters and Accessory Devices for Single Use with a (b) (4) acceptance criteria. In both tests, the joints were pulled until the point of failure and the maximum tensile strength of the joints was recorded. All breakages happened either at the distal tip or on the balloon material of the sample.
{6}------------------------------------------------
| Test | Acceptance Criteria | Diversatek Healthcare<br>Test Article Result |
|-----------------------------------|---------------------|----------------------------------------------|
| Impedance<br>Measurement Accuracy | 174+/- 100 Ohms | (b)(4)<br>Pass |
| Impedance Signal Noise | < 20 Ohms | (b)(4)<br>Pass |
| Impedance Thermal<br>Stability | +/- 100 Ohms | (b)(4)<br>Pass |
| Impedance Temporal<br>Stability | +/- 100 Ohms | (b)(4)<br>Pass |
Table 13.6 Impedance Measurements of MI Probe Sensors
To demonstrate impedance measurement accuracy in bench testing, a single probe was placed in b)(41% saline (which had ab)(4) ohms impedance measurements from all ten sensors on the probe were then recorded over the course of 1 minute via analog-to-digital (A/D) counts (The MI Adapter can function as an analog-to-digital converter, which converts the voltage or current into a digital number). The average measurement was(b) (4) Ohms, which is within the acceptance criteria (shown above).
The impedance signal noise was measured by setting the MI software to report the maximum and minimum A/D counts for each channel on each probe for a period of 1 second. The differences between the minimum and maximum A/D counts for every channel was then calculated.
For the impedance thermal stability and impedance temporal stability, the software was set to report the average A/D counts for each channel of each MI probe sensor still in in saline over a 1 minute period and 5 minute period respectively. For both tests the average resistance values were taken after 1 minute in room temperature saline and were compared to the impedance after 1 minute in body temperature saline (for thermal stability) and 5 minutes in room temperature saline (for the temporal stability).
Only one probe was tested for the impedance measurement tests. All sensors were tested on the probe.
# SUMMARY OF CLINICAL INFORMATION
Clinical data from the sponsor was used to support the safety and effectiveness of the device. The clinical information also supported the benefit-risk determination.
The first prospective study was performed on "" patients undergoing esophagogastroduodenoscopy, with or without wireless pH monitoring. Some patients had symptoms of GERD (erosive esophagitis or abnormal pH testing. n = 24) or active eosinophilic esophagitis (EoE, confirmed with pathology at both distal and proximal esophagus, n = 21); there were also patients with normal esophagogastroduodenoscopy (EGD) and pH testing (n = 24). The study results show that the device was able to measure the esophageal mucosal impedance in ohms for all 0149 patients. There was only one reported adverse event (a chest pain unrelated to the device) and there was no follow-up of the patients after the procedure ended.
{7}------------------------------------------------
Another prospective study was conducted with the subject device in a population that consisted of 23 adult patients with EoE, of whom 18 patients had > 15 eosinophils per high-power field (eos/HpF), and 5 patients had inactive EoE (4 patients were effectively treated with budesonide and 1 with omeprazole). There were 10 additional control patients consisting of 8 adults undergoing endoscopy for clinically-indicated Bravo capsule placement for assessment of GERD, and 2 patients were undergoing endoscopy for evaluation of possible celiac disease. The study results show that the MI Test System was able to measure the esophageal mucosal impedance in ohms for all 23 patients. There were no reported adverse events and there was no follow-up of the patients after the procedure ended.
# Pediatric Extrapolation
In this De Novo request, existing clinical information was not leveraged to support the use of the device in pediatric patient population
## LABELING
The labeling comprises physician labeling that includes the device indications for use, a description of the device, warnings, and precautions, clinical data on the device, and instructions for the safe and effective use of the device. The labeling satisfies the requirements of 21 CFR 801.109 Prescription devices.
Per the special controls for this generic type of device, labeling includes the following:
- Specific instructions regarding proper placement and use of the device. ●
- . An expiration date and shelf life for single use components.
- . Reprocessing instructions for the reusable components.
## RISKS TO HEALTH
The table below (Table 4) identifies the risks to health that may be associated with use of the esophageal tissue characterization system and the measures necessary to mitigate these risks.
| Identified Risks to Health | Mitigation Measures |
|------------------------------------------|-----------------------------------------------|
| Device Malfunction Related to: | Non-clinical performance testing |
| • Breaking | Shelf life testing |
| • Fractures | Software verification, validation, and hazard |
| • Unintentional separation of components | analysis |
| • Inaccurate reading | Labeling |
| • Failure to sense | |
| • Endoscope incompatibility | |
| Adverse tissue reaction | Biocompatibility evaluation |
#### Table 4: Identified Risks to Health and Mitigation Measures
{8}------------------------------------------------
| Electrical shock and electrical interference<br>from other devices | Electrical safety testing<br>Electromagnetic compatibility (EMC) testing<br>Labeling |
|-------------------------------------------------------------------------------|--------------------------------------------------------------------------------------|
| Procedural risks (which may include<br>procedures of endoscopy with sedation) | Labeling |
| Infection/cross-contamination | Reprocessing validation<br>Labeling |
## SPECIAL CONTROLS
In combination with the general controls of the FD&C Act, the esophageal tissue characterization system is subject to the following special controls:
- (1) All patient contacting components of the device must be demonstrated to be biocompatible.
- (2) Performance testing must demonstrate the mucosal impedance system can accurately measure the designated electrical characteristics.
- (3) Mechanical safety testing must demonstrate that the device will withstand forces encountered during use.
- (4) Software verification, validation, and hazard analysis must be performed.
- (5) Electromagnetic compatibility and electrical safety, mechanical, and thermal safety testing of the device must be performed.
- (6) Performance data must validate the reprocessing instructions for any reusable components of the device.
- (7) Labeling must include:
- Specific instructions regarding the proper placement and use of the device; (i)
- (ii) Instructions for reprocessing of any reusable components; and
- (iii) An expiration date for single use components.
## BENEFIT-RISK DETERMINATION
The probable benefits of the device are based on the ability to obtain the electrical characteristic of the esophageal tissue. In the case of the MI Test System, the device can be used by gastroenterologists, surgeons, and medically trained personnel during an endoscopy to obtain a real time measurement of esophageal epithelial impedance. This information as an adjunct to standard clinical practice can provide the clinician with information to assist in making a more informed decision for patient care.
{9}------------------------------------------------
The probable risks of the device include the risks associated with endoscopy and sedation, device malfunction, adverse tissue reaction, electrical shock and electrical interference, and crosscontamination or infection. Device-related adverse events were not reported in the clinical studies. The risk of device malfunctions includes the risk of inaccurate reading which could result in an incorrect determination by the clinician.
Based on the available performance data, the probability of such harmful events is low, and the incidence is reduced with the mitigation measures and special controls identified above.
The probable benefits of the device outweigh the probable risks.
# 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 Mucosal Integrity Conductivity Test System is indicated for use by gastroenterologists, surgeons, and medically trained personnel during an endoscopy to obtain a real time measurement of esophageal epithelial impedance. The device is not for use as a sole diagnostic screening tool.
The probable benefits outweigh the probable risks for the MI Test System. The device provides benefits, and the risks can be mitigated using general controls and the identified special controls.
# CONCLUSION
The De Novo request for the Mucosal Integrity Conductivity Test System is granted and the device is classified as follows:
Product Code: QIS Device Type: Esophageal tissue characterization system Regulation Number: 21 CFR 876.1450 Class: Class II
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.