DEN240018 · Nanosonics Limited · SEW · Mar 19, 2025 · General Hospital
Device Facts
Record ID
DEN240018
Device Name
CORIS System
Applicant
Nanosonics Limited
Product Code
SEW · General Hospital
Decision Date
Mar 19, 2025
Decision
DENG
Submission Type
Direct
Regulation
21 CFR 880.6994
Device Class
Class 2
Attributes
Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
DEN240018 · Mar 19, 2025
CORIS System
Nanosonics Limited
Clinical site endoscope reprocessing records
In-use testing was performed at a clinical site to evaluate the performance of the CORIS System under real-world conditions compared to manual cleaning.
In-use testing; Comparative performance evaluation in a clinical setting
Olympus EVIS EXERA III CF-HQ190L colonovideoscopes; Sample Size: 46 endoscopes (CORIS) and 46 endoscopes (manual); Number of Sites: 1
Manual cleaning
Cleaning markers (protein, TOC, and visual inspection)
Indications for Use
The Nanosonics CORIS System is indicated for cleaning of the channels of the Olympus EVIS EXERA III CF-HQ190L colonovideoscope. The CORIS System is suitable for use in healthcare facilities by trained healthcare workers.
Device Story
Automated endoscope channel cleaner; replaces manual cleaning of internal passages/ports of compatible flexible endoscopes. Uses cleaning agent exerting physical force (friction) to remove soil from channels. Operated by trained healthcare workers in healthcare facilities. Does not provide high-level disinfection or sterilization. Requires subsequent reprocessing steps. Benefits include standardized, automated removal of soil from endoscope channels, reducing reliance on manual cleaning techniques.
Clinical Evidence
No clinical data. Evidence based on non-clinical performance testing including design verification, simulated use testing under worst-case conditions, in-use testing under clinical conditions, cleaning agent residue quantitation, impact analysis on subsequent reprocessing, biocompatibility evaluation, and life cycle assessment.
Technological Characteristics
Automated endoscope channel cleaner; utilizes cleaning agent for physical force (friction) soil removal. Includes software components for system operation. Requires electromagnetic compatibility, electrical, and mechanical safety testing. Subject to special controls including cleaning agent shelf-life testing and compatibility testing with specific endoscope models.
Indications for Use
Indicated for cleaning internal channels of Olympus EVIS EXERA III CF-HQ190L colonovideoscope in healthcare facilities by trained healthcare workers.
Regulatory Classification
Identification
An automated endoscope channel cleaner is a device intended to replace all or a portion of manual cleaning of internal passages and ports of compatible, reusable flexible endoscopes. Cleaning is conducted using an agent that exerts physical force (e.g., friction) on single or multiple channels of compatible endoscopes for removal of soil. This device type is not intended to provide or replace high-level disinfection or sterilization.
Special Controls
In combination with the general controls of the FD&C Act, the automated endoscope channel cleaner 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, including that the device meets all design specifications and performance requirements:
(i) Design verification testing must ensure the device meets its specifications.
(ii) Simulated use testing must evaluate device cleaning efficacy under worst-case simulated use conditions.
(iii) In-use testing must evaluate device performance under clinical use conditions.
(iv) Evaluation of cleaning agent residues must include:
(A) Quantitation of residues in compatible endoscope channels and ports;
(B) Analysis of the impact of device use on subsequent reprocessing steps, such as high-level disinfection and sterilization; and
(C) Evaluation of impact of device use on endoscope biocompatibility.
(v) Compatibility testing of the device with compatible endoscope(s) must be conducted, to include a life cycle assessment study. The labeled life cycle must not exceed the endoscope manufacturer's life cycle specification.
(vi) Cleaning agent shelf-life testing must demonstrate continued performance of the cleaning agent over its labeled shelf life.
(2) Performance testing must demonstrate electromagnetic compatibility and electrical and mechanical safety of the device in the intended use environment.
(3) Software verification, validation, and hazard analysis must be performed for any software components of the device.
(4) Human factors testing must demonstrate that an intended user can correctly use the device for its intended use, based solely on its labeling and instructions for use.
(5) Labeling must include the following:
(i) A detailed summary of the device technical parameters, including any specifications;
(ii) A statement regarding user adherence to the endoscope manufacturer's recommendations for use and cleaning of external/incompatible surfaces, as well as adherence to the manufacturer's validated microbicidal process for the entire device, drying and storage conditions; and
(iii) Instructions for disinfection and maintenance of the automated endoscope channel cleaner.
Submission Summary (Full Text)
{0}
# DE NOVO CLASSIFICATION REQUEST FOR CORIS SYSTEM
## REGULATORY INFORMATION
FDA identifies this generic type of device as:
**Automated endoscope channel cleaner.** An automated endoscope channel cleaner is a device intended to replace all or a portion of manual cleaning of internal passages and ports of compatible, reusable flexible endoscopes. Cleaning is conducted using an agent that exerts physical force (e.g., friction) on single or multiple channels of compatible endoscopes for removal of soil. This device type is not intended to provide or replace high-level disinfection or sterilization.
**NEW REGULATION NUMBER:** 21 CFR 880.6994
**CLASSIFICATION:** Class II
**PRODUCT CODE:** SEW
## BACKGROUND
**DEVICE NAME:** CORIS System
**SUBMISSION NUMBER:** DEN240018
**DATE DE NOVO RECEIVED:** May 1, 2024
## SPONSOR INFORMATION:
Nanosonics Limited
Nancy Kaiser
7-11 Talavera Road
Macquarie Park, NSW 2113
Australia
## INDICATIONS FOR USE
The Nanosonics CORIS System is indicated for cleaning of the channels of the Olympus EVIS EXERA III CF-HQ190L colonovideoscope.
The CORIS System is suitable for use in healthcare facilities by trained healthcare workers.
{1}
De Novo Summary (DEN240018)
Page 2 of 11
# LIMITATIONS
The Nanosomics CORIS System is intended to be marketed for Over-The-Counter (OTC) use.
PLEASE REFER TO THE LABELING FOR A COMPLETE LIST OF WARNINGS, PRECAUTIONS AND CONTRAINDICATIONS.
# DEVICE DESCRIPTION
The CORIS System is an automated electromechanical device which utilizes the CORIS QUANTUM Cleaning Agent to clean endoscope channels (including interior of the lumens, ports, and cylinders) of validated and compatible reusable flexible endoscopes.
The CORIS System is intended to replace manual cleaning of the channels of Olympus EVIS EXERA III CFHQ190L colonovideoscope (CF-HQ190L) (primary DI number 04953170305115), with an automated cleaning cycle. The CORIS QUANTUM Cleaning Agent is provided as a dry powder, which upon installation is hydrated to create a slurry. During the cleaning cycle, the CORIS System delivers the cleaning agent providing physical cleaning to all endoscope channels. The endoscope channels are then rinsed and purged with air.
All external surfaces of the endoscope must still be cleaned and reprocessed according to the endoscope manufacturer's instructions. An endoscope that has had internal channels cleaned by the CORIS System must be high-level disinfected using an accelerated hydrogen peroxide-based solution, for example, Revital-Ox® RESERT® High Level Disinfectant.
The CORIS System is intended to be used in healthcare settings within reprocessing areas where endoscopes are cleaned, such as endoscope reprocessing departments and central sterile processing departments. The device is intended to be installed and used at the sink in the decontamination area of these departments.
The CORIS System consists of the CORIS Device and its accessories. CORIS accessories are not supplied with the CORIS Device and must be purchased separately, except the following components: 1) CORIS Splash Guard and 2) non-medical device components required during initial set up and installation only including the CORIS Splash Guard Drain Tube, CORIS Drain Spigot Adaptor, Air Supply Tube, Water Supply Tube, Power Supply Unit and Regional Mains Connector, CORIS Splash Guard Mounting Kit, CORIS Lifting Accessory, CORIS Wall Mount Fastening Kit, and CORIS Wall Mount.
{2}
De Novo Summary (DEN240018)
Page 3 of 11
# CORIS Device
| Front and left side | Right side |
| --- | --- |
| | |
| 1. Door
2. Touch screen display
3. Barcode reader
4. RFID reader
5. Adaptor port and lock (locked position)
6. Side door (contains the power socket and device label)
7. Device label* | 8. a. Power socket
b. Ethernet
c. 2 x USB ports
9. Power switch
10. Self-Disinfection Input Tube port
11. Location of air, water and drain ports |
# CORIS Device Door in Closed Position (left) and CORIS QUANTUM Cleaning Agent in Installed Position (right)

{3}
De Novo Summary (DEN240018)
Page 4 of 11
# CORIS System Accessories
| Part Name | Image |
| --- | --- |
| CORIS QUANTUM Cleaning Agent | |
| CORIS O1 Adaptor
1. Suction air/water connector
2. Biopsy connector
3. Auxiliary connector
4. Suction connector
5. Air pipe connector
6. Air/water supply connector | |
| CORIS Splash Guard
1. CORIS® Splash Guard Body (Reusable)
2. CORIS® Splash Guard Tube (24-hr use)
3. CORIS® Splash Guard Seal (Single use) | |
| 1. CORIS Lens Cover
2. CORIS Lens Cover Aid | |
| Part Name | Image |
| --- | --- |
| CORIS Self-Disinfection Kit
1. CORIS Self-Disinfection Adaptor
2. CORIS Self-Disinfection Input Tube
3. CORIS Self-Disinfection Plug | |
{4}
SUMMARY OF NONCLINICAL/BENCH STUDIES
## REPROCESSING, STERILITY AND SHELF-LIFE
The exterior of the CORIS Device and the CORIS Splash Guard body must be cleaned and disinfected with a Quaternary Ammonium (Quat) wipe after each day or when required in accordance with the CORIS System User Manual.
With the exception of the CORIS QUANTUM Cleaning Agent, the CORIS Device and the associated accessories are provided non-sterile and as such are not labeled with expiration dating (shelf-life). A self-disinfection cycle should be run at least daily; performed according to the CORIS User Manual.
The CORIS QUANTUM Cleaning Agent is labeled with a 6-month shelf life based on data at T - 0 and T - 6-month Real Time. Shelf life testing evaluated the following parameters: moisture content, cleaning agent, performance in CORIS device as a cleaning agent and visual observation of packaging label.
## BIOCOMPATIBILITY
The CORIS System biocompatibility risk evaluation was performed by sponsor in accordance with the FDA 2020 Biocompatibility Guidance document, Use of International Standard ISO 10993-1, "Biological evaluation of medical devices - Part 1: Evaluation and testing within a risk management process," found at https://www.fda.gov/media/142959/download. The CORIS System has no direct or indirect contact with patient during its intended use. The CORIS User Manual cautions that users should wear appropriate personal protective equipment during operation of the CORIS System.
Additionally, residual testing of the cleaning agent was conducted to assess impact of residual cleaning agent on subsequent reprocessing steps, such as high-level disinfection and sterilization. The sponsor demonstrated that cleaning agent residues do not interfere with subsequent reprocessing steps. Based on the acceptable results of cleaning agent residue analysis, additional biocompatibility testing was not needed and was not performed.
## SOFTWARE & CYBERSECURITY
The CORIS device is an automated software controlled electro-mechanical device that houses a touch screen display and Graphical User Interface (GUI) that allows the user to interact with the device. This screen sets and displays the cleaning cycle, cleaning time and cleaning status. The software testing was conducted as per FDA guidance document, "Content of premarket submissions for Device Software Functions," found at https://www.fda.gov/media/153781/download.
Cybersecurity testing was conducted per FDA guidance documents, "Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions" found at https://www.fda.gov/media/119933/download, and the results were found acceptable.
De Novo Summary (DEN240018)
{5}
De Novo Summary (DEN240018)
Page 6 of 11
# ELECTROMAGNETIC COMPATIBILITY & ELECTRICAL SAFETY
Electromagnetic Compatibility (EMC) of the CORIS device has been evaluated in accordance with IEC 61326-1, Electrical equipment for measurement, control and laboratory use - EMC requirements - Part 1: General requirements, and IEC 60601-1-2, Medical electrical equipment - Part 1-2: General requirements for basic safety and essential performance - Collateral Standard: Electromagnetic disturbances - Requirements and tests.
Electrical safety testing of the CORIS device was completed in accordance with IEC 61010-1, Safety requirement for electrical equipment for measurement, control and laboratory use. Part 1: General requirements and IEC 61010-2-040, Safety requirements for electrical equipment for measurement, control and laboratory use. Part 2-040: Particular requirement for sterilizers and washer-disinfectors used to treat medical materials. Testing has been successfully completed per the referenced standards, including electrical, mechanical resistance to shock/impact, and mechanical safety testing.
# COMPATIBILITY TESTING
The sponsor performed compatibility testing within a lifetime cycle study to evaluate potential damage to the functionality of the endoscope following repeated usage. At the completion of the study, results demonstrated compatibility with the endoscope for [b] (4) cleaning cycles, [c] disinfectant cycle (total of [b] (4) cycle) and [c] cycles for the CORIS adapter.
# HUMAN FACTORS TESTING
Summative and supplementary human factors testing were performed (which included two different studies in a simulated use environment) to support the use-safety and effectiveness of use of the CORIS System. The studies evaluated use of the device, and assessed modifications to the device user interface, labeling and training. At the completion of testing, residual risks were demonstrated to be acceptable.
# PERFORMANCE TESTING - BENCH
The sponsor conducted the following performance tests to support that the device can achieve its intended use:
- Cleaning Validation – Simulated Use Testing
Simulated use testing was performed in accordance with FDA guidance documentation: “FDA Class II Special Controls Guidance Document: Medical Washers and Medical Washer-Disinfectors; Guidance for the Medical Device Industry and FDA Review Staff (February 7, 2002)”, “FDA Guidance on Premarket Notification [510(k)] Submissions for Automated Endoscope Washers, Washer/Disinfectors, and Disinfectors Intended for Use in Health Care Facilities (1993)”, and “Reprocessing Medical Devices in Health Care Settings: Validation Methods and Labelling (2015)” under worst-case simulated use conditions (using Artificial Test Soil 2015 with 20% coagulable blood (cATS) and Combination Test
{6}
Soil (CTS) (a mixture of Defibrinated Blood Soil and British Standard Soil at a 9:1 ratio)).
Cleaning validation for the CORIS system assessed colonovideoscopes inoculated with cATS and CTS artificial test soils. Cleaning assessment consisted of quantification of protein and total organic carbon (TOC) using nine endoscope test devices, one negative device control, and one positive device control.
Residual protein and TOC for CORIS cleaned colonovideoscopes were compared to manually cleaned endoscopes for both cATS and CTS. For visual inspection, nine test devices and at least three negative controls were prepared.
Test devices underwent six sequential full simulated use and processing cycles, consisting of soiling of the entire channel surfaces, soil dwelling (1 hour), cleaning with the CORIS system, high level disinfection, flushing with alcohol, and drying. Cleaning efficacy was assessed after a seventh cycle of soiling, soil dwelling, and cleaning with the CORIS system.
At the conclusion of simulated use testing, results met acceptance criteria for residual protein (<3 μg/cm²), TOC (<6 μg/cm²) and visual inspection (visually clean). The results demonstrated that CORIS System is comparable to or better than manual cleaning based on the acceptance criteria, for all individual channels (suction/biopsy, air/water, and auxiliary channels) of the indicated colonovideoscope.
- Cleaning Validation – In Use Testing
In-use testing was evaluated in accordance with FDA guidance: “FDA Class II Special Controls Guidance Document: Medical Washers and Medical Washer-Disinfectors; Guidance for the Medical Device Industry and FDA Review Staff (February 7, 2002)” and “FDA Guidance on Premarket Notification [510(k)] Submissions for Automated Endoscope Washers, Washer/Disinfectors, and Disinfectors Intended for Use in Health Care Facilities (1993)” and ISO 15883-1:2009+A1:2014 (Washer-Disinfectors – Part 1: General Requirements, Terms and Definitions and Tests) to assess CORIS device performance under real-world use conditions.
EVIS EXERA III CF-HQ190L colonovideoscopes (Olympus) used in a clinical site were employed for the in-use testing. 46 endoscopes were cleaned using the CORIS System covering each channel (suction/biopsy, air/water and auxiliary) and assessment for cleaning markers. The results met acceptance criteria. Additional 46 endoscope replicates were cleaned manually covering each channel (suction/biopsy, air/water, and auxiliary) and evaluated for cleaning markers. Endpoints (protein, TOC and visual inspection) for both endoscope groups were compared. The results demonstrated that the CORIS System performed comparably or better than manual.
- Cleaning Agent Residues Testing
Residual testing was conducted per FDA Guidance: “FDA Class II Special Controls Guidance Document: Medical Washers and Medical Washer-Disinfectors; Guidance
De Novo Summary (DEN240018)
Page 7 of 11
{7}
for the Medical Device Industry and FDA Review Staff (February 7, 2002), "FDA Guidance on Premarket Notification [510(k)] Submissions for Automated Endoscope Washers, Washer/Disinfectors, and Disinfectors Intended for Use in Health Care Facilities (1993)" and "Reprocessing Medical Devices in Health Care Settings Validation Methods and Labeling—Guidance for Industry and Food and Drug Administration Staff (2015)" and ISO 15883-1:2006 and ISO 15883-5:2021.
Under worst-case conditions, cleaning agent residues remaining in the suction/biopsy channel, air/water channel, auxiliary channel, and distal tip of a CF-HQ190L colonovideoscope after cleaning with the CORIS System were measured 7 times before and after one cleaning cycle and 3 times before and after three back-to-back cleaning cycles. In addition, the sponsor conducted Mycobacteria potency testing to assess the impact of cleaning agent residues on the effectiveness of the Revital-Ox Resort high level disinfectant.
The results of cleaning agent residues assessment demonstrated that residual cleaning agent in the channels does not interfere with subsequent high-level disinfection.
- **Self-Disinfection Cycle Validation**
The CORIS System User Manual recommends that a self-disinfection cycle should be run at least daily. Self-disinfection validation testing was performed under worst-case conditions to demonstrate that high level disinfection of the CORIS system is achieved by the self-disinfection cycle using Revital-Ox Resort HLD solution. The result demonstrated that following self-disinfection, the Colony Forming Unit count of the CORIS device rinse water (seen in the post self-disinfection sample) was not significantly worse than the quality of input utility water.
- **Exterior Cleaning/Disinfection Validation**
The sponsor performed cleaning and disinfection validation of the CORIS device exterior surface and Splash Guard, which are non-critical equipment surfaces that have no direct or indirect patient contact but will become soiled during use. The validation demonstrated that cleaning and low-level disinfection is suitable for reprocessing of the CORIS device exterior surface and Splash Guard body.
**LABELING**
The labeling consists of a product label and User Manual.
Labeling for this device is in accordance with the special controls listed below.
De Novo Summary (DEN240018)
Page 8 of 11
{8}
De Novo Summary (DEN240018)
Page 9 of 11
# RISKS TO HEALTH
The table below identifies the risks to health that may be associated with use of the CORIS System
| Risks to Health | Mitigation Measures |
| --- | --- |
| Electrical, mechanical or thermal hazards resulting in:
• Ineffective cleaning, leading to patient infection
• User discomfort or injury | Electromagnetic compatibility testing
Electrical, mechanical, and thermal safety testing
Software verification, validation, and hazard analysis
Labeling |
| Misuse or use error resulting in patient infection | Human factors/usability testing
Labeling |
| Device failure due to software malfunction and mechanical failure resulting in:
• Ineffective cleaning, leading to patient infection
• User discomfort or injury | Non-clinical performance testing
Software verification, validation, and hazard analysis
Cleaning agent shelf-life testing
Labeling |
| Cleaning agent residues impacting further reprocessing, leading to patient infection or adverse tissue reaction | Non-clinical performance testing
Biocompatibility evaluation |
# SPECIAL CONTROLS
In combination with the general controls of the FD&C Act, the automated endoscope channel cleaner 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, including that the device meets all design specifications and performance requirements:
(i) Design verification testing must ensure the device meets its specifications.
(ii) Simulated use testing must evaluate device cleaning efficacy under worst-case simulated use conditions.
(iii) In-use testing must evaluate device performance under clinical use conditions.
(iv) Evaluation of cleaning agent residues must include:
(A) Quantitation of residues in compatible endoscope channels and ports;
(B) Analysis of the impact of device use on subsequent reprocessing steps, such as high-level disinfection and sterilization; and
(C) Evaluation of impact of device use on endoscope biocompatibility.
{9}
(v) Compatibility testing of the device with compatible endoscope(s) must be conducted, to include a life cycle assessment study. The labeled life cycle must not exceed the endoscope manufacturer's life cycle specification.
(vi) Cleaning agent shelf-life testing must demonstrate continued performance of the cleaning agent over its labeled shelf life.
(2) Performance testing must demonstrate electromagnetic compatibility and electrical and mechanical safety of the device in the intended use environment.
(3) Software verification, validation, and hazard analysis must be performed for any software components of the device.
(4) Human factors testing must demonstrate that an intended user can correctly use the device for its intended use, based solely on its labeling and instructions for use.
(5) Labeling must include the following:
(i) A detailed summary of the device technical parameters, including any specifications;
(ii) A statement regarding user adherence to the endoscope manufacturer's recommendations for use and cleaning of external/incompatible surfaces, as well as adherence to the manufacturer's validated microbicidal process for the entire device, drying and storage conditions; and
(iii) Instructions for disinfection and maintenance of the automated endoscope channel cleaner.
## BENEFIT-RISK DETERMINATION
### Benefits
The bench studies performed support that the CORIS System cleans small endoscope channels (that are typically not accessible with brushes) using friction, unlike manual cleaning where liquid detergents are installed through the small channels during cleaning.
The small endoscope channels (air/water and auxiliary channels) are very narrow or geometrically complex by design which makes these channels difficult to clean. Due to the mechanism of action of the cleaning agent (i.e., friction between lumen wall and cleaning agent), the sponsor was able to demonstrate better cleaning of these hard-to-reach endoscope channels compared to the manual cleaning process.
### Risks
The identified risks include but are not limited to inadequate cleaning validation which could result in contamination leading to patient infection, cleaning agent interference of subsequent
De Novo Summary (DEN240018)
Page 10 of 11
{10}
reprocessing steps (i.e., high-level disinfection or sterilization), device-endoscope incompatibility, deterioration of endoscope channels over time, inappropriate labeling causing use errors, electrical, mechanical and thermal hazards. These risks can be mitigated with appropriate performance bench testing, electromagnetic compatibility testing, software validation/verification and hazard analysis, material compatibility testing, residues analysis, human factors studies, special controls, and labeling.
## 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 Nanosonics CORIS System is indicated for cleaning of the channels of the Olympus EVIS EXERA III CF-HQ190L colonovideoscope.
The CORIS System is suitable for use in healthcare facilities by trained healthcare workers.
The probable benefits outweigh the probable risks for the CORIS System. The device provides probable benefits, and the probable risks can be mitigated using general controls and the identified special controls.
## CONCLUSION
The De Novo request for the CORIS System is granted and the device is classified as follows:
Product Code: SEW
Device Type: Automated endoscope channel cleaner
Regulation Number: 21 CFR 880.6994
Class: II
De Novo Summary (DEN240018)
Page 11 of 11
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.