StoneChecker is a standalone post-processing software application which assists trained professionals in evaluating DICOM computed tomography image studies of patients diagnosed with kidney stones. The software provides tools to enable the user to navigate images, select regions of interest, and generate information from those regions. The generated information consists of regional statistical measurements of image texture and heterogeneity, including means, standard deviation, skewness, and kurtosis. The information also includes regional physical measurements of stone size, volume, and position. StoneChecker does not make clinical decisions and the information provided by StoneChecker must not be used in isolation when making patient management decisions.
Device Story
Standalone post-processing software; loads DICOM CT studies; assists trained physicians in evaluating kidney stones. User identifies stone regions of interest (ROI) on non-contrast KUB CT scans. Software calculates physical measurements (stone volume, mean Hounsfield Unit density, skin-to-stone distance) and statistical texture/heterogeneity metrics (mean, standard deviation, skewness, kurtosis, entropy). Output displayed on PC; report generation available in Excel. Used in clinical settings for treatment planning; adjunct to medical history, physical exam, and urine analysis. Does not make clinical decisions; requires physician interpretation. Benefits include standardized, easy-to-acquire quantitative data to aid clinical decision-making.
Clinical Evidence
Bench testing (functional and integration) confirmed accurate computation of outputs. Usage validation conducted at two clinical sites (Oxford, UK; Beijing, China) with physicians analyzing KUB CT scans to validate functionality and clinical usability. No clinical diagnostic performance metrics (sensitivity/specificity) reported; device is an adjunct tool.
Technological Characteristics
Standalone software; operates on off-the-shelf PC hardware. Conforms to DICOM (NEMA PS 3.1-3.20). Uses Laplacian filter for texture analysis. Calculates statistical metrics (mean, SD, skewness, kurtosis, entropy) and physical measurements (volume, HU density, distance). Software life cycle per ANSI AAMI IEC 62304. Risk management per ISO 14971.
Indications for Use
Indicated for patients diagnosed with kidney stones requiring medical intervention. Used by trained professionals (physicians/radiologists) to evaluate DICOM CT image studies of the kidneys, ureters, and bladder (KUB).
Regulatory Classification
Identification
A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.
Special Controls
*Classification.* Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).
{0}------------------------------------------------
Image /page/0/Picture/0 description: The image contains the logos of the Department of Health and Human Services and the Food and Drug Administration (FDA). The Department of Health and Human Services logo is on the left, and the FDA logo is on the right. The FDA logo includes the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG ADMINISTRATION" in blue text.
Imaging Biometrics, LLC Timothy Dondlinger COO 13416 Watertown Plank Road, Suite 260 ELM GROVE, WISCONSIN 53122
Re: K191530
Trade/Device Name: StoneChecker Regulation Number: 21 CFR 892.2050 Regulation Name: Picture Archiving and Communications System Regulatory Class: Class II Product Code: LLZ Dated: June 7, 2019 Received: June 10, 2019
Dear Timothy Dondlinger:
We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's
September 26, 2019
{1}------------------------------------------------
requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
For
Thalia Mills, Ph.D. Director Division of Radiological Health OHT7: Office of In Vitro Diagnostics and Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
#### Indications for Use
510(k) Number (if known) 191530
Device Name StoneChecker
#### Indications for Use (Describe)
StoneChecker is a standalone post-processing software application which assists trained professionals in evaluating DICOM computed tomography image studies of patients diagnosed with kidney stones. The software provides tools to enable the user to navigate images, select regions of interest, and generate information from those regions.
The generated information consists of regional statistical measurements of image texture and heterogeneity, including means, standard deviation, skewness, and kurtosis. The information also includes regional physical measurements of stone size, volume, and position.
StoneChecker does not make clinical decisions and the information provided by StoneChecker must not be used in isolation when making patient management decisions.
| Type of Use (Select one or both, as applicable) | |
|-------------------------------------------------|--|
| | |
X | Prescription Use (Part 21 CFR 801 Subpart D)
| | Over-The-Counter Use (21 CFR 801 Subpart C)
#### CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
#### *DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.*
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
> Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{3}------------------------------------------------
# 510(k) Summary
#### 510(k) Notification K191530
This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of SMDA 1990 and 21 CFR 807.92.
| Applicant / Owner : | Imaging Biometrics, LLC<br>13416 Watertown Plank Road, Suite 260<br>Elm Grove, WI 53122 |
|----------------------|-------------------------------------------------------------------------------------------------------|
| Contact Person: | Timothy Dondlinger<br>(262) 439-8252 (telephone)<br>(262) 439-8301 (fax)<br>tim@imagingbiometrics.com |
| Date Prepared: | June 7, 2019 |
| Common Name: | System, Image Processing, Radiological |
| Trade Name: | StoneChecker |
| Classification Name: | Picture archiving and communications system |
| Review Panel: | Radiology |
| Regulation Number: | 892.2050 |
| Device Class: | II |
| Product Code: | LLZ |
### Predicate Device Information
| 510(k) | Trade Name | Manufacture | Type | Regulation Number |
|---------|------------------------------|-------------------|------------------------|-------------------|
| K141745 | IQQA-BodyImaging<br>Software | EDDA Technology | Primary<br>Predicate | 892.2050 |
| K110332 | ClearCanvas<br>RIS/PACS | ClearCanvas, Inc. | Secondary<br>Predicate | 892.2050 |
{4}------------------------------------------------
## Device Description
StoneChecker (SC) is a standalone software application intended to load DICOMformatted CT studies, let the trained user identify stone regions of interest, and provide computed information consisting of physical measurements and statistical measurements of stone heterogeneity from a single source making it easier for the user to determine the best treatment option. SC is an optional tool used during the treatment planning of a patient diagnosed with kidney stones.
StoneChecker provides the user tools to select and evaluate various physical characteristics of a kidney stone displayed on a non-contrast enhanced Kidneys, Ureters, and Bladder (KUB) CT scan slice. The measurement and calculated values are displayed on the PC screen for the user and the user has an option to generate a report. The calculated output includes stone volume, mean Hounsfield Unit (HU) density, skin to stone distance, and texture values (mean, mean of positive pixels, standard deviation, skewness, kurtosis, and entropy). This data can be used by the physician as an aid to decision making and are intended to be an adjunct to other clinical data such as medical history, physical examination, and urine analysis. Thus, additional analysis of all kidney stones is required. StoneChecker software is designed exclusively for use in assessing kidney stones.
StoneChecker is designed to provide easy-to-acquire useful data for helping clinicians make the best decisions for their patients.
StoneChecker includes the following features:
- . Processes standard DICOM image sets,
- . Novel proven statistical algorithms,
- Time-saving kidney stone regions of interest (ROI) and measurement tools, .
- . Rapid calculation results, and
- Saves results in standard Excel spreadsheets. .
### Indications for Use
StoneChecker is a standalone post-processing software application which assists trained professionals in evaluating DICOM computed tomography image studies of patients diagnosed with kidney stones. The software provides tools to enable the user to navigate images, select regions of interest, and generate information from those regions.
The generated information consists of regional statistical measurements of image texture and heterogeneity, including means, standard deviation, skewness, and kurtosis. The information also includes regional physical measurements of stone size, volume, and position.
StoneChecker does not make clinical decisions and the information provided by StoneChecker must not be used in isolation when making patient management decisions.
{5}------------------------------------------------
# Substantial Equivalence
| | Intended Use | Subject | Primary IQQA Body<br>Imaging Software<br>(K141745) | Secondary<br>ClearCanvas RIS /<br>PACS (K110332) |
|----|---------------------------------------------------------------------------------------------|---------|----------------------------------------------------|--------------------------------------------------|
| 1. | To be used on standard PC<br>based hardware. | Yes | Yes | Yes |
| 2. | To be run as medical device<br>standalone software. | Yes | Yes | Yes |
| 3. | To be used to load standard<br>DICOM CT studies. | Yes | Yes | Yes |
| 4. | To be used by clinicians to<br>identify region of interests<br>(ROIs). | Yes | Yes | Yes |
| 5. | To be used for displaying,<br>measuring, and analyzing<br>images controlled by the<br>user. | Yes | Yes | Yes |
| 6. | To be used for providing<br>output used in the treatment<br>of a patient. | Yes | Yes | Yes |
{6}------------------------------------------------
### Subject Device (Indications for Use): StoneChecker
StoneChecker is a standalone post-processing software application which assists trained professionals in evaluating DICOM computed tomography image studies of patients diagnosed with kidney stones. The software provides tools to enable the user to navigate images, select regions of interest, and generate information from those regions. The generated information consists of regional statistical measurements of image texture and heterogeneity, including means, standard deviation, skewness, and kurtosis. The information also includes regional physical measurements of stone size. volume, and position. StoneChecker does not make clinical decisions and the information provided by StoneChecker must not be used in isolation when making patient management decisions.
### Primary Predicate IFU Statement: IQQA-BodyImaging Software (K141745)
IQQA-BodyImaging is a PC-based, self-contained, non-invasive image analysis software application for reviewing body imaging studies (including thoracic, abdominal and pelvic) derived from CT and MR scanners. Combining image viewing, processing and reporting tools, the software is designed to support the visualization, and reporting of body imaging studies and physician-identified lesions. The software supports a workflow based on automated image registration for viewing and analyzing multiphase and multiple time-point volume datasets. It includes tools for interactive segmentation and labeling of organ segments and vascular/ductal/airway structures. The software provides functionalities for manual or interactive segmentation of physician-identified lesions, interactive definition of virtual resection plane and virtual needle path and allows for regional volumetric analysis of such lesions in terms of size, position, margin, and enhancement pattern, providing information for physician's evaluation and treatment planning, monitoring, and follow-up. The software is designed for use by trained professionals, including physicians and technicians. Image source: DICOM.
### Secondary Predicate IFU Statement: ClearCanvas RIS/PACS (K110332)
The ClearCanvas RIS/PACS is an image management system whose intended use is to provide scaleable DICOM compatible PACS solutions for hospitals and related institutions and sites, which will archive, distribute, retrieve and display images and data from all hospital modalities (such as CR, CT, DR, MR, and other devices) and information systems. This also includes the display of structured reports and mammography images that have been created according to DICOM "For Presentation", and will include standard features and other tools for analyzing mammography images.
Lossy compressed mammography images and digitized film screen images must not be used for primary image interpretations. Mammography images may only be interpreted using an FDA approved monitor that offers at least 5 mega-pixel resolution and meets other technical specifications approved by the FDA.
{7}------------------------------------------------
| Use Characteristic | Subject | IQQA Body Imaging<br>Software<br>(K141745) | ClearCanvas RIS /<br>PACS<br>(K110332) |
|------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------|-----------------------------------------------------------------------|------------------------------------------------------------------|
| Indications for Use Statements | | | |
| 1. Statement references a<br>software only device. | Yes | Yes | Yes |
| 2. Statement references DICOM<br>standard. | Yes | Yes | Yes |
| 3. Statement references the<br>display / view of medical<br>images. | Yes | Yes | Yes |
| 4. Statement references the<br>output of information. | Yes | Yes | Yes |
| 5. Statement references the<br>user selection of ROIs | Yes | Yes | No |
| 6. Statement references<br>providing the clinician with<br>information about an ROI. | Yes | Yes | No |
| 7. Statement references<br>providing the user with<br>information related to kidney<br>stones. | Yes | No | No |
| 8. Intended Users | Trained physicians,<br>Radiologists. | Trained professional,<br>including physicians and<br>technicians | Physicians,<br>Radiologists,<br>clinicians, or<br>technologists. |
| 9. Target population | Patients diagnosed with<br>kidney stones that<br>require medical<br>intervention. | No restrictions | No restrictions |
| 10. Anatomical sites | Kidneys, ureters, and<br>bladder (KUB) | Body imaging studies<br>(including thoracic,<br>abdominal and pelvic) | No restrictions |
| 11. Where used | No restrictions | No restrictions | No restrictions |
{8}------------------------------------------------
A comparison of the devices' technical characteristics is summarized in the following table:
| Technical<br>Characteristic¹ | Subject | IQQA Body<br>Imaging Software<br>(K141745) | ClearCanvas<br>RIS / PACS<br>(K110332) |
|---------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------|
| 1. Standalone software device that operates<br>on off-the-shelf hardware. | Yes | Yes | Yes |
| 2. Software device uses standard windowing<br>user interface. | Yes | Yes | Yes |
| 3. Software device uses software algorithms<br>for image post processing analysis. | Yes | Yes | Yes |
| 4. Conforms to DICOM standards (PS 3.10) | Yes | Yes | Yes |
| 5. Data loading of CT image series using<br>DICOM standard | Yes | Yes | Yes |
| 6. 2D image review | Yes | Yes | Yes |
| 7. Image navigation tools (pan, zoom, scroll,<br>window/level) | Yes | Yes | Yes |
| 8. Measurement tools (ruler, ROI) | Yes | Yes | Yes |
| 9. Size calculations (area, volume) | Yes | Yes | Area |
| 10. Statistical calculations | Mean, standard<br>deviation (SD),<br>mean of positive<br>pixels, skewness,<br>kurtosis, entropy | Regional volumetric<br>analysis of<br>physician-identified<br>lesions in terms of<br>size, position,<br>margin, and<br>enhancement<br>pattern | Mean, SD |
| 11. CT texture analysis calculations2 | Yes | Yes | No |
| 12. Display output of measurements and<br>information. | Yes | Yes | Yes |
| 13. Report generation | Excel | Unknown | DICOM Print |
| Physical Characteristics | | | |
| 14. Post-processing (non-real-time, non-<br>contacting, non-life supporting and not life<br>sustaining) | Yes | Yes | Yes |
1 Because the subject and predicate devices have no patient contact and do not control any life sustaining devices, several areas of comparison were considered not relevant and are not discussed in this table.
2 The CT texture analysis calculations of the subject device consist of the statistical calculations listed (mean, standard deviation, mean of positive pixels, skewness, kurtosis, and entropy) computed from image intensity data which has first been processed through a Laplacian filter, effectively highlighting features of different sizes.
The intended use and technical characteristics for StoneChecker are similar to both predicate devices listed in the Predicate Device Information section above for a stand-alone software application that provides a user interface to allow a clinician to load, display, measure, and identify regions of interests. The software algorithms calculate statistical information based on the intensities of the image pixels contained within the regions of interest. The calculated values provide a clinician with relevant information for stone evaluation.
{9}------------------------------------------------
SC is operated as stand-alone software, is non-patient contacting, and is used by trained physicians. SC does not provide any interpretation of the statistical parameters displayed to the user. The trained physician is responsible for identifying, measuring, and interpreting the images and data being displayed.
SC and both its predicate devices are substantially equivalent in the categories of technical characteristics and features. SC does not raise any different questions of safety or effectiveness as demonstrated through performance testing and is therefore substantially equivalent to the predicate device.
# Standards Conformance
During the development of StoneChecker, the following standards were observed:
| Standard | FDA Recognition<br>Number |
|------------------------------------------------------------------------------------------------------------|---------------------------|
| NEMA PS 3.1 – 3.20 (2016)<br>Digital Imaging and Communications in Medicine (DICOM) | 12-300 |
| ISO 14971 Second edition 2007-03-01<br>Medical devices – Application of risk management to medical devices | 5-40 |
| ANSI AAMI IEC 62304:2006<br>Medical device software - Software life cycle processes | 13-32 |
# Testing Information and Performance
All product specifications were verified and validated. Testing was performed according to internal company procedures. Software testing and validation were conducted according to written test protocols established before testing was conducted. Test results were reviewed by designated technical professionals before software proceeded to release. Test results support the conclusion that actual device performance satisfies the design intent. Testing was performed in accordance with the FDA guidance document, "General Principles of Software Validation," issued January 11, 2002.
Bench testing (functional and integration) was conducted for StoneChecker during product development. Test results demonstrate StoneChecker output is computed accurately based on input. However, to obtain consistent output, stones to be analyzed should be at least 5mm in size, and images should be obtained at resolutions with sub-mm pixel sizes. StoneChecker texture analysis calculations are extremely sensitive to changes in resolution, so image resolutions must be constant, and, ideally, slice thicknesses and spacing should also be similar.
To supplement the software verification, StoneChecker underwent usage validation at two clinical sites in Oxford, UK and Beijing, China. The purpose of the testing was to have physicians use StoneChecker to analyze KUB CT scans, validate major functionalities provided by StoneChecker, and provide feedback on the clinical usability of StoneChecker. Where appropriate, tester feedback was incorporated into StoneChecker software modifications.
The StoneChecker risk analysis was completed and risk control measures were implemented to mitigate unacceptable hazards. StoneChecker relies upon user
{10}------------------------------------------------
expertise to determine the usability of images for analysis. Images with excessive noise, distortion, and/or artifacts obscuring any portion of a stone should not be used for analysis. Testing for verification and validation of StoneChecker was found acceptable to support the claims of substantial equivalence.
### Conclusion
StoneChecker has the same intended use as the predicate devices. The technological characteristics such as software platform, CT series loading, image viewing, and measurement tools are the same. Any differences between StoneChecker and the predicate devices do not raise different questions of safety and effectiveness. The result of all testing conducted was found acceptable to support the claim of substantial equivalence.
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.