K260167 · BunkerHill Health · JAK · Mar 6, 2026 · Radiology
Device Facts
Record ID
K260167
Device Name
Bunkerhill Contrast AVC
Applicant
BunkerHill Health
Product Code
JAK · Radiology
Decision Date
Mar 6, 2026
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 892.1750
Device Class
Class 2
Attributes
AI/ML, Software as a Medical Device, Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K260167 · Mar 6, 2026
Bunkerhill Contrast AVC
BunkerHill Health
Multi-site clinical chest CT images
Retrospective clinical data was used to validate the device's performance in detecting, localizing, and quantifying aortic valve calcification, and to establish agreement with ground truth.
Pivotal retrospective study: multi-site dataset across three geographical regions in the United States
—
Indications for Use
Bunkerhill Contrast AVC is a software device intended for use in detecting presence and estimating quantity of aortic valve calcification for adult patients aged 40 years and above. The device automatically analyzes non-gated, contrast-enhanced chest computed tomography (CT) images collected during clinical care and outputs the region of interest (intended for informational purposes only) and quantification of detected calcium. The output of the subject device is made available to the physician on-demand as part of his or her standard workflow. The device-generated quantification can be viewed in the patient report at the discretion of the physician, and the physician also has the option of viewing the device- generated calcium region of interest in a diagnostic image viewer. The subject device output in no way replaces the original patient report or the original non-gated, contrast-enhanced CT scan; both are still available to be viewed and used at the discretion of the physician. The device is intended to provide information to the physician to provide assistance during review of the patient's case. Results of the subject device are not intended to be used on a stand- alone basis and are solely intended to aid and provide information to the physician. In all cases, further action taken on a patient should only come at the recommendation of the physician after further reviewing the patient's results.
Device Story
Software as a Medical Device (SaMD) for aortic valve calcification (AVC) analysis; inputs non-gated, contrast-enhanced chest CT images (DICOM). Operates via deep-learning CNN to segment calcifications, calculate volume (mm³), and generate region of interest (ROI). Deployed via on-premises 'Bunkerhill Edge Server' and cloud processing; integrates into clinician PACS. Physician reviews output on-demand as part of standard workflow; results aid clinical decision-making but do not replace original scans or reports. Benefits include automated quantification of calcium burden to assist in patient case review.
Clinical Evidence
Retrospective stand-alone study (multi-site, US) validated detection, localization, and agreement. Co-primary endpoints met: Sensitivity 0.972 (95% CI: 0.940-1.000), Specificity 0.933 (95% CI: 0.895-0.971), Precision 0.862, Recall 0.919. Bland-Altman agreement showed bias of -20.86 mm³ (LOA: -172.58 to 130.85 mm³). Bridging study (n=65) comparing contrast vs. non-contrast images showed mean bias of 2.05 mm³ (LOA: -30.45 to 34.54 mm³).
Technological Characteristics
Software-only; DICOM input; deep-learning CNN architecture. Processes non-gated chest CTs (slice thickness ≤ 3.0mm). Outputs volume (mm³) and ROI. Connectivity: On-premises Edge Server to Cloud Server. No built-in viewer; integrates with PACS.
Indications for Use
Indicated for adult patients aged 40+ to detect and quantify aortic valve calcification using non-gated, contrast-enhanced chest CT images. Adjunctive tool for physician review; not for standalone diagnosis.
Regulatory Classification
Identification
A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.
{0}
FDA U.S. FOOD & DRUG ADMINISTRATION
March 6, 2026
BunkerHill Health
% John Smith
Partner
Hogan Lovells US LLP
555 Thirteenth St., NW
WASHINGTON DC 20004
Re: K260167
Trade/Device Name: Bunkerhill Contrast AVC
Regulation Number: 21 CFR 892.1750
Regulation Name: Computed Tomography X-Ray System
Regulatory Class: Class II
Product Code: JAK
Dated: January 20, 2026
Received: January 20, 2026
Dear John Smith:
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 (the 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 available 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.
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
{1}
K260167 - John Smith
Page 2
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
Your device is also subject to, among other requirements, the Quality Management System Regulation (QMSR) (21 CFR Part 820), which includes, but is not limited to, ISO 13485 clause 7.3 (Design controls), ISO 13484 clause 8.3 (Nonconforming product), and ISO 13485 clause 8.5 (Corrective and preventative action). Please note that regardless of whether a change requires premarket review, the QMSR requires device manufacturers to review and approve changes to device design and production (ISO 13485 clause 7.3 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).
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 requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting (reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the Quality Management System Regulation (QMSR) (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 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-devices/medical-device-safety/medical-device-reporting-mdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/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-devices/device-advice-comprehensive-regulatory-
{2}
K260167 - John Smith
Page 3
assistance/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,

Lu Jiang, Ph.D.
Assistant Director
Diagnostic X-Ray Systems Team
DHT8B: Division of Radiological Imaging Devices and Electronic Products
OHT8: Office of Radiological Health
Office of Product Evaluation and Quality
Center for Devices and Radiological Health
Enclosure
{3}
FORM FDA 3881 (8/23)
Page 1 of 1
PSC Publishing Services (301) 443-6740
EF
| DEPARTMENT OF HEALTH AND HUMAN SERVICES Food and Drug Administration Indications for Use | Form Approved: OMB No. 0910-0120 Expiration Date: 07/31/2026 See PRA Statement below. |
| --- | --- |
| 510(k) Number (if known) K260167 | |
| Device Name Bunkerhill Contrast AVC | |
| Indications for Use (Describe) Bunkerhill Contrast AVC is a software device intended for use in detecting presence and estimating quantity of aortic valve calcification for adult patients aged 40 years and above. The device automatically analyzes non-gated, contrast-enhanced chest computed tomography (CT) images collected during clinical care and outputs the region of interest (intended for informational purposes only) and quantification of detected calcium. The output of the subject device is made available to the physician on-demand as part of his or her standard workflow. The device-generated quantification can be viewed in the patient report at the discretion of the physician, and the physician also has the option of viewing the device- generated calcium region of interest in a diagnostic image viewer. The subject device output in no way replaces the original patient report or the original non-gated, contrast-enhanced CT scan; both are still available to be viewed and used at the discretion of the physician. The device is intended to provide information to the physician to provide assistance during review of the patient's case. Results of the subject device are not intended to be used on a stand- alone basis and are solely intended to aid and provide information to the physician. In all cases, further action taken on a patient should only come at the recommendation of the physician after further reviewing the patient's results. | |
| Type of Use (Select one or both, as applicable) ☑ 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." | |
{4}
510(K) SUMMARY Bunkerhill Contrast AVC
K260167
BunkerHill Health
% John Smith, Partner
Hogan Lovells US LLP
555 Thirteenth St., NW
Washington, District of Columbia 20004
Phone: (202) 637 3638
Contact Person: Eren Alkan
Date Prepared: March 2, 2026
## Proposed Device
| Proprietary Name | Bunkerhill Contrast AVC |
| --- | --- |
| Classification Name | Computed tomography x-ray system |
| Regulation Number | 21 CFR 892.1750 |
| Product Code | JAK |
| Regulatory Class | II |
## Predicate Device
| Proprietary Name | Bunkerhill AVC |
| --- | --- |
| Premarket Notification | K243229 |
| Classification Name | Computed tomography x-ray system |
| Regulation Number | 21 CFR 892.1750 |
| Product Code | JAK |
| Regulatory Class | II |
## Device Description
Bunkerhill Contrast AVC is a software as a medical device (SaMD) product that interfaces with compatible and commercially available computed tomography (CT) systems. Bunkerhill Contrast AVC detects localizes, and quantifies aortic valve calcification in non-gated, contrast-enhanced chest CT studies. The core features of the product are:
- Detection of aortic valve calcification volume at a threshold of 0 mm³.
- Quantification of the overall aortic valve calcification burden in the form of an estimated volume score (mm³).
{5}
- Localization of estimated calcium burden in the form of AVC region of interest applied to a copy of the original CT scan.
The device integrates into the clinician's PACS and does not include a built-in viewer. It works in parallel with and runs in the background of the physician's workflow. When chest CT scans are captured, the images are automatically sent via the DICOM protocol to an on-premises server ("Bunkerhill Edge Server") running the Bunkerhill software. Images are de-identified on the Bunkerhill Edge Server and sent to a Bunkerhill Cloud Server for processing, where the artificial intelligence algorithm (Bunkerhill Contrast AVC) is applied to the image to detect, estimate, and localize aortic valve calcium. The results from the algorithm are then relayed back to the on-premises Bunkerhill Edge Server, where the associated chest CT images are re-identified, and results are paired with the appropriate images and routed to be made available in the physician's workflow.
## Algorithm Overview
The Bunkerhill Contrast AVC device is a deep-learning model for detecting aortic valve calcification on non-gated, contrast-enhanced chest computed tomography (CT) exams. The device consists of a convolutional neural network (CNN) architecture trained to segment calcifications on CT volumes with slice thickness at most $3.0\mathrm{mm}$. The calcifications are grouped into calcified lesions, and the area of each lesion is summed across the slices to determine a volume score in cubic millimeters for the entire CT scan. This fully automatic algorithm was designed to take a non-gated, contrast-enhanced chest CT volume as input and provide an estimated aortic valve calcification volume and region of interest as output.
## Intended Use / Indications for Use
Bunkerhill Contrast AVC is a software device intended for use in detecting presence and estimating quantity of aortic valve calcification for adult patients aged 40 years and above. The device automatically analyzes non-gated, contrast-enhanced chest computed tomography (CT) images collected during clinical care and outputs the region of interest (intended for informational purposes only) and quantification of detected calcium.
The output of the subject device is made available to the physician on-demand as part of his or her standard workflow. The device-generated quantification can be viewed in the patient report at the discretion of the physician, and the physician also has the option of viewing the device- generated calcium region of interest in a diagnostic image viewer. The subject device output in no way replaces the original patient report or the original non-gated, contrast-enhanced CT scan; both are still available to be viewed and used at the discretion of the physician.
The device is intended to provide information to the physician to provide assistance during review of the patient's case. Results of the subject device are not intended to be used on a stand- alone basis and are solely intended to aid and provide information to the physician. In all cases, further action taken on a patient should only come at the recommendation of the physician after further reviewing the patient's results.
## Technological Characteristics Comparison:
The subject device and predicate device are all intended for use in detecting presence and estimating quantity calcification. The only difference in intended use between subject and predicate device is that while the predicate device analyzes non-gated, non-contrast chest CT images the subject device analyzes non-gated, contrast-enhanced chest CT images. Given the identical principles of operation and
{6}
technological characteristics, the differences do not raise any new questions of safety and effectiveness. Both the subject and predicate device assist the medical professionals in detecting presence and location of calcifications. Both subject and predicate devices are to aid medical professionals in viewing and analyzing cardiac computed tomography (CT) data to determine presence and extent of calcification.
Table 1: Substantial Equivalence-Intended Use Table
| | Proposed Device: Bunkerhill Contrast AVC | Predicate Device: Bunkerhill AVC (K243229) |
| --- | --- | --- |
| Intended use / Indications for use | Bunkerhill Contrast AVC is a software device intended for use in detecting presence and estimating quantity of aortic valve calcification for adult patients aged 40 years and above. The device automatically analyzes non-gated, contrast-enhanced chest computed tomography (CT) images collected during clinical care and outputs the region of interest (intended for informational purposes only) and quantification of detected calcium. The output of the subject device is made available to the physician on-demand as part of his or her standard workflow. The device-generated quantification can be viewed in the patient report at the discretion of the physician, and the physician also has the option of viewing the device- generated calcium region of interest in a diagnostic image viewer. The subject device output in no way replaces the original patient report or the original non-gated, contrast-enhanced CT scan; both are still available to be viewed and used at the discretion of the physician. | Bunkerhill AVC is a software device intended for use in detecting presence and estimating quantity of aortic valve calcification for adult patients aged 40 years and above. The device automatically analyzes non-gated, non- contrast chest computed tomography (CT) images collected during clinical care and outputs the region of interest (intended for informational purposes only) and quantification of detected calcium. The output of the subject device is made available to the physician on- demand as part of his or her standard workflow. The device-generated quantification can be viewed in the patient report at the discretion of the physician, and the physician also has the option of viewing the device- generated calcium region of interest in a diagnostic image viewer. The subject device output in no way replaces the original patient report or the original non- gated, non- contrast CT scan; both are still available |
{7}
| | Proposed Device: Bunkerhill Contrast AVC | Predicate Device: Bunkerhill AVC (K243229) |
| --- | --- | --- |
| | The device is intended to provide information to the physician to provide assistance during review of the patient’s case. Results of the subject device are not intended to be used on a stand- alone basis and are solely intended to aid and provide information to the physician. In all cases, further action taken on a patient should only come at the recommendation of the physician after further reviewing the patient’s results. | to be viewed and used at the discretion of the physician.
The device is intended to provide information to the physician to provide assistance during review of the patient’s case.
Results of the subject device are not intended to be used on a stand- alone basis and are solely intended to aid and provide information to the physician. In all cases, further action taken on a patient should only come at the recommendation of the physician after further reviewing the patient’s results. |
## Summary of Technological Characteristics
- Both the predicate(s) and the subject device use deep-learning algorithms to identify the presence of calcification and estimate calcification.
- Both devices analyze non-gated chest computed tomography (CT) images that are sent to the software in DICOM format.
- Both the predicate and the subject device quantify the calcification by generating a metric (an estimated score).
- Both devices serve as support tools to provide information to the physician. Both can be used on-demand or optionally by the physician and do not provide a definitive diagnosis. Both devices do not replace clinical evaluation and do not alter the standard of care. Both require the physician to use this information to decide next steps and/or additional diagnostic work up.
- Both devices provide a visual representation of the region of the detected calcification for better explainability and for the physician to confirm the device output.
- There are no major technological differences between the subject device and predicate device. The only technological difference that exists between the subject and predicate device is that the subject device outputs volume in mm3 using a deterministic mathematical formula based on the raw segmentation maps, while the predicate devices output Agatston Units using a deterministic formula based on raw segmentation maps.
{8}
| | Proposed Device: Bunkerhill Contrast AVC | Predicate Device: Bunkerhill AVC (K243229) | Summary |
| --- | --- | --- | --- |
| Product code | JAK | JAK | Same |
| Regulation number | 21 CFR §892.1750 | 21 CFR §892.1750 | Same |
| Modality | Computed tomography (CT) | Computed tomography (CT) | Same |
| Image format | DICOM | DICOM | Same |
| Supported CT Scan | Contrast-enhanced, Non-cardiac-gated CT scan | Non-contrast, Non-cardiac-gated CT scan | Similar |
| Slice thickness | Up to 5 mm | Up to 5 mm | Same |
| Calcification detection | Automatic | Automatic | Same |
| Main image quality | DICOM | DICOM | Same |
| Annotation of detected calcium | Yes | Yes | Same |
| Visual Output format | Visual output in the form a Region of Interest or ROI (intended for informational purposes only). The estimated visual output can be viewed by the physician in a diagnostic image viewer. The physician's standard method for viewing unaltered chest CT scans in PACS will remain available to them even if the subject device is being used. However, the physician will also have an option to view the visual output estimated by the subject device as a separate series within PACS. | Visual output in the form a Region of Interest or ROI (intended for informational purposes only). The estimated visual output can be viewed by the physician in a diagnostic image viewer. The physician's standard method for viewing unaltered chest CT scans in PACS will remain available to them even if the subject device is being used. However, the physician will also have an option to view the visual output estimated by the subject device as a separate series within PACS. | Similar |
| Generate patient report | Optional to copy result to clipboard, insert in report, DICOM Secondary Capture | Optional to copy result to clipboard, insert in report, DICOM Secondary Capture | Same |
| Report of the calcium score | Yes, estimated calcification volume (mm3) score and binary output (presence/absence) | Yes, estimated exact Agatston-equivalent score and binary output (presence/absence) | Similar |
| Type of Interpretation | Adjunctive information | Adjunctive information | Same |
{9}
| | Proposed Device: Bunkerhill Contrast AVC | Predicate Device: Bunkerhill AVC (K243229) | Summary |
| --- | --- | --- | --- |
| Intended User | Qualified medical professionals such as | Qualified medical professionals such as | Same |
| Patient population | Patients aged 40 years and above | Patients aged 40 years and above | Same |
| Anatomical location | Chest (aortic valve) | Chest (aortic valve) | Same |
| Intended location | Medical facility | Medical facility | Same |
| Rx or OTC | Rx | Rx | Same |
# Performance Data
Safety and performance of Bunkerhill Contrast AVC has been evaluated and verified in accordance with software specifications and applicable performance standards through Software Development and Validation & Verification Process to ensure performance according to specifications, User Requirements and Federal Regulations and Guidance documents, "Content of Premarket Submissions for Device Software Functions" and Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions.
The Contrast AVC performance was validated in a stand-alone retrospective study for detection, localization and agreement of the device output compared to the established ground truth. The pivotal dataset was curated from multiple sites across three geographical regions in the United States. The co-primary endpoints of Sensitivity and Specificity (Se/Sp), Precision and Recall of the circular ROI and correlation coefficient were met successfully. The acceptance criteria were derived from the performance of the predicate device and clinical literature in high impact journals that investigate the inter-reader agreement of manual segmentation. The co-primary endpoint of a Bland Altman agreement was also successfully met. The observed bias in the pivotal study was $-20.86\mathrm{mm}^3$ and lower and upper limits agreements were $-172.58\mathrm{mm}^3$ and $130.85\mathrm{mm}^3$ , respectively. As result, Bunkerhill Contrast AVC met the mean difference and limits of agreement acceptance criteria, thus satisfying all the endpoints of the pivotal testing study. The low mean difference demonstrates that Bunkerhill Contrast AVC has a bias of low magnitude. The observed Sensitivity was 0.972 (0.940, 1.000), the observed specificity was 0.933 (0.895, 0.971), the observed Precision was 0.862 (0.820, 0.899) and the observed Recall was 0.919 (0.887, 0.945). As a result, Bunkerhill Contrast AVC met all study acceptance criteria.
An additional bridging study comparing the volume generated by the Contrast AVC device on a contrast-enhanced image to the calcification volume on the same patient calculated on a non-contrast image was conducted. This study intended to further demonstrate the validity of the Contrast AVC device in detecting and quantifying aortic valve calcification in patients in line with its intended use. 65 cases were included in the bridging study. The study met the predefined acceptance criteria with a mean bias of $2.05\mathrm{mm}^3$ and LOA of $-30.45\mathrm{mm}^3$ to $34.54\mathrm{mm}^3$ .
{10}
The testing demonstrates that the device is substantially equivalent to the predicate as required by 21 CFR 807.92(b)(3) since both the predicate and subject device demonstrated that with the cited mean difference and limits of agreement, the primary endpoint for calcium score was met.
7
{11}
8
# Conclusions
Bunkerhill Contrast AVC is substantially equivalent to the predicate Bunkerhill AVC Device (K243229). The subject device has the same intended uses and similar indications, technological characteristics, and principles of operation as its predicate devices. The minor differences in indications do not alter the intended diagnostic use of the device and do not affect its safety and effectiveness when used as labeled. In summary, any minor differences between Bunkerhill Contrast AVC and the predicate devices do not raise any issues of safety or effectiveness.
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.