K202808 · Advantis Medical Imaging Single Member P.C. · LLZ · Oct 14, 2021 · Radiology
Device Facts
Record ID
K202808
Device Name
Brainance MD
Applicant
Advantis Medical Imaging Single Member P.C.
Product Code
LLZ · Radiology
Decision Date
Oct 14, 2021
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 892.2050
Device Class
Class 2
Attributes
Software as a Medical Device
Indications for Use
Brainance MD is an advanced visualization and processing software, with specific focus on providing algorithms designed to analyze brain MRI data. The software is web-accessible and can be used with data and images acquired through DICOM compliant imaging devices and modalities. The software is intended to be used by medical personnel, including but not limited to radiologists and medical technicians, trained in the methods provided by the application.
Device Story
Brainance MD is a web-accessible software for post-processing and visualization of brain MRI data. It accepts DICOM-compliant images; performs BOLD fMRI analysis (neuronal activity/blood flow), DTI (water diffusion/white matter fiber tracking), and DSC perfusion (blood vessel characteristics). Operated by radiologists or medical technicians in clinical/hospital settings. Output includes parametric maps (e.g., blood flow, mean transit time, fractional anisotropy) and 3D visualizations. Clinicians use these outputs to assess brain structure and function, aiding in clinical decision-making for neurological conditions. Benefits include standardized, automated analysis of complex MRI sequences.
Clinical Evidence
Bench testing only. Comparative study performed between Brainance MD and predicate using DSC Perfusion, fMRI, and DTI sequences from adult subjects (healthy controls, metastasis, or glioblastoma multiforme). Maps compared using ICC and Bland-Altman analysis; fiber tracts compared using Mean Relative Difference (MRD). Results met pre-defined acceptance criteria, demonstrating equivalence in computed outputs.
Technological Characteristics
Web-accessible software application; client-server architecture. Processes DICOM and Nifti data. Implements BOLD (General Linear Model), DTI (tensor-based tractography), and DSC (T2 first-pass perfusion) algorithms. Compliant with DICOM standards. Software developed in accordance with IEC 62304, ISO 13485:2016, and 21 CFR 820.
Indications for Use
Indicated for analysis and visualization of dynamic brain MRI data, presenting derived properties and parameters in a clinically useful context for adult patients, including healthy controls and those with conditions such as metastasis or glioblastoma multiforme.
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/10 description: The image contains the logo of the U.S. Food & Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
Advantis Medical Imaging Single Member P.C. % Paris Ziogkas COO Eleftheriou Venizelou Avenue 99 Nea Smirni Athens, 17123 GREECE
Re: K202808
Trade/Device Name: Brainance MD Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: LLZ Dated: September 21, 2021 Received: September 27, 2021
Dear Paris Ziogkas:
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 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
October 14, 2021
{1}------------------------------------------------
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 (QS) 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 T. 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) K202808
Device Name Brainance MD
Indications for Use (Describe)
Brainance MD provides analysis and visualization capabilities of dynamic MRI data of the brain, presenting the derived properties and parameters in a clinically useful context.
| 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
### Submitter
Submitter Name : Advantis Medical Imaging Single Member P.C. Submitter Address: Eleftheriou Venizelou Avenue 99, Nea Smirni, Athens, Greece, 17123 Phone : +302109329558 Contact Person : Paris Ziogkas (pz@advantis.io) Date prepared : September 21 st 2021
### Device
Device Trade Name : Brainance MD Device Common Name : PACS Device : System, Image Processing, Radiological Classification Name : Medical image management and processing system Classification Regulation: 21 CFR 892.2050 Class : Il Panel : Radiology Product Code : LLZ Predicate Device
Primary Predicate : K163324, nordicBrainEx This predicate has not been subject to a recall. Reference Device Name 1 : K090546, nordicICE Software This reference device has not been subject to a recall. Reference Device Name 2 : K162513, Arterys Software v2.0
This reference device has not been subject to a recall.
# Device Description
Brainance MD is a web-accessible medical viewing and post-processing software application. Brainance MD offers comprehensive functionality for dynamic image analysis and visualization of brain MRI data which are acquired through DICOM compliant imaging devices and modalities.
The following algorithms provide the main functional analyses of the software application.
- · BOLD: BOLD fMRI analysis is used to highlight small magnetic susceptibility changes in the human brain in areas with altered bloodflow resulting from neuronal activity.
- · DTI: Diffusion analysis is used to visualize local water diffusion properties from the analysis of diffusion-weighted MRI data. Fiber tracking utilizes the directional dependency of the diffusion to display the white matter structure in the brain.
- DSC Perfusion: Calculations of perfusion related parameters that provide information about the blood vessel structure and characteristics. Examples of such maps are blood flow, time to peak, mean transit time and leakage.
Apart from the aforementioned functionalities, Brainance MD offers general visualization tools, a data upload, data download and a reporting feature.
{4}------------------------------------------------
# Intended use
Brainance MD is an advanced visualization and processing software, with specific focus on providing algorithms designed to analyze brain MRI data. The software is web-accessible and can be used with data and images acquired through DICOM compliant imaging devices and modalities.
The software is intended to be used by medical personnel, including but not limited to radiologists and medical technicians, trained in the methods provided by the application.
# Indications for Use
Brainance MD provides analysis and visualization capabilities of dynamic MRI data of the brain, presenting the derived properties and parameters in a clinically useful context.
# Comparison of Technological Characteristics with the Predicate Device
| | Subject Device | Primary Predicate<br>Device | Reference Device 1 | Reference<br>Device 2 | Differences |
|----------------------------------|-------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------|----------------------------------------------|------------------------|
| Device Name | Brainance MD | nordicBrainEx | nordicICE | Arterys<br>Software v2.0 | - |
| 510(k)Number | K202808 | K163324 | K090546 | K162513 | - |
| Manufacturer | Advantis Medical<br>Imaging Single Member<br>P.C. | NordicNeuroLab AS | NordicNeuroLab AS | Arterys Inc. | - |
| Regulation<br>Number | 892.2050 | 892.2050 | 892.2050 | 892.2050 | No<br>difference |
| Device<br>Classification<br>Name | System, Image<br>Processing,<br>Radiological | System, Image<br>Processing,<br>Radiological | System, Image<br>Processing,<br>Radiological | System, Image<br>Processing,<br>Radiological | No<br>difference |
| Product Code | LLZ | LLZ | LLZ | LLZ | No<br>difference |
| Development<br>Framework | Web development<br>framework | Embarcadero C++<br>Builder XE2 | Embarcadero C++<br>Builder XE2 | Web<br>development<br>framework | Difference -<br>Note 1 |
| Operating<br>Environment | Client-server | "Off-the-shelf" windows<br>PC workstation | "Off-the-shelf"<br>windows PC<br>workstation | Client-server | Difference -<br>Note 2 |
| Input data | DICOM compliant MR<br>data, Nifti | DICOM compliant MR<br>data | DICOM compliant MR<br>data ,RAW, Analyze,<br>Nifti | - | Difference -<br>Note 3 |
| Organ/Area | Brain | Brain | Brain | - | No<br>difference |
| General<br>Functionality | 2D MPR visualization,<br>3D Visualization,<br>Volumes of interest,<br>Measurement tools,<br>DICOM compliant node,<br>Reporting tool | 2D MPR visualization,<br>3D Visualization,<br>Volumes of interest,<br>Measurement tools,<br>DICOM compliant node,<br>Reporting tool | 2D MPR visualization,<br>3D Visualization,<br>Regions of interest,<br>Measurement tools,<br>DICOM compliant<br>node | - | No<br>difference |
{5}------------------------------------------------
| | Subject Device | Primary Predicate<br>Device | Reference Device 1 | Reference<br>Device 2 | Differences |
|--------------------------|---------------------------------------------------------|---------------------------------------------------------|---------------------------------------------------------|------------------------------------------------------------|-------------------------|
| Dynamic<br>Analyses | BOLD, DTI, DSC | BOLD, DTI, DSC, DCE | - | - | Difference -<br>Note 4 |
| Analyses of<br>BOLD fMRI | Note 5 | Note 6 | - | - | No<br>difference |
| Analyses of<br>DTI | Note 7 | Note 8 | - | - | No<br>difference |
| Analyses of<br>DSC | Note 9 | Note 10 | - | - | Difference -<br>Note 11 |
| Environment<br>of Use | Intended for use in<br>clinical/hospital<br>environment | Intended for use in<br>clinical/hospital<br>environment | Intended for use in<br>clinical/hospital<br>environment | Intended for<br>use in<br>clinical/hospital<br>environment | No<br>difference |
#### Notes
#### Note 1
The subject device and reference device 2 are developed using web frameworks while primary predicate device 1 are developed using Embarcadero C++ Builder XE2. The aforementioned difference does not raise any safety or performance issues.
#### Note 2
The subject device and reference device 2 make use of the client server model while primary predicate device 1 operate on "Off-the-shelf" windows PC workstations. The aforementioned difference does not raise any safety or performance issues.
#### Note 3
The subject device and reference device 1 can accept and proccess input data of both DICOM and Nifti format while the primary predicate device can only accept and process DICOM data. The comparison with reference device 2 in this field is not applicable. The aforementioned difference does not raise any safety or performance issues.
#### Note 4
Regarding dynamic analyses the subject device is designed to analyse BOLD, DTI, and DSC sequences while the primary predicate device can also be used for the analysis of DCE apart from the other three aforementioned difference does not raise any safety or performance issues.
#### Note 5
Possibility for importing, creating or editing BOLD design files including: BOLD paradigm and contrasts, Preprocessing steps (Slice time correction, Motion correction, smoothing, High-Pass filtering), BOLD analysis with the General Linear Model, 2D/3D visualization or activations overlaid structural datasets, Combined 3D visualizations and white matter fiber tracts from Diffusion Tensor lmaging studies, Interactive thresholding of statistical maps, Automated or-registration of functional datasets, Possibilities for saving statistical maps and 3D snapshots to various file formats.
#### Note 6
Possibility for importing, creating or editing BOLD design files including: BOLD paradigm and contrasts, Preprocessing steps (Slice time correction, Motion correction, smoothing, High-Pass filtering), BOLD analysis with the General Linear Model, 2D/3D visualization or activations overlaid structural datasets, Combined 3D visualizations and white matter fiber tracts from Diffusion Tensor lmaging studies, Interactive thresholding of statistical maps, Automated or-registration of functional datasets, Possibilities for saving statistical maps and 3D snapshots to various file formats.
#### Note 7
Possibility of processing DTI files including: Co-registration between DTI series and structural datasets, Automatic attempt to extract diffusion gradient configuration from DICOM header, Custom configuration possible, including from file, Fast generation of parametric maps (Color-coded DTI, Fractional anisotropy (FA), Apparent diffusivity (ADC), Tensor eigenvalues (λ1, λ2 and λ3)), 3D tractography using seed/target approach, Optimize tracking results by selection of teria (FA-value, tract
{6}------------------------------------------------
turning angle and minimum fiber length), 3D visualization of white matter fiber tracts superimposed on various underlay volumes (structural, FA, color-coded eigenvector maps etc.), Interactive selection of specific white matter fiber bundles using Region-of-interest tools, Superimposing of 3D BOLD fMRI activations, Saving parametric maps and 3D snapshots to various file formats.
#### Note 8
Possibility of processing DTI files including: Co-registration between DTI series and structural datasets, diffusion gradient configuration, Automatic attempt to extract diffusion gradient configuration from DICOM header, Custom configuration possible, including uploading from file, Fast generation of parametric maps (Color-oded DTI, Fractional anisotropy (FA), Apparent diffusivity (ADC), Trace weighted, Tensor eigenvalues (λ1, λ2 and λ3)), 3D tractography using seed/target approach, Optimize tracking results by selection of termination criteria (FA-value, tract turning angle and minimum fiber length), 3D visualization of white matter fiber tracts superimposed on various underlay volumes (structural, FA, color-coded eigenvector maps etc.), Interactive selection of specific white matter fiber bundles using Region-of-Interest tools, Superimposing of 3D BOLD fMRI activations, Saving parametric maps and 3D snapshots to various file formats.
#### Note 9
The module includes perfusion analysis of T2 first-pass effects, contrast agent leakage correction to extravascular space, "One-button" perfusion analysis using predefined settings for the following maps: Relative blood flow (rBF), Relative blood volume (rBV), Mean transit time (MTT), Leakage map. The module also includes: Optional automatication to automatically segmented white matter, Visual inspection of dynamic curves for one or multiple ROIs, Methods for leakage correction, Gamma-variate fitting of input function and tissue curves, Easy image fusion (drag & drop) of perfusion maps and structural images.
#### Note 10
The module includes perfusion analysis of both T1 and T2 first-pass effects, various methods for contrast agent leakage to extravascular space, "One-button" perfusion analysis using predefined settings for the following maps: Relative blood flow (rBF), Relative blood volume (rBV), Mean transit time (MTT), Time to peak (TTP)/Delay, Leakage map (apparent contrast agent permeability (Ktrans) map), Chi-square map, Multiple additional output maps for advanced analysis and quality control. The module also includes: Optional automatic normalizally segmented white matter, grey matter or both, Choice of manual or fully automatic (slice-wise or whole volume) selection of arterial input function (AlF), or population based AlF, Visual inspection of dynamic curves from AlF-pixels/ROJ, Methods for leakage correction, Optional gamma-variate fitting of input function and tissue curves, Integrated motion correction, Easy image fusion (drag & drop) of perfusion maps and structural images.
#### Note 11
In the analysis of DSC perfusion, the subject device includes a single method for correction of contrast agent leakage while the primary predicate device offers multiple methodologies. The subject device does not chi-square map while the primary predicate device does. The subject device annlies normatically segmented white matter while the primary predicate device applies normalization to automatically segmented white matter or both. The subject device does not compute the Arterial Input Function (AlF) while the primary predicate does. The subject device does no vessel segmentation while the primary predicate device does. The aforementioned difference does not raise any safety or performance issues.
#### Comparison of Intended Use
Apart from the Technological Characteristics it is noteworthy that the subject device and the primary predicate device have the same Intended Use and Indications for Use.
Brainance MD: is an advanced visualization and processing software, with specific focus on providing algorithms designed to analyze brain MRI data. The software is web-accessible and can be used with data and images acquired through DICOM compliant imaging devices and modalities. The software is intended to be used by medical personnel, including but not limited to radiologists and medical technicians, trained in the methods provided by the application.
nordicBrainEx: is an advanced visualization and processing software, with specific focus on providing algorithms designed to analyze functional MR data of the brain. The software runs on a standard "off-the-shelf" PC workstation and can be used with data and images acquired through DICOM compliant imaging devices and modalties. The software is intended to be used by medical personnel, such as radiologists or medical technicians, trained in the application. In order to best accommodate this group of users, it is specifically designed to have an easy to use and streamlined workflow, as well as an intuitive graphical user interface.
#### Comparison of Indications for Use
Brainance MD: Brainance MD provides and visualization capabilities of dynamic MRI data of the brain, presenting the derived properties and parameters in a clinically useful context.
nordicBrainEx provides analysis and visualization capabilities of dynamic MRI data of the brain, presenting the derived properties and parameters in a clinically useful context.
{7}------------------------------------------------
### Software
Brainance MD was successfully validated and verified against the requirements specification and its intended use. The results from the validation and verification activities justify that Brainent specifications and intended use, which is deemed to be substantially equivalent to the predicate.
Validation and verification activities were controlled environment and in compliance with IEC 62304, ISO 13485:2016 and 21 CFR 820. Brainance MD is also in compliance with the DICOM standard.
The verification and validation activities conducted demonstrate that Brainance MD is at least as safe and effective as the predicate device and does not introduce any new risks.
### Performance
The performance testing conducted demonstrates that Brainance MD is as safe and as effective to use as the predicate device and does not introduce any new risks
More specifically, apart from the standard software verification and validation testing conducted and documented in compliance with the FDA Guidance, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices, a detailed comparative study was performed between the subject device and the primary predicate device on the basis of the core functionalities.
### Performance Testing Summary
A comparative study was conducted in order to validate the equivalence of results computed by Brainance MD and the primary predicate device reqarding the processing of DSC Perfusion, fMRI and DTI sequences. Towards this direction two sequences that were part of two different exams/subjects (either healthy control or diseased) were selected for the comparison conducted for each modality. The subjects selected were all adults and either healthy controls or diseased diagnosed with metastasis or glioblastoma multiforme.
The two sequences selected for each modality were processed with each one of the software MD and primary predicate device) using the exact same processing protocol and parameters for each user defined function.
The maps that resulted from the processing were compared using ICC & Bland-Altman analysis on all valid pixel values for every subject in the dataset. The fiber tracts that resulted were compared using Mean Relative Difference (MRD) as Percentage across each tract, which is the mean across samples of the absolute difference divided by the maximum absolute value.
The final results matched the criteria of acceptance/approval priorly set by the manufacturer and thus equivalent the two devices on a result level was proven.
# Discussion Summary
According to the comparisons between the subject device, we can conclude that the subject device dees not raise any new potential safety risks when compared to the chosen predicate device and performs in accordance with its intended use.
The subject device is substantially equivalent to the predicate device. is based on the following observations:
- · The indications for use and intended uses of both the subject device and predicate device are equivalent
- The subject and predicate devices consist of software applications which visualize and analyze brain MR data
- The subject and predicate device are both standalone software applications to facilitate the import and visualization of MR data sets
- The subject and predicate device offer similar visualities and incorporate well known and extensivelly tested methodologies
- · Both the subject and predicate device are intended to be used in the same environment and by trained healthcare professionals
- Performance testing demonstrates that the subject device performs at least as safely and effectively as the predicate device
# Conclusion
Based on the information submitted in this premarket notifications for use, technological characteristics, performance testing and technological comparison to the predicate devices no new risks of safety and effectiveness and is substantially equivalent to the predicate devices.
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.