Retrospective clinical database of 811 subjects with echocardiographic data
The retrospective database was used to validate the accuracy of the device's segmental volumes, ejection fractions, and strains against manual measurements by expert cardiologists, and to compare device performance against a predicate device across various clinical and age-based subpopulations.
Retrospective Database Validation; Retrospective analysis of clinical database
811 subjects including heart failure, heart transplant, valvular heart disease, elite athletes, healthy controls, and pediatric patients; Sample Size: 811
Predicate device (TomTec-Arena TTA2) and manual expert cardiologist measurements
Accuracy of segmental volumes, EFs, and strains; comparison of EDV, ESV, SV, and EF against predicate device
cMRI Validation; Retrospective analysis
3 subjects with available retrospective Cardiac Magnetic Resonance Imaging (cMRI); Sample Size: 3
Not applicable for this study
RV volumes and ejection fraction (EF)
Indications for Use
Indications for use of the Argus Cognitive ReVISION Software are quantification and reporting of right ventricle (RV) structures and function of patients (adults only) with suspected disease to support physicians' diagnosis.
Device Story
ReVISION Software assesses global and segmental right ventricle (RV) function using 3D echocardiography datasets. Input consists of 3D RV models (exported from predicate devices). Device uses rule-based, non-AI/ML algorithms to segment the RV into 15 segments and decompose wall motion into longitudinal, radial, and anteroposterior components. It quantifies relative contributions to global RV ejection fraction and calculates longitudinal, circumferential, and area strains. Used in hospitals, clinics, and physician offices by licensed medical practitioners or technicians. Output provides morphological and functional assessments to support clinical decision-making regarding RV health. Benefits include detailed segmental analysis beyond standard global metrics, aiding in the diagnosis of suspected cardiac disease.
Clinical Evidence
No clinical testing conducted. Performance supported by non-clinical bench testing, including software verification (IEC 62304) and usability testing (IEC 62366-1). Accuracy validated against 30 subjects (10 healthy, 20 with cardiac disease) using manual expert segmentation as ground truth. Database validation performed on 811 retrospective subjects comparing ReVISION outputs to predicate device metrics (EDV, ESV, SV, EF, and strain correlations). cMRI validation performed on 3 subjects.
Technological Characteristics
Software as a medical device (SaMD). Performs 3D RV surface model segmentation and motion decomposition. Rule-based algorithm (non-AI/ML). Complies with IEC 62304:2005 (software lifecycle) and IEC 62366-1:2015 (usability). Standalone software application.
Indications for Use
Indicated for quantification and reporting of right ventricle (RV) structures and function in adult patients with suspected cardiac disease to support physician diagnosis.
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 shows the logo for the U.S. Food & Drug Administration (FDA). The logo consists of two parts: on the left, there is a symbol representing the Department of Health & Human Services, and on the right, there is the text "FDA U.S. FOOD & DRUG ADMINISTRATION" in blue. The text is arranged in two lines, with "FDA" being larger and bolder than the rest of the text.
Argus Cognitive, Inc. % Andrea Marosan Official Correspondent Dartmouth Regional Technical Center 16 Cavendish Court LEBANON NH 03766
June 24, 2023
Re: K223322
Trade/Device Name: Argus Cognitive ReVISION Software Application Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: LLZ Dated: June 16, 2023 Received: June 16, 2023
Dear Andrea Marosan:
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
{1}------------------------------------------------
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 (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 medical devices and radiation-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.
Jessica Lamb
Jessica Lamb, Ph.D. Assistant Director Imaging Software 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
{2}------------------------------------------------
# Indications for Use
510(k) Number (if known) K223322
#### Device Name
Argus Cognitive ReVISION Software Application
Indications for Use (Describe)
Indications for use of the Argus Cognitive ReVISION Software are quantification and reporting of right ventricle (RV) structures and function of patients (adults only) with suspected disease to support physicians' diagnosis.
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."
{3}------------------------------------------------
# 510(k) Notification K223322
### GENERAL INFORMATION [807.92(a)(1)]
### Applicant:
Argus Cognitive, Inc. Dartmouth Regional Technical Center 16 Cavendish Court Lebanon, NH 03766 Phone: 603-400-2440 www.arguscognitive.com
### Contact Person:
Attila Meretei President Argus Cognitive, Inc. (603)-400-2440 attila@arguscognitive.com
# Date Prepared: June 16, 2023
# DEVICE INFORMATION [807.92(a)(2)]
#### Trade Name:
Argus Cognitive ReVISION Software Application
#### Generic/Common Name:
Image review and quantification software
#### Classification:
21 CFR 892.2050, Medical image management and processing system
# Product Code:
LLZ, System, Image Processing, Radiological
{4}------------------------------------------------
# PREDICATE DEVICE(S) [807.92(a)(3)]
K150122 - TomTec-Arena TTA2
# DEVICE DESCRIPTION [807.92(a)(4)]
The Argus Cognitive ReVISION Software ("ReVISION Software") assesses global and segmental function of the right ventricle (RV) of the heart via the decomposition of longitudinal, radial, and anteroposterior motions of the RV walls and quantifies their relative contribution to global RV ejection fraction along with longitudinal, circumferential and area strains using 3D datasets obtained by echocardiography. Segmentation is performed on the end-diastolic 3D RV model using a rule-based, non-AI/ML algorithm to have 15 RV segments. This segmentation is then projected to all models in the corresponding cardiac cycle.
# INDICATIONS FOR USE [807.92(a)(5)]
Indications for use of the Argus Cognitive ReVISION Software are quantification and reporting of right ventricle (RV) structures and function of patients (adults only) with suspected disease to support physicians' diagnosis.
### COMPARISON OF TECHNOLOGICAL CHARACTERISTICS WITH THE PREDICATE DEVICES [807.92(a)(6)]
Please refer to Table 2: Substantial Equivalence Table.
# SUBSTANTIAL EQUIVALENCE
The proposed indications for the Argus Cognitive ReVISION Software is substantially equivalent to the indications for use for the predicate device. Any differences in the technological characteristics between the devices do not raise any new or different questions of safety or effectiveness. Thus, the Argus Cognitive ReVISION Software is substantially equivalent to the predicate device.
# PERFORMANCE DATA [807.92(b)]
All necessary software testing was conducted on the Argus Cognitive ReVISION Software to support a determination of substantial equivalence to the predicate device. The testing followed internal company procedures. Software testing was carried out at the module and system levels, following predefined test protocols.
# Nonclinical Testing Summary [807.92(b)(1)]:
All necessary performance testing was conducted on the Argus Cognitive ReVISION Software to support a determination of substantial equivalence to the predicate device. Testing acceptance criteria have been predefined in all test protocols to ensure that the subject device is safe and effective. Software verification was performed according to the standard IEC 62304:2005. Medical device software - Software lifecycle processes. Usability testing was performed according to IEC 62366-1:2015. Medical devices – Part 1: Application of usability engineering to medical devices. The collective results of the non-clinical testing demonstrate that the Argus Cognitive ReVISION Software meets the established specifications and complies with the aforementioned standards.
The nonclinical testing is summarized in Table 1: Summary of Testing Performed.
{5}------------------------------------------------
| Test | Acceptance Criteria | Result |
|----------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------|
| Unit/Integration Testing | | |
| Mesh Processing | Mesh orientation parameters for apex, inflow, and outflow centers are within<br>specifications. | Pass |
| Volume<br>Calculation | Volume calculations are consistent with predicate device and are reproducible. | Pass |
| Motion<br>Decomposition | Interobserver and intraobserver variability of decomposed end-systolic<br>volumes are within specifications.<br>Pre- and postoperative values for ejection fraction are reproducible. | Pass |
| Volumetric<br>Segmentation | The relative volumes of each segment to the total volume fall within<br>specifications.<br>The sum of segmental volumes is equal to the global volume. Interobserver<br>and intraobserver variability of segmental end-diastolic and end-systolic<br>volumes are within specifications. | Pass |
| 3D Strain<br>Calculation | Septal and free wall longitudinal strain, and global circumferential strain<br>values are consistent with predicate device.<br>Interobserver and intraobserver reliability of global longitudinal strain are<br>within specifications. | Pass |
| Verification Tests | Global and segmental metrics are calculated in more than 99% of cases.<br>When inadequate input is presented, the data is not analyzed and an error<br>message is presented.<br>Movement decomposition and volume calculations of known geometric data<br>are accurate. | Pass |
| Mathematical<br>Unit Tests | The area of a two-dimensional polygon is calculated accurately.<br>The relations between a two-dimensional line or a three-dimensional plane and<br>a point are calculated accurately.<br>The closest point on a line, segment, ray, or plane to a given point is calculated<br>accurately.<br>The distance between two points, a segment and a point, a line and a point, a<br>ray and a point, a plane and a point is calculated accurately.<br>The collinearity of three points or of two lines is calculated accurately.<br>The relation of a point to another point, line, segment, ray, plane, or polygon is<br>calculated accurately.<br>The intersection point of two lines, a line and a triangle, a line and a plane, a<br>ray and a triangle, a ray and a plane is calculated accurately.<br>The intersection of two segments, a segment and a line, a segment and a plane,<br>a segment and a ray, a segment and a triangle is calculated accurately.<br>The points of a polygon are not duplicated and are labeled accurately. | Pass |
| Evaluation Time | Average evaluation time must be under 15 minutes. | Pass |
| System Leveling Testing | | |
| Response Time | Response time must be under 10 seconds. | Pass |
| Response to Stress<br>Conditions | No delay in the ReVISION Software functionality. | Pass |
| Validation Testing | | |
| Accuracy<br>Validation | 30 subjects (10 healthy adults, 10 adult subjects with established cardiac<br>diseases but maintained right ventricular ejection fraction, and 10 adult<br>subjects with established cardiac diseases and reduced right ventricular<br>ejection fraction) were randomly selected from a comprehensive clinical<br>database of 811 retrospective subjects with available echocardiographic data.<br>The accuracy of segmental volumes, EFs, and strains was evaluated by 3<br>expert cardiologists with expertise in 3D echocardiography who was blinded to<br>REVISION Software results. The cardiologists manually performed<br>segmentation and contouring on the same 3D models that were analyzed by<br>REVISION Software. Acceptance criteria for this validation was <30%<br>relative difference for each of the segmental metrics between the ReVISION<br>Software and the manual measurements performed by the cardiologists.<br>The accuracy of global longitudinal and circumferential strains were also<br>evaluated by the expert cardiologists who created longitudinally and<br>circumferentially oriented contours using manual labeling. Acceptance criteria<br>for this validation was <10% relative difference in global strain values between<br>the ReVISION Software and the manual measurements performed by the<br>cardiologists.<br>In order to validate that decomposed ejection fractions (LEF, REF, AEF) are<br>calculated based on such 3D models that are indeed shortened in the given<br>direction only (i.e., longitudinal, radial, and anteroposterior), we created a test<br>pipeline for expert human readers. By overlaying the decomposed end-systolic<br>3D surface to the end-diastolic 3D surface using the test population's 30 cases,<br>the expert cardiologists' task was to verify visually that the decomposition<br>direction indeed corresponds to the desired one. Acceptance criterion was that<br>the 3D model shortens only in the corresponding direction in 100% of the cases. | Pass |
| Database<br>Validation | Using the retrospective 3D echocardiographic clinical database of 811<br>subjects, the following parameters were evaluated by the ReVISION Software<br>and by the predicate device.<br>Acceptance criteria for this comparison were:<br>1. ReVISION-derived end-diastolic volume (EDV) has a clinically<br>negligible bias compared with the TomTec-derived EDV<br>2. ReVISION-derived end-systolic volume (ESV) has a clinically<br>negligible bias compared with the TomTec-derived ESV<br>3. ReVISION-derived stroke volume (SV) has a clinically negligible<br>bias compared with the TomTec-derived SV<br>4. ReVISION-derived ejection fraction (EF) has a clinically negligible<br>bias compared with the TomTec-derived EF<br>5. ReVISION-derived global longitudinal strain correlates with TomTec-<br>derived EF<br>6. ReVISION-derived global circumferential strain correlates with<br>TomTec-derived EF<br>7. ReVISION-derived global area strain correlates with TomTec-derived<br>EF<br>These evaluations were performed in the following populations:<br>A. The entire database (n=811)<br>B. Clinical subpopulations in the database:<br>1. Heart failure patients (n=95)<br>2. Heart transplantation patients (n=86) | Pass |
| | 3. Valvular heart disease patients (n=148)<br>4. Elite athletes (n=137)<br>5. Adult healthy controls (n=191)<br>6. Other adult cardiovascular disease patients (n=50)<br>7. Pediatric renal transplant patients (n=53)<br>8. Pediatric healthy controls (n=51)<br>C. Age category subpopulations:<br>1. Child (2-12 years of age) (n=19)<br>2. Adolescent (12-18) (n=55)<br>3. Transitional adolescent (18-21) (n=79)<br>4. Adult (21+) (n=645)<br>D. Subpopulations based on RV dysfunction present/absent:<br>1. RV dysfunction (n=107)<br>2. No RV dysfunction (n=704) | |
| cMRI Validation | Three (3) subjects with available retrospective Cardiac Magnetic Resonance<br>Imaging (cMRI) were evaluated by ReVISION Software by calculating right<br>ventricular (RV) volumes and ejection fraction (EF).<br>Acceptance criteria for end-diastolic volume (EDV) was ±45 mL absolute<br>difference.<br>Acceptance criteria for end-systolic volume (ESV) was ±28 mL absolute<br>difference.<br>Acceptance criteria for ejection fraction (EF) was ±10 % absolute difference. | Pass |
| Usability Testing | | |
| Usability Evaluation | 15 participants completed a usability test focusing on the main elements of<br>ReVISION Software workflow and use errors. Acceptable results found no<br>further risks, hazards, or areas for immediate modification. | Pass |
# Table 1: Summary of Testing Performed
{6}------------------------------------------------
{7}------------------------------------------------
# Clinical Testing Summary [807.92(b)(2)]:
No clinical testing was conducted on the Argus Cognitive ReVISION Software to support a determination of substantial equivalence to the predicate device.
# CONCLUSIONS [807.92(b)(3)]
Completion of all verification and validation activities demonstrate that the subject device meets all design and performance requirements and is substantially equivalent to the predicate device.
{8}------------------------------------------------
| Table 2: Substantial Equivalence Table | | | | |
|----------------------------------------|--|--|--|--|
|----------------------------------------|--|--|--|--|
| Feature | Predicate Device<br>TomTec-Arena TTA2 4D RV (K150122) | Subject Device<br>ReVISION Software (K223322) | Rationale for Substantial<br>Equivalence |
|-----------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| K-number | K150122 | Not available | Subject of this submission is the<br>ReVISION Software. |
| Regulation Number and<br>Regulation Name | 21CFR 892.2050; Medical image management and<br>processing system | 21CFR 892.2050; Medical image management and<br>processing system | Identical to predicate device. |
| Classification Product<br>Code | LLZ | LLZ | Identical to predicate device. |
| Class | 2 | 2 | Identical to predicate device. |
| Classification Panel | Radiology | Radiology | Identical to predicate device. |
| Device Description | TomTec-Arena TTA2 is a clinical software<br>package for reviewing, quantifying and reporting<br>digital medical data. The 4D RV-Function of the<br>TomTec-Arena TTA2 software is a right<br>ventricular (RV) quantification tool for routine<br>clinical work, pulmonary hypertension, and right-<br>sided heart failure. The application helps to<br>overcome complexity of right-ventricle analysis by<br>calculating standard values based on a semi-<br>automatically generated 3D surface model. | The ReVISION Software assesses global and<br>segmental function of the right ventricle (RV) of<br>the heart via the decomposition of longitudinal,<br>radial, and anteroposterior motions of the RV walls<br>and quantifies their relative contribution to global<br>RV ejection fraction along with longitudinal,<br>circumferential and area strains using 3D datasets<br>obtained by echocardiography. | Similar general device description to<br>predicate device. |
| Indication for Use | Indications for use of TomTec-Arena software is<br>the quantification and reporting of cardiovascular,<br>fetal, and abdominal structures and function of<br>patients with suspected disease to support the<br>physicians in the diagnosis. | Indications for use of the Argus Cognitive<br>ReVISION Software are quantification and<br>reporting of right ventricle (RV) structures and<br>function of patients (adults only) with suspected<br>disease to support physicians' diagnosis. | A subset of the predicate device's<br>intended use. |
| Site of Use | Hospitals, clinics and physician's offices. | Hospitals, clinics and physician's offices. | Identical to predicate device. |
| Application Description<br>/ Quantification<br>Technology of RV | Software function provides a morphological and<br>functional assessment of the right ventricle based<br>on a surface model of the RV. | Software function provides a morphological and<br>functional assessment of the right ventricle based<br>on a surface model of the RV. | Identical to predicate device. |
| Intended User Group | TomTec-Arena is intended to be used only by<br>licensed medical practitioners or assistant medical<br>technicians. | The ReVISION Software is intended to be used<br>only by licensed medical practitioners or assistant<br>medical technicians. | Identical to predicate device. |
| Feature | Predicate Device<br>TomTec-Arena TTA2 4D RV (K150122) | Subject Device<br>ReVISION Software (K223322) | Rationale for Substantial<br>Equivalence |
| Design | Software as a medical device | Software as a medical device | Identical to predicate device. |
| 2D RV calculated<br>parameters | RVDd base (RVD1): Right Ventricle Distance base (mm) RVDd mid (RVD2): Right Ventricle Distance medial (mm) RVLd (RVD3): Right Ventricle Distance Longitudinal (mm) TAPSE: Tricuspid annular plane systolic excursion (mm) FAC: Fractional area change (%) RVLS (free wall): right ventricular longitudinal strain (free wall) (%) RVLS (Septum): right ventricular longitudinal strain (septum) (%) Global strain TAPSE: MMode measurement for movement of TV between ED and ES RV distance measurements: 3 distance measurements in the RV A4C in ED. RVD1: maximal short-axis dimension in the basal one third of the right ventricle RVD2: distance is measured on 50% of RVLd (RVD3) and parallel to the RVD1 RVD3: base-apex length | None | Only 3D parameters are calculated. |
| 3D RV calculated<br>parameters | EDV: End-diastolic Volume EDVI: End-diastolic Volume Index ESV: End-systolic Volume ESVI: End-systolic Volume Index SV: Stroke Volume EF: Ejection Fraction | EDV: End-diastolic Volume ESV: End-systolic Volume SV: Stroke Volume EF: Ejection Fraction…
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.