Retrospective cohort of 611 anonymized chest and abdominal CT cases
3 (US Board-Certified Radiologists)
Indications for Use
HealthVCF is a passive notification for prioritization-only, parallel-workflow software tool used by clinicians to prioritize specific patients within the standard-of-care bone health setting for suspected vertebral compression fractures. HealthVCF uses an artificial intelligence algorithm to analyze chest and abdominal CT scans and flags those that are suggestive of the presence of at least one vertebral compression at the exam level. These flags are viewed by the clinician in Bone Health and Fracture Liaison Service programs in the medical setting via a worklist application on their Picture Archiving and Communication System (PACS). HealthVCF does not send a proactive alert directly to the user. Health VCF does not provide diagnostic information beyond triage and prioritization, it does not remove cases from the radiology worklist, and should not be used in place of full patient evaluation, or relied upon to make or confirm diagnosis.
Device Story
HealthVCF is a software-only tool for triage and prioritization of chest and abdominal CT scans; identifies suspected vertebral compression fractures. Input: chest/abdominal CT scans. Processing: AI algorithm analyzes scans for fracture presence; flags suggestive cases. Output: passive notification to standalone desktop 'Zebra Worklist' application; includes three sagittal preview images for informational purposes. Usage: clinical setting (Bone Health/Fracture Liaison Service programs); operated by bone-health clinicians. Workflow: operates in parallel to standard-of-care radiology; does not alter images or remove cases from radiology worklists. Benefit: reduces time to alert physicians to potential fractures; enables earlier patient recall and evaluation. Clinicians use output to prioritize worklist review; final diagnosis remains with clinician after scan review.
Clinical Evidence
Retrospective cohort study of 611 anonymized chest and abdominal CT cases (306 positive for vertebral compression fractures, 305 negative). Ground truth established by three US Board-Certified Radiologists. Results: AUC 0.9504 (95% CI: 0.9348–0.9660), sensitivity 90.20% (95% CI: 86.35%–93.05%), specificity 86.89% (95% CI: 82.63%–90.22%). Average analysis time: 61.36 seconds.
Technological Characteristics
Software-only device; AI-based algorithm for image analysis. Operates on chest and abdominal CT scans. Integrates with PACS/workstation via standalone desktop application. No hardware components. Validated per FDA software guidance.
Indications for Use
Indicated for clinicians in Bone Health and Fracture Liaison Service programs to prioritize patients with suspected vertebral compression fractures identified on chest and abdominal CT scans. Not for diagnostic use; not to replace full patient evaluation.
Regulatory Classification
Identification
Radiological computer aided triage and notification software is an image processing prescription device intended to aid in prioritization and triage of radiological medical images. The device notifies a designated list of clinicians of the availability of time sensitive radiological medical images for review based on computer aided image analysis of those images performed by the device. The device does not mark, highlight, or direct users' attention to a specific location in the original image. The device does not remove cases from a reading queue. The device operates in parallel with the standard of care, which remains the default option for all cases.
Special Controls
Radiological computer aided triage and notification software must comply with the following special controls: 1. Design verification and validation must include: i. A detailed description of the notification and triage algorithms and all underlying image analysis algorithms including, but not limited to, a detailed description of the algorithm inputs and outputs, each major component or block, how the algorithm affects or relates to clinical practice or patient care, and any algorithm limitations. ii. A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will provide effective triage (e.g., improved time to review of prioritized images for pre-specified clinicians). iii. Results from performance testing that demonstrate that the device will provide effective triage. The performance assessment must be based on an appropriate measure to estimate the clinical effectiveness. The test dataset must contain sufficient numbers of cases from important cohorts (e.g., subsets defined by clinically relevant confounders, effect modifiers, associated diseases, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals for these individual subsets can be characterized with the device for the intended use population and imaging equipment. iv. Standalone performance testing protocols and results of the device. v. Appropriate software documentation (e.g., device hazard analysis; software requirements specification document; software design specification document; traceability analysis; description of verification and validation activities including system level test protocol, pass/fail criteria, and results). 2. Labeling must include the following: i. A detailed description of the patient population for which the device is indicated for use. ii. A detailed description of the intended user and user training that addresses appropriate use protocols for the device. iii. Discussion of warnings, precautions, and limitations must include situations in which the device may fail or may not operate at its expected performance level (e.g., poor image quality for certain subpopulations), as applicable. iv. A detailed description of compatible imaging hardware, imaging protocols, and requirements for input images. v. Device operating instructions. vi. A detailed summary of the performance testing, including: test methods, dataset characteristics, triage effectiveness (e.g., improved time to review of prioritized images for pre-specified clinicians), diagnostic accuracy of algorithms informing triage decision, and results with associated statistical uncertainty (e.g., confidence intervals), including a summary of subanalyses on case distributions stratified by relevant confounders, such as lesion and organ characteristics, disease stages, and imaging equipment.
*Classification.* Class II (special controls). The special controls for this device are:(1) Design verification and validation must include:
(i) A detailed description of the notification and triage algorithms and all underlying image analysis algorithms including, but not limited to, a detailed description of the algorithm inputs and outputs, each major component or block, how the algorithm affects or relates to clinical practice or patient care, and any algorithm limitations.
(ii) A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will provide effective triage (
*e.g.,* improved time to review of prioritized images for pre-specified clinicians).(iii) Results from performance testing that demonstrate that the device will provide effective triage. The performance assessment must be based on an appropriate measure to estimate the clinical effectiveness. The test dataset must contain sufficient numbers of cases from important cohorts (
*e.g.,* subsets defined by clinically relevant confounders, effect modifiers, associated diseases, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals for these individual subsets can be characterized with the device for the intended use population and imaging equipment.(iv) Stand-alone performance testing protocols and results of the device.
(v) Appropriate software documentation (
*e.g.,* device hazard analysis; software requirements specification document; software design specification document; traceability analysis; description of verification and validation activities including system level test protocol, pass/fail criteria, and results).(2) Labeling must include the following:
(i) A detailed description of the patient population for which the device is indicated for use;
(ii) A detailed description of the intended user and user training that addresses appropriate use protocols for the device;
(iii) Discussion of warnings, precautions, and limitations must include situations in which the device may fail or may not operate at its expected performance level (
*e.g.,* poor image quality for certain subpopulations), as applicable;(iv) A detailed description of compatible imaging hardware, imaging protocols, and requirements for input images;
(v) Device operating instructions; and
(vi) A detailed summary of the performance testing, including: test methods, dataset characteristics, triage effectiveness (
*e.g.,* improved time to review of prioritized images for pre-specified clinicians), diagnostic accuracy of algorithms informing triage decision, and results with associated statistical uncertainty (*e.g.,* confidence intervals), including a summary of subanalyses on case distributions stratified by relevant confounders, such as lesion and organ characteristics, disease stages, and imaging equipment.
{0}------------------------------------------------
Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left, there is a symbol representing the Department of Health & Human Services-USA. To the right of the symbol, there is a blue square with the letters 'FDA' in white. Next to the blue square, the words 'U.S. FOOD & DRUG' are written in blue, followed by 'ADMINISTRATION' in a smaller font size.
Zebra Medical Vision Ltd. % Ms. Flair Bar VP Operations and QA/RA Shefayim Commercial Center PO Box 25 Shefayim, 6099000 ISRAEL
May 12, 2020
## Re: K192901
Trade/Device Name: HealthVCF Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological computer-assisted prioritization software Regulatory Class: Class II Product Code: QFM Dated: April 2, 2020 Received: April 8, 2020
Dear Ms. Bar:
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,
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) K192901
Device Name HealthVCF
### Indications for Use (Describe)
HealthVCF is a passive notification for prioritization-only, parallel-workflow software tool used by clinicians to prioritize specific patients within the standard-of-care bone health setting for suspected vertebral compression fractures. HealthVCF uses an artificial intelligence algorithm to analyze chest and abdominal CT scans and flags those that are suggestive of the presence of at least one vertebral compression at the exam level. These flags are viewed by the clinician in Bone Health and Fracture Liaison Service programs in the medical setting via a worklist application on their Picture Archiving and Communication System (PACS). HealthVCF does not send a proactive alert directly to the user.
Health VCF does not provide diagnostic information beyond triage and prioritization, it does not remove cases from the radiology worklist, and should not be used in place of full patient evaluation, or relied upon to make or confirm diagnosis.
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}------------------------------------------------
Image /page/3/Picture/0 description: The image shows the Zebra Medical Vision logo. The logo consists of a yellow horizontal line, a black and white abstract zebra-like symbol, and the word "zebra" in black lowercase letters. Below the word "zebra" is the text "MEDICAL.VISION" in smaller black letters.
# 5. 510 (k) Summary
## 510(K) Summary - HealthVCF Zebra Medical Vision Ltd.
## 510(k) Number –K192901
- I. Applicant's Name: Zebra Medical Vision Ltd. Shefayim Commercial Center PO Box 25 Shefayim, 6099000 ISRAEL Telephone: +972-9-8827795 Fax: +972-9-8827795
Date Prepared: May 07, 2020
#### II. Device
Trade Name: HealthVCF
Classification Name: QFM - Radiological Computer-Assisted Prioritization Software
## Regulation Number: 892.2080
### Classification:
Class II, Radiology
#### III. Predicate Device:
The HealthVCF device is substantially equivalent to the following device:
| Proprietary Name | CmTriage |
|------------------------|--------------------------------------------------------|
| Premarket Notification | K183285 |
| Classification Name | Radiological Computer-Assisted Prioritization Software |
| Regulation Number | 21 CFR 892.2080 |
| Product Code | QFM |
| Regulatory Class | II |
#### IV. Device Description
{4}------------------------------------------------
Image /page/4/Picture/0 description: The image shows the logo for Zebra Medical Vision. The logo consists of a stylized "Z" symbol on the left, followed by the word "zebra" in a bold, sans-serif font. Below the word "zebra" are the words "MEDICAL.VISION" in a smaller font. The "Z" symbol is made up of black and white stripes, giving it a zebra-like appearance.
Zebra's HealthVCF solution is a software product that automatically identifies suspected findings suggestive of vertebral compression fractures on chest and abdominal CT scans and provides a passive notification to the workstation of the presence of this finding in the scan. This notification is received by the standalone desktop Zebra Worklist application which flags the identified scan and assists clinicians engaged in bone-health management in viewing the scan ahead of others. The device aim is to aid in prioritization and triage of radiological medical images only and does not provide diagnostic information beyond triage.
The software uses an artificial intelligence algorithm to automatically analyze chest and abdominal CT scans. If a suspected vertebral compression fracture is found in a scan, the alert is automatically sent to the Zebra Worklist application on the workstation used by the bone-health clinician in parallel with the ongoing standard of care within the bone health setting. The standard of care radiology workflow (i.e. reviewing and reporting the findings that initiated the request for CT) continues unaffected by the parallel workflow of the bone health program. For clarity, the HealthVCF device does not flag/prioritize cases within this radiology workflow. The standalone desktop application, Zebra Worklist, includes three sagittal preview images meant for informational purposes only and is not intended for diagnostic use. The Zebra Worklist presents all cases processed by the algorithm, and flags those with a suspected finding.
Zebra's HealthVCF device works in parallel to and in conjunction with the standard care of workflow within bone health programs, and completely independent of the standard of care workflow within the radiology department. After a chest or abdominal CT scan has been performed, a copy of the study is automatically retrieved and processed by the HealthVCF device. The device performs the analysis of the study and returns a notification about a suspected vertebral compression fractures to the Zebra Worklist to notify the clinicians in Bone Health and Fracture Prevention Programs reviewing the chest and abdominal CTs for at-risk patients. The clinician is then able to review the study earlier and recall the patient for further evaluation.
The primary benefit of the product is the ability to reduce the time it takes to alert physicians to the presence of a finding such as a vertebral compression fracture. The software does not recommend treatment or provide a diagnosis. It is meant as a tool to assist in improved workload prioritization of cases in bone health and fracture prevention programs. The final diagnosis is provided by a clinician after reviewing the scan itself.
The following modules compose the HealthVCF software:
Data input and validation: Following retrieval of a study, the validation feature assessed the input data (i.e. age, modality, view) to ensure compatibility for processing by the algorithm. HealthVCF algorithm: Once a study has been validated, the algorithm analyzes the chest and abdominal CT scans for detection of suspected finding suggestive of vertebral compression fracture.
{5}------------------------------------------------
Image /page/5/Picture/0 description: The image shows the Zebra Medical Vision logo. The logo consists of a stylized "Z" symbol made of black and white stripes, followed by the word "zebra" in black lowercase letters. Below the word "zebra" are the words "MEDICAL.VISION" in smaller black letters. The logo is simple and modern, and the use of black and white stripes is reminiscent of a zebra's coat.
IMA Integration feature: The study analysis and the results of a successful study analysis is provided to IMA, to then be sent to Zebra Worklist application for triaging.
Error codes feature: In the case of a study failure during data validation or the analysis by the algorithm, an error is provided to the system.
#### V. Intended Use/Indication for Use:
HealthVCF is a passive notification for prioritization-only, parallel-workflow software tool used by clinicians to prioritize specific patients within the standard-of-care bone health setting for suspected vertebral compression fractures. HealthVCF uses an artificial intelligence algorithm to analyze chest and abdominal CT scans and flags that are suggestive of the presence of at least one vertebral compression at the exam level. These flags are viewed by the clinician in Bone Health and Fracture Liaison Service programs in the medical setting via a worklist application on their Picture Archiving and Communication System (PACS). HealthVCF does not send a proactive alert directly to the user.
HealthVCF does not provide diagnostic information beyond triage and prioritization, it does not remove cases from the radiology worklist, and should not be used in place of full patient evaluation, or relied upon to make or confirm diagnosis.
#### VI. Technological Characteristics Compared to Predicate Device:
The technological characteristics, e.g., overall design, mechanism of action, mode of operation, performance characteristics, etc., and the intended use of the Health VCF device are substantially equivalent to the predicate device cited above.
A comparison of the technological characteristics with the predicate is summarized below.
| Technological<br>Characteristics | Proposed Device<br>HealthVCF | Predicate Device<br>cmTriage (K183285) | Summary |
|----------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Indication for<br>Use/Intended Use | HealthVCF is a passive<br>notification for<br>prioritization-only,<br>parallel-workflow<br>software tool used by<br>clinicians to prioritize<br>specific patients within<br>the standard-of-care bone<br>health setting for<br>suspected vertebral<br>compression fractures.<br>HealthVCF uses an<br>artificial intelligence<br>algorithm to analyze chest<br>and abdominal CT scans<br>and flags those that are | cmTriage is a passive<br>notification for prioritization-<br>only, parallel-workflow<br>software tool used by<br>radiologists to prioritize<br>specific patients within the<br>standard-of-care image<br>worklist for 2D FFDM<br>screening mammograms.<br>cmTriage uses an artificial<br>intelligence algorithm to<br>analyze 2D FFDM screening<br>mammograms and flags those<br>that are suggestive of the<br>presence of at least one<br>suspicious finding at the | Similar expect for<br>anatomy, imaging<br>modality, and lesion<br>type |
| Notification-only,<br>parallel workflow<br>tool | | | |
| User | | | |
| | suggestive of the presence<br>of at least one vertebral<br>compression at the exam<br>level. These flags are<br>viewed by the clinician in<br>Bone Health and Fracture<br>Liaison Service programs<br>in the medical setting via<br>a worklist application on<br>their Picture Archiving<br>and Communication<br>System (PACS).<br>HealthVCF does not send<br>a proactive alert directly<br>to the user.<br>HealthVCF does not<br>provide diagnostic<br>information beyond triage<br>and prioritization, it does<br>not remove cases from the<br>radiology worklist, and<br>should not be used in<br>place of full patient<br>evaluation, or relied upon<br>to make or confirm<br>diagnosis. | exam level. These flags are<br>viewed by the radiologist via<br>their Picture Archiving and<br>Communication System<br>(PACS) worklist. The<br>decision to use cmTriage<br>codes and how to use<br>cmTriage codes is ultimately<br>up to the radiologist.<br>cmTriage does not send a<br>proactive alert directly to the<br>radiologist. Radiologists are<br>responsible for reviewing<br>each exam on a diagnostic<br>viewer according to the<br>current standard of care.<br>cmTriage is limited to the<br>categorization of exams, does<br>not provide any diagnostic<br>information beyond triage<br>and prioritization, does not<br>remove images from the<br>radiologist's worklist, and<br>should not be used in lieu of<br>full patient evaluation, or<br>relied upon to make or<br>confirm diagnosis. cmTriage<br>is for prescription use only. | |
| Yes | Yes | Same | |
| Bone Health Clinician | Radiologist | Different, but both<br>users include a<br>"designated list of<br>clinicians" per 21<br>CFR 892.2080 | |
| Identify patients<br>with prespecified<br>clinical condition | Yes | Yes | Same |
| Clinical condition | Vertebral compression<br>fracture | Breast Cancer | Different, but both<br>findings suggestive of<br>a pre-specified clinical<br>condition |
| Alert to finding | Yes; notification flagged<br>for review | Yes; notification flagged for<br>review | Same |
| Independent of<br>standard of care<br>workflow | Yes; No cases are<br>removed<br>from worklist | Yes; No cases are removed<br>from worklist | Same |
| Modality | CT | FFDM screening<br>mammograms | Different, but both run<br>on "radiological |
| | | | |
| Body part | Chest and abdomen | Breast | medical images” per<br>21 CFR 892.2080<br>Different anatomical<br>sites but both<br>“operates on<br>radiological images of<br>the human body” per<br>21 CFR 892.2080. |
| Artificial<br>Intelligence<br>algorithm | Yes | Yes | Same |
| Limited to analysis<br>of imaging data | Yes | Yes | Same |
| Aids prompt<br>identification of<br>cases with<br>indicated findings | Yes | Yes | Same |
| Where results are<br>received | PACS / Workstation | PACS / Workstation | Same |
{6}------------------------------------------------
Image /page/6/Picture/0 description: The image is a logo for Zebra Medical Vision. The logo consists of a stylized letter Z on the left and the word "zebra" on the right. Below the word "zebra" is the text "MEDICAL.VISION".
{7}------------------------------------------------
Image /page/7/Picture/0 description: The image shows the Zebra Medical Vision logo. The logo consists of a stylized letter Z made of black and white stripes, followed by the word "zebra" in black, lowercase letters. Below the word "zebra" are the words "MEDICAL.VISION" in smaller, black letters.
#### VII. Performance Data:
Safety and performance of HealthVCF 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, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices".
The performance of the HealthVCF device has been validated in a performance study for triage of chest and abdominal CT cases. The data included a retrospective cohort of 611 anonymized Chest and abdominal CT cases from the USA and Israel, including 306 cases positive for vertebral compression fractures (severe and moderate fractures) and 305 cases negative for vertebral compression fractures (mild or no fracture), as well as confounding imaging factors. The validation data set was truthed (ground truth) by three US Board-Certified Radiologists (truthers). The standalone detection accuracy was measured on this cohort respective to the ground truth.
The HealthVCF device detection accuracy met the accuracy performance goals for AUC, sensitivity, and specificity. Overall, the HealthVCF was able to demonstrate an area under the curve (AUC) of 0.9504 (95% CI: [0.9348, 0.9660), which is both comparable to the predicate device, and meets the required technical method under the QFM product code. The device establishes effective triage based on an AUC >95%. The HealthVCF performance met the performance goal and demonstrated high performance substantially equivalent to the predicate
{8}------------------------------------------------
Image /page/8/Picture/0 description: The image shows the Zebra Medical Vision logo. The logo consists of a stylized "Z" made of black and white stripes, followed by the word "zebra" in black, lowercase letters. Below "zebra" is the text "MEDICAL.VISION" in smaller, black letters. To the left of the "Z" is a yellow rectangle.
device. The reported results for this operating point was a sensitivity of 90.20% (95% CI: [86.35%;93.05%]) and specificity was 86.89% (95% CI: [82.63%;90.22%]).
In addition, we assessed the performance time of the HealthVCF that reflects the time it takes for the device to analyze the study. The average performance time of the HealthVCF was 61.36 seconds, a timing performance that is substantially equivalent to the predicate.
## VIII. Conclusion
The subject HealthVCF device and the cmTriage predicate device are both software-only devices intended to aid in triage of radiological images, independent and in-parallel of care workflow. The labeling of both devices are limited to the categorization of exams and are not to be used in-lieu of full patient evaluation or relied upon to make or confirm diagnosis.
Both devices operate in parallel to the standard of care workflow in the sense that they do not change the original image, do not provide any marking, and do not remove cases from the standard of care. The minor differences between the subject device and the predicate raise no new issues of safety or effectiveness. In addition, performance testing demonstrates that the Health VCF performs as intended. The HealthVCF device is therefore substantially equivalent to the cmTriage predicate.
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.
