A retrospective, non-interventional validation study was conducted using over 300 previously-acquired clinical studies to evaluate the performance of the EchoMD AutoEF software against the biplane method of disks ejection fraction.
Adult patients; dataset balanced for gender, ejection fraction values, and body mass index levels; Sample Size: Over 300 previously-acquired studies
Biplane method of disks ejection fraction
Root Mean Square Deviation (RMSD) of EchoMD AutoEF measurements compared to biplane method
AI Performance
Output
Algorithm
Acceptance
Observed
Dev DS
Dev Readers
Test DS
Test Readers
Left Ventricular Ejection Fraction
Convolutional network
Root Mean Square Deviation below a set threshold
8.290% RMSD, p-value 0.00052
—
—
Retrospective, non-interventional validation study: over 300 previously-acquired studies.
>1 (cardiologists)
Indications for Use
The Bay Labs, Inc. EchoMD Automated Ejection Fraction software is used to process previously acquired transthoracic cardiac ultrasound images, to store images, and to manipulate and make measurements on images using a personal computer or a compatible DICOM-compliant PACS system in order to provide automated estimation of left ventricular ejection. This measurement can be used to assist the clinician in a cardiac evaluation.
Device Story
EchoMD Automated Ejection Fraction (AutoEF) software processes previously acquired transthoracic cardiac ultrasound images to estimate left ventricular ejection fraction (LVEF). Operating as a microservice between DICOM source and destination PACS, the software automatically selects relevant apical four-chamber and two-chamber video clips. It utilizes a convolutional neural network to estimate LVEF directly from image data without generating endocardial traces. The system provides qualitative and quantitative feedback on image quality to the clinician. Results are forwarded to a PACS server for clinician review, where they can be confirmed, rejected, or manually edited. By automating clip selection and EF calculation, the device streamlines cardiac evaluation workflows, assisting clinicians in assessing left ventricular function.
Clinical Evidence
Retrospective, non-interventional validation study using 300+ previously acquired cardiac studies. Dataset balanced for gender, EF values, and BMI across multiple ultrasound manufacturers. Primary endpoint: Root Mean Square Deviation (RMSD) of EchoMD EF measurements compared to biplane method of disks ground truth. Result: 8.290% RMSD (p=0.00052). Additional study performed with independent cardiologists to confirm generalizability.
Technological Characteristics
Machine learning-based software; convolutional neural network architecture. Operates as a microservice background function within a DICOM-compliant PACS environment. Inputs: transthoracic cardiac ultrasound DICOM clips. Outputs: LVEF percentage estimate and image quality feedback. Connectivity: Networked (PACS/ultrasound integration).
Indications for Use
Indicated for use in adult patients for automated estimation of left ventricular ejection fraction from previously acquired transthoracic cardiac ultrasound images.
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 of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health and Human Services seal on the left and the FDA acronym and name on the right. The FDA acronym is in a blue box, and the full name is in blue text. The text reads "FDA U.S. FOOD & DRUG ADMINISTRATION".
June 14, 2018
Bay Labs, Inc. % Yarmela Pavlovic Partner Hogan Lovells US LLP 3 Embarcadero Center, Suite 1500 SAN FRANCISCO CA 94111
Re: K173780
Trade/Device Name: EchoMD Automated Ejection Fraction Software Regulation Number: 21 CFR 892.2050 Regulation Name: Picture archiving and communications system Regulatory Class: II Product Code: LLZ Dated: May 22, 2018 Received: May 22, 2018
Dear Yarmela Pavlovic:
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. 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); good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
{1}------------------------------------------------
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 http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm.
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/DeviceRegulationandGuidance/) and CDRH Learn (http://www.fda.gov/Training/CDRHLearn). 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 (http://www.fda.gov/DICE) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Michael D. O'Hara For
Robert Ochs, Ph.D. Director Division of Radiological Health Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
| DEPARTMENT OF HEALTH AND HUMAN SERVICES |
|-----------------------------------------|
| Food and Drug Administration |
Indications for Use
Form Approved: OMB No. 0910-0120 Expiration Date: 06/30/2020 See PRA Statement below
510(k) Number (if known)
K173780
Device Name
Bay Labs, Inc. EchoMD Automated Ejection Fraction Software
#### Indications for Use (Describe)
The Bay Labs, Inc. EchoMD Automated Ejection Fraction software is used to process previously acquired transthoracic cardiac ultrasound images, to store images, and to manipulate and make measurements on images using a personal computer or a compatible DICOM-compliant PACS system in order to provide automated estimation of left ventricular ejection. This measurement can be used to assist the clinician in a cardiac evaluation.
The EchoMD Automated Ejection Fraction Software is indicated for use in adult patients.
| Type of Use ( <i>Select one or both, as applicable</i> ) | |
|---------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------|
| <b> </b> <span style="font-size:14px">☑ Prescription Use (Part 21 CFR 801 Subpart D)</span> | <span style="font-size:14px">☐ Over-The-Counter Use (21 CFR 801 Subpart C)</span> |
CONTINUE ON A SEPARATE PAGE IF NEEDEDThis 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
# Bay Labs, Inc. EchoMD Automated Ejection Fraction Software
#### Submitter's Name, Address, Telephone Number, Contact Person
Bay Labs, Inc. 290 King Street, Suite 9 San Francisco, CA 94107
Contact Person: Charles Cadieu, CEO Phone: 415 671 4711 email: charles@baylabs.io
Date Prepared: May 21, 2018
## Name of Device
Common or Usual Name: Picture Archival and Communications Systems Workstation
Proprietary Name: EchoMD Automated Ejection Fraction Software
Classification Name: 21 CFR § 892.2050
Regulatory Class: II
Product Code: LLZ, System, Image processing, Radiological
## Predicate Device
Diacardio, Ltd. LVivo EF Software (K130779)
#### Intended Use / Indications for Use
The Bay Labs, Inc. EchoMD Automated Ejection Fraction software is used to process previously acquired transthoracic cardiac ultrasound images, and to manipulate and make measurements on images using a personal computer or a compatible DICOM-compliant PACS system in order to provide automated estimation of left ventricular ejection. This measurement can be used to assist the clinician in a cardiac evaluation.
The EchoMD Automated Ejection Fraction Software Application is indicated for use in adult patients.
The intended use/indications for use statement is worded slightly differently than that of the predicate device, but the minor differences do not alter the intended diagnostic effect of the subject device; both products are intended to process echocardiogram images and produce ejection fraction calculations. The minor differences also do not raise different questions of safety or effectiveness, as in both instances the key question is whether the software can both produce ejection fraction calculations acceptable for clinical use.
{4}------------------------------------------------
#### Device Description
The EchoMD Automated Ejection (AutoEF) software applies machine learning algorithms to process echocardiography images in order to calculate left ventricular ejection fraction. The software operates in between the DICOM source and the DICOM destination. EchoMD AutoEF performs left ventricular ejection measurements using both the apical four chamber and apical two chamber cardiac ultrasound views.
The software selects the image clips to be used, performs the AutoEF calculation, and forwards the results to a destination PACS server for clinician viewing. The output of the Ejection Fraction estimate stated as a percentage, which is displayed via the destination PACS system. The software applies machine learning algorithms to assess image quality and provides this information as qualitative and quantitative user feedback. By automating the estimation of ejection fraction, the EchoMD software is designed to streamline the clinician's calculation of the measurement.
#### Summary of Technological Characteristics
The technological principle underlying both the EchoMD AutoEF and the predicate device is the calculation of ejection fraction (EF) on previously acquired cardiac scans using machine learning-based algorithms and biplane apical echocardiographic images. Ultimately, the key question for both products is whether the EF calculation provides adequate information for the clinician.
While the two products use slightly different approaches to achieving their shared purpose, these differences do not raise different questions of safety or effectiveness. EchoMD AutoEF operates as a microservice background function communicating with ultrasound systems and PACS workstation systems, which provide the user interface. The predicate device may operate in this manner but also is configurable to provide its own user interface. EchoMD AutoEF automates the selection of image video clips on which to operate. The predicate device includes manual user selection of image video clips. EchoMD AutoEF utilizes a convolutional network design which operates on the image data in order to estimate ejection fraction without creating endocardial traces. The predicate generates endocardial traces. Other minor differences arise due to the design of the EchoMD running as part of a PACS system, rather than as a fully stand-alone application like the predicate.
A tabular comparison of the key features of the subject and predicate devices is provided at the end of this Summary.
## Performance Data
EchoMD EF software was developed and tested in accordance with Bay Labs' Design Control processes and has been subjected to extensive safety and performance testing. Non-clinical verification and validation test results established that the device meets its design requirements and intended use. Specifically, software verification was conducted at unit, module, and system integration levels. Risk management analysis generated multiple risk mitigation measures and verification activities. A Cybersecurity Analysis and data security testing were conducted to verify that data and patient protected health information security measures are included in the software.
Verification and validation testing was conducted to demonstrate the substantial equivalence of EchoMD AutoEF. In both tests, the success criterion was that the EchoMD AutoEF would produce an
{5}------------------------------------------------
ejection fraction number with a Root Mean Square Deviation below a set threshold as compared to the reference ground truth EF.
A formal retrospective, non-interventional validation study was conducted using over 300 previously-acquired studies where the biplane method of disks ejection fraction was reported. This patient dataset was constructed to provide a balanced range of gender, ejection fraction values, and body mass index levels. Testing included a wide array of ultrasound system manufacturers to verify that EchoMD AutoEF performs acceptably across multiple scanner platforms. Variability testing was also performed to demonstrate that EchoMD AutoEF performs acceptably with a variety of image clips and frames from the same patient. Test datasets were strictly segregated from algorithm training datasets. EchoMD AutoEF ejection fraction measurements were compared to the biplane method ejection fraction, and a root mean square deviation was calculated and used as the primary endpoint. The primary endpoint was met (results: 8.290% RMSD, p-value 0.00052). An additional study was performed with a different set of cardiologists on a subset of the validation patient studies to further demonstrate the generalizability of the software. Based on the clinical performance as documented in this pivotal clinical study, the device has a safety and effectiveness profile that is similar to the predicate Diacardio LVivo EF Software device.
# Conclusion
The EchoMD AutoEF Software is as safe and effective as the Diacardio LVivo EF Software. The subject device has the same intended uses and similar indications, technological characteristics, and principles of operation as its predicate device. The minor differences in indications do not alter the intended diagnostic use of the device and do not affect its safety and effectiveness when used as labeled. In addition, the minor technological differences between the EchoMD AutoEF and its predicate device do not raise different questions of safety or effectiveness. Performance data demonstrate that the subject device is as safe and effective as the identified predicate. Thus, the EchoMD Automated Ejection Fraction Software is substantially equivalent.
| | Bay Labs EchoMD Automated Ejection<br>Fraction Software Application | DiaCardio, Ltd, LVivo EF Software<br>Application (K130779, Predicate) |
|--------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Product Code | LLZ | LLZ |
| Intended Use | The Bay Labs, Inc. EchoMD Automated<br>Ejection Fraction software is used to<br>process previously acquired transthoracic<br>cardiac ultrasound images, to store images,<br>and to manipulate and make<br>measurements on images using a personal<br>computer or a compatible DICOM-<br>compliant PACS system in order to provide<br>automated estimation of left ventricular<br>ejection fraction. This measurement can be<br>used to assist the clinician in a cardiac<br>evaluation. | DiaCardio's L Vivo EF Software<br>Application is intended for non-invasive<br>processing of already acquired<br>echocardiographic images in order to<br>detect, measure, and calculate the left<br>ventricular wall for left ventricular<br>function evaluation. This measurement<br>can be used to assist the clinician in a<br>cardiac evaluation. |
| Machine Learning-<br>Based Algorithm | Yes | Yes |
## Comparison Table: EchoMD AutoEF versus Predicate
{6}------------------------------------------------
| | Bay Labs EchoMD Automated Ejection<br>Fraction Software Application | DiaCardio, Ltd, LVivo EF Software<br>Application (K130779, Predicate) |
|---------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------|
| Operates on DICOM<br>clips | Yes | Yes |
| Automation level | Fully automated, including clip selection | Fully automated (with manually-<br>selected clips) |
| EF Method | Biplane (non-segmentation/non-<br>endocardial trace) | Biplane Method of Disks<br>Segmentation (endocardial trace) |
| Offline EF evaluation<br>using clips from multiple<br>ultrasound scanners | Yes | Yes |
| Image Clip Selection | Automated | Manual |
| Automated Ejection<br>Fraction Calculation | Yes | Yes |
| Ejection Fraction<br>reported | Whole number estimate (percentage) | Whole number estimate<br>(percentage) |
| Algorithm Confidence | Qualitative and quantitative user<br>feedback on transthoracic cardiac<br>ultrasound image quality | Display of endocardial border tracing |
| EF Result shown with<br>video clip | Yes | Yes |
| User confirmation/<br>rejection of result | Yes | Yes |
| Manual editing of<br>automated result by<br>user | Yes (on PACS workstation) | Yes (in application) |
| Left ventricular volumes<br>measurements | Not internal. Uses manual trace option<br>PACS workstation | Yes |
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.