The Caption Interpretation 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 an ultrasound device, 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 Caption Interpretation Automated Ejection Fraction Software is indicated for use in adult patients.

Device Description

The Caption Interpretation Automated Ejection Fraction Software applies machine learning algorithms to process echocardiography images in order to calculate left ventricular ejection fraction. Caption Interpretation AutoEF performs left ventricular ejection fraction measurements using the apical four chamber, apical two chamber or parasternal long-axis cardiac ultrasound views or a combination of those views. The software selects the image clips to be used, performs the AutoEF calculation, and forwards the results to the desired destination for clinician viewing. The output of the program is the Ejection Fraction estimate stated as a percentage, along with an indications of confidence regarding that estimate.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

Acceptance Criteria and Reported Device Performance

Acceptance Criteria Category	Specific Criteria	Reported Device Performance
Clip Annotator Study	PPV for identification of imaging mode and view > 97%	Observed PPV point estimates > 97%
Clip Annotator Study	Sensitivity across views and imaging mode > 90%	Observed sensitivity point estimates > 90%
Pivotal Clinical Study (Primary Endpoint)	RMSD between AutoEF derived values (best available view combination) and reference method	Met predetermined acceptance criteria
Pivotal Clinical Study (Secondary Endpoint)	RMSD for combinations of views (AP2, AP4, PLAX)	Met same predetermined acceptance criteria
Pivotal Clinical Study (Single-View AP4)	RMSD for AP4 view	Observed results less than acceptance criterion
Pivotal Clinical Study (Single-View AP4)	Performance compared to physicians in qualitative and quantitative visual assessment	Superior to physicians
Pivotal Clinical Study (Single-View AP2)	RMSD for AP2 view	Observed results did not meet acceptance criteria, but performed superior on a quantitative visual assessment
Pivotal Clinical Study (Single-View PLAX)	RMSD for PLAX view	Observed results did not meet acceptance criteria, but performed superior on a quantitative visual assessment
Pivotal Clinical Study (Single-View AP2/PLAX RMSD compared to sonographers)	AP2-only and PLAX-only RMSD compared to sonographers' biplane tracing before cardiologist overread	Observed RMSD lower than sonographers' biplane tracing before cardiologist overread
Confidence Metric Functionality	Successful performance in estimating error range of EF estimates around reference EF with normally distributed difference (estimated vs. reference EF)	Verified successful performance

Detailed Study Information:

Sample sizes used for the test set and data provenance:
- The document does not explicitly state the sample sizes (number of patients or echocardiograms) used for the test sets in either the Clip Annotator study or the pivotal clinical investigation.
- Data Provenance: The document does not specify the country of origin of the data. It implies the data was "previously acquired transthoracic cardiac ultrasound images," but does not explicitly state if it was retrospective or prospective data.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Clip Annotator Study: "a panel of expert readers" was used. The exact number of experts and their specific qualifications are not provided beyond "expert readers."
- Pivotal Clinical Study: The "reference method" is mentioned, implying a ground truth was established, but the number and qualifications of experts involved in creating this reference (e.g., conventional EF calculation methods by cardiologists) are not detailed. It mentions "sonographers' biplane tracing before a cardiologist overread" in the context of comparison, suggesting cardiologist input in the reference.
Adjudication method for the test set:
- Clip Annotator Study: "Results of the Clip Annotator were compared to evaluation by a panel of expert readers." This suggests a direct comparison rather than a specific multi-reader adjudication method like 2+1 or 3+1. It's unclear if there was an adjudication for disagreements among the panel.
- Pivotal Clinical Study: The document refers to a "reference method" for EF calculation. It doesn't specify an adjudication method for this reference, nor for any disagreements in the human interpretations used for comparison (e.g., sonographers' tracings).
If a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done, and the effect size of how much human readers improve with AI vs without AI assistance:
- The document implies a comparison between the AI's performance and human performance, stating the AP4 view was "superior to physicians in making a qualitative and quantitative visual assessment" and that AP2-only and PLAX-only RMSD was "lower than the RMSD of sonographers' biplane tracing before a cardiologist overread."
- However, it does not explicitly describe a formal MRMC comparative effectiveness study where human readers' performance with AI assistance is directly compared to their performance without AI assistance. The comparisons made seem to be between the AI's standalone performance and human performance (or a component of human performance like tracing).
- Therefore, an effect size of how much human readers improve with AI vs. without AI assistance cannot be extracted from this text.
If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, the core objective of the studies described is to evaluate the standalone performance of the "Caption Interpretation Automated Ejection Fraction Software" in calculating EF and selecting clips. The reported "AutoEF accuracy" and RMSD values are indicative of standalone algorithm performance.
The type of ground truth used:
- Clip Annotator Study: Expert consensus/evaluation by a panel of expert readers concerning the correct imaging mode and view.
- Pivotal Clinical Study: "Conventional EF calculation methods" served as the "reference method." This likely implies expert-derived EF measurements, potentially involving cardiologist overread of sonographer tracings, and possibly other established clinical methods.
The sample size for the training set:
- The document states, "The algorithms for estimating ejection fraction have been further optimized though additional training." and "Images and cases used for verification testing were carefully separated from training algorithms."
- However, the specific sample size for the training set is not provided in this document.
How the ground truth for the training set was established:
- The document states that the algorithms were "optimized though additional training" but does not detail how the ground truth for this training data was established. It only mentions that "Images and cases used for verification testing were carefully separated from training algorithms," which relates to data splitting, not ground truth establishment for training.

Summary

{0}------------------------------------------------

July 22, 2020

Image /page/0/Picture/1 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

Caption Health % Mr. Sam Surette Head of RA/QA 2000 Sierra Point Pkwy, 8th Floor BRISBANE CA 94005

Re: K200621

Trade/Device Name: Caption Interpretation Automated Ejection Fraction Software Regulation Number: 21 CFR 892.2050 Regulation Name: Picture archiving and communications system Regulatory Class: Class II Product Code: QIH Dated: June 24, 2020 Received: June 24, 2020

Dear Mr. Surette:

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/cfpmp/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see

{1}------------------------------------------------

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}------------------------------------------------

510(k) Number (if known)

K200621

Device Name

Caption Interpretation Automated Ejection Fraction Software

Indications for Use (Describe)

The Caption Interpretation Automated Ejection Fraction Software is indicated for use in adult patients.

Type of Use (Select one or both, as applicable)

□ Over-The-Counter Use (21 CFR 801 Subpart C) � Prescription Use (Part 21 CFR 801 Subpart D)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{3}------------------------------------------------

510(k) SUMMARY K200621 Caption Health Inc.'s

Caption Interpretation Automated Ejection Fraction Software

Submitter's Name, Address, Telephone Number, Contact Person

Caption Health, Inc. 2000 Sierra Point Parkway, 8th Floor Brisbane, CA 94005

Contact Person: Sam Surette, Head of RA/QA

Phone: 415 671 4711 email: sam@captionhealth.com

Date Prepared: June 24, 2020

Name of Device

Common or Usual Name: Picture Archival and Communications Systems Workstation

Proprietary Name: Caption Interpretation Automated Ejection Fraction Software

Classification Name: 21 CFR § 892.2050

Regulatory Class: II

Product Code: QIH, Automated Radiological Image Processing Software

Predicate Device

Bay Labs, Inc. EchoMD Automated Ejection Fraction Software (K173780)

Device Description

{4}------------------------------------------------

Ejection Fraction estimate stated as a percentage, along with an indications of confidence regarding that estimate.

Intended Use / Indications for Use

The Caption Interpretation 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 an ultrasound device, personal computer, or a compatible DICOM-compliant PACS system in order to provide automated estimation of left ventricular ejection fraction. This measurement can be used to assist the clinician in a cardiac evaluation.

The Caption Interpretation Automated Ejection Fraction Software is indicated for use in adult patients.

The intended use/indications for use statement has been slightly updated compared to the predicate device in order to acknowledge that the software may be located on an ultrasound device in addition to personal computer or PACS system. This minor adjustment in indications for use does not alter the intended use of the product and is substantially equivalent to the predicate.

Summary of Technological Characteristics

The Caption Interpretation Automated Ejection Fraction Software is an updated version of the predicate device and features very similar technological characteristics. Both products use machine learning algorithms to select clips from those available and for producing an estimation of ejection fraction. Caption Interpretation AutoEF can estimate ejection from a wider range of views, and minor modifications have been made to the methodology for selecting clips. The algorithms for estimating ejection fraction have been further optimized though additional training. None of the differences raise different questions of safety or effectiveness and available data demonstrate that Caption Interpretation performs in a substantially equivalent manner.

Performance Data

The Caption Interpretation Automated Ejection Fraction Software was developed and tested in accordance with Caption Health's Design Control processes and has been subjected to extensive safety and performance testing. Software 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. Extensive algorithm development and software verification testing assessed the performance of the software's image video clip selection function, performance characteristics of the algorithm including AutoEF accuracy, risk management, and overall functional performance. Images and cases used for verification testing were carefully separated from training algorithms.

In addition, AutoEF has undergone multiple tests and studies to demonstrate the acceptable performance. A Clip Annotator study verified the ability of the software to receive, annotate and select clips for interpretation by the AutoEF Calculation Service. Results of the Clip Annotator were compared

{5}------------------------------------------------

to evaluation by a panel of expert readers. That study met the pre-defined acceptance criteria and found that the observed PPV point estimates for the Clip Annotator were greater than 97% for identification of the imaging mode and the view. Similarly, observed sensitivity point estimates were greater than 90% across views and imaging mode.

Caption Interpretation AutoEF was also the subject of a pivotal clinical investigation to validate successful performance of the EF calculation in comparison to conventional EF calculation methods. This testing showed that AutoEF, including clip selection and calculation together, performs as expected and in a manner that is substantially equivalent to the predicate device. Specifically, the primary endpoint evaluating the relationship (RMSD) between AutoEF derived values based on the best available view combination and the reference method met the predetermined acceptance criteria. Secondary hypothesis testing evaluating combinations of views (i.e., EF estimation based on two or more views of AP2, AP4 or PLAX) met the same predetermined acceptance criteria. Single-view EF estimation based on the AP4 view was also observed to be less than the acceptance criterion, and superior to physicians in making a qualitative and quantitative visual assessment. The AP2 and PLAX views observed results did not meet the acceptance criteria, but performed superior on a quantitative visual assessment. Furthermore, the AP2-only and PLAX-only RMSD was observed to be lower than the RMSD of sonographers' biplane tracing before a cardiologist overread.

Finally, testing of the confidence metric functionality verified successful performance of the Confidence Metric in estimating the error range of the EF estimates around the reference EF with evidence that the difference between the estimated EF and the reference EF is normally distributed.

Taken together, the performance testing demonstrates that the Caption Interpretation Automated Ejection Fraction Software performs as expected and in a manner that is substantially equivalent to the predicate device.

Conclusions

The Caption Interpretation Automated Ejection Fraction Software has the same intended use and nearly identical indications compared to the predicate device. In addition, the two products have very similar technological characteristics and principles of operation. The minor differences in the indications for use statements of the two devices do not change the intended use. In addition, the only notable technological differences between the Caption Interpretation AutoEF and its predicate do not present any new issues of safety or effectiveness because in both cases the key question is whether the EF output of the respective systems is sufficiently accurate and whether the user can review the results to determine whether they are adequate for clinical use. In both cases the systems provide the user with multiple methods to verify the acceptability of image clips used for processing and multiple methods to accept or reject the automated EF estimation. Additionally, the extensive performance testing of the software demonstrates that these differences do not raise any new types of safety or effectiveness questions. Thus, the Caption Interpretation Automated Ejection Software is substantially equivalent to the predicate device.

Regulation Number and Section

§ 892.2050 Medical image management and processing system.

(a)
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.(b)
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).