CogNet QmTRIAGE

K220080 · Medcognetics, Inc. · QFM · Sep 29, 2022 · Radiology

Device Facts

• Record ID: K220080
• Device Name: CogNet QmTRIAGE
• Applicant: Medcognetics, Inc.
• Product Code: QFM · Radiology
• Decision Date: Sep 29, 2022
• Decision: SESE
• Submission Type: Traditional
• Regulation: 21 CFR 892.2080
• Device Class: Class 2
• Attributes: AI/ML, Software as a Medical Device

Intended Use

The MedCognetics (CogNet) QmTRIAGE™ software is a passive notification for prioritization-only, parallel-workflow software tool used by MQSA qualified interpreting physicians to prioritize patients with suspicious findings in the medical care environment. QmTRIAGE™ utilizes an artificial intelligence algorithm to analyze 2D FFDM screening mammograms and flags those that are suggestive of the presence of at least one suspicious finding at the exam level. QmTRIAGE™ produces an exam level output to a PACS/Workstation for flagging the suspicious study and allows for worklist prioritization. MQSA qualified interpreting physicians are responsible for reviewing each exam on a display approved for use in mammography, according to the current standard of care. The QmTRIAGE™ device is limited to the categorization of exams, does not provide any diagnostic information beyond triage and prioritization, does not remove images from the interpreting physician's worklist, and should not be used in lieu of full patient evaluation, or relied upon to make or confirm diagnosis. The QmTRIAGE™ device is intended for use with complete 2D FFDM mammography exams acquired using validated FFDM systems only.

Device Story

CogNet QmTRIAGE is a cloud-based SaMD for radiological triage; inputs 2D FFDM screening mammograms; utilizes AI algorithm to analyze images for suspicious findings; outputs exam-level flags to PACS/workstation to assist radiologists in worklist prioritization. Operates in parallel with standard clinical workflow; does not remove images from worklist or provide diagnostic confirmation. Used by MQSA-qualified interpreting physicians in clinical environments. Benefits patient by enabling faster identification of potentially cancerous cases, facilitating timely clinical review.

Clinical Evidence

Retrospective study of 800 anonymized 2D FFDM mammograms (399 cancer-positive, 401 negative/BI-RADS 1-2). Primary endpoints: AUROC, sensitivity, and specificity. Results: AUROC 0.9569 (95% CI: 0.9364-0.9738), sensitivity 87%, specificity 89%. Data included diverse demographics (ages 22-80+, various ethnicities) and imaging vendors (Hologic, GE, Siemens, Fujifilm).

Technological Characteristics

SaMD using AI algorithm for image analysis. Cloud-based deployment. Inputs: 2D FFDM screening mammograms. Outputs: Exam-level triage notification to PACS/workstation. Non-contact, parallel workflow. Complies with design controls for medical device software.

Indications for Use

Indicated for MQSA qualified interpreting physicians to prioritize 2D FFDM screening mammograms in female patients aged 22 and older. Used for triage of exams suggestive of suspicious findings; not for diagnostic confirmation or replacing standard of care 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.

Predicate Devices

• HealthMammo (K200905)

Submission Summary (Full Text)

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

September 29, 2022

Image /page/0/Picture/1 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 & Human Services logo on the left and the FDA logo on the right. The FDA logo is in blue and includes the letters "FDA" in a square and the words "U.S. FOOD & DRUG ADMINISTRATION".

MedCognetics, Inc. % Diane Rutherford Regulatory Affairs Manager 17217 Waterview Parkway Suite 1.202E DALLAS TX 75252

Re: K220080

Trade/Device Name: CogNet OmTRIAGE Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological computer aided triage and notification software Regulatory Class: Class II Product Code: QFM Dated: August 30, 2022 Received: August 30, 2022

Dear Diane Rutherford:

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 mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email ([e-mail]) or phone [phone] or 301-796-7100).

Sincerely,

Yanna Kang, Ph. D.

Acting Assistant Director Mammography and Ultrasound Team DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Quality 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: 06/30/2023 See PRA Statement below.

510(k) Number (if known) K220080

Device Name CogNet QmTRIAGETM

#### Indications for Use (Describe)

The MedCognetics (CogNet) QmTRIAGE™ software is a passive notification-only, parallel-workflow software tool used by MQSA qualified interpreting physicians to prioritize patients with suspicious findings in the medical care environment. QmTRIAGE™ utilizes an artificial intelligence algorithm to analyze 2D FFDM screening mammograms and flags those that are suggestive of the presence of at least one suspicious finding at the exam level. QmTRIAGE™ produces an exam level output to a PACS/Workstation for flagging the suspicious study and allows for worklist prioritization.

MQSA qualified interpreting physicians are responsible for reviewing each exam on a display approved for use in mammography, according to the current standard of care. The OmTRIAGE™ device is limited to the categorization of exams, does not provide any diagnostic information beyond triage and prioritization, does not remove images from the interpreting physician's worklist, and should not be used in lieu of full patient evaluation, or relied upon to make or confirm diagnosis.

The QmTRIAGE™ device is intended for use with complete 2D FFDM mammography exams acquired using validated FFDM systems only.

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

> Prescription Use (Part 21 CFR 801 Subpart D)

Over-The-Counter Use (21 CFR 801 Subpart C)

#### CONTINUE ON A SEPARATE PAGE IF NEEDED.

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

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

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

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

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

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

## 5. 510(k) SUMMARY

### a)

| Submitter: | MedCognetics, Inc.<br>Mr. Debasish “Ron” Nag<br>Chief Executive Officer & President<br>17217 Waterview Parkway, Suite 1.202E<br>Dallas, TX 75252 USA<br>[e-mail] | | |
|-------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------|----------------------------|
| Contact Person: | MedCognetics, Inc.<br>Ms. Diane Rutherford<br>Regulatory Affairs Manager<br>17217 Waterview Parkway, Suite 1.202E<br>Dallas, TX 75252 USA<br>TEL: [phone]<br>[e-mail] | | |
| Date Prepared: | August 30, 2022 (revised) | | |
| b) | | | |
| Trade Name: | CogNet QmTRIAGE | | |
| Common Name: | Radiological computer aided triage and notification software | | |
| Classification Name: | Radiological computer aided triage and notification software | | |
| Product Code: | QFM | Class 2 | Regulation Number 892.2080 |
| c) | | | |
| Predicate Devices: | K200905   Zebra Medical Vision Ltd.  HealthMammo   Cleared July 16, 2020 | | |
| d)<br>Device Description: | The MedCognetics (CogNet) QmTRIAGE is a non-invasive computer-assisted<br>triage and notification software as a medical device (SaMD) that analyzes 2D<br>FFDM screening mammograms using a machine learning algorithm and notifies a<br>PACS/workstation of the presence of findings suspicious of cancer in a study. The<br>passive-notification enables radiologists to prioritize their worklist and assists them<br>in viewing prioritized studies using the standard PACS or workstation viewing<br>software. The device aim is to aid in the prioritization and triage of radiological<br>medical images only. It is a software tool for MQSA interpreting physicians reading<br>mammograms and does not replace complete evaluation according to the standard<br>of care.<br>Data sets used for training the algorithm were independent of the testing datasets<br>and were obtained from various sites worldwide including North America, South<br>America, Europe, Africa, and Southeast Asia. | | |
| e)<br>Statement of<br>Intended Use: | The MedCognetics (CogNet) QmTRIAGE™ software is a passive notification for<br>prioritization-only, parallel-workflow software tool used by MQSA qualified<br>interpreting physicians to prioritize patients with suspicious findings in the medical<br>care environment. QmTRIAGE™ utilizes an artificial intelligence algorithm to<br>analyze 2D FFDM screening mammograms and flags those that are suggestive of | | |

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

the presence of at least one suspicious finding at the exam level. QmTRIAGE™ produces an exam level output to a PACS/Workstation for flagging the suspicious study and allows for worklist prioritization.

MQSA qualified interpreting physicians are responsible for reviewing each exam on a display approved for use in mammography, according to the current standard of care. The QmTRIAGE™ device is limited to the categorization of exams, does not provide any diagnostic information beyond triage and prioritization, does not remove images from the interpreting physician's worklist, and should not be used in lieu of full patient evaluation, or relied upon to make or confirm diagnosis.

The QmTRIAGE™ device is intended for use with complete 2D FFDM mammography exams acquired using validated FFDM systems only.

f)

Summary of Technological Characteristics:

CogNet QmTRIAGE shares technological characteristics with the predicate device. Both are classified under the same product code and regulation, have the same intended use, flag suspicious images at the study/exam level, are parallel workflow processes that do not alter the original image, are non-contact, and are SaMD using AI for analysis.

The proposed device also has minor differences in technological characteristics from that of the predicate device. While both the proposed device and the predicate offer cloud-based analysis, the predicate also offers an on-premise option. The differences in the technological characteristics are minor and reflect market strategy and/or perceived user preferences and do not impact the safety, effectiveness, or substantial equivalence of the device.

| Technological<br>Characteristics | New Device [K220080]<br>CogNet QmTRIAGE - MedCognetics | Predicate Device [K200905]<br>HealthMammo - Zebra Medical Vision Ltd. | Status |
|--------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------|
| Indication for Use<br>/ Intended Use | The MedCognetics (CogNet) QmTRIAGE<br>software is a passive notification for<br>prioritization-only, parallel-workflow software<br>tool used by MQSA qualified interpreting<br>physicians to prioritize patients with suspicious<br>findings in the medical care environment.<br>QmTRIAGE utilizes an artificial intelligence<br>algorithm to analyze 2D FFDM screening<br>mammograms and flags those that are<br>suggestive of the presence of at least one<br>suspicious finding at the exam level.<br>QmTRIAGE produces an exam level output to a<br>PACS/Workstation for flagging the suspicious<br>study and allows for worklist prioritization.<br>MQSA qualified interpreting physicians are<br>responsible for reviewing each exam on a<br>display approved for use in mammography,<br>according to the current standard of care. The<br>QmTRIAGE device is limited to the<br>categorization of exams, does not provide any<br>diagnostic information beyond triage and<br>prioritization, does not remove images from<br>the interpreting physician's worklist, and<br>should not be used in lieu of full patient<br>evaluation, or relied upon to make or confirm<br>diagnosis.<br>The QmTRIAGE device is intended for use with<br>complete 2D FFDM mammography exams<br>acquired using validated FFDM systems only. | The Zebra HealthMammo is a passive<br>notification for prioritization-only, parallel-<br>workflow software tool used by MQSA-<br>qualified interpreting physicians to prioritize<br>patients with suspicious findings in the<br>medical care environment. HealthMammo<br>utilizes an artificial intelligence algorithm to<br>analyze 2D FFDM screening mammograms<br>and flags those that are suggestive of the<br>presence of at least one suspicious finding at<br>the exam-level. HealthMammo produces an<br>exam level output to a PACS/Workstation for<br>flagging the suspicious case and allows<br>worklist prioritization.<br>MQSA-qualified interpreting physicians are<br>responsible for reviewing each exam on a<br>display approved for use in mammography<br>according to the current standard of care.<br>HealthMammo device is limited to the<br>categorization of exams, does not provide any<br>diagnostic information beyond triage and<br>prioritization, does not remove images from<br>the interpreting physician's worklist, and<br>should not be used in lieu of full patient<br>evaluation, or relied upon to make or confirm<br>diagnosis.<br>The HealthMammo device is intended for use<br>with complete 2D FFDM mammography<br>exams acquired using validated FFDM systems<br>only. | Same |
| Notification Only | Yes | Yes | Same |
| Parallel Workflow | Yes | Yes | Same |
| User | Interpreting physician | Interpreting physician | Same |
| Alert to finding | Yes.<br>Passive notification flagged for review | Yes.<br>Passive notification flagged for review | Same |

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

# K220080

| Technological<br>Characteristics | | New Device [K220080]<br>CogNet QmTRIAGE - MedCognetics | Predicate Device [K200905]<br>HealthMammo - Zebra Medical Vision Ltd. | Status |
|-------------------------------------------------------------------------|---------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------|
| Independent of<br>SoC workflow | | Yes.<br>No cases are removed from worklist | Yes.<br>No cases are removed from worklist | Same |
| Modality | | FFDM screening mammograms | FFDM screening mammograms | Same |
| FFDM<br>Manufacturer | | Hologic | Hologic | Same |
| Body Part | | Breast | Breast | Same |
| Al algorithm | | Yes | Yes | Same |
| Limited to analysis<br>of imaging data | | Yes | Yes | Same |
| Performance Study | Inclusion<br>Criteria | Standard 2D FFDM screening<br>mammograms<br>Biopsy proven cancer studies studies (soft<br>tissues and microcalcifications)<br>BIRADS 1 and 2 normal/benign cases with<br>2-year follow-up of a negative diagnosis<br>Female patients 22 and older<br>Bilateral Studies with 4 standard views<br>(LCC, LMLO, RCC, RMLO) | 2D FFDM screening<br>mammograms<br>Biopsy proven cancer studies<br>(soft tissues and microcalcifications)<br>BIRADS 1 and 2 normal cases with 2 year<br>follow-up<br>Studies with 4 standard views (LCC,<br>LMLO, RCC, RMLO) BIRADS 1 and 2<br>normal cases with 2 year follow-up | Different |
| | Exclusion<br>Criteria | Digital breast tomosynthesis images<br>2D synthetic views from tomosynthesis | Digital Breast tomosynthesis studies<br>3D studies<br>Studies that did not include all four views<br>Studies that do not comply with the<br>inclusion criteria | Different |
| | Multiple<br>Operating<br>points | Not Applicable | Yes. Three optional operating points | Different |
| Aids in prompt<br>identification of<br>cases with indicated<br>findings | | Yes | Yes | Same |
| Results Preview | | The device operates in parallel with the<br>standard of care, which remains the default<br>option for all cases. Encapsulated PDF stored<br>with original DICOM study and may be<br>downloaded and viewed as a PDF. | Presentation of notification and preview of<br>the study for initial assessment not meant for<br>diagnostic purposes. The device operates in<br>parallel with the standard of care, which<br>remains the default option for all cases. | Equivalent |
| Deployment | | Cloud based | Cloud based<br>On-premise option | Different |
| Where results are<br>received | | PACS / Workstation | PACS / Workstation | Same |

g)

Summary of Performance Testing:

The software was developed and validated in accordance with design controls and software documentation requirements for medical devices.

CogNet QmTRIAGE utilizes an artificial intelligence (AI) algorithm. The validation of the performance of MedCognetics' QmTRIAGE algorithm for triage of 2D FFDM achieved an overall Area Under Receiver Operating Characteristics (AUROC) of 0.9569 with 95% CI: 0.9364-0.9738 across the entire test dataset, without subgroup breakdown.

Also validated was Sensitivity and Specificity, achieving an overall Sensitivity of 87% and a Specificity of 89% across the entire test dataset, without subgroup breakdown, which exceeded the standard of care as reported in the Breast Cancer Surveillance Consortium (BCSC) study.

The performance of the MedCognetics' QmTRIAGE has been validated for triage of 2D FFDM in mammogram cases. The study data included a retrospective cohort of 800 anonymized 2D FFDM mammograms from the USA and Germany, including 399 cases positive for cancer with biopsy confirmation and 401 cases negative for breast cancer (BI-RADS1 and BI-RADS2) with a two-year follow-up of a negative diagnosis. The test dataset excludes screening BI-RADS 0 cases that were determined to be benign after diagnostic workup.

{6}------------------------------------------------

The mammogram cases were all from female patients, ages 22 to 80+ with the median age group being the 50-59 group. Ethnicities represented included American Indian, Asian, Black (non-Hispanic), Hispanic, and White (non-hispanic).

Imaging from Hologic, GE, Siemens, and Fujifilm, were used in the performance study and design validation but the complete vendor/model information was not provided with all images. The Hologic Selenia Dimension has been identified as the vendor/model for the initial release.

The performance test was constructed to ensure that confounding factors that are present in the population are addressed in the data such that it is consistent with the population of women undergoing breast cancer screening examination. The confounding factors that were considered include 1) lesion type, 2) breast density 3) age and 4) race. The triage accuracy was measured for these cohorts against the ground-truth.

Independence of test and training data was ensured by storing testing data in an isolated storage location. Once the relevant clinical sites had been identified for inclusion in the test set, all data from these sites were isolated into a controlled storage space. Data in this controlled storage space is only made available when conducting the performance test, ensuring total independence of the test set. Secondary software checks are also implemented against the list of cases in the training and test sets to further guarantee test set independence.

MedCognetics considers CogNet QmTRIAGE to be substantially equivalent to the Conclusion: predicate device listed above. This conclusion is based on the similarities in primary intended use, principles of operation, functional design, and established medical use and performance testing of CogNet OmTRIAGE which demonstrated adequate performance for the device in line with its intended use.