(98 days)
Brainomix Triage LVO is a notification-only, parallel workflow tool for use by hospital networks and trained clinicians to identify and communicate images of specific patients to a specialist, independent of standard of care workflow.
Brainomix Triage LVO uses an artificial intelligence algorithm to analyze images for findings suggestive of a prespecified clinical condition and to notify an appropriate medical specialist of these findings in parallel to standard of care image interpretation of suspected findings is not for diagnostic use beyond notification. Specifically, the device analyzes CT angiogram images of the brain acquired in the acute setting, and sends notifications to a neurovascular specialist that a suspected large vessel occlusion (LVO) has been identified and recommends review of those images. Images can be previewed through a mobile application or via email. Brainomix Triaqe LVO is intended to analyze terminal ICA and MCA-M1 vessels for LVOs.
lmages that are previewed through the mobile application are compressed and are for informational purposes only and not intended for diagnostic use beyond notification. Notified clinicians are responsible for viewing noncompressed images on a diagnostic viewer and engaging in appropriate patient evaluation and relevant discussion with a treating physician before making care-related decisions or requests.
Brainomix Triage LVO is limited to analysis of imaging data and should not be used in-lieu of full patient evaluation or relied upon to make or confirm diagnosis.
Brainomix 360 Triage LVO is a radiological computer aided triage and notification (CADt) software package compliant with the DICOM standard and running on an off-the-shelf physical or virtual server.
The Triage LVO module is a CTA processing module which operates within the integrated Brainomix 360 Platform to provide triage and notification of suspected LVO. Brainomix 360 Triage LVO is a stand-alone software device which uses machine learning algorithms that uses advanced non adaptive imaging algorithms, artificial intelligence, and large data analytics to automatically identify suspected LVO on CTA imaging in the acute setting. The output of the module is a priority notification to clinicians indicating the suspicion of LVO based on positive findings. Specifically, Brainomix 360 Triage LVO is optimized to evaluate occlusions of the intracranial internal carotid artery (ICA) and proximal middle cerebral artery (M1 segment). The Triage LVO module uses the basic services supplied by the Brainomix 360 Platform including DICOM processing, job management, imaging module execution and imaging output including the notification and compressed image.
Brainomix 360 Triage LVO notification capabilities enable clinicians to review and preview images via mobile app notification. Alternatively, intended users can also access the notification (a "Suspected LVO" flag) and straightened images via the Brainomix 360 web user interface. Images that are previewed via mobile app are compressed, are for preview informational purposes only, and not intended for diagnostic use beyond notification.
The device is intended for use as an additional tool for assisting study triage within existing patient pathways. It does not replace any part of the current standard of care. It is designed to assist in prioritization of studies for reading within a worklist, in addition to any other pre-existing formal or informal methods of study prioritization in place. Specifically, it does not remove cases from a reading queue and operates in parallel to the standard of care. This device is not intended to replace the usual methods of communication and transfer of information in the current standard of care.
Brainomix 360 Triage LVO notification capabilities enable clinicians to preview compressed and informational images through via mobile application with preview of unprocessed image attachments. Alternatively, the user may review unprocessed images via web user interface on a radiology workstation.
Here's a breakdown of the acceptance criteria and the study proving the device's performance, based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance (95% CI) | Goal |
|---|---|---|
| Sensitivity (Positive %) | 90% (84.2-94.3) | ≥ 80% (lower bound) |
| Specificity (Negative %) | 92.9% (88.0-94.3) | ≥ 80% (lower bound) |
| Time-to-Notification | 86.3 to 178.2 seconds | ≤ 3.5 minutes |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: 308 CTA scans (studies)
- Data Provenance: Retrospective study. Data were obtained from 14 different hospitals and clinics in the U.S. The majority of patients were scanned at Mayo Clinic Rochester (N=129) and Boston Medical Centre (N=179), with 56 scans transferred from 11 hospitals in the Massachusetts area. The patient cohort was enriched to ensure an approximately equal balance of LVO positive and negative studies and to ensure the distribution of clinical and demographic variables (e.g., age and gender) for generalizability.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: Two ground truthers, with a third ground truther used in the event of disagreement.
- Qualifications: All truthers were US board-certified neuroradiologists.
4. Adjudication Method for the Test Set
- Adjudication Method: 2+1 (Two ABR-certified neuroradiologists reviewed each case, and a third neuroradiologist provided consensus in the event of disagreement).
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was it done? No, the document only describes a standalone performance evaluation of the device.
- Effect size of human readers improving with AI vs. without AI assistance: Not applicable, as no MRMC study was performed or reported.
6. Standalone Performance Study
- Was it done? Yes, a standalone performance evaluation was done. The study assessed the device's image analysis in terms of sensitivity and specificity against a ground truth established by expert neuroradiologists.
7. Type of Ground Truth Used
- Type of Ground Truth: Expert consensus by US board-certified neuroradiologists.
8. Sample Size for the Training Set
- Sample Size: Over 1600 CT brain imaging studies.
9. How the Ground Truth for the Training Set was Established
- Ground Truth Establishment: The dataset used to train the algorithm was labeled by "trained radiologists" regarding the presence of LVO.
{0}------------------------------------------------
Image /page/0/Picture/0 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 USA seal. To the right of the seal is the FDA logo in blue, with the words "U.S. FOOD & DRUG" stacked on top of the word "ADMINISTRATION".
June 28, 2024
Brainomix Limited Thais Sala Regulatory Affairs Manager First Floor, Seacourt Tower West Way Oxford. OX2 0JJ United Kingdom
Re: K231837
Trade/Device Name: Brainomix 360 Triage LVO Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological Computer Aided Triage And Notification Software Regulatory Class: Class II Product Code: QAS
Dear Thais Sala:
The Food and Drug Administration (FDA) is sending this letter to notify you of an administrative change for your device cleared on April 21, 2023. Specifically, FDA is updating this SE Letter because FDA inadvertently indicated that the SE determination also included review and clearance of a predetermined change control plan (PCCP). However, your 510(k) submission did not include a PCCP, so FDA is providing this administrative correction. Please see the attached revised clearance letter.
Please note that the 510(k) submission was not re-reviewed. For questions regarding this letter please contact Jessica Lamb, OHT8: Office of Radiological Health, 301-796-6167, Jessica.Lamb(0)fda.hhs.gov.
Sincerely,
Jessica Lamb
Jessica Lamb, Ph.D. Assistant Director DHT8B: Division of Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
{1}------------------------------------------------
Image /page/1/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 & Human Services logo on the left and the FDA logo on the right. The FDA logo is in blue and includes the letters "FDA" followed by the words "U.S. FOOD & DRUG ADMINISTRATION".
June 28, 2024
Brainomix Limited % Thais Sala Regulatory Affairs Manager First Floor, Seacourt Tower. West Wav Oxford, OX2 0JJ UNITED KINGDOM
Re: K231837
Trade/Device Name: Brainomix 360 Triage LVO Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological computer aided triage and notification software Regulatory Class: Class II Product Code: OAS Dated: August 29, 2023 Received: August 29, 2023
Dear Thais Sala:
The Food and Drug Administration (FDA) is sending this letter to notify you of an administrative change for your device cleared on April 21, 2023.
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 (the 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 available at https://www.accessdata.fda.gov/scripts/cdrb/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.
{2}------------------------------------------------
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.
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.70) and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).
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 Part 803) for devices or postmarketing safety reporting (21 CFR Part 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 (OS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 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-regulatory
{3}------------------------------------------------
assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Jessica Lamb
Jessica Lamb, Ph.D. Assistant Director Imaging Software Team DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
{4}------------------------------------------------
Indications for Use
Submission Number (if known)
Device Name
Brainomix 360 Triage LVO
Indications for Use (Describe)
Brainomix Triage LVO is a notification-only, parallel workflow tool for use by hospital networks and trained clinicians to identify and communicate images of specific patients to a specialist, independent of standard of care workflow.
Brainomix Triage LVO uses an artificial intelligence algorithm to analyze images for findings suggestive of a prespecified clinical condition and to notify an appropriate medical specialist of these findings in parallel to standard of care image interpretation of suspected findings is not for diagnostic use beyond notification. Specifically, the device analyzes CT angiogram images of the brain acquired in the acute setting, and sends notifications to a neurovascular specialist that a suspected large vessel occlusion (LVO) has been identified and recommends review of those images. Images can be previewed through a mobile application or via email. Brainomix Triaqe LVO is intended to analyze terminal ICA and MCA-M1 vessels for LVOs.
lmages that are previewed through the mobile application are compressed and are for informational purposes only and not intended for diagnostic use beyond notification. Notified clinicians are responsible for viewing noncompressed images on a diagnostic viewer and engaging in appropriate patient evaluation and relevant discussion with a treating physician before making care-related decisions or requests.
Brainomix Triage LVO is limited to analysis of imaging data and should not be used in-lieu of full patient evaluation or relied upon to make or confirm diagnosis.
Type of Use (Select one or both, as applicable)
Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 801 Subpart C)
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{5}------------------------------------------------
K213837
Image /page/5/Picture/1 description: The image shows the logo for BRAINOMIX. The logo consists of a stylized brain icon on the left, followed by the word "BRAINOMIX" in a sans-serif font. The brain icon is teal, while the letters are dark gray, except for the "A" which is teal. The logo has a modern and clean design.
510(K) Summary Brainomix Limited – Brainomix 360 Triage LVO
| Date Prepared: | 19Jun2023 |
|---|---|
| Applicant's Name: | Brainomix Limited |
| Applicant's Address: | First Floor, Seacourt Tower, West WayOxford, OX 0JJUnited Kingdom |
| Official Contact: | Thais Sala+44 (0) 7375 967 695tsala@brainomix.com |
| Device Proprietary Name: | Brainomix 360 Triage LVO |
| Device Common Name: | Radiological Computer-Assisted Triage And Notification Software |
| Regulatory Class: | Class II |
| Product Code: | QAS |
| Regulation: | 21 C.F.R. §892.2080 |
| Reference Device: | Rapid LVO 1.0 (K200941) |
Brainomix 360 Triage LVO is Substantially Equivalent to the following Legally Marketed device:
| 510(k) Number | Trade Name | Manufacturer |
|---|---|---|
| K223042 | Viz LVO | Viz AI |
1 Device Description
Brainomix 360 Triage LVO is a radiological computer aided triage and notification (CADt) software package compliant with the DICOM standard and running on an off-the-shelf physical or virtual server.
The Triage LVO module is a CTA processing module which operates within the integrated Brainomix 360 Platform to provide triage and notification of suspected LVO. Brainomix 360 Triage LVO is a stand-alone software device which uses machine learning algorithms that uses advanced non adaptive imaging algorithms, artificial intelligence, and large data analytics to automatically identify suspected LVO on CTA imaging in the acute setting. The output of the module is a priority notification to clinicians indicating the suspicion of LVO based on positive findings. Specifically, Brainomix 360 Triage LVO is optimized to evaluate occlusions of the intracranial internal carotid artery (ICA) and proximal middle cerebral artery (M1 segment). The Triage LVO module uses the basic services supplied by the Brainomix 360 Platform including DICOM processing, job management, imaging module execution and imaging output including the notification and compressed image.
Images used to train the algorithm were sourced from datasets that included a range of equipment manufacturers including Toshiba, GE, Siemens, Philips and Canon/Toshiba. This dataset, which contained over 1600 CT brain imaging studies, was labelled by trained radiologists regarding the presence of LVO. The performance of the device's Al algorithms were validated in a standalone
{6}------------------------------------------------
Image /page/6/Picture/0 description: The image shows the logo for BRAINOMIX. The logo consists of a stylized brain icon on the left, followed by the word "BRAINOMIX" in a sans-serif font. The brain icon is split into two halves, with the left half being a solid teal color and the right half being an outline of the same color. The word "BRAINOMIX" is in a dark gray color, except for the "A", which is in a gradient of teal to blue.
performance evaluation, utilizing and independent dataset than the one used for algorithm training, in which the case-level output from the device was compared with a reference standard ('ground truth'). This was determined by two ground truthers, with a third ground truther used in the event of disagreement. All truthers were US board-certified neuroradiologists.
Brainomix 360 Triage LVO notification capabilities enable clinicians to review and preview images via mobile app notification. Alternatively, intended users can also access the notification (a "Suspected LVO" flag) and straightened images via the Brainomix 360 web user interface. Images that are previewed via mobile app are compressed, are for preview informational purposes only, and not intended for diagnostic use beyond notification.
The device is intended for use as an additional tool for assisting study triage within existing patient pathways. It does not replace any part of the current standard of care. It is designed to assist in prioritization of studies for reading within a worklist, in addition to any other pre-existing formal or informal methods of study prioritization in place. Specifically, it does not remove cases from a reading queue and operates in parallel to the standard of care. This device is not intended to replace the usual methods of communication and transfer of information in the current standard of care.
Brainomix 360 Triage LVO notification capabilities enable clinicians to preview compressed and informational images through via mobile application with preview of unprocessed image attachments. Alternatively, the user may review unprocessed images via web user interface on a radiology workstation.
2 Intended Use / Indications for Use
Brainomix Triage LVO is a notification-only, parallel workflow tool for use by hospital networks and trained clinicians to identify and communicate images of specific patients to a specialist, independent of standard of care workflow.
Brainomix Triage LVO uses an artificial intelligence algorithm to analyze images for findings suggestive of a prespecified clinical condition and to notify an appropriate medical specialist of these findings in parallel to standard of care image interpretation. Identification of suspected findings is not for diagnostic use beyond notification. Specifically, the device analyzes CT angiogram images of the brain acquired in the acute setting, and sends notifications to a neurovascular specialist that a suspected large vessel occlusion (LVO) has been identified and recommends review of those images can be previewed through a mobile application or via email. Brainomix Triage LVO is intended to analyze terminal ICA and MCA-M1 vessels for LVOs.
lmages that are previewed through the mobile application are compressed and are for informational purposes only and not intended for diagnostic use beyond notification. Notified clinicians are responsible for viewing noncompressed images on a diagnostic viewer and engaging in appropriate patient evaluation and relevant discussion with a treating physician before making care-related decisions or requests.
Brainomix Triage LVO is limited to analysis of imaging data and should not be used in-lieu of full patient evaluation or relied upon to make or confirm diagnosis.
{7}------------------------------------------------
Image /page/7/Picture/0 description: The image shows the logo for BRAINOMIX. The logo consists of a stylized brain icon on the left, followed by the word "BRAINOMIX" in a sans-serif font. The brain icon is a gradient of blue and green, while the letters "AI" in the word "BRAINOMIX" are also in the same gradient of blue and green, while the rest of the letters are in a dark gray color.
3 Performance Data
The following performance data have been provided to support evaluation of substantial equivalence.
Software Verification and Validation Testing
Software verification and validation testing was conducted, and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices", May 11, 2005.
Performance Testing
Brainomix performed standalone performance in accordance with the §892.2080 special controls to show acceptance of the clinical performance of the Brainomix 360 Triage LVO module. The test dataset used during standalone performance evaluation was newly acquired and appropriate steps were taken to ensure it is independent from the training dataset used in model development.
A retrospective study has been carried out to assess the standalone performance of the image analysis algorithm and notification functionality of Triage LVO. The study evaluated the Triage LVO image analysis in terms of sensitivity and specificity with respect to a ground truth, as established by US board certified neuroradiologists, in the detection of large vessel occlusion (LVO) in the brain.
A sample size of 308 CTA scans (studies) were obtained 14 different hospitals and clinics in the U.S. The majority of patients were scanned at Mayo Clinic Rochester (N= 129) and Boston Medical Centre (N= 179) of which 56 scans were transferred from a total of 11 hospitals in the Massachusetts area. The patient cohort was enriched to ensure an approximately equal balance of LVO positive and negative studies and to ensure the distribution of clinical and demographic variables (e.g., age and gender) allows generalizability to the patient population for whom use is intended. To determine the ground truth, each case was reviewed by two ABR-certified neuroradiologists (ground truthers), with a consensus determined by a third ground truther in the event of disagreement.
In the CTA image dataset, the slice thickness distribution was median 0.75mm [IQR: 0.625 – 0.8] with a minimum of 0.5mm (n=2) and a maximum of 1mm (n=42). In-plane (axial) resolution showed a range of 0.381mm to 0.72mm with a median of 0.49mm. Four different tube voltage (KvP, peak kilovoltage) values were encountered in the dataset (90KvP n=64; 120KvP n=137 and 140KvP, n=99). Tube current was median of 526mA [IQR: 445mA - 645mA]. With respect to contrast phase during acquisition, 62 studies were Early Arterial (EA), 130 Peak Arterial (PA), 110 in Equilibrium phase (EQ), 3 in Peak Venous (PV), and 3 in Late Venous (LV). All the images used a standard or a soft (low-pass filter) convolution kernel for reconstruction (e.g., STANDARD in GE MEDICAL SYSTEMS).
{8}------------------------------------------------
Image /page/8/Picture/0 description: The image shows the logo for BRAINOMIX. The logo consists of a stylized brain icon on the left, followed by the word "BRAINOMIX" in a sans-serif font. The brain icon is a gradient of blue and green, while the letters of the word "BRAINOMIX" are in a dark gray color, except for the "AI" which is in a gradient of blue and green.
The cases (n=308) were all successfully processed with the algorithm. The confusion matrix was as follows: True Positives (TP): 126, True Negatives (TN): 156, False Positives (FP): 12, False Negatives (FN): 14. The standalone performance exceeded the 80% goal using the lower bound of the 95% Confidence Interval (Cl) for Sensitivity (or positive percentage agreement, defined as TP/[TP+FN]) and Specificity (or negative percentage agreement, defined as TN/(TN+FP). The observed results are Sensitivity of 90% (95% Cl: 84.2-94.3) and Specificity 92.9% (95% Cl: 88.0-94.3) with a receiver operating curve (ROC) AUC of 91.4% (95% CI: 88.2-94.5), as shown in Figure 1.
Image /page/8/Figure/3 description: This image is a plot titled "Triage LVO Operating Point". The plot shows the True Positive Rate on the y-axis and the False Positive Rate on the x-axis. There are two curves plotted: one for "Detection, AUC=91.429" and another for "Random guess".
Figure 1. Receiver Operating Curve for the device, with the operating point (sensitivity 90%, specificity 92.9%) shown in the red triangle.
As part of a secondary analysis, the company stratified the device performance by various confounding variables: age (Table 1); by gender (Table 2); by race (Table 3); by scanner manufacturer (Table 4); by clinical site (Table 5); by vessel affected (Table 6) and by presence of stenosis as noted by the truthers (Table 7).
In addition, the performance for LVO detection in the left and right hemispheres was explored. This showed very similar performance for left hemisphere (sensitivity = 88.6%, Cl: 79.4-94.8%) and right hemisphere (91.4%, CI: 83.0-96.7%) LVOs.
{9}------------------------------------------------
Image /page/9/Picture/0 description: The image shows the logo for BRAINOMIX. The logo consists of a stylized brain icon on the left, followed by the word "BRAINOMIX" in a sans-serif font. The "AI" in the word "BRAINOMIX" is a gradient of blue and green, while the rest of the letters are gray.
Table 1. Summary performance metrics from patients sub-categorized by age, with 95% confidence intervals where appropriate
| Metrics | Age 22-50 | Age 50-70 | Age 70+ |
|---|---|---|---|
| Total N | 57 | 132 | 119 |
| TP | 12 | 44 | 70 |
| TN | 39 | 75 | 42 |
| FN | 3 | 8 | 3 |
| FP | 3 | 5 | 4 |
| Sensitivity | 80.0 (55.2-95.3) | 84.6 (72.9-92.8) | 95.9 (89.2-99.1) |
| Specificity | 92.9 (79.4-95.9) | 93.8 (84.1-94.5) | 91.3 (88.7-97.5) |
| AUC | 86.4 (74.0-96.7) | 89.2 (83.4-94.2) | 94.0 (89.3-98.2) |
Table 2. Summary performance matrix from patients sub-categorized by gender, with 95% confidence intervals where appropriate
| Metrics | Male | Female |
|---|---|---|
| Total N | 140 | 168 |
| TP | 57 | 69 |
| TN | 72 | 84 |
| FN | 4 | 10 |
| FP | 7 | 5 |
| Sensitivity | 93.4 (84.9-98.2) | 87.3 (78.6-93.6) |
| Specificity | 91.1 (86.7-95.9) | 94.4 (86.0-94.6) |
| AUC | 92.3 (87.7-96.5) | 91.3 (87.0-95.3) |
Table 3. Summary of performance metrics from patients sub-categorized by race-ethnicity, with 95% confidence intervals where appropriate. *CI could not be calculated due to lack of evidence (low N).
| Metrics | White | Black/AfricanAmerican | Hispanic/ Latino | Asian/AsianAmerican | Unknown/Refused |
|---|---|---|---|---|---|
| Total N | 148 | 85 | 27 | 7 | 40 |
| TP | 74 | 19 | 10 | 4 | 19 |
| TN | 58 | 61 | 14 | 3 | 19 |
| FN | 11 | 2 | 0 | 0 | 1 |
| FP | 5 | 3 | 3 | 0 | 1 |
| Sensitivity | 87.1 (78.6-93.2) | 90.5 (72.3-98.5) | 100.0 (77.5-100.0) | 100.0 (58.3-100.0) | 95.0 (84.5-99.3) |
| Specificity | 92.1 (83.4-93.6) | 95.3 (87.4-98.0) | 82.4 (72.8-97.5) | 100.0 (70.8-100.0) | 95.0 (84.5-99.3) |
| AUC | 88.9 (83.3-93.5) | 92.9 (85.8-98.6) | 88.5 (75.0-100.0) | 100.0 (NA*) | 95.0 (87.5-100.0) |
{10}------------------------------------------------
Image /page/10/Picture/0 description: The image shows the logo for BRAINOMIX. The logo consists of a stylized brain icon on the left, followed by the word "BRAINOMIX" in a sans-serif font. The "AI" in the word "BRAINOMIX" is in a gradient of blue, while the rest of the letters are in a dark gray color.
Table 4. Summary of performance metrics from patients sub-categorized by scanner manufacturer, with 95% confidence intervals where appropriate
| Metrics | SIEMENS | GE MedicalSystems | Philips | Canon/ Toshiba |
|---|---|---|---|---|
| Total N | 133 | 96 | 75 | 4 |
| TP | 51 | 38 | 33 | 4 |
| TN | 72 | 48 | 36 | 0 |
| FN | 5 | 4 | 5 | 0 |
| FP | 5 | 6 | 1 | 0 |
| Sensitivity | 91.1 (81.3-97.0) | 90.5 (78.6-97.3) | 86.6 (73.3-95.4) | NA |
| Specificity | 93.5 (87.0-96.2) | 88.9 (82.2-94.8) | 97.3 (84.1-96.9) | NA |
| AUC | 92.3 (87.8-97.2) | 89.7 (83.3-95.6) | 92.4 (86.1-97.6) | NA |
Table 5. Summary of performance metrics from patients site, with 95% confidence intervals where appropriate. MCR = Mayo Clinic Rochester, BMC = Boston Medical Center.
| Metrics | MCR | BMC |
|---|---|---|
| Total N | 129 | 179 |
| TP | 51 | 75 |
| TN | 70 | 86 |
| FN | 3 | 11 |
| FP | 5 | 7 |
| Sensitivity | 94.4 (85.6-98.8) | 87.2 (78.9-93.3) |
| Specificity | 93.3 (88.5-97.2) | 92.5 (84.9-93.8) |
| AUC | 93.5 (89.0-97.7) | 89.8 (85.2-93.8) |
Table 6. Summary performance metrics from patients sub-categorized by affected vessel, with 95% confidence intervals where appropriate. ICA = intracranial carotid artery. MCA M1 = proximal segment of the middle cerebral artery.
| Metrics | ICA | MCA M1 |
|---|---|---|
| TP | 29 | 98 |
| TN | 156 | 156 |
| FN | 1 | 13 |
| FP | 14 | 12 |
| Sensitivity | 96.6 (84.3-99.8) | 88.7 (81.3-93.5) |
| Specificity | 91.8 (86.9-95.3) | 92.9 (88.2-96.2) |
| AUC | 83.0 (75.0-90.3) | 90.6 (86.9-93.8) |
{11}------------------------------------------------
Image /page/11/Picture/0 description: The image shows the logo for BRAINOMIX. The logo consists of a stylized brain image on the left, followed by the word "BRAINOMIX" in a sans-serif font. The brain image is a gradient of blue and teal, and the letters "AI" in the word "BRAINOMIX" are also in the same gradient of blue and teal, while the rest of the letters are in a dark gray color.
Table 7. Summary performance from patients with or without stenosis as noted by the truthers, with 95% confidence intervals where appropriate.
| Metrics | With Stenosis | Without Stenosis |
|---|---|---|
| Total N | 30 | 278 |
| TP | 7 | 119 |
| TN | 19 | 137 |
| FN | 3 | 11 |
| FP | 1 | 11 |
| Sensitivity | 70.0 (38.9-92.3) | 91.5 (85.8-95.6) |
| Specificity | 95.0 (71.0-96.1) | 92.6 (88.4-94.9) |
| AUC | 82.5 (66.3-96.7) | 92.1 (88.6-95.0) |
In addition, the device time-to-notification was assessed, which includes: (1) transferring data from PACS (picture archiving and communication system) or scanner to the Brainomix 360 server; (2) processing the case and producing and output; (3) sending results to the Brainomix 360 cloud service; and (4) delivering the notification to the user's mobile device through push notification services. The total time-to-notification ranged from 86.3 to 178.2 seconds, meeting the goal of time-to-notification of ≤3.5minutes, as the reference device Rapid LVO 1.0 (K200941).
4 Prescriptive Statement
Caution: Federal law restricts this device to sale by or on the order of a physician.
Safety and Effectiveness ട്
Brainomix 360 Triage LVO has been designed, verified and validated in compliance with 21 CFR, Part 820.30 requirements. The device has been designed to meet the requirements associated with ISO 14971:2019 (risk management).
Summary of Technological Characteristics ട
Both proposed and predicate device are a notification-only, parallel workflow tool for use by hospital networks and trained clinicians to identify and communicate images of specific patients to a specialist, independent of standard of care workflow. Notifications generated from both proposed and predicate devices are shared with clinicians to alert that a suspected large vessel occlusion has been identified and recommends review of those images.
The proposed and predicate devices are equally intended for use as an additional tool for assisting study triage within existing patient pathways. They do not replace any part of the current standard of care. Likewise, they are designed to assist in prioritization of studies for reading within a worklist, in addition to any other pre-existing formal or informal methods of study prioritization in place.
Both proposed and predicate devices are designed to be used by trained clinicians in a hospital / clinical environment.
{12}------------------------------------------------
Image /page/12/Picture/0 description: The image shows the logo for BRAINOMIX. The logo consists of a stylized brain icon on the left, followed by the word "BRAINOMIX" in a sans-serif font. The brain icon is teal, while the text is a gradient of teal to gray. The "A" in BRAINOMIX is stylized to resemble a brain.
Both proposed and predicate devices run on standard physical and/or virtual servers which are installed within a hospital network and within the protection of hospital firewalls.
The predicate device notifies the user via mobile and provides compressed original images which are used for informational purposes only. Likewise, the images which are shared on notifications by the proposed device are compressed and for informational purposes only. As the predicate, a persistent warning is displayed to alert users that the images are compressed and not intended for diagnostic purposes.
Where Brainomix 360 Triage LVO differs from the predicate is that the proposed device may also notify the user of a suspected LVO via the web user interface, as an additional channel of output. The unprocessed images are subjected to rotation and resampling (pre-processing and registration) which do not alter the original imaging in relation to aid for diagnostic. Identically to the predicate, the notified clinicians are responsible for viewing non-compressed images on a diagnostic viewer and engaging in appropriate patient evaluation and relevant discussion with a treating physician before making care-related decisions or requests. Therefore, the technical differences in how the notification may be sent to the user between the proposed and predicate devices do not raise different questions of safety and effectiveness.
7 Substantial Equivalence
| Characteristic/Parameter | Brainomix 360 Triage LVOProposed Device | Viz.Al Viz LVOPredicate Device (K223042) |
|---|---|---|
| Application Number | K231837 | K223042 |
| Product Code | QAS | QAS |
| Regulation | 21 C.F.R. §892.2080 | 21 C.F.R. §892.2080 |
| Indications for Use | Brainomix Triage LVO is a notification-only, parallel workflow tool for use by hospital networks and trained clinicians to identify and communicate images of specific patients to a specialist, independent of standard of care workflow.Brainomix Triage LVO uses an artificial intelligence algorithm to analyze images for findings suggestive of a prespecified clinical condition and to notify an appropriate medical specialist of these findings in parallel to standard of care image interpretation. | Viz LVO is a notification-only, parallel workflow tool for use by hospital networks and trained clinicians to identify and communicate images of specific patients to a specialist, independent of standard of care workflow.Viz LVO uses an artificial intelligence algorithm to analyze images for findings suggestive of a prespecified clinical condition and to notify an appropriate medical specialist of these findings in parallel to standard of care image interpretation. Identification of suspected |
| Identification of suspectedfindings is not for diagnosticuse beyond notification.Specifically, the deviceanalyzes CT angiogram imagesof the brain acquired in theacute setting, and sendsnotifications to aneurovascular specialist that asuspected large vesselocclusion LVO has beenidentified and recommendsreview of those images.Images can be previewedthrough a mobile application.Brainomix Triage LVO isintended to analyze terminalICA and MCA-M1 vessels forLVOs.Images that are previewedthrough the mobile applicationare compressed and are forinformational purposes onlyand not intended fordiagnostic use beyondnotification. Notified cliniciansare responsible for viewingnoncompressed images on adiagnostic viewer andengaging in appropriatepatient evaluation andrelevant discussion with atreating physician beforemaking care-related decisionsor requests.Brainomix Triage LVO is limitedto analysis of imaging data andshould not be used in-lieu offull patient evaluation or reliedupon to make or confirmdiagnosis. | findings is not for diagnosticuse beyond notification.Specifically, the deviceanalyzes CT angiogram imagesof the brain acquired in theacute setting, and sendsnotifications to aneurovascular specialist that asuspected large vesselocclusion has been identifiedand recommends review ofthose images. Images can bepreviewed through a mobileapplication. Viz LVO isintended to analyze terminalICA and MCA-M1 vessels forLVOs.Images that are previewedthrough the mobile applicationare compressed and are forinformational purposes onlyand not intended fordiagnostic use beyondnotification. Notified cliniciansare responsible for viewingnoncompressed images on adiagnostic viewer andengaging in appropriatepatient evaluation andrelevant discussion with atreating physician beforemaking care-related decisionsor requests.Viz LVO is limited to analysis ofimaging data and should notbe used in-lieu of full patientevaluation or relied upon tomake or confirm diagnosis. | |
| Environment of useEnergy used and/or delivered | Clinical/Hospital environmentNone - software onlyapplication. The softwareapplication does not deliver ordepend on energy delivered toor from patients | Clinical/Hospital environmentNone - software onlyapplication. The softwareapplication does not deliver ordepend on energy delivered toor from patients |
| Primary Users | Neurovascular Specialist | Neurovascular Specialist |
| Anatomical Region | Head | Head |
| Technical Implementation | Artificial intelligence algorithmwith database of images | Same |
| Diagnostic application | Notification-only | Notification-only |
| Segmentation of region ofinterest | No; the device does not mark,highlight, or direct users'attention to a specific locationin the original image | Internal, no image marking |
| Alteration of original image | No | No |
| Preview Images | Presentation of a preview ofthe study for initialinformational purposes | Same |
| Interference with standardworkflow | No. Cases are not removedfrom worklist or deprioritized | Same |
| Notification | Mobile application and webuser interface | Mobile |
| Design: DICOM compliance | Yes | Yes |
| Design: Computer Platform | Standard off-the-shelf serveror virtual server | Same |
| Design: Data acquisition | Acquires medical image datafrom DICOM compliantimaging devices and modalities | Same |
| Materials | N/A - Software only device | Same |
| Biocompatibility | N/A - Software only device | Same |
| Sterility | N/A - Software only device | Same |
| Electrical Safety | N/A - Software only device | Same |
| Mechanical Safety | N/A - Software only device | Same |
| Chemical Safety | N/A - Software only device | Same |
| Thermal Safety | N/A - Software only device | Same |
| Radiation Safety | N/A - Software only device | Same |
A table comparing the key features of the subject and predicate devices is provided below.
{13}------------------------------------------------
Image /page/13/Picture/0 description: The image shows the logo for BRAINOMIX. The logo consists of a stylized brain icon on the left, followed by the word "BRAINOMIX" in a sans-serif font. The brain icon is teal, and the word "BRAINOMIX" is dark gray, except for the "AI" which is teal.
{14}------------------------------------------------
Image /page/14/Picture/0 description: The image shows the logo for BRAINOMIX. The logo consists of a stylized brain icon on the left, followed by the word "BRAINOMIX" in a sans-serif font. The brain icon is a gradient of blue and green, while the letters "AI" in the word "BRAINOMIX" are also in the same gradient of blue and green.
8 Conclusion
In conclusion, Brainomix 360 Triage LVO has the same intended use and is substantially equivalent in technological characteristics, safety, and performance characteristics to the legally marketed predicate device, Viz LVO (K223042). Brainomix 360 Triage LVO is therefore substantially equivalent to the selected legally marketed predicate device and does not raise any questions of safety or effectiveness.
§ 892.2080 Radiological computer aided triage and notification software.
(a)
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.(b)
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.