(165 days)
No reference devices were used in this submission.
Yes
The document explicitly states that the device uses an "artificial intelligence (AI) algorithm" which is a "convolutional neural network trained using deep-learning techniques."
No.
The device is designed to aid in triage and prioritization of studies by identifying features suggestive of certain findings, but it is not intended to directly treat or prevent a disease or condition. It is a workflow tool to prioritize radiological images.
Yes
Explanation: The device identifies findings such as acute subdural/epidural hematoma, acute subarachnoid hemorrhage, intra-axial hemorrhage, and intraventricular hemorrhage from non-contrast brain CT studies. While it is not intended for standalone clinical decision-making, its primary function is to identify and prioritize studies with "features suggestive of" these findings, which are diagnostic indicators. The device also provides performance metrics like sensitivity and specificity, typically associated with diagnostic devices.
Yes
The device description explicitly states "Annalise Enterprise CTB Triage Trauma is a software workflow tool". It processes existing medical images and interfaces with other software systems (PACS/RIS) without mentioning any dedicated hardware components included with the device itself.
Based on the provided information, this device is not an In Vitro Diagnostic (IVD).
Here's why:
- IVDs analyze biological samples: In Vitro Diagnostics are designed to examine specimens taken from the human body, such as blood, urine, or tissue, to provide information about a person's health.
- This device analyzes medical images: The Annalise Enterprise device analyzes non-contrast brain CT studies, which are medical images, not biological samples.
- The intended use is image analysis for triage: The primary function described is to analyze images using an AI algorithm to identify potential findings and aid in the prioritization of studies for review. This is a function related to medical imaging interpretation workflow, not the analysis of biological specimens.
Therefore, based on the definition and typical scope of In Vitro Diagnostics, this device falls outside of that category. It is a medical device that utilizes artificial intelligence for image analysis and workflow support in radiology.
No
The provided text does not contain any explicit statement that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device.
Intended Use / Indications for Use
Intended context:
Annalise Enterprise is a device designed to be used in the medical care environment to aid in triage and prioritization of studies with features suggestive of the following findings:
- acute subdural/ epidural hematoma*
- acute subarachnoid hemorrhage *
- intra-axial hemorrhage*
- intraventricular hemorrhage*
*These findings are intended to be used together as one device.
The device analyzes studies using an artificial intelligence algorithm to identify findings. It makes study-level output available to an order and imaging management system for worklist prioritization or triage.
The device is not intended to direct attention to specific portions of an image and only provides notification for suspected findings. Its results are not intended:
- to be used on a standalone basis for clinical decision making
- to rule out specific findings, or otherwise preclude clinical assessment . of CTB studies
Intended modality: Annalise Enterprise identifies suspected findings in non-contrast brain CT studies.
Product codes
QAS
Device Description
Annalise Enterprise CTB Triage Trauma is a software workflow tool which uses an artificial intelligence (Al) algorithm to identify suspected findings on non-contrast brain CT studies in the medical care environment. The findings identified by the device include acute subdural/ epidural hematoma, acute subarachnoid hemorrhage, intra-axial hemorrhage, and intraventricular hemorrhage.
Radiological findings are identified by the device using an AI algorithm - a convolutional neural network trained using deep-learning techniques. Images used to train the algorithm were sourced from datasets that included a range of equipment manufacturers including Toshiba, GE Medical Systems, Siemens, Philips, and Canon Medical Systems. This dataset, which contained over 200,000 CT brain imaging studies, was labelled by trained radiologists regarding the presence of the four findings of interest.
The performance of the device's AI algorithm was validated in a standalone performance evaluation, 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 truther used in the event of disagreement. All truthers were US board-certified neuroradiologists.
The device interfaces with image and order management systems (such as PACS/RIS) to obtain noncontrast brain CT studies for processing by the AI algorithm. Following processing, if any of the clinical findings of interest are identified in a non-contrast brain CT study, the device provides a notification to the image and order management system for prioritization of that study in the worklist. This enables users to review the studies containing features suggestive of these clinical findings earlier than in the standard clinical workflow. It is important to note that the device will never decrease a study's existing priority in the worklist. This ensures that worklist items will never have their priorities downgraded based on AI results.
The device workflow is performed parallel to and in conjunction with the standard clinical workflow for interpretation of non-contrast brain CTs. The device is intended to aid in prioritization and triage of radiological medical images only.
Mentions image processing
The device analyzes studies using an artificial intelligence algorithm to identify findings. It makes study-level output available to an order and imaging management system for worklist prioritization or triage.
The device interfaces with image and order management systems (such as PACS/RIS) to obtain noncontrast brain CT studies for processing by the AI algorithm.
Mentions AI, DNN, or ML
Annalise Enterprise CTB Triage Trauma is a software workflow tool which uses an artificial intelligence (Al) algorithm to identify suspected findings on non-contrast brain CT studies in the medical care environment.
Radiological findings are identified by the device using an AI algorithm - a convolutional neural network trained using deep-learning techniques.
The device analyzes studies using an artificial intelligence algorithm to identify findings.
Input Imaging Modality
non-contrast brain CT studies
Anatomical Site
brain
Indicated Patient Age Range
The intended population is patients who are 22 years or older.
Intended User / Care Setting
Intended user: The device is intended to be used by trained clinicians who, as part of their scope of practice, are qualified to interpret brain CT studies.
Intended context: Annalise Enterprise is a device designed to be used in the medical care environment to aid in triage and prioritization of studies with features suggestive of the following findings:
Description of the training set, sample size, data source, and annotation protocol
Images used to train the algorithm were sourced from datasets that included a range of equipment manufacturers including Toshiba, GE Medical Systems, Siemens, Philips, and Canon Medical Systems. This dataset, which contained over 200,000 CT brain imaging studies, was labelled by trained radiologists regarding the presence of the four findings of interest.
Description of the test set, sample size, data source, and annotation protocol
The test dataset used during the standalone performance evaluation was newly acquired and independent from the training dataset used in model development. The standalone performance study was conducted on four independently assessed cohorts which equated to a total dataset of 1,485 cases for slice thickness ≤1.5mm (positive n=1,003 and negative n=482) and 1,878 cases for slice thickness >1.5mm (positive n=1,257 and negative n=621), collected consecutively from five US hospital network sites.
The performance testing datasets included representation across subgroups for patient demographics (gender [female: 44.9-52.2%, male: 47.8-55.1%], age [mean: 66.5-68.0 years, min: 22, max: 99-105], ethnicity [Hispanic: 5.9-11.3%], race [White/Caucasian: 76.6-82.1%, Other: 13.6-19.3%, Unknown: 2.7-6.9%]), co-existing findings or abnormalities and technical parameters (imaging equipment make, model). The datasets included GE Healthcare, Siemens and Toshiba CT scanners for the pivotal study. Additional analyses were conducted with GE, Philips, Siemens and Toshiba scanners to demonstrate the generalizability of the device.
To determine the ground truth, each deidentified case was annotated in a blinded fashion by at least two ABR-certified and protocol-trained neuroradiologists (ground truthers), with consensus determined by two ground truthers and a third ground truther in the event of disagreement.
Summary of Performance Studies
Performance of the subject device was assessed in four performance studies to satisfy requirements set forth in the special controls per 21CFR892.2080. These included standalone performance and triage effectiveness evaluations.
Standalone performance was assessed via a retrospective, anonymized study of adult patient, DICOMcompliant non-contrast brain CT cases. The test dataset used during the standalone performance evaluation was newly acquired and independent from the training dataset used in model development. The standalone performance study was conducted on four independently assessed cohorts which equated to a total dataset of 1,485 cases for slice thickness ≤1.5mm (positive n=1,003 and negative n=482) and 1,878 cases for slice thickness >1.5mm (positive n=1,257 and negative n=621), collected consecutively from five US hospital network sites.
The performance testing datasets included representation across subgroups for patient demographics (gender [female: 44.9-52.2%, male: 47.8-55.1%], age [mean: 66.5-68.0 years, min: 22, max: 99-105], ethnicity [Hispanic: 5.9-11.3%], race [White/Caucasian: 76.6-82.1%, Other: 13.6-19.3%, Unknown: 2.7-6.9%]), co-existing findings or abnormalities and technical parameters (imaging equipment make, model). The datasets included GE Healthcare, Siemens and Toshiba CT scanners for the pivotal study. Additional analyses were conducted with GE, Philips, Siemens and Toshiba scanners to demonstrate the generalizability of the device.
Key results are summarized in the table below. The results demonstrate the subject device establishes effective triage within a clinician's queue based on high sensitivity and specificity. Further, these results are substantially equivalent to those of the predicate device.
Triage effectiveness (turn-around time) was assessed by an internal bench study using a dataset of n=277 cases positive for any of the findings eligible for prioritization. These cases were collected from multiple data sources spanning a variety of geographical locations, patient demographics and technical characteristics. The results demonstrated a triage turn-around time of 81.6 (95% CI: 80.3 - 82.9) seconds, which is substantially equivalent to the total performance time published for the predicate device.
Key Metrics
| Finding | Slice Thickness Range | Operating Point | Sensitivity % (Se) (95% CI) | Specificity % (Sp) (95% CI) |
|---|---|---|---|---|
| Acute subdural/ Epidural hematoma | 1.5mm & ≤5.0mm | 0.060177 | 82.4 (78.6,86.1) | 89.6 (83.7,94.8) |
| Acute subarachnoid hemorrhage | 1.5mm & ≤5.0mm | 0.020255 | 90.7 (86.3,95.1) | 92.4 (86.7,97.1) |
| 0.030010 | 87.4 (82.4,91.8) | 96.2 (92.4,99.0) | ||
| Intra-axial hemorrhage | 1.5mm & ≤5.0mm | 0.203600 | 93.4 (91.3,95.1) | 85.1 (80.9,88.9) |
| 0.322700 | 90.3 (87.9,92.5) | 90.3 (86.8,93.8) | ||
| Intraventricular hemorrhage | 1.5mm & ≤5.0mm | 0.008430 | 95.6 (91.2,98.9) | 86.0 (78.5,92.5) |
| 0.015487 | 92.3 (86.8,96.7) | 89.2 (82.8,94.6) | ||
| 0.051859 | 87.9 (80.2,94.5) | 97.8 (94.6,100.0) |
Predicate Device(s)
Reference Device(s)
No reference devices were used in this submission.
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 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.
0
April 3, 2023
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, followed by the words "U.S. FOOD & DRUG" and "ADMINISTRATION".
Annalise-AI Pty Ltd. % Haylee Bosshard Regulatory Affairs Manager Level P. 24 Campbell Street Sydney. New South Wales 2000 AUSTRALIA
Re: K223240
Trade/Device Name: Annalise Enterprise CTB Triage Trauma Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological computer aided triage and notification software Regulatory Class: Class II Product Code: QAS Dated: March 1, 2023 Received: March 1, 2023
Dear Haylee Bosshard:
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 (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Lu Jiang
for
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
2
Indications for Use
510(k) Number (if known) K223240
Device Name
Annalise Enterprise CTB Triage Trauma
Indications for Use (Describe)
Intended context:
Annalise Enterprise is a device designed to be used in the medical care environment to aid in triage and prioritization of studies with features suggestive of the following findings:
- · acute subdural/epidural hematoma*
· acute subarachnoid hemorrhage *
· intra-axial hemorrhage*
· intraventricular hemorrhage*
*These findings are intended to be used together as one device.
The device analyzes studies using an artificial intelligence algorithm to identify findings. It makes study-level output available to an order and imaging management system for worklist prioritization or triage.
The device is not intended to direct attention to specific portions of an image and only provides notification for suspected findings.
Its results are not intended:
· to be used on a standalone basis for clinical decision making
· to rule out specific findings, or otherwise preclude clinical assessment of CTB studies
Intended modality:
Annalise Enterprise identifies suspected findings in non-contrast brain CT studies.
Intended user:
The device is intended to be used by trained clinicians who, as part of their scope of practice, are qualified to interpret brain CT studies.
Intended patient population:
The intended population is patients who are 22 years or older.
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.
3
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."
4
K223240
510(k) Summary
I. SUBMITTER
| Company Name | Annalise-AI Pty Ltd |
|---|---|
| Address | Level P, 24 Campbell Street |
| Sydney, NSW 2000 | |
| Australia | |
| Phone Number | +61 1800-958487 |
| Contact Person | Haylee Bosshard |
| Date Prepared | March 31, 2023 |
II. SUBJECT DEVICE
| Manufacturer Name | Annalise-AI Pty Ltd |
|---|---|
| Device Name | Annalise Enterprise CTB Triage Trauma |
| Classification Name | Radiological computer aided triage and notification software |
| (21CFR892.2080) | |
| Regulatory Class | II |
| Product Code | QAS |
PREDICATE DEVICE III.
| Manufacturer Name | Infervision Medical Technology Co., Ltd. |
|---|---|
| Device Name | InferRead CT Stroke.AI |
| 510(k) reference | K211179 |
| Classification Name | Radiological computer aided triage and notification software |
| (21CFR892.2080) | |
| Regulatory Class | II |
| Product Code | QAS |
This predicate has not been subject to a design-related recall. No reference devices were used in this submission.
5
DEVICE DESCRIPTION IV.
Annalise Enterprise CTB Triage Trauma is a software workflow tool which uses an artificial intelligence (Al) algorithm to identify suspected findings on non-contrast brain CT studies in the medical care environment. The findings identified by the device include acute subdural/ epidural hematoma, acute subarachnoid hemorrhage, intra-axial hemorrhage, and intraventricular hemorrhage.
Radiological findings are identified by the device using an AI algorithm - a convolutional neural network trained using deep-learning techniques. Images used to train the algorithm were sourced from datasets that included a range of equipment manufacturers including Toshiba, GE Medical Systems, Siemens, Philips, and Canon Medical Systems. This dataset, which contained over 200,000 CT brain imaging studies, was labelled by trained radiologists regarding the presence of the four findings of interest.
The performance of the device's AI algorithm was validated in a standalone performance evaluation, 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 truther used in the event of disagreement. All truthers were US board-certified neuroradiologists.
The device interfaces with image and order management systems (such as PACS/RIS) to obtain noncontrast brain CT studies for processing by the AI algorithm. Following processing, if any of the clinical findings of interest are identified in a non-contrast brain CT study, the device provides a notification to the image and order management system for prioritization of that study in the worklist. This enables users to review the studies containing features suggestive of these clinical findings earlier than in the standard clinical workflow. It is important to note that the device will never decrease a study's existing priority in the worklist. This ensures that worklist items will never have their priorities downgraded based on AI results.
The device workflow is performed parallel to and in conjunction with the standard clinical workflow for interpretation of non-contrast brain CTs. The device is intended to aid in prioritization and triage of radiological medical images only.
6
INDICATIONS FOR USE V.
The Indications for Use statement is as follows:
Intended context Annalise Enterprise is a device designed to be used in the medical care environment to aid in triage and prioritization of studies with features suggestive of the following findings:
- acute subdural/ epidural hematoma* ●
- acute subarachnoid hemorrhage * ●
- intra-axial hemorrhage* ●
- intraventricular hemorrhage*
*These findings are intended to be used together as one device.
The device analyzes studies using an artificial intelligence algorithm to identify findings. It makes study-level output available to an order and imaging management system for worklist prioritization or triage.
The device is not intended to direct attention to specific portions of an image and only provides notification for suspected findings. Its results are not intended:
- to be used on a standalone basis for clinical decision making ●
- to rule out specific findings, or otherwise preclude clinical assessment . of CTB studies
Intended Annalise Enterprise identifies suspected findings in non-contrast brain CT modalitv studies. The device is intended to be used by trained clinicians who, as part of their Intended user scope of practice, are qualified to interpret brain CT studies. Intended patient The intended population is patients who are 22 years or older.
population
The Indications for Use statement of the subject device differs to the predicate device only in the clinical conditions of interest, however a standalone performance evaluation was conducted and demonstrated that the device is as safe and effective for its intended use. Both the subject and predicate device are intended for use to assist with worklist triage by providing notifications of suspected findings and their associated priority.
7
VI. COMPARISON OF TECHNOLOGICAL CHARACTERISTICS WITH THE PREDICATE DEVICE
The subject device was evaluated and compared to the predicate device with respect to the following characteristics:
-
- Indications for Use
-
- Anatomical site and modality
-
- Intended user and clinical use environment
-
- Technical method for notification and prioritization
-
- Device input and radiological image protocol
-
- System components
-
- Location where results are received
-
- Prioritization relationship to standard of care workflow
-
- Ability to support effective triage
-
- Device output and means of notification to user
The following characteristics showed a difference between the subject and predicate devices. The different characteristics include:
-
- Set of findings and algorithm
The difference between the subject and predicate device is the set of findings that the subject device identifies and the underlying artificial intelligence algorithm. The performance of the subject device algorithm for each of the findings was addressed in a standalone performance evaluation and showed that the subject device is as safe and effective for its intended use as the predicate device.
- Set of findings and algorithm
8
VII. PERFORMANCE DATA
The following performance data have been provided to support evaluation of substantial equivalence.
Software Verification and Validation Testing A.
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 B.
Performance of the subject device was assessed in four performance studies to satisfy requirements set forth in the special controls per 21CFR892.2080. These included standalone performance and triage effectiveness evaluations.
Standalone performance was assessed via a retrospective, anonymized study of adult patient, DICOMcompliant non-contrast brain CT cases. The test dataset used during the standalone performance evaluation was newly acquired and independent from the training dataset used in model development. The standalone performance study was conducted on four independently assessed cohorts which equated to a total dataset of 1,485 cases for slice thickness ≤1.5mm (positive n=1,003 and negative n=482) and 1,878 cases for slice thickness >1.5mm (positive n=1,257 and negative n=621), collected consecutively from five US hospital network sites.
The performance testing datasets included representation across subgroups for patient demographics (gender [female: 44.9-52.2%, male: 47.8-55.1%], age [mean: 66.5-68.0 years, min: 22, max: 99-105], ethnicity [Hispanic: 5.9-11.3%], race [White/Caucasian: 76.6-82.1%, Other: 13.6-19.3%, Unknown: 2.7-6.9%]), co-existing findings or abnormalities and technical parameters (imaging equipment make, model). The datasets included GE Healthcare, Siemens and Toshiba CT scanners for the pivotal study. Additional analyses were conducted with GE, Philips, Siemens and Toshiba scanners to demonstrate the generalizability of the device.
To determine the ground truth, each deidentified case was annotated in a blinded fashion by at least two ABR-certified and protocol-trained neuroradiologists (ground truthers), with consensus determined by two ground truthers and a third ground truther in the event of disagreement. The key results of the study are summarized in the table below.
9
| Finding | Slice Thickness Range | Operating Point | Sensitivity % (Se)
(95% CI) | Specificity % (Sp)
(95% CI) |
|--------------------------------------|-----------------------|-----------------|--------------------------------|--------------------------------|
| Acute subdural/ Epidural
hematoma | 1.5mm & ≤5.0mm | 0.060177 | 82.4 (78.6,86.1) | 89.6 (83.7,94.8) |
| Acute subarachnoid
hemorrhage | 1.5mm & ≤5.0mm | 0.020255 | 90.7 (86.3,95.1) | 92.4 (86.7,97.1) |
| | | 0.030010 | 87.4 (82.4,91.8) | 96.2 (92.4,99.0) |
| Intra-axial hemorrhage | 1.5mm & ≤5.0mm | 0.203600 | 93.4 (91.3,95.1) | 85.1 (80.9,88.9) |
| | | 0.322700 | 90.3 (87.9,92.5) | 90.3 (86.8,93.8) |
| Intraventricular hemorrhage | 1.5mm & ≤5.0mm | 0.008430 | 95.6 (91.2,98.9) | 86.0 (78.5,92.5) |
| | | 0.015487 | 92.3 (86.8,96.7) | 89.2 (82.8,94.6) |
| | | 0.051859 | 87.9 (80.2,94.5) | 97.8 (94.6,100.0) |
The results demonstrate the subject device establishes effective triage within a clinician's queue based on high sensitivity and specificity. Further, these results are substantially equivalent to those of the predicate device.
Triage effectiveness (turn-around time) was assessed by an internal bench study using a dataset of n=277 cases positive for any of the findings eligible for prioritization. These cases were collected from multiple data sources spanning a variety of geographical locations, patient demographics and technical characteristics. The results demonstrated a triage turn-around time of 81.6 (95% CI: 80.3 - 82.9) seconds, which is substantially equivalent to the total performance time published for the predicate device.
Therefore, the subject device has been shown to satisfy the performance requirements per 21CFR892.2080, for 'Radiological computer aided triage and notification software', by providing clinically effective triage for non-contrast brain CT studies containing features suggestive of clinical findings of interest. This data demonstrates the subject device is safe and effective for its intended use, and thereby supports substantial equivalence.
10
VIII.CONCLUSIONS
The subject device and the predicate device are both software only packages, devices intended to assist with worklist triage by providing notification of findings. The subject and predicate devices utilize the same principles of operation and work in parallel to the current standard of care workflow.
Both the subject and predicate devices use an artificial intelligence algorithm to identify findings in images and require the same inputs (DICOM image data) and provide the same outputs (prioritization for a medical worklist).
The technological differences between the subject and predicate devices do not raise new questions of safety and effectiveness.
Standalone performance testing and the comparison of technological characteristics with the predicate devices shows that the subject device:
- performs as intended, ●
- is safe and effective for its intended use, and
- is therefore substantially equivalent to the predicate device. ●