Search Results

EFAI ICHCT is a software workflow tool designed to aid in prioritizing the clinical assessment of adult non-contrast head CT cases with features suggestive of acute intracranial hemorrhage (ICH). EFAI ICHCT analyzes cases using deep learning algorithms to identify suspected ICH findings. It makes case-level output available to a PACS/workstation for worklist prioritization or triage.

EFAI ICHCT is not intended to direct attention to specific portions of an image or to anomalies other than acute ICH. Its results are not intended to be used on a stand-alone basis for clinical decision-making nor is it intended to rule out hemorrhage or otherwise preclude clinical assessment of CT studies.

EFAI NEUROSUITE CT ICH ASSESSMENT SYSTEM (EFAI ICHCT) is a radiological computer-assisted triage and notification software system. The software uses deep learning techniques to automatically analyze non-contrast head CTs and alerts the PACS/RIS workstation once images with features suggestive of acute ICH are identified.

Through the use of EFAI ICHCT, a radiologist is able to review studies with features suggestive of acute ICH earlier than in standard of care workflow.

The device is intended to provide a passive notification through the PACS/workstation to the radiologists indicating the existence of a case that may potentially benefit from the prioritization. It does not mark, highlight, or direct users' attention to a specific location on the original non-contrast head CT. The device aims to aid in prioritization and triage of radiological medical images only.

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

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance

• Test Set Sample Size: 288 CT studies (132 ICH positives and 156 ICH negatives).
• Data Provenance: Retrospective, consecutively collected from 23 clinical sites in the United States (U.S.). None of these studies were used in model development or analytical validation.

3. Number and Qualifications of Experts for Ground Truth

• Number of Experts: Three (3)
• Qualifications of Experts: U.S. board-certified neuroradiologists. (Specific years of experience are not mentioned, but board certification implies significant expertise).

4. Adjudication Method for the Test Set

• Method: Majority agreement between the three experts.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• Was it done? No. The provided text describes a standalone performance validation study. The closest mention of human interaction is that the device "can provide case-level notifications with features suggestive of ICH with satisfactory results" in the "absence of any interaction with a clinician."

6. Standalone Performance (Algorithm Only)

• Was it done? Yes. The study details "the standalone performance validation study demonstrated that EFAI ICHCT by itself, in the absence of any interaction with a clinician, can provide case-level notifications with features suggestive of ICH with satisfactory results."

7. Type of Ground Truth Used

• Type of Ground Truth: Expert consensus (majority agreement of three U.S. board-certified neuroradiologists).

8. Sample Size for the Training Set

• Training Set Sample Size: 3,776 cases. (There was also a validation set of 1,038 cases and a separate test set of 551 cases from the initial collection for model development, distinct from the clinical validation test set).

9. How Ground Truth for the Training Set Was Established

• The text states, "During the process of model development, a total of 5,365 adult cases were retrospectively collected between 2010 and 2018 from Taiwan."
• While it mentions these cases were "subsequently divided into training, validation, and testing datasets," the method for establishing ground truth specifically for the training set is not explicitly detailed in the provided text. It can be inferred that a similar process of expert review would have been used, but the number of experts or adjudication method for the training data is not specified.

Ask a specific question about this device