(176 days)
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
| Metric | Acceptance Criteria (Lower Bound of 95% CI) | Reported Device Performance (95% CI) | Met? |
|---|---|---|---|
| Sensitivity | > 0.8 | 0.947 (0.895 - 0.974) | Yes |
| Specificity | > 0.8 | 0.949 (0.902 - 0.974) | Yes |
| System Processing Time | Not explicitly stated (compared to predicate) | 34.96 seconds (33.89 - 36.03) | N/A |
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.
§ 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.