(53 days)
uAl Easy Triage ICH is a radiological computer-assisted triage and notification software device indicated for analysis of non-enhanced head CT images. The device is intended to assist hospital networks and trained radiologists in workflow triage by flagging and prioritizing studies with suspected positive findings of Intracranial Hemorrhage (ICH).
uAI Easy Triage ICH is a radiological computer-assisted triage and notification software intended to assist radiologists by flagging potential intracranial hemorrhage (ICH) in non-contrast head CT images. The Triage Software is a component of the uAI Easy Triage platform, a comprehensive medical imaging communication system designed to integrate and deploy specialized image processing applications.
The uAI Easy Triage ICH algorithm uses artificial intelligence CNN (convolutional neural networks) and advanced image processing to triage the non-contrast CT images for suspicious intracranial hemorrhage.
The uAI Easy Triage ICH alerts users to new studies with suspicious ICH findings via pop-up notifications. The software provides both active and passive notification mechanisms. Active notifications are presented as an alert icon with a count of pending cases, and an alert status bar displaying patient details, suspected findings, and the time of examination. Passive notifications are represented by an icon beside the patient's name in the list for cases with detected ICH findings. Additionally, the application offers a DICOM image preview feature for radiologists to review. This preview is strictly informational, devoid of diagnostic markers, and is not to be used for definitive diagnosis.
The uAI Easy Triage ICH embodies the core algorithmic technology that identifies image characteristics consistent with intracranial hemorrhage. The application reads DICOM files, verifies their compatibility with the prescribed acquisition protocols, executes the triage algorithm, and communicates findings in DICOM format, compatible with the uAI Easy Triage Platform.
Acceptance Criteria and Study Details for uAI Easy Triage ICH
1. Acceptance Criteria and Reported Device Performance
| Metric | Acceptance Criteria | Reported Device Performance (95% CI) |
|---|---|---|
| Sensitivity | ≥ 80% | 92% (86%-96%) |
| Specificity | ≥ 80% | 95% (90%-98%) |
| Time to Notification | Not explicitly stated as a numerical criterion, but noted as "similar to the predicate device's time" | 41.1 seconds (40.1, 42.1) (mean with 95% CI) |
Note: The document does not explicitly state a numerical acceptance criterion for "Time to Notification" but indicates that the device's performance is similar to the predicate device. The 80% acceptance criteria for sensitivity and specificity are mentioned in the text "exceeding the acceptance criteria of 80%."
2. Sample Size for Test Set and Data Provenance
- Sample Size: 295 non-contrast CT scans (studies)
- 147 positive for ICH
- 148 negative for ICH
- Data Provenance: Retrospective data obtained from different zip codes across four U.S. states.
3. Number of Experts and Qualifications for Ground Truth Establishment
- Number of Experts: 3 U.S.-board-certified neuroradiologists.
- Qualifications: U.S.-board-certified neuroradiologists. Specific years of experience are not mentioned.
4. Adjudication Method for the Test Set
- Adjudication Method: Majority read of the 3 U.S.-board-certified neuroradiologists. (Implies a "3+1" or similar consensus approach where at least two out of three experts agreed to establish the ground truth).
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- The document does not indicate that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done to assess human reader improvement with AI assistance. The study focuses on the standalone performance of the AI algorithm.
6. Standalone Algorithm Performance
- Yes, a standalone (algorithm only without human-in-the-loop performance) study was conducted. The reported sensitivity, specificity, and time to notification are for the uAI Easy Triage ICH software itself, compared to the expert-established ground truth.
7. Type of Ground Truth Used
- Expert Consensus: The ground truth was established by the majority read of 3 U.S.-board-certified neuroradiologists.
8. Sample Size for the Training Set
- Sample Size: 9791 data points (cases) were collected for training and internal testing.
9. How Ground Truth for the Training Set was Established
- The ground truth for the training set was established in the form of ICH positive/negative by radiologists. Specific details on the number or qualifications of these radiologists, or the adjudication method, are not provided for the training set.
§ 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.