(146 days)
RAPID ICH is a radiological computer aided triage and notification software indicated for use in the analysis of nonenhanced head CT images.
The device is intended to assist hospital networks and trained radiologists in workflow triage by flagging and communication of suspected positive findings of pathologies in head CT images, namely Intracranial Hemorrhage (ICH). RAPID ICH uses an artificial intelligence algorithm to analyze images and highlight cases with detected ICH on a server or standalone desktop application in parallel to the ongoing standard of care image interpretation. The user is presented with notifications for cases with suspected ICH findings. Notifications include compressed preview images, that are meant for informational purposes only and not intended for diagnostic use beyond notification. The device does not alter the original medical image and is not intended to be used as a diagnostic device.
The results of RAPID ICH are intended to be used in conjunction with other patient information and based on professional judgment, to assist with triage /prioritization of medical images. Notified clinicians are responsible for viewing full images per the standard of care.
RAPID ICH is a clinical module which operates within the integrated RAPID Platform to provide triage and notification of suspected intra-cranial hemorrhage (ICH). The RAPID ICH module consists of the core RAPID Platform software which provides the administration and services for the RAPID; and the RAPID ICH module which functions as one of many image processing modules hosted by the platform.
The RAPID platform is a software package that provides for the visualization and study of changes in tissue using digital images captured by diagnostic imaging systems including CT (Computed Tomography), CTA, XA3D and MRI (Magnetic Image Resonance), as an aid to physician diagnosis. RAPID can be installed on a customer's Server or it can be accessed online as virtual system. It provides viewing, quantification, analysis and reporting capabilities. The RAPID platform has multiple modules a clinician may elect to run and provide analysis for decision making.
RAPID ICH provides an automatic analysis of received NCCT scan data for the triage and notification of ischemic hemorrhage (ICH). The application is selected via DICOM encoding which is processed by the DICOM handler within the RAPID Platform. Once the DICOM server identifies the selected ICH processing modality, the Job Manager initiates image processing using the ICH Module.
Upon processing a case with suspicion of ICH, the clinical team is notified via messaging, the case has a suspicion of ICH. The notifications are sent to the PACS/Workstation, via email and to a mobile application. The notification provides the attending clinical team physician that suspicion of hemorrhage has been identified and immediate attention to the case should be given. The messaging provides notification and compressed image data of the case. The compressed preview is informational only and labeling identifies it as not to be used for diagnostic use and to review the data within the PACS/Workstation prior to making any diagnostic decisions. No additional information markings are added to the case.
The notifications are pop-up messages or email with the appropriate case information and suspicion or non-suspicion of ICH labelled. In all cases, the normal standard of care workflow is adhered to, this ensures the case is still reviewed when non-suspicion is determined.
Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary for RAPID ICH:
Acceptance Criteria and Device Performance
1. Table of Acceptance Criteria and the Reported Device Performance
| Metric | Acceptance Criteria (Performance Goal) | Reported Device Performance | 95% Confidence Interval |
|---|---|---|---|
| Sensitivity | > 80% | 0.899 | (0.847 - 0.935) |
| Specificity | > 80% | 0.943 | (0.895 - 0.970) |
| Time to Notification | Not explicitly stated as a hard acceptance criterion, but a secondary endpoint aim. | 2.28 minutes | (2.24 - 2.33) |
2. Sample Size and Data Provenance
- Test Set Sample Size: 336 cases
- Data Provenance: Retrospective, blinded, multicenter, multinational study.
- Countries of Origin: US (4 Sites and 1 Multisite Study) and OUS (1 site, 1 multisite).
- Nature of Study: Retrospective.
- Case Distribution: Approximately an equal number of positive cases (images with ICH) and negative cases (images without ICH) were included in the analysis.
3. Number of Experts and Qualifications for Ground Truth
The document states "reader truthing of the data" was used, but it does not explicitly state the number of experts or their specific qualifications (e.g., "radiologist with 10 years of experience") for establishing the ground truth of the test set.
4. Adjudication Method for the Test Set
The document mentions "reader truthing," but it does not specify the adjudication method used (e.g., 2+1, 3+1, none) for the test set.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No MRMC comparative effectiveness study was done or reported. The study focused on the standalone performance of the AI algorithm. Therefore, there is no information on how human readers improve with AI vs without AI assistance.
6. Standalone (Algorithm Only) Performance Study
Yes, a standalone (algorithm only) performance study was conducted. The entire "Performance Data" section describes the RAPID ICH software's ability to identify ICH independently, reporting its sensitivity and specificity.
7. Type of Ground Truth Used
The ground truth for the test set was established through "reader truthing of the data." This implies expert consensus or expert interpretation as the basis for ground truth, rather than pathology or outcomes data.
8. Sample Size for the Training Set
The document does not explicitly state the sample size used for the training set. It only mentions that the device uses a "deep learning algorithm trained on medical images."
9. How the Ground Truth for the Training Set Was Established
The document does not explicitly detail how the ground truth for the training set was established. It generally states the algorithm was "trained on medical images," implying that these images were annotated or labeled with ground truth information (e.g., presence or absence of ICH) by experts, but the process or expert involvement is not described.
§ 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.