(147 days)
Hyper Insight - ICH is a notification-only workflow tool for trained clinicians to identify patients' brain CT images and share them with medical specialists in parallel with standard patient care workflow. Hyper Insight - ICH uses deep learning-based AI algorithms to analyze images to find suspected intracranial hemorrhage and notifies and shares the findings to medical specialists. Identification of images with suspected intracranial hemorrhage is for notification purposes only, not diagnostic purposes.
In particular, this medical device analyzes non-contrast brain CT images, and if a suspected intracranial hemorrhage is identified, it sends a notification to medical specialists, who are advised to review these images may be previewed through the mobile app but are for informational purposes only and are not intended to be used for diagnostic purposes other than notifications and previews. The medical specialist who received the notification is responsible for reading the image in a diagnostic viewer.
Hyper Insight - ICH is limited to the purpose of analysis of image data and should not be used as a substitute for a full patient assessment or relied upon to make or confirm a diagnosis.
Hyper Insight - ICH is software as a medical device (SaMD) that detects intracranial hemorrhage (ICH) condition by analyzing non-contrast CT images. The software needs to be integrated with a third-party worklist application to receive analysis requests and the corresponding DICOM images and return the ICH findings (whether suspected ICH is found) to the worklist to alert the radiologists.
To help radiologists triage and prioritize reading of images for patients with ICH, Hyper Insight - ICH uses deep learning methods to automatically detect acute ICH in non-contrast head CT scans.
The software analyzes the input image and returns a binary prediction as to whether the exam suggests the presence of acute ICH. The Hyper Insight-ICH device is for notification purposes only and should be not used for final diagnosis.
Here's a summary of the acceptance criteria and study details for the Hyper Insight - ICH device, based on the provided text:
Acceptance Criteria and Device Performance
| Metric | Acceptance Criteria (Lower Bound of 95% CI) | Reported Device Performance [95% CI] |
|---|---|---|
| Sensitivity | ≥ 80% | 95.45% [91.55, 97.90] |
| Specificity | ≥ 80% | 98.47% [95.59, 99.68] |
| AUC of ROC | Not explicitly stated, but high AUC generally desired | 0.9864 [0.9738, 0.9989] |
| Average time to alerting a specialist | Not explicitly stated, but faster is better than predicate | 16.39 ± 5.46 seconds (0.27 ± 0.091 minutes) |
Conclusion: The study met the pre-specified performance goals for sensitivity and specificity, as the lower bound of each confidence interval exceeded 80%.
Study Details
1. Sample Size for the Test Set and Data Provenance:
- Sample Size: 394 brain Computed Tomography (CT) images.
- Data Provenance: Obtained from 13 clinical sites in the U.S.
- Retrospective/Prospective: Retrospective study.
2. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:
- Number of Experts: Not explicitly stated as a specific number, but referred to as "trained neuro-radiologists" and a "Reference Standard Establishment Committee."
- Qualifications: "Trained neuro-radiologists."
3. Adjudication Method for the Test Set:
- The text states the clinical sensitivity was "evaluated against the reading results of intracranial hemorrhage from brain CT images by the Reference Standard Establishment Committee." It doesn't specify a numerical adjudication method (e.g., 2+1, 3+1).
4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- Was it done? No, a traditional MRMC study comparing human readers with and without AI assistance was not conducted. The study evaluated the standalone performance of the AI algorithm.
- Effect Size: Not applicable, as an MRMC comparative effectiveness study was not performed.
5. Standalone Performance Study:
- Was it done? Yes, a standalone (algorithm only without human-in-the-loop performance) study was conducted. The device's sensitivity, specificity, and AUC were measured against an expert-established ground truth.
6. Type of Ground Truth Used:
- Expert consensus, established by a "Reference Standard Establishment Committee" comprised of "trained neuro-radiologists."
7. Sample Size for the Training Set:
- The document does not explicitly state the sample size for the training set. It only mentions the test set size.
8. How the Ground Truth for the Training Set Was Established:
- The document does not provide details on how the ground truth for the training set was established. It only describes the ground truth establishment for the test 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.