(98 days)
Annalise Enterprise is a device designed to be used in the medical care environment to aid in triage and prioritization of studies with features suggestive of the following finding:
· vasogenic edema
The device analyzes studies using an artificial intelligence algorithm to identify the finding. It makes study-level output available to an order and imaging management system for worklist prioritization or triage.
The device is not intended to direct attention to specific portions of an image and only provides notification for the suspected finding.
Its results are not intended:
- · to be used on a standalone basis for clinical decision making
- · to rule out a specific finding, or otherwise preclude clinical assessment of CTB studies
Intended modality:
Annalise Enterprise identifies the suspected finding in non-contrast brain CT studies.
Intended user:
The device is intended to be used by trained clinicians who, as part of their scope of practice, are qualified to interpret brain CT studies.
Intended patient population: The intended population is patients who are 22 years or older.
Annalise Enterprise CTB Triage Trauma is a software workflow tool which uses an artificial intelligence (AI) algorithm to identify suspected findings on non-contrast brain CT studies in the medical care environment. The findings identified by the device include vasogenic edema.
Radiological findings are identified by the device using an AI algorithm - a convolutional neural network trained using deep-learning techniques. Images used to train the algorithm were sourced from datasets that included a range of equipment manufacturers and models. The performance of the device's AI algorithm was validated in a standalone performance evaluation, in which the case-level output from the device was compared with a reference standard ('ground truth'). This was determined by two ground truthers, with a third truther used in the event of disagreement. All truthers were US board-certified neuroradiologists.
The device interfaces with image and order management systems (such as PACS/RIS) to obtain noncontrast brain CT studies for processing by the AI algorithm. Following processing, if any of the radiological findings of interest are identified in a non-contrast brain CT study, the device provides a notification to the image and order management system for prioritization of that study in the worklist. This enables users to review the studies containing features suggestive of these radiological findings earlier than in the standard clinical workflow. It is important to note that the device will never decrease a study's existing priority in the worklist. This ensures that worklist items will never have their priorities downgraded based on AI results.
The device workflow is performed parallel to and in conjunction with the standard clinical workflow for interpretation of non-contrast brain CTs. The device is intended to aid in prioritization and triage of radiological medical images only.
Here is a detailed breakdown of the acceptance criteria and study that proves the device meets the acceptance criteria, based on the provided document.
1. Acceptance Criteria and Reported Device Performance
The core acceptance criteria for this device, a Radiological Computer-Aided Triage and Notification Software, are demonstrated through its standalone performance in identifying vasogenic edema. The performance is assessed using Sensitivity and Specificity at different operating points for two slice thickness ranges.
Table of Acceptance Criteria (Implicit) and Reported Device Performance for Vasogenic Edema Detection:
| Finding | Slice Thickness Range | Operating Point | Sensitivity % (Se) (95% CI) | Specificity % (Sp) (95% CI) |
|---|---|---|---|---|
| Vasogenic Edema | ≤1.5mm | 0.060584 | 91.7 (85.0, 98.3) | 89.7 (83.2, 95.3) |
| 0.094076 | 90.0 (81.7, 96.7) | 90.7 (85.0, 96.3) | ||
| 0.145352 | 90.0 (81.7, 96.7) | 93.5 (88.8, 97.2) | ||
| >1.5mm & ≤5.0mm | 0.060584 | 94.9 (89.9, 99.0) | 93.3 (89.7, 96.4) | |
| 0.094076 | 93.9 (88.9, 98.0) | 94.3 (90.7, 97.4) | ||
| 0.145352 | 90.9 (84.8, 96.0) | 95.4 (92.3, 97.9) | ||
| 0.261255 | 89.9 (83.8, 94.9) | 97.4 (94.8, 99.5) |
Beyond these specific metrics, an additional performance metric focused on Triage Effectiveness (Turn-around time) was assessed. The reported performance was:
- Triage Turn-around Time: 81.6 seconds (95% CI: 80.3 - 82.9)
The implication is that these reported values meet or exceed
the pre-defined acceptance criteria, thereby demonstrating "effective triage within a clinician's queue based on high sensitivity and specificity," and "substantially equivalent to those of the predicate device" for the standalone performance and turn-around time.
2. Sample Sizes and Data Provenance
- Test Set Sample Size:
- For slice thickness ≤1.5mm: 167 cases (60 positive, 107 negative)
- For slice thickness >1.5mm & ≤5.0mm: 293 cases (99 positive, 194 negative)
- Data Provenance: The test data was retrospective and anonymized, collected from five US hospital network sites.
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: At least two neuroradiologists, with a third neuroradiologist for adjudication in case of disagreement.
- Qualifications of Experts: All truthers were US board-certified neuroradiologists and were protocol-trained.
4. Adjudication Method for the Test Set
The adjudication method used was 2+1. Each de-identified case was annotated in a blinded fashion by at least two (2) ABR-certified and protocol-trained neuroradiologists. Consensus was determined by these two initial ground truthers. A third (1) ground truther was used in the event of disagreement between the first two.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
An MRMC comparative effectiveness study was not explicitly mentioned in the provided text for assessing human reader improvement with AI assistance. The study focused on the standalone performance of the AI algorithm and its triage effectiveness (measured by turn-around time) rather than how human readers' performance improved. The device's intended use is for triage and prioritization, not necessarily to assist in the primary diagnosis or interpretation task of the radiologist per se (e.g., drawing attention to specific portions of an image is explicitly stated as not intended).
6. Standalone Performance (Algorithm Only)
Yes, a standalone performance evaluation was done. The document explicitly states: "Standalone performance was assessed via a retrospective, anonymized study of adult patient, DICOMcompliant non-contrast brain CT cases." The metrics provided in the table (Sensitivity and Specificity) represent this standalone performance of the AI algorithm.
7. Type of Ground Truth Used
The ground truth used was expert consensus. It was determined by multiple ABR-certified neuroradiologists through a consensus and adjudication process.
8. Sample Size for the Training Set
The document states: "The test dataset used during the standalone performance evaluation was newly acquired and independent from the training dataset used in model development." However, the sample size for the training set is not provided in the given text.
9. How the Ground Truth for the Training Set was Established
The document states that the AI algorithm was "trained using deep-learning techniques" and that "Images used to train the algorithm were sourced from datasets that included a range of equipment manufacturers and models." However, no specific information is provided on how the ground truth for this training set was established.
§ 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.