Search Results

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:

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.

Ask a specific question about this device