(249 days)
Annalise Enterprise CXR Triage Trauma is a software workflow tool designed to aid the clinical assessment of adult chest X-ray cases with features suggestive of pleural effusion and pneumoperitoneum in the medical care environment.
The device analyzes cases using an artificial intelligence algorithm to identify findings. It makes case-level output available to a PACS or RIS for worklist prioritization or triage.
The device is intended to be used by trained clinicians who are qualified to interpret chest X-rays as part of their scope of practice.
The device is not intended to direct attention to specific portions of an image or to anomalies other than pleural effusion and pneumoperitoneum.
Its results are not intended to be used on a standalone basis for clinical decision making nor is it intended to rule out specific critical findings, or otherwise preclude clinical assessment of X-ray cases.
Standalone performance evaluation of the device was performed on a dataset that included supine and erect positioning. Use of this device with prone positioning may result in differences in performance.
Standalone performance evaluation of the device was performed on a dataset where most cases were of unilateral right sided and bilateral pneumoperitoneum. Use of this device for unilateral left sided pneumoperitoneum may result in differences in performance.
Specificity may be reduced for pleural effusion in the presence of scarring and and/or pleural thickening.
Annalise Enterprise CXR Triage Trauma is a software workflow tool which uses an artificial intelligence (AI) algorithm to identify suspected findings on chest X-ray (CXR) studies in the medical care environment. The findings identified by the device include pleural effusion and pneumoperitoneum.
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 across three continents, including 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 radiologists.
The device interfaces with image and order management systems (such as PACS/RIS) to obtain CXR studies for processing by the AI algorithm. Following processing, if any of the clinical findings of interest are identified in a CXR 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 clinical 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 CXRs. The device is intended to aid in prioritization and triage of radiological medical images only.
Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:
Acceptance Criteria and Device Performance
The document describes the performance of the Annalise Enterprise CXR Triage Trauma device in identifying pleural effusion and pneumoperitoneum. The acceptance criteria are implicitly demonstrated by the reported sensitivities and specificities at various operating points, which are presented as evidence of effective triage and substantial equivalence to the predicate device. While explicit "acceptance criteria" are not listed as pass/fail thresholds in the provided text, the performance metrics below are what the sponsor used to demonstrate the device met the requirements.
Table of Reported Device Performance:
| Finding | Operating point | Sensitivity (95% CI) | Specificity (95% CI) | AUC (95% CI) |
|---|---|---|---|---|
| Pleural effusion | 0.2302 | 96.0 (94.2,97.7) | 88.3 (85.3,91.1) | 0.980 (0.972-0.986) |
| 0.2990 | 93.8 (91.5,95.8) | 91.7 (89.3,94.1) | ||
| 0.4355 | 86.3 (83.0,89.4) | 95.6 (93.7,97.2) | ||
| Pneumoperitoneum | 0.0322 | 90.1 (84.2,95.0) | 87.4 (82.4,92.3) | 0.969 (0.950-0.984) |
| 0.0484 | 86.1 (79.2,92.1) | 89.6 (85.2,94.0) | ||
| 0.2266 | 82.2 (75.2,89.1) | 96.2 (93.4, 98.9) |
Additionally, the device achieved an average triage turn-around time under 30.0 seconds. This implies an implicit acceptance criterion for speed, aiming for a rapid triage capability.
Study Details
1. Sample Sizes and Data Provenance
- Test Set Sample Size: A total of 1269 CXR cases (582 positive, 687 negative) were used across two independent cohorts.
- Data Provenance: The data was collected retrospectively and anonymized from four US hospital network sites. The cases were collected consecutively. The text also mentions that training data was sourced from "datasets across three continents."
2. Number of Experts and Qualifications for Ground Truth
- Number of Experts: For ground truth determination, a minimum of two experts were used, with a third expert used in case of disagreement.
- Qualifications: All experts (ground truthers) were ABR-certified and protocol-trained radiologists. No specific years of experience are mentioned.
3. Adjudication Method for the Test Set
- The adjudication method for establishing ground truth was 2+1 consensus. This means two ground truthers blinded to each other's assessments first reviewed the cases, and a third ground truther was consulted to resolve any disagreements.
4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly mentioned as being performed to show how human readers improve with AI vs. without AI assistance. The performance evaluation focused on the standalone performance of the AI algorithm for triage effectiveness.
5. Standalone Performance (Algorithm Only)
- Yes, a standalone performance evaluation was performed. The reported sensitivities, specificities, and AUC values in the table above demonstrate the algorithm's performance without integration into human workflow for diagnostic purposes, although it is evaluated for its "triage effectiveness."
6. Type of Ground Truth Used
- The ground truth was established by expert consensus of ABR-certified and protocol-trained radiologists.
7. Sample Size for the Training Set
- The specific sample size for the training set is not provided in the given text. It only states that the training dataset was "independent from the training dataset used in model development" relative to the test set and sourced from "datasets across three continents."
8. How the Ground Truth for the Training Set was Established
- The text does not explicitly detail how the ground truth for the training set was established. It only states that the AI algorithm was "trained using deep-learning techniques" and that the "Images used to train the algorithm were sourced from datasets across three continents." It can be inferred that a similar expert review process, likely by radiologists, would have been used to label the training data, but this is not explicitly stated in the provided excerpt.
§ 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.