(84 days)
Accipiolx is a software workflow tool designed to aid in prioritizing the clinical assessment of adult non-contrast head CT cases with features suggestive of acute intracranial hemorrhage in the acute care environment. Accipiolx analyzes cases using an artificial intelligence algorithm to identify suspected findings. It makes case-level output available to a PACS/workstation for worklist prioritization or triage.
Accipiolx is not intended to direct attention to specific portions of an image or to anomalies other than acute intracranial hemorrhage. Its results are not intended to be used on a stand-alone basis for clinical decision-making nor is it intended to rule out hemorrhage or otherwise preclude clinical assessment of CT cases.
Accipiolx is a software device designed to be installed within healthcare facility radiology networks to identify and prioritize non-contrast head CT (NCCT) scans based on algorithmically-identified findings of acute intracranial hemorrhage (alCH). The device, which utilizes deep learning technologies, facilitates prioritization of CT scans containing findings of alCH. Accipiolx receives CT scans identified by the Accipio Agent or other compatible Medical Image Communications Device (MICD), processes them using algorithmic methods involving execution of multiple computational steps to identify suspected presence of alCH, and generates a results file to be transferred by the Accipio Agent or a similar MICD device for output to a PACS system or workstation for worklist prioritization.
Accipiolx works in parallel to and in conjunction with the standard care of workflow. After a CT scan has been performed, a copy of the study is automatically retrieved and processed by Accipiolx. The device performs identification and classification of objects consistent with alCH, and provides a case-level indicator which facilitates prioritization of cases with potential acute hemorrhagic findings for urgent review.
Here's a breakdown of the acceptance criteria and study details for the MaxQ AI Accipiolx device, based on the provided text:
1. Table of Acceptance Criteria & Reported Device Performance
| Performance Metric | Acceptance Criteria (Predefined Goals) | Reported Device Performance (Accipiolx K201310) | Predicate Device Performance (Accipiolx K182177) |
|---|---|---|---|
| Sensitivity | Not explicitly stated as a number for the acceptance criteria but implied to be high, and the reported performance is compared favorably to the predicate. | 97% (95% CI: 92.8% - 98.8%) | 92% (95% CI: 87.29 - 95.68%) |
| Specificity | Not explicitly stated as a number for the acceptance criteria but implied to be high, and the reported performance is compared favorably to the predicate. | 93% (95% CI: 88.6% - 96.6%) | 86% (95% CI: 80.18 - 90.81%) |
| Processing Time | Not explicitly stated as a numerical acceptance criterion, but the stated goal is "improved benefit in time saving compared to the predicate device." | 1.17 minutes (95% CI: 1.16 - 1.18 minutes) | 4.1 minutes (95% CI: 3.8 - 4.3 minutes) |
| Negative Predictive Value (NPV) | Not explicitly stated as a number, but high NPV is implied for a triage device. | 99.8% (95% CI: 99.7% - 100%) | Not explicitly stated in the predicate's performance table, but stated it has "very low probability of false positive results." |
| Positive Predictive Value (PPV) | Not explicitly stated as a number. | 43.3% (95% CI: 43.3% - 53%) | Not explicitly stated in the predicate's performance table. |
| Sensitivity for Intra-Axial Hemorrhages | Not explicitly stated as an independent acceptance criterion. | 100% (95% CI: 96.6% - 100%) | Not explicitly stated for the predicate. |
| Sensitivity for Extra-Axial Hemorrhages | Not explicitly stated as an independent acceptance criterion. | 92% (95% CI: 82.7% - 96.9%) | Not explicitly stated for the predicate. |
Note: While specific numerical acceptance criteria (e.g., "Sensitivity must be >= 95%") are not explicitly listed in the document for each metric, the text states that "These results exceeded the predefined performance goals." This implies that the reported performance values were at or above the company's internal targets.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: 360 newly tested cases.
- Data Provenance: Retrospective study. Cases were collected from multiple sites across 17 US states.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
The document does not specify the number of experts or their qualifications used to establish the ground truth for the test set. It only mentions that performance was validated by comparing results to "predefined performance goals."
4. Adjudication Method for the Test Set
The document does not describe an explicit adjudication method (e.g., 2+1, 3+1, none) for the test set's ground truth.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No, the document does not mention an MRMC comparative effectiveness study where human readers improve with AI vs. without AI assistance. The study focuses on the standalone performance of the AI algorithm.
6. If a Standalone (Algorithm Only) Performance Study Was Done
Yes, a standalone (algorithm only) performance study was done. The reported metrics (Sensitivity, Specificity, Processing Time, NPV, PPV) are for the Accipiolx device's performance in identifying acute intracranial hemorrhage directly from the CT scans.
7. The Type of Ground Truth Used
The document implicitly suggests the ground truth was established by clinical assessment, as the device's output "prioritizes cases with potential acute hemorrhagic findings for urgent review." While not explicitly stated as "expert consensus," the context of a "workflow tool" aiding "clinical assessment" implies a human expert review of the cases to establish the presence or absence of ICH for comparison against the algorithm's output. The comparison of device performance to "predefined performance goals" further supports this.
8. The Sample Size for the Training Set
The document does not specify the exact sample size for the training set. It only states that the device was "developed using training CT cases collected from multiple institutions and CT manufacturers."
9. How the Ground Truth for the Training Set Was Established
The document does not explicitly describe how the ground truth for the training set was established. It mentions a "training process" that "included pilot development, optimization of object and feature identification, algorithmic training and selection/optimization of thresholds." This strongly implies that the training data was meticulously labeled for the presence of acute intracranial hemorrhage, likely by medical experts, to enable the deep learning algorithm to learn patterns associated with ICH.
§ 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.