(101 days)
JLK-SDH is a notification-only, parallel workflow tool that is intended to assist trained radiologists to identify and communicate images of specific patients to a specialist, independent of the standard of care workflow.
JLK-SDH uses an artificial intelligence algorithm to analyze images for findings suggestive of a prespecified clinical condition and to notify an appropriate user of these findings in parallel to standard of care image interpretation. Identification of suspected findings is not for diagnostic use beyond notification. Specifically, the device analyzes non-contrast CT images of the head for subdural hemorrhage (SDH) and sends notifications to a clinician that a suspected SDH has been identified and recommends a review of those images. Images can be previewed and compressed through PACS and mobile applications.
Notified clinicians are responsible for viewing non-compressed images on a diagnostic viewer and engaging in appropriate patient evaluation and relevant discussion with a treating physician before making care-related decisions or requests.
JLK-SDH is limited to the analysis of imaging data and should not be used in lieu of full patient evaluation or relied upon to make or confirm the diagnosis.
JLK-SDH is a radiological computer-assisted triage and notification (CADt) software package compliant with the DICOM standard. The device functions as a Non-Contrast Computed Tomography (NCCT) processing module, providing triage and notification for suspected hemispheric subdural hemorrhage (SDH). It serves as a notification-only, parallel workflow tool for hospital networks and trained clinicians. The device helps to identify and communicate specific patient images to trained radiologists, independent of the standard of care workflow. Utilizing an artificial intelligence algorithm, the system automatically receives and analyzes NCCT studies for image features indicating the presence of SDH and sends a notification to alert a radiologist of the case.
This algorithm, hosted on JLK servers, is designed to analyze non-contrast CT images of the head acquired on CT scanners and forwarded to JLK servers. The mobile software module that enables user to receive and toggle notifications for suspected subdural hemorrhages identified by the JLK-SDH Image Analysis Algorithm. Users can view a patient list, and nondiagnostic CT scans through the mobile application. Image viewing through the mobile application interface is for non-diagnostic purposes only.
Here's a detailed breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Metric | Acceptance Criteria (Target) | Reported Device Performance (JLK-SDH) |
|---|---|---|
| Sensitivity | > 80% | 97.1 (95% CI: 94.4%, 99.4%) |
| Specificity | > 80% | 97.4 (95% CI: 95.8%, 99.0%) |
| AUC | Not explicitly stated | 0.974 (95% CI: 0.958, 0.989) |
| Time to Notification | Meets or exceeds predicate's 1.15 ± 0.57 minutes | 0.19 ± 0.05 minutes |
2. Sample Size for the Test Set and Data Provenance
- Sample Size: 560 NCCT scans
- 174 SDH positive cases
- 386 SDH negative cases
- Data Provenance: Retrospective study. Scans were obtained from various regions in the U.S.
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: Three.
- Qualifications: All truthers were US board-certified neuroradiologists.
4. Adjudication Method for the Test Set
- Adjudication Method: 2+1 truther scheme. Ground truth was determined by two neuroradiologists, with a third neuroradiologist intervening in cases of disagreement. (28 cases were sent to the third truther).
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was an MRMC study done? No, the text describes a standalone performance evaluation of the device's AI algorithm.
6. Standalone (Algorithm Only) Performance
- Was a standalone performance study done? Yes. The performance data section explicitly states, "JLK, Inc. performed a standalone performance in accordance with the §892.2080 special controls to demonstrate adequate clinical performance of the JLK-SDH module."
7. Type of Ground Truth Used
- Type of Ground Truth: Expert consensus of US board-certified neuroradiologists.
8. Sample Size for the Training Set
- Sample Size: 29,524 non-contrast CT (NCCT) scans
- 3,330 patients had SDH
- 11,732 had different kinds of intracranial hemorrhage (IPH, IVH, SAH, or EDH)
- 14,462 patients did not have any intracranial hemorrhage
9. How the Ground Truth for the Training Set Was Established
- The document does not explicitly detail the exact method for establishing ground truth for the training set. It only mentions that the images "had been obtained in patients with and without intracranial hemorrhage" and categorizes them by the type of hemorrhage. While it suggests clinical diagnoses, the specific process (e.g., expert review, clinical reports, pathology) used to label these training cases is not described.
Clarification on "Acceptance Criteria"
The document states that the "primary endpoints, sensitivity and specificity, both exceeded 80%." This implies that >80% for both sensitivity and specificity served as the acceptance criteria for the standalone performance study. For time-to-notification, the acceptance criterion was to 'meet the target' established by the predicate device.
§ 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.