Search Results
Found 1 results
510(k) Data Aggregation
(146 days)
Neurocareai Inc.
NeuroICH is a notification-only, parallel workflow tool for use by hospital networks and trained clinicians to identify and communicate images of suspected ICH patients to a specialist, independent of standard of care workflow.
The device uses an artificial intelligence algorithm to analyze non-contrast CT images of the head acquired in the acute setting for findings suggestive of intracranial hemorrhage (ICH) in parallel to the ongoing standard of care image interpretation and notify an appropriate clinician of these findings. Notifications include non-diagnostic preview images that are meant for informational purposes only. The device does not alter or remove the original medical image and is not intended to be used as a diagnostic device. Images can be previewed through a mobile application.
Notified clinicians are responsible for viewing high quality images on a diagnostic viewer per the standard of care and engaging in appropriate patient evaluation in conjunction with other patient information before making care-related decisions. NeuroICH is limited to analysis of imaging data and should not be used in-lieu of full patient evaluation or relied upon to make or confirm diagnosis.
NeurolCH is a software-only parallel workflow tool designed for use by hospital networks and trained clinicians to identify and communicate prioritized images of specific patients to an appropriate specialist such as neurovascular or neurosurgical specialist independent of the standard of care workflow. NeuroICH mainly consists of an image analysis module hosted on cloud, and a mobile application for preview of notification and non-diagnostic images. The standalone software device automatically receives and analyzes non-contrast head CT (NCCT) studies of patients undergoing stroke protocol, for image features that indicate the presence of an intracranial hemorrhage (ICH) using deep learning artificial intelligence algorithm, and upon detection of a suspected ICH case, sends a notification along with non-diagnostic image on mobile application to alert a specialist clinician.
Here's an analysis of the acceptance criteria and study details for NeuroICH, based on the provided FDA 510(k) summary:
Acceptance Criteria and Device Performance for NeuroICH
1. Table of Acceptance Criteria and Reported Device Performance
| Metric | Acceptance Criteria (Lower Bound of 95% CI) | Reported Device Performance (95% CI) | Met Criteria? |
|---|---|---|---|
| Sensitivity | 80% | 94.81% (89.68% - 97.43%) | Yes |
| Specificity | 80% (Implied by comparison to predicate) | 92.53% (88.50% - 95.21%) | Yes |
| Accuracy | Not explicitly stated (reported for context) | 93.35% (90.37% - 95.45%) | N/A |
| AUC | Not explicitly stated (reported for context) | 0.9367 | N/A |
| Time-to-Notification (TTN) | Comparable to predicate (0.49±0.08 min) | 0.37 ± 0.20 minutes | Yes |
Note: The acceptance criteria for specificity, accuracy, and AUC are not explicitly quantified in the text as a lower bound. However, the text states that the performance was "comparative to the values achieved by the predicate device Viz ICH" and that "the clinical utility and potential benefits of the classifier" were demonstrated. For Time-to-Notification, the primary criterion was comparability to the predicate device.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: 376 studies.
- Data Provenance: The document states "recognizable representation of positive and negative ICH cases (35.90 % ICH positive studies and 64.09 % normal studies)". No specific country of origin is mentioned, nor is it explicitly stated whether the data was retrospective or prospective. However, given it's a "retrospective, blinded study," the data provenance is retrospective.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
- Number of Experts: Three (3)
- Qualifications: US board-certified Neurologists. No specific years of experience are mentioned.
4. Adjudication Method for the Test Set
The adjudication method is not explicitly stated as 2+1, 3+1, or similar. It only mentions that the ground truth was "established by three US board certified Neurologists." This implies a consensus-based approach, but the specific mechanics (e.g., majority vote, independent review with tie-breaking) are not detailed.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
There is no mention of a multi-reader multi-case (MRMC) comparative effectiveness study being performed to assess how much human readers improve with AI vs. without AI assistance. The study focuses on the standalone performance of the AI algorithm and its time-to-notification compared to standard of care and the predicate device.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
Yes, a standalone study was conducted. The performance metrics (Sensitivity, Specificity, Accuracy, AUC, and Time-to-Notification) were calculated by comparing the "NeurolCH's output to the ground truth." This indicates the algorithm's performance without direct human intervention in the detection or interpretation phase. The document specifies it's a "notification-only, parallel workflow tool," further supporting its standalone function in identifying and notifying.
7. Type of Ground Truth Used
The ground truth used was expert consensus from three US board-certified Neurologists.
8. Sample Size for the Training Set
The document does not specify the sample size used for the training set. It only mentions the test set of 376 studies.
9. How the Ground Truth for the Training Set Was Established
The document does not provide information on how the ground truth for the training set was established. It only describes the ground truth establishment for the test set.
Ask a specific question about this device
Page 1 of 1