autoSCORE
Holberg EEG ASautoSCORE is a software tool that assists neurologists by automatically analyzing EEG recordings to identify and categorize abnormal brain activity such as epileptiform and non-epileptiform abnormalities. It acts as a decision support system, marking potential abnormal areas on EEG data, thereby helping clinicians review EEGs more efficiently and accurately. The device does not provide final diagnostic conclusions but rather supports professional judgment in interpreting EEG results.
Intended Use
autoSCORE is intended for review, monitoring and analysis of EEG recordings made by electroencephalogram devices using scalp electrodes, aiding neurologists in EEG assessment with spike detection and classification of abnormalities.
Technology
autoSCORE is a software-only decision support product using a convolutional neural network algorithm trained on large datasets. It analyzes raw EEG signals post-hoc to assess probability and categorize epileptiform and non-epileptiform abnormalities, outputting abnormality markers to EEG review software without altering the original EEG data.
Performance
Performance was validated via non-clinical (software verification and validation) and clinical studies comparing autoSCORE outputs to human expert assessments and predicate devices. Clinical validation used multiple datasets totaling thousands of EEGs, measuring sensitivity, specificity, and correlation for detection of abnormalities with strong agreement demonstrated, including comparison with predicate devices encevis and Persyst.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
4/14/2023
8 months - 2
FDA Approval
1/7/2024
Ready to Sharpen Your Edge?
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.