autoSCORE (V 2.0.0)
Holberg EEG ASautoSCORE V2.0 is an AI-based software that helps medical professionals review EEG recordings by identifying and classifying sections indicating brain abnormalities such as epileptiform and non-epileptiform activities. It assists neurologists by marking likely abnormal EEG segments, providing probabilities for specific abnormality types, thereby enhancing the efficiency and accuracy of EEG interpretation without replacing clinical judgment.
Intended Use
autoSCORE is intended for the review, monitoring and analysis of EEG recordings using scalp electrodes to aid neurologists in assessment of EEG, marking potential spikes and classifying abnormalities, intended for qualified medical practitioners.
Technology
autoSCORE is a software-only device that uses a deep learning AI model trained on a large dataset to identify and categorize EEG abnormalities into predefined types including focal and generalized epileptiform and non-epileptiform abnormalities. It integrates with compatible EEG reviewing software, receives EEG data and metadata, computes annotations including abnormality type and probability, and sends outputs to the EEG software for clinician review. The model is locked and does not learn in the field.
Performance
The performance was validated via software verification and validation tests including code review, unit, system, and integration testing. Clinical validation was performed retrospectively on 80 EEG recordings comparing autoSCORE outputs to those of human experts and predicate devices encevis and autoSCORE V1.4. Results demonstrate that autoSCORE V2 performs comparably to predicate devices with good accuracy, sensitivity, specificity, and positive predictive values for detection and classification of EEG abnormalities, supporting its safety and effectiveness.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
12/4/2024
4 months - 2
FDA Approval
4/9/2025
Other devices from Holberg EEG AS
- autoSCORE2024 • 510K
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.