autoSCORE
by Holberg EEG AS
· Based in Norway →
— The world's first analysis tool that leverages advanced deep learning to streamline EEG review and interpretation.
Regulatory Status Disclosed
Overview
autoSCORE, developed by Holberg EEG AS, is a software-only decision support product featuring an AI algorithm trained on over 30,000 expertly annotated EEGs. It performs with expert-level accuracy in differentiating between normal and abnormal EEG recordings and sub-categorizing various abnormalities. The tool assesses the probability of abnormalities in previously acquired EEG sections and classifies them into specific types, including focal epileptiform, generalized epileptiform, focal non-epileptiform, and diffuse non-epileptiform. Designed to assist qualified medical practitioners, autoSCORE integrates seamlessly with compatible EEG review software, such as Natus NeuroWorks EEG software, to indicate potential abnormality markers. It aims to accelerate EEG review, reduce reporting variability, improve assessment quality, and enhance overall productivity by providing AI-driven insights without a direct user interface, allowing neuro care teams to focus more on patient care.
Reviewed by Pouyan Golshani, MD — Interventional Radiologist
Key Features
- AI algorithm trained on over 30,000 annotated EEGs
- Expert-level EEG interpretation, comparable to human experts
- Flags clinically relevant abnormalities in EEG recordings
- Provides study-level insights across LTM, ambulatory, and routine studies
- Automates routine assessments and highlights key findings
- Classifies abnormalities into four subtypes: focal epileptiform, generalized epileptiform, focal non-epileptiform, diffuse non-epileptiform
- Provides visual preview of abnormality prevalence before opening a study
- Helps navigate to abnormal EEG segments based on type and probability score
- Seamlessly integrated into Natus NeuroWorks EEG software
- Acts as a decision support tool to aid clinical workflow
Use Cases
- Streamlining EEG review and interpretation
- Reducing EEG reporting variability and improving quality
- Reducing time and cost for EEG users
- Assisting neurologists in the assessment of EEG
- Supporting timely clinical decisions in neuro care
- Enhancing productivity in high-volume EEG environments
What Physicians Need to Know
Evidence Base
autoSCORE's AI algorithm was trained on over 30,000 expertly labeled EEG recordings from the SCORE database, the world's largest repository of structured, highly annotated EEGs collected over 10 years. The underlying SCORE standard is endorsed by the International Federation of Clinical Neurophysiology (IFCN) and the International League Against Epilepsy (ILAE), and is included in revised EEG guidelines and glossaries. A key publication validating the model is 'Automated Interpretation of Clinical Electroencephalograms Using Artificial Intelligence' in JAMA Neurology (2023).
Clinical Validation Studies
autoSCORE performs non-inferior to human experts in differentiating normal from abnormal EEG recordings and sub-categorizing abnormalities. A diagnostic study trained the AI model on 30,493 EEGs and validated it using three independent test datasets (9,945 EEGs), demonstrating diagnostic accuracy similar to human experts. A 2023 JAMA study reported autoSCORE consistently achieved accuracy, sensitivity, and specificity near or above 90%, performing on par with leading human experts and outperforming similar AI models. Clinical validation included comparisons against independent human experts and predicate devices.
Alert Fatigue Management
While not explicitly detailing 'alert fatigue management' features, autoSCORE is designed to streamline EEG review by flagging clinically relevant abnormalities and providing study-level insights, thereby reducing manual review burden and helping guide prioritization. It offers a visual preview of abnormality prevalence and enables quick navigation to abnormal segments, aiming to improve efficiency and reduce excessive workloads for experts.
Clinical Workflow Integration
autoSCORE is seamlessly integrated exclusively with Natus NeuroWorks EEG software (version 10 or higher). It sends information to the EEG software to place markers indicating abnormalities, accelerating EEG review, supporting timely clinical decisions, and enhancing overall workflow efficiency by optimizing resources and reducing review burden.
Physician Tip
Leverage autoSCORE as an AI-driven second opinion tool to accelerate EEG review and prioritize critical cases, especially in high-volume settings. Utilize its ability to classify abnormalities into specific subtypes to inform your differential diagnosis process. Remember that autoSCORE assists in assessing the probability and type of abnormalities; your professional judgment remains paramount for final diagnosis and patient management.
autoSCORE is exclusively available as an integrated component within Natus NeuroWorks EEG software (version 10 or higher). This tight integration ensures a streamlined user experience and direct communication of AI-generated insights within the existing EEG review workflow.
Details
| Category | Clinical Decision Support & Reference, Neurology AI |
| Pricing | Unknown |
| Deployment | Integrated with Natus NeuroWorks EEG software (version 10 or higher). |
| Compliance | |
| BAA Available | Unknown AI-estimated |
| HIPAA Compliant | Unknown AI-estimated |
| FDA Status |
1 AI-estimated autoSCORE received FDA 510(k) clearance (K231068) on January 7, 2024, as a Class II device (Regulation Number: 21 CFR 882.1400, Product Code: OMB). It is intended to assist neurologists in the assessment of EEG recordings by identifying and classifying abnormalities, and has an expanded indication for routine, long-term monitoring (LTM), and ambulatory EEG studies. |
| Integrations | |
| EHR | Not specified |
| Specialties | Neurology |
Ratings & Reviews
No reviews yet. Be the first to review this tool!
Rate autoSCORE
Press & Coverage
Natus Medical Incorporated
Natus Acquires Holberg EEG, Expanding Innovation in Neurodiagnostic AI Solutions
Natus Medical Incorporated announced its acquisition of the remaining minority shares in Holberg EEG, making it a wholly-owned subsidiary. This acquisition integrates Holberg EEG's autoSCORE, an AI model for comprehensive clinical EEG interpretation, with Natus' neurodiagnostics portfolio to advance brain health solutions.
2025-09
PR Newswire
Natus introduces autoSCORE, an innovative AI solution capable of a new era of expert-level clinical EEG interpretation
Natus Medical Incorporated launched autoSCORE, an AI model developed by Holberg EEG, capable of automatic and comprehensive clinical EEG interpretation with accuracy comparable to medical experts. The application was trained on over 30,000 expertly labeled EEG recordings and is FDA cleared for routine EEG studies.
2024-08
JAMA Neurology
Automated Interpretation of Clinical Electroencephalograms Using Artificial Intelligence
A multicenter diagnostic accuracy study published in JAMA Neurology detailed the development and validation of SCORE-AI (autoSCORE), an AI model trained on over 30,000 EEGs to differentiate normal from abnormal recordings and classify abnormalities with accuracy similar to human experts. The study suggests autoSCORE can improve diagnosis and patient care.
2023-06
Natus
Transforming Care at Abbott Northwestern Hospital with autoSCORE - Natus
This article highlights the implementation of autoSCORE at Allina Health Abbott Northwestern Hospital, making them the first in the US to use this FDA-cleared AI model for routine EEG interpretation. Dr. Ram Mohan Sankaraneni found autoSCORE significantly improved workflow efficiency and diagnostic accuracy.
2025-01
BioSpace
Natus partners with Holberg EEG to advance the diagnosis of Epilepsy
Natus Medical Incorporated announced a partnership with Holberg EEG AS to advance the development and distribution of the autoSCORE algorithm. This collaboration aims to automate EEG classifications, reduce reporting variability, and improve efficiency in epilepsy diagnosis.
2020-05
Signify Research
BD releases next-gen hemodynamic monitor, GE HealthCare joins SDC initiative, Boston Scientific invests in Anumana | Signify Research
This news roundup mentions Holberg EEG receiving FDA approval for its autoSCORE 2.0 software for Long-Term Monitoring (LTM) and ambulatory EEG in April 2025. It also notes that the first-generation autoSCORE was commercially launched in the US in August 2024 in partnership with Natus Medical.
2025-05
accessdata.fda.gov
K243743 - 510(k) Premarket Notification - FDA
This FDA 510(k) Premarket Notification document confirms the clearance of autoSCORE (V 2.0.0) from Holberg EEG AS on April 9, 2025, under regulation number 882.1400.
2025-04
ISRCTN Registry
Evaluation of autoSCORE: an artificial intelligence based algorithm for EEG classification versus human experts
This study protocol outlines the evaluation of the autoSCORE algorithm, an AI-based tool trained on a large dataset to classify EEGs as normal or abnormal and further into four sub-groups. The study aims to prove autoSCORE's non-inferiority to human experts in EEG interpretation.
2022-03
Videos
Product demos, reviews, and walkthroughs for autoSCORE.
SCORE EEG - How to report a normal EEG
Holberg EEG
Frequently Asked Questions
autoSCORE is seamlessly integrated into Natus NeuroWorks software (version 10 or higher), designed to enhance EEG workflow efficiency by automating routine assessments and highlighting key findings. It helps neurocare teams more efficiently and consistently perform EEG data analysis, streamlining the review process.
autoSCORE has received FDA 510(k) clearance for routine EEG, Long-Term Monitoring (LTM), and Ambulatory EEG studies. Additionally, it holds the CE mark for European and other international markets, signifying its compliance with relevant regulatory standards for clinical deployment.
While traditional spike and seizure detectors exist, autoSCORE differentiates itself by offering comprehensive clinical EEG interpretation, assessing multiple clinically relevant abnormalities, and providing study-level assessments. It has demonstrated performance on par with leading human experts and has outperformed similar AI models on the market.
Specific pricing details for autoSCORE are typically handled through Natus sales representatives, as it is exclusively available with Natus NeuroWorks EEG software. Pricing models for such specialized medical software often involve licensing fees, subscriptions, or per-use charges, which can vary based on the institution's size and usage volume.
autoSCORE is intended for adult and pediatric routine, LTM, and ambulatory EEG analysis, but it is not validated for ICU and neonatal recordings or for EEGs recorded in home/non-hospital settings. It also does not provide diagnostic conclusions, requiring physician review and clinical judgment for final interpretation.
As a medical device handling Protected Health Information (PHI), autoSCORE, offered by Natus, is expected to adhere to strict data privacy and security standards. This implies compliance with regulations like HIPAA, which typically involves appropriate administrative, physical, and technical safeguards, as well as business associate agreements.
autoSCORE was developed using a deep-learning model trained on over 30,000 expertly labeled EEG recordings and has been extensively validated by experts, with results published in peer-reviewed journals like JAMA. Studies indicate it consistently performs with accuracy, sensitivity, and specificity near or above 90%, comparable to leading human experts.
Suggest an Edit →
| Last Verified: 2026-04-18 | First Added: 2026-04-18