Authors: Ali Saeizadeh, Douglas Schonholtz, Daniel Uvaydov, Raffaele Guida, Emrecan Demirors, Pedram Johari, Jorge M. Jimenez, Joseph S. Neimat, Tommaso Melodia

Published on: January 12, 2024

Impact Score: 8.45

Arxiv code: Arxiv:2401.06644

Summary

• What is new: SeizNet introduces a novel closed-loop system using deep learning and implantable sensors for highly accurate seizure prediction.
• Why this is important: One out of three epilepsy patients suffer from drug-resistant epilepsy and current predictive systems are not adequately effective.
• What the research proposes: SeizNet combines data from iEEG and ECG sensors using deep learning to predict seizures with high specificity and sensitivity.
• Results: SeizNet achieves up to 99% accuracy in seizure prediction, surpassing traditional single-modality and non-personalized systems.

Technical Details

Technological frameworks used: Deep Learning (DL)

Models used: Custom DL algorithms designed for edge execution

Data used: Intracranial electroencephalogram (iEEG) and electrocardiogram (ECG) data

Potential Impact

Pharmaceutical companies, healthcare providers, and medical device manufacturers focusing on epilepsy treatment and management

Want to implement this idea in a business?

We have generated a startup concept here: PredictaSeize.