Seizure forecasting with epilepsy cycles: On the causality of forecasting pipelines

Key Points

• Forecasting algorithms show a significant gap between prospective and retrospective abilities, indicating limitations in current methods.
• This performance gap implies that previous studies may have overestimated the effectiveness of seizure forecasts using noncausal models.
• Novel cycle-extraction methods are necessary to improve forecasting accuracy in real-time predictive settings, especially for epilepsy cycles.
• Future research should prioritize developing robust algorithms that can work effectively with historical data in real-time.