Comparative Analysis of Epilepsy Prediction using Machine Learning and Deep Learning

Chandu, Y. Sai; Shaik, Fathimabi

doi:10.1109/i-smac55078.2022.9987428

Cited by 1 publication

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite decades of research on automatic seizure detection and forecasting [12][13][14], the latter task turns out to be extremely challenging [15]. Nevertheless, inspired by the successes of artificial intelligence (AI) in clinical diagnosis [16] and disease forecasting [17], consistent research efforts are being made to tackle the seizure prediction problem using advanced deep learning techniques [18][19][20]. For example, a study reported sensitivity rates of 96% and 94% in two different benchmark datasets [21], while another study reported an accuracy of almost 100% [22].…”

Section: Introductionmentioning

confidence: 99%

Calibrating Deep Learning Classifiers for Patient-Independent Electroencephalogram Seizure Forecasting

Shafiezadeh,

Duma,

Mento

et al. 2024

Sensors

View full text Add to dashboard Cite

The recent scientific literature abounds in proposals of seizure forecasting methods that exploit machine learning to automatically analyze electroencephalogram (EEG) signals. Deep learning algorithms seem to achieve a particularly remarkable performance, suggesting that the implementation of clinical devices for seizure prediction might be within reach. However, most of the research evaluated the robustness of automatic forecasting methods through randomized cross-validation techniques, while clinical applications require much more stringent validation based on patient-independent testing. In this study, we show that automatic seizure forecasting can be performed, to some extent, even on independent patients who have never been seen during the training phase, thanks to the implementation of a simple calibration pipeline that can fine-tune deep learning models, even on a single epileptic event recorded from a new patient. We evaluate our calibration procedure using two datasets containing EEG signals recorded from a large cohort of epileptic subjects, demonstrating that the forecast accuracy of deep learning methods can increase on average by more than 20%, and that performance improves systematically in all independent patients. We further show that our calibration procedure works best for deep learning models, but can also be successfully applied to machine learning algorithms based on engineered signal features. Although our method still requires at least one epileptic event per patient to calibrate the forecasting model, we conclude that focusing on realistic validation methods allows to more reliably compare different machine learning approaches for seizure prediction, enabling the implementation of robust and effective forecasting systems that can be used in daily healthcare practice.

show abstract