Artificial Intelligence and Deep Learning in Seizure Detection for Alzheimer's Disease: A Review

Abstract

Alzheimer’s disease (AD) is a neurodegenerative disorder that leads to seizures, failure to manage the disease and stimulates cognitive decline. The comprehensive development of the dataset for the early detection of the predicted model involves intricate steps. In this article, we explore the various approaches for the detection of seizure from the AD patients with the collection of datasets and annotation by focusing on multi-modal data sources, including neuroimaging, Electroencephalography, physiological signals, and cognitive evaluations. The detection models are included in this study with the integration of deep learning, machine learning approaches along with wearable sensor technology, EEG monitoring, and neuro-imaging analysis with the usage of large-scale datasets. The challenges in developing the datasets and detection of seizures are analysed to provide better detection of AD. The application of artificial intelligence techniques for identifying AD using various datasets is analyzed. This study provides the way for the generation of standardized publicly available datasets and therein significantly helps in detecting AD from the patients earlier.