In the medical domain, the diagnosis of neurological disorders is complicated due to the complex nervous system. Neurological disorders include epilepsy, dementia, and Alzheimer’s disease. There are also cerebrovascular diseases such as stroke, multiple sclerosis, Parkinson’s disease. According to the WHO’s report, neurological disorders affect up to one billion people worldwide. As a result, approximately 6.8 million people die from these neurological disorders every year. A prompt and well-timed diagnosis of these neurological disorders can significantly improve a patient’s life. Currently, there are a substantial number of advanced technologies to diagnose neurological disorders. For instance, magnetic resonance imaging (MRI), electroencephalogram (EEG), electromyography (EMG), computed tomography (CT), and angiogram. These technologies help doctors make accurate decisions. These technologies yield a vast amounts of data in various dimensions and sizes, ranging from a few megabytes to hundreds of megabytes, which require large storage capacities.

It is challenging to accumulate, manage, analyze, and assimilate a large amount of data because the medical data is complex in terms of velocity and volume. The visual analysis of such data is not an acceptable way for a reliable and precise diagnosis because the patient can be subject to fatigue. Furthermore, there can be errors and it can be time-consuming. Therefore, there is a need for a system that can give the support neurologists require. The system should make an accurate diagnosis in a timely manner to improve the patient’s health. Thus, medical analytics are developing automatic decision systems by utilizing computational intelligence for fast, accurate, and efficient diagnosis and prognosis. This will improve the consistency of diagnosis and increase the success of treatment, save lives, and reduce cost and time. Signal processing, medical image analysis, and integration of physiological data tackle alike challenges to deal with different big data sources. It has been noticed that experts require online computer-aided design (CAD) systems for real-time evaluation instead of offline CAD. To generate even more accurate diagnostic systems, we need to develop general feature extraction methods, robust classification methods, and efficient online CAD systems. Moreover, we should balance the trade-offs between accuracy and efficiency.

The aim of this Special Issue is to bring together original research and review articles discussing big medical data for the diagnosis of neurological disorders. We welcome submissions related to computational methods and tools for the diagnosis of neurodegenerative disorders.

Potential topics include but are not limited to the following:

• Computer aided diagnosis systems for diagnosing neurodegenerative disorders
• Computational methods to detect neurodegenerative disorders from medical data
• Robust classification methods for classifying neurodegenerative disorders
• Precise and reliable biomarkers to distinguish normal and interested disease, and differentiable between different diseases
• Medical image analysis for diagnosing neurodegenerative disorders
• Medical signal processing for diagnosing neurodegenerative disorders