Computational Intelligence and Neuroscience

Significant advancements in information and communication technology (ICT) have been utilized in many applications in healthcare, playing a key role in almost all processes that provide health services. The current ICT systems provide many benefits to the health sector, but there is a large opportunity for utilizing artificial intelligence and smart computing to enhance the quality of health services, reduce costs and improve the health of citizens. The deadliest global diseases include cancer, coronary artery disease, stroke, lower respiratory infections, chronic obstructive pulmonary disease, diabetes, Alzheimer’s disease, tuberculosis, and recently, COVID-19. It is important for the healthcare sector to improve early and accurate detection, diagnosis, and prediction of these diseases. According to the World Health Organization (WHO), cancer is considered one of the second leading causes of death in the world and was accountable for about 9.6 million deaths in 2018. The most common cancers based on the number of death cases are lung, breast, colorectal, prostate, skin, and stomach cancers.

Computational methods such as artificial intelligence and machine learning have been applied to improve the detection of these diseases. Some studies used medical images such as magnetic resonance imaging (MRI), ultrasound, computed tomography (CT), and lung monitoring for diagnosis. Additionally, several intelligent methods used gene expression for classifying cancers and other diseases into specific diagnostic types. One of the issues in gene expression datasets is the high dimensionality, where there are many irrelevant or redundant features (genes) that affect the prediction’s accuracy. Therefore, there is a need to select a subset of these genes that are more informative. Several ensemble feature selection methods could be investigated and applied to select the important ones to enhance the performance of the classification methods. It is known that combining and integrating different sources of data using ensemble or fusion-based methods can help to improve the effectiveness of the applied methods in the feature engineering or classification phases. Deep learning is a part of machine learning methods that are based on artificial neural networks with representation learning. Deep learning includes several architectures such as convolutional neural networks, deep neural networks, deep belief networks, and recurrent neural networks. It has been widely used in healthcare to diagnose and detect many diseases, including different types of cancer, lung diseases, cardiovascular disease, diseases from medical imaging, and others. In addition, it has been used for medical imaging, healthcare data analytics, mental health chatbots, personalized medical treatments, prescription audits, responding to patient queries, monitoring of patients’ progress, and other health care applications.

This Special Issue will investigate the advances in smart systems and methods to enhance the detection rate of these diseases. In addition, the Issue will cover several topics in healthcare including the applications of clinical decision support systems, natural language processing, data and text mining, data engineering, internet of things, big data analytics, security and privacy of healthcare data, bio and nature-inspired computing and other related topics. We welcome original research and review articles.

Potential topics include but are not limited to the following: