E-health can be defined as the use of information and communication technology for the enablement or improvement of healthcare. The rapid development of technology with increasing internet access around the world and the pervasiveness of smartphones makes E-health relevant to all. E-health has expanded from web-based services to health apps, online video services, and social media, and new services and technologies are constantly being presented. Social networks such as Twitter are a very valuable source of real-time information to gain new knowledge, for example, of when and where a new disease or pandemic will happen and how to track it over time.

Increasing and ageing populations with more chronic illnesses are straining health services in both developed and developing countries. Existing knowledge-based systems in E-health services with learning capabilities may improve access to quality health information and improve self-management and thereby help alleviate the burden on health services. In addition, E-health knowledge-based systems can improve the quality of health services by increasing shared decision-making and by empowering patients. Monitoring, learning, knowledge validation, transparency, accountability, bias, and responsibility would be part of the E-health systems and must cope with the challenges of limited external intervention and varying data acquisition (e.g., behavioural, personalised health models, physiological, etc.).

This Special Issue aims to serve researchers and developers to publish original, innovative, and state-of-the-art machine learning methods, algorithms, and architectures to analyze the modern vision of intelligent solutions in E-health and medical communications services. Descriptions of innovative solutions are welcome, in the form of frameworks for intelligent systems for personalised health, and novel algorithms that take into account several important factors such as knowledge via social networks to measure behavioural risk factors and localize illnesses by demographics for reproducibility and trustworthiness of different data sources. We welcome original research and review articles that address these challenges, especially from medical, psychological, and societal perspectives. The description of E-health services and their use, studies of why E-health services are used, the various outcomes of using such services, and how E-health services impact traditional health services are examples of topics that are within the scope of this Special Issue.

Potential topics include but are not limited to the following:

• Machine learning for data mining in E-Health services
• Industrial and commercial applications of Intelligent knowledge-based systems in healthcare studies
• Learning from unlabelled data, unsupervised learning, and online learning
• Crowdsourcing models, frameworks, and algorithms for health surveillance
• Legal, ethical, and social consequences of automated decision-making systems in E-health
• Intelligent agents and systems for personalised medicine
• Big data management systems and data analytics in healthcare services
• Personalised health ontologies and models