The practical advantages of artificial intelligence (AI), specifically machine learning and deep learning, in healthcare are developing. A model that continually learns and evolves depending on a higher number of input values while keeping previously gained information is defined as a continual learner. Supervised training enables the network to learn and alter its behavior while remembering the original task. Netflix and Amazon's recommender systems are well-known instances of continuous learning. As users engage with the model output, these systems automatically capture fresh tagged data. The healthcare sector and its consumers might also benefit from cognitive computing concepts and technology (patients, physicians, and so on). Data acquired through these methods might also assist health care officials to better grasp what the public wants and needs. Assisting the doctor with activities such as diagnosis and decision making is perfect for a continuous learning model (learning using tagged static health information). The model would have to use its past learning of new information, fine-tune its given tasks, or perhaps even discover different tasks progressively.

This Special Issue brings together academics and industry to address issues and propose answers for the development of adequate solutions for cognitive-based continual and traditional deep learning-powered healthcare sector informatics frameworks. This Special Issue will explore this new dimension by covering cutting-edge emerging challenges. Original research and review papers on this subject are encouraged to be published in this Special Issue.

Potential topics include but are not limited to the following:

• Cognitive computation and continual deep learning in healthcare recommender systems
• Personality-driven, continual deep learning techniques in biomedical recommender systems
• Cognitive-based AI applications in healthcare with a continual learning paradigm
• Emotion recognition in surveillance systems for the healthcare industry
• Analyzing feedback from patients to determine cure efficiency
• Machine and deep learning pharmacogenomics research in neuroscience
• Development of cognitive recommender systems based on machine and deep learning for health informatics post-marketing tracking
• Develop machine and deep learning algorithms for user tonality tracking in the field of medical and healthcare informatics
• Benchmarking the development of a cognitively driven, machine-readable corpora of adverse reactions and health problems
• A continuous deep learning system incorporating routine health information and a professional set of inputs