About this Research Topic
Deep learning strategies have emerged as valuable methodologies for applications in human physiology and healthcare because they have delivered promising and obvious outcomes in these disciplines. The advent of new medical diagnostics and therapeutics has given rise to the difficult fields of intelligent virtual design and smart testing of simulation technologies for an anatomy in a physiological environment. Patient-specific models that are coupled with artificial intelligence can now be generated from the real physiology faster and more efficiently than ever before, thanks to recent advances in medical imaging, computational power, machine learning, and mathematical algorithms. In particular, deep learning has paved the way for the tackling of problems in human physiology, which may advance a paradigm shift in computer-aided diagnostics of the examined physiological problem. Such a framework has the potential of giving rise to an integrated deep learning and physiology concept, which we termed as deep physiology.
Traditionally, physiology research has been conducted in laboratories, where experiments frequently necessitate the imposition of repetitive impacts on an organic system. Recently, deep learning has been presented as a research tool in solving problems in human physiology, potentially reducing the number of invasive measurements and anticipating pathologic processes which are not discovered by traditional testing. However, the effectiveness of deep learning in human physiology has yet to be demonstrated. Researchers are invited to submit work on recent advances in the area of physiology based on deep learning techniques. This Research Topic will feature a compilation of research and review articles emphasizing significant findings in the field of human physiology. Potential topics include, but are not limited to:
• Deep learning-based models for human physiological system
• Deep learning applications in exercise physiology, pre-and post-operative diagnostics
neurology, and hematology
• Knowledge engineering in human physiology
• Deep learning for epigenetics and future medical applications
• Recurrent neural network (RNN) developments for human physiology
Topic Editor Yubing Shi is receiving a research grant from Alibaba Cloud. All other Topic Editors declare no competing interests with regards to the Research Topic subject.
Traditionally, physiology research has been conducted in laboratories, where experiments frequently necessitate the imposition of repetitive impacts on an organic system. Recently, deep learning has been presented as a research tool in solving problems in human physiology, potentially reducing the number of invasive measurements and anticipating pathologic processes which are not discovered by traditional testing. However, the effectiveness of deep learning in human physiology has yet to be demonstrated. Researchers are invited to submit work on recent advances in the area of physiology based on deep learning techniques. This Research Topic will feature a compilation of research and review articles emphasizing significant findings in the field of human physiology. Potential topics include, but are not limited to:
• Deep learning-based models for human physiological system
• Deep learning applications in exercise physiology, pre-and post-operative diagnostics
neurology, and hematology
• Knowledge engineering in human physiology
• Deep learning for epigenetics and future medical applications
• Recurrent neural network (RNN) developments for human physiology
Topic Editor Yubing Shi is receiving a research grant from Alibaba Cloud. All other Topic Editors declare no competing interests with regards to the Research Topic subject.
Keywords: Human Physiology, Deep Learning, Digital Physiology, Physiology, RNN for human physiology
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
