About this Research Topic
The tasks of clinical predictive modeling and clinical decision making are largely driven by the advancement of AI techniques in recent years. As more and more data accumulated, there is a great need for the data mining, information extraction and data reuse for various types of disease, different types of medication and multi-modal Electronic health record (EHR) data.
The goal of this Research Topic is to attract research on data mining and predictive modeling on large clinical data, including structured EHR, clinical notes, clinical literature, clinical images, etc. Involved techniques may include machine learning technologies such as pre-training, transfer learning, reinforcement learning, adversarial training, and graph mining. Associated models may include deep convolutional neural networks (CNN), recurrent neural networks (RNN), attention mechanism, graph neural networks (GNN), Transformer, and related algorithms and variants.
• natural language processing on clinical text including clinical notes, research papers, etc.
• knowledge construction techniques including knowledge graph, ontology, terminology, etc.
• predictive modeling over large structured EHR data, unstructured EHR and multimodal HER
• transfer learning techniques over big data
• agent-based modeling and reinforcement learning techniques on clinical data
We also acknowledge the contribution of Dr. Fang Li, Dr. Zhiheng Li, and Prof. Arko Barman in initiating and preparing this project
Keywords: artificial intelligence, deep learning, EHR, data mining, predictive modeling
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.