AI and Biostatistics in Clinical Decision Support Systems

The advancement of artificial intelligence (AI) and biostatistical methods have permeated many disciplines. In recent years, the integration of AI and biostatistical approaches has contributed significantly to the research in the medical and public health industries. For example, censored survival data are traditionally processed with statistical approaches such as Cox proportional hazards model while recently many cutting-edge AI algorithms including deep learning methods are adapted to effectively handle these challenging problems. In causal inference, data-adaptive machine learning methods have been advocated as an alternative approach to estimate nuisance functions in high-dimensional data while not imposing restrictive functional form assumptions.

This progress indicates that the intersection of AI and biostatistics has a great impact to develop clinical decision support systems and provide references for the evaluation of patients in medical studies. This article collection aims to stimulate further interdisciplinary research on this important topic.

This Research Topic invites original, high-quality contributions that investigate the joint efforts of AI and biostatistics in clinical decision support systems. The main topics of interest include but are not limited to the following:

• Few shots learning
• Reinforcement Learning
• Federated Learning
• Meta-Learning
• Big data mining
• Drug design
• Inference for ultra-high dimensional and/or small sample size data
• Clinical Decision Support with other AI and/or statistical approaches

The Topic Editors would like to acknowledge the key and strategic contribution of Prof. Shu-Kay Angus Ng, School of Medicine and Dentistry, Griffith University, during the development of the Research Topic.