About this Research Topic
In recent years, the rapid development of machine learning (ML), the core of artificial intelligence, has provided novel ideas and methods for solving clinical problems. ML includes supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Due to its significant advantages in processing massive and high-dimensional data, ML has been rapidly applied to medical fields to solve classification and regression problems by developing prediction models. Compared to traditional patient selection methods that rely on healthcare workers' professional knowledge or consensus guidelines, ML is a simpler, faster, and more efficient method of identifying high-risk patients with significant clinical applicability. For instance, a prediction platform based on ML can be used to identify patients at high risk of potentially inappropriate prescriptions.
This Research Topic aims to collect new methodologies and examples of the translational use of ML in clinical practice and discuss the strengths and weaknesses of machine learning methods. The summary and review of some of the key developments in pharmacotherapy using supervised machine learning algorithms are highly welcomed, which is critical for leading researchers to envision rapid advances in this research area. Moreover, this Research Topic aims to gather expert consensus or technical specifications for developing prediction models to solve clinical problems.
This Research Topic focuses on using machine learning technology to solve practical problems in pharmacologic therapy. Specifically, this includes articles that use machine learning algorithms to establish predictive models for key patient indicators such as patient disease progression, risks of adverse drug reactions, and insufficient therapeutic effects. The potential subtopics relevant to this Research Topic, but not limited to, include:
• Application of machine learning in predicting complications
• Application of machine learning in predicting insufficient therapeutic effect
• Application of machine learning in predicting risks of adverse drug reactions
• Application of machine learning in predicting the occurrence of cardiovascular events in pharmacologic therapy
• Application of machine learning in pharmacoeconomic analysis, effectiveness analysis, or safety analysis
Please note that clinical studies and Original research based solely on in silico techniques will not be considered for review.
This Research Topic aims to collect new methodologies and examples of the translational use of ML in clinical practice and discuss the strengths and weaknesses of machine learning methods. The summary and review of some of the key developments in pharmacotherapy using supervised machine learning algorithms are highly welcomed, which is critical for leading researchers to envision rapid advances in this research area. Moreover, this Research Topic aims to gather expert consensus or technical specifications for developing prediction models to solve clinical problems.
This Research Topic focuses on using machine learning technology to solve practical problems in pharmacologic therapy. Specifically, this includes articles that use machine learning algorithms to establish predictive models for key patient indicators such as patient disease progression, risks of adverse drug reactions, and insufficient therapeutic effects. The potential subtopics relevant to this Research Topic, but not limited to, include:
• Application of machine learning in predicting complications
• Application of machine learning in predicting insufficient therapeutic effect
• Application of machine learning in predicting risks of adverse drug reactions
• Application of machine learning in predicting the occurrence of cardiovascular events in pharmacologic therapy
• Application of machine learning in pharmacoeconomic analysis, effectiveness analysis, or safety analysis
Please note that clinical studies and Original research based solely on in silico techniques will not be considered for review.
Keywords: Supervised machine learning algorithms, Clinical prediction, Risk prediction model, Pharmacologic therapy
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.
