Artificial intelligence and machine learning in clinical pharmacological research.

Area of Science:

• Pharmacology
• Computational Biology
• Data Science

Background:

• Clinical pharmacology research has historically relied on computational analysis.
• The growing volume of drug-related data necessitates advanced analytical approaches.
• Integrating artificial intelligence (AI) and machine learning (ML) offers a powerful avenue to advance clinical pharmacology.

Purpose of the Study:

• To identify and summarize key research topics and prevalent machine learning (ML) methods used in clinical pharmacology.
• To analyze publication trends in clinical pharmacology research employing ML/AI.

Main Methods:

• Searched the PubMed database for publications related to clinical pharmacology.
• Included research from institutes specializing in clinical pharmacology, focusing on drug-human interactions.
• Extracted and summarized research topics and ML methods from identified publications.

Main Results:

• Machine learning (ML) was identified in 674 clinical pharmacology publications, with a marked increase in activity over the past decade.
• Key research areas utilizing ML/AI include COVID-19 clinical pharmacology, neuropharmacology, drug safety, oncology, and antimicrobial/antiviral research.
• Frequently employed ML methods include neural networks, random forests, and support vector machines.

Conclusions:

• Machine learning (ML) and AI are becoming integral to diverse clinical pharmacology research domains.
• This review highlights specific applications and prevalent ML methodologies in the field.
• The findings underscore the growing impact of AI and ML on advancing our understanding of drug-human interactions.