Pharmacogenetics aims to investigate the correlation between patient genetic characteristics and the efficacy of pharmaceutical agents, while concurrently evaluating the risks of adverse reactions. This field of research necessitates the application of complex statistical analysis methodologies, and artificial intelligence (AI) capabilities are increasingly being leveraged for such analyses. AI represents an advanced technology employed to automate the execution of tasks that traditionally demand substantial human intellectual effort. A review of scientific literature on the application of machine learning models in pharmacogenetic research has demonstrated that AI is a highly sophisticated and flexible tool capable of facilitating the widespread implementation of pharmacogenetics in clinical practice. A promising area for the application of AI in pharmacogenetics involves the integration of this technology into tasks related to the analysis, detection, prediction, and support of pharmacogenetic information and decision-making systems. The utilization of deep learning technologies has the potential to expand the understanding of drug pharmacodynamics, indications, and contraindications, which may potentially lead to the updating of educational and methodological literature on pharmacology and substantially advance the quality of patient pharmacotherapy. However, the implementation of AI technologies may be hindered by factors such as a shortage of qualified personnel, ethical disagreements, and complexities in legal regulation of this domain. Nonetheless, the application of AI technologies in pharmacogenetic research demonstrates high effectiveness and expediency, despite the existing challenges.
Read full abstract