• Applications of Artificial Intelligence in Drug Personalization
  • Roksana Pirdayeh,1,*
    1. Islamic Azad University, Science and Research Branch


  • Introduction: The traditional "one-size-fits-all" model of medicine often leads to variable patient outcomes, with treatments that are highly effective for some and ineffective or even harmful for others.5 This variability is largely due to the unique genetic and molecular characteristics of each individual.6 Personalized medicine seeks to address this by leveraging an individual’s genetic, environmental, and lifestyle factors to guide medical decisions.1 The field has been propelled by advancements in high-throughput sequencing and biomedical data collection, which now generate an unprecedented amount of complex data that exceeds the capacity of traditional statistical methods.2 This is where AI emerges as a powerful solution.7 This review aims to explore the cutting-edge applications of AI in the field of drug personalization, detailing how AI algorithms are being employed to analyze biological data to predict drug efficacy, identify drug targets, and optimize dosages.1
  • Methods: This review was conducted through a comprehensive literature search of prominent scientific databases, including PubMed, Scopus, and Web of Science, focusing on recent, high-impact articles published from 2020 to 2025. The search strategy included terms such as "artificial intelligence," "machine learning," "deep learning," "personalized medicine," "drug personalization," "pharmacogenomics," and "drug repurposing".4 Only peer-reviewed articles directly relevant to the use of AI for drug personalization were included.
  • Results: The literature review revealed several key areas where AI is significantly impacting drug personalization. The primary applications can be categorized as follows: Predicting Drug Response and Toxicity: AI models, particularly those based on deep learning, have been successfully applied to analyze genomic data to predict how individual patients will respond to specific drugs.8 For example, the deep learning model PASO has been used to predict drug sensitivity in cancer cells, helping clinicians select the most effective chemotherapy agents for a patient's tumor.6 Similarly, AI is being used to predict adverse drug reactions by analyzing patient electronic health records and genetic data.9 Biomarker Discovery and Patient Stratification: AI algorithms can sift through vast datasets to identify novel biomarkers that predict drug efficacy.8 These biomarkers can be genetic, proteomic, or imaging-based, helping to identify patient subgroups that are more likely to respond to a particular therapy.8 This allows for the stratification of patients into clinically meaningful groups, ensuring the right treatment is given to the right patient.5 Drug Repurposing and Discovery: AI is accelerating the discovery of new drugs and the identification of new uses for existing ones. By analyzing molecular structures and their interactions with biological targets, AI models can predict potential drug candidates more quickly and efficiently than traditional methods.4 This process, once opportunistic, has become a "systematic science" with AI.4 The COVID-19 pandemic highlighted how AI can be a rapid response tool for repurposing drugs.10
  • Conclusion: The integration of artificial intelligence into the healthcare landscape represents a paradigm shift towards truly personalized medicine.11 As this review demonstrates, AI is a vital tool being actively employed to overcome the data-driven challenges of drug personalization. By analyzing complex biological and clinical data, AI algorithms are enabling the prediction of individual drug responses, the discovery of novel biomarkers, and the optimization of treatment plans.8 These advancements promise to significantly enhance the efficacy and safety of drug therapies, ultimately improving patient outcomes.1 While substantial progress has been made, challenges remain, including data privacy concerns, algorithmic bias from imbalanced datasets, and the interpretability of complex AI models.7 However, the rapid evolution of AI technology and increasing collaboration suggest a future where AI-driven drug personalization is a standard of care.7
  • Keywords: Artificial Intelligence, Personalized Medicine, Pharmacogenomics, Precision Medicine, Healthcare