INTEGRATING ARTIFICIAL INTELLIGENCE WITH BIOLOGICAL DATA FOR PREVENTIVE PHARMACOTHERAPY: A SYSTEMATIC LITERATURE REVIEW
DOI:
https://doi.org/10.33533/jbhi.v1i1.14224Keywords:
Artificial Intelligence, Biological Data, Disease Prevention, Precision Medicine, Preventive PharmacotherapyAbstract
Background
Chronic non-communicable diseases (NCDs) remain the leading causes of global morbidity and mortality, necessitating a transition from reactive treatment to proactive prevention strategies. The integration of artificial intelligence (AI) with biological data offers a promising approach to enhance preventive pharmacotherapy through improved risk prediction, early detection, and personalized treatment planning.
Methods
This study employed a systematic literature review following PRISMA guidelines. A comprehensive search was conducted across Scopus, PubMed, and Web of Science databases for articles published between 2020 and 2026. Eligible studies included peer-reviewed research examining AI or machine learning applications integrating biological data—such as genomics, proteomics, biomarkers, and electronic health records—in preventive pharmacotherapy contexts. A total of 47 studies were included for qualitative synthesis, with 42 studies contributing to quantitative analysis.
Results
The findings indicate that AI-driven models consistently outperform conventional approaches, achieving accuracy above 90% and AUC-ROC values exceeding 0.96 in several applications. Machine learning and deep learning models, particularly hybrid and ensemble approaches, demonstrated superior performance in disease risk prediction, early detection, and treatment optimization. Integration of multi-omics and clinical data enhanced predictive capabilities and enabled precision prevention strategies across cardiovascular, metabolic, oncological, and renal disease domains.
Conclusions
The integration of AI with biological data significantly improves the effectiveness of preventive pharmacotherapy and supports the transition toward precision prevention. However, challenges related to clinical validation, implementation, and data governance must be addressed to ensure successful translation into routine healthcare practice.
