Harnessing big data and artificial intelligence for personalized medicine: from multi-omics integration to clinical decision-making

High-throughput technologies generate large and complex biological datasets that can challenge conventional methods of analysis and visualization. Artificial intelligence (AI) can support the analysis and integration of these datasets, provide new analytical approaches, and accelerate biological research. However, reliable AI applications depend on high-quality, consistent data. Technical errors, bias, and deficiencies in analytical methods can produce misleading findings and undermine reproducibility. AI-based approaches may help identify errors and improve data quality, but poor-quality or biased datasets, limited reproducibility, and concerns about privacy and ethics remain important barriers to their use in biological research. A literature search was performed in PubMed for papers published between 2015 and 2025. This review summarizes recent advances in AI for biological data analysis, including its main applications and potential benefits. It also discusses methodological, translational, and ethical challenges that may limit implementation. Particular attention is given to data quality and reliability, alongside the responsible use of AI in biological research and its translation to personalized medicine.