The quick process of digitization of the healthcare system and high-dimensional biomedical data reveal constraints in the context of traditional population-based decision-making. The similar gaps are tackled by accuracy medicine which incorporates every biological, clinical, and behavioral information at the individual level. It is possible through artificial intelligence and big data analytics to conduct multi-omics data, electronic health records, medical imaging, and wearable sensor analyses on a scalable basis. This paper is a data-driven and systematic review of big data analytics based on AI in the field of precision medicine, with a focus on predictive, preventive, and personalized care. Results demonstrate that combined AI systems are more efficient than independent approaches in disease stratification, real time-based, and clinical decision support, and determine problems of scalability, interpretability, privacy, and ethical control.