THE SCIENCE OF DATA AND EVIDENCE-BASED MEDICINE

Abstract

Background. Evidence-based medicine is undergoing profound transformation under the influence of data science, big data technologies, precision medicine, and artificial intelligence. The traditional hierarchy of evidence, primarily centered on randomized controlled trials and meta-analyses, increasingly reveals methodological constraints, publication bias, and limited applicability in complex real-world clinical environments.
Materials and Methods. The study was conducted using systematic and comparative analysis of contemporary scientific publications addressing the evolution of evidence-based medicine and the implementation of data science, big data analytics, Internet of Things technologies, and artificial intelligence in healthcare. An interdisciplinary synthesis approach was applied to evaluate the prospects of integrating hybrid human–artificial intelligence models into modern evidence-based clinical practice.
Results. The analysis indicates that fragmentation of medical data, redundancy of low-quality systematic reviews, and inconsistencies in evidence interpretation reduce the practical value of traditional evidence hierarchies. The integration of large-scale clinical, laboratory, genomic, imaging, and electronic health record data enables the development of predictive analytics and supports personalized, patient-centered care. Machine learning algorithms and hybrid human–AI systems improve evidence interpretation, facilitate clinical decision support, and enhance adaptability to multifactorial and context-dependent medical conditions.
Conclusions. The further development of evidence-based medicine requires dynamic adaptation of its principles through the integration of data science methodologies, standardized data governance, and advanced analytical platforms. Hybrid human-AI collaboration represents a promising paradigm for achieving adaptive, personalized, and scientifically grounded healthcare in the era of digital transformation.