A scoping review and bibliometric analysis (ScoRBA) of machine learning in genetic data analysis: unveiling the transformative potential

Abstract

 This study uses scoping review and bibliometric analysis; ScoRBA, to comprehensively highlight the recurrent themes linked to machine learning (ML) applications in genetic data analytics. Using relevant documents and the VOSviewer software, co-occurrence keywords analysis was performed. The important domains identified are Cancer Genomics, Bioinformatics, Precision Medicine, Disease Biomarkers, and Genetic Algorithms. These domains benefit from ML's data-driven insights, which have the potential to revolutionize healthcare and biomedical research. The study reveals a surge in research publications and citations in recent years, indicating the growing importance of ML in genetic data analysis. It identifies research gaps and challenges within each domain, offering recommendations for future investigations. This review emphasizes the potential for personalized, data-driven healthcare by highlighting the power of ML and advanced computational methods. By addressing the identified research gaps and following the proposed recommendations, these interdisciplinary fields promise to improve disease diagnosis, prognosis, and treatment, while deepening our understanding of human biology. In conclusion, this study provides an overview of the application of ML in genetic data analysis, highlighting its pattern, advances, gaps and future directions.