From Prediction to Prevention: A Systematic Review of AI-Driven Predictive Analytics In Healthcare

Purpose: This study examined how Artificial Intelligence (AI)-enabled predictive analytics moves from technical prediction towards actionable preventive healthcare and identified the conditions that enable or constrain this translation. Design/methodology/approach: A systematic literature review of 12 peer-reviewed studies published between 2021 and 2026 was conducted using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-guided screening, Critical Appraisal Skills Programme (CASP) quality assessment, and open, axial, and selective coding with frequency analysis. Findings: Three themes emerged: predictive performance does not equal preventive value, timeliness and actionability shape preventive utility, and implementation conditions shape translation into practice. The findings show that preventive value depends on the alignment of predictive validity, timely action, workflow integration, decision ownership, and governance. Originality/value: The study introduces the prediction-to-prevention translation gap and develops a decision-oriented framework for evaluating AI beyond model performance.