Evolution of Quality Control in Clinical Laboratories: Transition from Traditional Quality Control to Patient-based Real-time Quality Control and Artificial Intelligence-based Intelligent Quality Control

Patient-based real-time quality control (PBRTQC) has emerged as an important approach for continuous monitoring of analytical performance in modern clinical laboratories.By utilizing patient test results rather than intermittent control materials, PBRTQC enables real-time detection of baseline shifts, drift, and other analytical variations.Recently, artificial intelligence (AI) techniques have shown strong potential to complement and expand these capabilities, offering enhanced pattern recognition, anomaly detection, and predictive assessment of analytical risks.This review summarizes the conceptual principles, strengths, and limitations of PBRTQC; explores current trends in AI-driven quality control; and discusses how the integration of these two approaches can evolve into an intelligent QC framework.The proposed integrated model highlights the complementary roles of PBRTQC's patient-derived signals and AI-based predictive analytics in establishing proactive and data-driven quality management.Through this synthesis, the review provides a forward-looking perspective on the future direction of laboratory QC and outlines essential considerations for its clinical implementation.