The role of AI in pre-analytical phase - use cases.

The pre-analytical phase of laboratory testing, encompassing processes from test ordering to sample analysis, represents the most error-prone component of laboratory medicine, accounting for 68-98 % of laboratory mistakes. These errors compromise patient safety, increase healthcare costs, and disrupt operational efficiency. Artificial intelligence (AI) and machine learning (ML) technologies have emerged as promising solutions to address these challenges across multiple pre-analytical applications. This narrative review examines current AI research applications and commercial implementations across seven key pre-analytical domains: clot detection, wrong blood in tube (WBIT) error detection, sample dilution management, chemical manipulation detection in urine samples, serum quality assessment based on hemolysis/icterus/lipemia (HIL), test utilization optimization, and automated tube handling. Research studies demonstrate impressive performance, with neural networks achieving accuracies exceeding 95 % for clot detection, XGBoost models reaching 98 % accuracy for WBIT detection, and deep learning systems attaining AUCs above 0.94 for test recommendation systems. However, a significant translation gap persists between research prototypes and commercial deployment. Academic models excel at pattern recognition using curated datasets but face limitations including single-center validation, retrospective designs, and integration challenges. Commercial solutions prioritize deterministic controls, barcoding, and sensor-based approaches that ensure reliability and scalability, with limited explicit AI implementation. Successful clinical laboratory translation requires multicenter prospective validation, robust laboratory information system integration, regulatory compliance frameworks, and evaluation metrics focused on operational outcomes rather than solely statistical performance. As infrastructure and standards mature, strategic AI adoption in pre-analytical tasks offers measurable improvements in safety, efficiency, and cost-effectiveness.