Artificial Intelligence and Automation in Pre-analytical Phase of Laboratory Testing: A Narrative Review
Rameez Ahmed Khan, Varsha Chowdhry, Nitin Sharma, Deepa ThadaniBackground and Aims:
Pre-analytical errors account for nearly 60%–70% of laboratory inaccuracies and commonly arise during patient identification, specimen collection, labelling, transportation and storage. These errors may lead to unreliable results, misdiagnosis, delayed treatment and increased healthcare costs. To improve diagnostic accuracy and workflow efficiency, artificial intelligence (AI) and automation are increasingly being adopted to reduce human error and enhance pre-analytical laboratory processes.
Methods:
This narrative review evaluated published studies on AI and automation in the pre-analytical phase of laboratory testing. Literature published between 1998 and 2025 was searched using PubMed, Scopus and Google Scholar. Relevant English-language articles on laboratory errors, specimen handling, workflow automation and AI applications were critically reviewed and summarised.
Results:
AI and automation significantly improve the accuracy and efficiency of the pre-analytical phase of laboratory testing. Technologies such as biometric patient identification, robotic phlebotomy, automated sample sorting, barcode and RFID tracking and real-time monitoring systems were found to reduce human errors, enhance specimen traceability, improve workflow standardisation and strengthen quality assurance. These advancements contributed to better diagnostic reliability, patient safety and overall laboratory performance. Conclusions: AI and automation play an important role in reducing pre-analytical laboratory errors by improving accuracy, traceability and workflow efficiency. Their integration into laboratory practice enhances diagnostic reliability, supports patient safety and contributes to better clinical outcomes, although continued human supervision and proper staff training remain essential.