QI Meets AI—Implications and Opportunities for Laboratory Medicine

Abstract

Abstract The integration of artificial intelligence (AI) and large language models into healthcare is reshaping quality improvement (QI), creating unprecedented opportunities while introducing new risks that require dedicated governance frameworks and professional competencies. AI-enabled QI has significant implications for laboratory medicine across four key domains: healthcare delivery, problem definition and prioritization, intervention design, and quality control and governance. AI is expected to transform healthcare delivery by integrating fragmented data systems across clinical, pathological, radiological, and pharmacy settings, while incorporating patient-generated information and supporting care beyond traditional healthcare facilities. Within QI, AI’s greatest contribution lies in its ability to characterize system-level problems with greater precision than conventional approaches, drawing on unstructured patient feedback, electronic health records, and comparisons between individual clinical histories and evidence-based guidelines. AI also functions as a QI intervention itself by supporting clinical decision-making, enabling risk prediction, and facilitating continuous guideline monitoring. At the same time, current competencies often lag behind technological capabilities. Emerging failure modes, including algorithmic drift, hallucinations, and unintended consequences resulting from interactions among disparate datasets, necessitate robust governance structures and advanced surveillance mechanisms that remain insufficiently developed. Laboratory professionals play a critical role in this evolving landscape by ensuring the integrity of data used to train and inform AI systems, characterizing relationships between laboratory and other clinical data sources, and implementing quality surveillance processes that safeguard patients from AI misapplication.