Key points are not available for this paper at this time.
Total laboratory automation (TLA) in microbiology integrates robotic specimen processing, automated conveyor systems, smart incubators, and high-resolution digital imaging to automate culture-based workflows from specimen setup to plate reading. Successful implementation requires careful planning, including assessment of existing laboratory infrastructure and a strategy for interfacing third-party instruments and information systems. Major barriers include capital investment, interoperability, and the need for standardized information technology interfaces. Recent advances in artificial intelligence (AI), particularly machine learning and convolutional neural networks, have extended the value of TLA by enabling automated image interpretation, culture plate screening, and predictive analyses. These tools can reduce manual workload and turnaround time while improving standardization. In this review, drawing primarily on our institutional experience, we examine the impact of TLA and AI on diagnostic microbiology workflows, implementation strategies, and performance assessment. We also discuss automated digital microscopy, the integration of phenotypic and molecular methods, and the principal limitations that still constrain broader adoption. Finally, we highlight the need for molecular diagnostic stewardship to preserve clinical relevance and cost-effectiveness.
Cherkaoui et al. (Mon,) studied this question.