Revolutionizing Medical Laboratory Diagnostics through Artificial Intelligence and Multi-Criteria Decision-Making: An Application of TOPSIS and VIKOR Methods

Abstract

Artificial intelligence (AI) is rapidly changing clinical laboratories, but it has limited the ability to translate research findings into practice. To guide future development and adoption of AI, it is important to understand the current state of use of such applications as well as the benefits they provide; also to recognize persistent implementation barriers. The aim of this systematic review is to evaluate the current applications of artificial intelligence in laboratory medicine, assess the measurable improvements in diagnostic accuracy, operational efficiency, and error reduction, identify technical, regulatory, ethical, or workforce-related challenges, as well as provide evidence-based recommendations for successfully implementing AI in clinical settings. This paper focuses on the applications of AI in clinical laboratory settings and examined peer-reviewed literature published between 2014 and 2026. Machine learning, deep learning and natural language processing along with computer vision applications across chemistry, hematology, microbiology, genomics and point-of-care testing domains were also reviewed. As a result, the study shows that AI technologies can now deliver diagnostic accuracy > 90% in many applications; reduce unnecessary testing by up to 50%; cut turnaround times from 23-60%; increase result reliability by 25%; and reduce preanalytical errors by 30%. In laboratory medicine, artificial intelligence has the potential to revolutionize diagnostic accuracy and operation, while also improving patient outcomes. Achieving this potential requires a coordinated approach across research, regulatory and institutional levels, as well as across educational institutions. The priority areas are the establishment of strong validation frameworks, transparent regulatory pathways, investment in interoperable infrastructure, comprehensive training programs for laboratory professionals, algorithmic fairness, and sustainable AI practices. Laboratory medicine is poised to become a future where human expertise and artificial intelligence work together to provide accurate, personalized, and globally accessible diagnostics.

Keywords: Artificial Intelligence, Laboratory Medicine, Machine Learning, Diagnostic Accuracy, Clinical Laboratory, Healthcare Implementation