SEQC Spanish Society of Laboratory Medicine

Spanish Society of Laboratory Medicine

• The integration of information extraction techniques, advanced data analysis, and process automation is changing laboratory practice: reducing errors and costs, simplifying workflows, and increasing productivity.

• A balance needs to be established between the technological advance that massive data analysis and Artificial Intelligence entails and the privacy risks for patients, as well as correctly understanding and interpreting their results.

Laboratory Medicine is one of the specialties that uses Artificial Intelligence (AI) as a support tool for clinical practice. Its use has led to improved precision in laboratory tests, greater productivity, and simplification of workflows. However, the incorporation of AI in healthcare practice must not compromise the privacy of patients, nor the correct understanding and interpretation of their results. The XVII National Congress of the Clinical Laboratory (LABCLIN 2023), organized by the Spanish Society of Laboratory Medicine (SEQC^ML), the Spanish Association of Medical Biopathology (AEBM-ML) and the Spanish Association of the Clinical Laboratory (AEFA), addressed these issues from October 18 to 20 in Zaragoza.

Specifically, in the symposium, “Big Data: Advanced Data Analysis and Artificial Intelligence in the Laboratory”, moderated by Dr. Germán Seara Aguilar, from the Hospital 12 de Octubre Research Institute (i+12), the use of data and AI in the healthcare field was examined in depth. According to Dr. Germán Seara Aguilar, “the application of Artificial Intelligence in the automation of processes has led to an improvement in precision, with a reduction in errors, and a simplification of workflows, with an increase in productivity and reduced costs.” Additionally, he said, automatic reporting improves communication with clinicians and patients and allows for the semi-automatic introduction of personalized recommendations.

The incorporation of massive data analysis, Machine Learning (ML) and Deep Learning algorithms in Artificial Intelligence models has greatly increased their power of application, decreasing their “explainability”, that is, the ability to understand and interpret correctly how you arrived at your results. The congress delved into the need to establish a balance between the technological advances represented by massive data analysis and AI and the risks of privacy for patients and “explainability.”

Training needs

Data Mining and Machine Learning allow us to improve data analysis, their description, classification and segmentation, the discovery of behavioral patterns, and the generation of predictive models. "At the same time, it requires professional training in the field of AI, systematic interdisciplinary work, the incorporation of mechanisms for verification and auditing of results, and an increased need for security measures, both in computer science and in privacy, to ensure ethical management of new technologies,” commented Dr. Germán Seara Aguilar.

Finally, he highlighted that the current digital revolution and the expansion of massive data analysis and Artificial Intelligence techniques are changing the way of practicing the profession and communicating with society. Despite this, Dr. Germán Seara Aguilar reminded that the future should not focus on replacing professionals, “but rather on supporting them in their work, improving the quality of services and value for patients. And it doesn't seem like it's optional. Either we join in or it will devastate us,” he concluded.