English 
Italian Introduzione ai Big Data e all’Intelligenza Artificiale in Medicina di Laboratorio
Introduction to Big Data and Artificial Intelligence in Laboratory Medicine
AUTORI
1Dipartimento Innovazione, Sperimentazione e Ricerca Clinica e Traslazionale, Laboratorio Patologia Clinica, Azienda Ospedaliera Universitaria Senese - Dipartimento Biotecnologie Mediche, Università degli Studi di Siena
2Dipartimento di Medicina (DIMED), Università degli Studi di Padova - Dipartimento di Medicina di Laboratorio, Azienda-Ospedale Università di Padova
3UOC Sistemi e Tecnologie Informatiche e di Comunicazione, Asl Roma 1, Roma
4Servizio Tecnologie Informatiche e Telematiche, Azienda USL di Reggio Emilia, IRCCS
5Dipartimento di Medicina di Laboratorio e Anatomia Patologica, Azienda Ospedaliera Universitaria- AUSL di Modena
ABSTRACT
Introduction to Big Data and Artificial Intelligence in Laboratory Medicine
Currently, thanks to the growing computing capacity and the increasing availability of digital data, Data Science is playing an important role in the future development of Laboratory Medicine. However, the concepts of Big Data (BD) and Artificial Intelligence (AI) can still be interpreted in various ways. Clinical laboratories are certainly among the health care organizations producing an important number of data that can be considered BD and it is certainly not a coincidence that they are among the first health organizations to have implemented computer systems within their workflows. Through a process called Data Mining it is possible to extract useful information from BD using automatic or semi-automatic methods that must be preceded by Data Cleaning in order to ensure the cleanliness and correctness of the data themself. Regarding Data Analysis, several Machine Learning or Deep Learning techniques based on different algorithms or on the functioning principle of neural networks can be used; for the development of these techniques, R and Python programming languages are really useful. Although many applications can be useful in Laboratory Medicine, there are still some obstacles to overcome, including poor harmonization of data or fragmentation of sources; moreover, the issue of data accessibility must be managed considering patient’s privacy as a priority. Finally, there is an increase apprehension related to the awareness of the inevitable innovation in the Laboratory Medicine field in the near future, because of these new approaches. To face these challenges, it is necessary that these topics become familiar to the professionals of Laboratory Medicine. Aim of this Document is to share information about BD and AI in order to contribute to the introduction and development of these methodologies in the field of Laboratory Medicine.