دانلود رایگان مقاله انگلیسی کلان داده در علوم پزشکی و پزشکی قانونی - الزویر 2018

Abstract

In less than a decade, big data in medicine has become quite a phenomenon and many biomedical disciplines got their own tribune on the topic. Perspectives and debates are flourishing while there is a lack for a consensual definition for big data. The 3Vs paradigm is frequently evoked to define the big data principles and stands for Volume, Variety and Velocity. Even according to this paradigm, genuine big data studies are still scarce in medicine and may not meet all expectations. On one hand, techniques usually presented as specific to the big data such as machine learning techniques are supposed to support the ambition of personalized, predictive and preventive medicines. These techniques are mostly far from been new and are more than 50 years old for the most ancient. On the other hand, several issues closely related to the properties of big data and inherited from other scientific fields such as artificial intelligence are often underestimated if not ignored. Besides, a few papers temper the almost unanimous big data enthusiasm and are worth attention since they delineate what is at stakes. In this context, forensic science is still awaiting for its position papers as well as for a comprehensive outline of what kind of contribution big data could bring to the field. The present situation calls for definitions and actions to rationally guide research and practice in big data. It is an opportunity for grounding a true interdisciplinary approach in forensic science and medicine that is mainly based on evidence.

6 – A call for definitions and actions

Now that we got more familiar with several and somehow undetermined aspects of big data, it may be time to assess its relevance to medicine and forensics sciences in a scientific, rigorous way. We suggest several actions to ensure the development of a fair, useful and sustainable big data framework in forensic science (table 1). Nonetheless, this work cannot be the work of a few people but should be grounded on a broad concertation.

Big data is an opportunity for researchers to practice a genuine interdisciplinary approach of their work, based on both observations and evidence and techniques adapted to handle vast amounts of heterogeneous, unstructured and distributed data. Big data in medicine should be grounded on both personalized approaches, at several scales (genetic, phenotypic, epigenetic and psychological scales) and social approaches, all based on observations and aiming at predicting and explaining events.

More specifically, big data is for forensic science an unprecedented means for reuniting research, practice and education, both for health professionals and patients. It can provide an excellent framework that abolishes frontiers between narrower specialties, e.g. toxicology, thanatology or victimology and that allows every practitioners working with common, standardized tools on evidence data. It should encourage transparency in research and practice methodologies, in data and expertise sharing, and enhance the reproducibility capability that any science needs to remain sound and sane. Finally, it may favor international collaborations for the best of this field.