Best Practices for Big Data Sources and Methods in Surgery

Ce dossier présente un ensemble de guides pratiques concernant l'intelligence artificielle et les sources de données massives dans la recherche en chirurgie

Résumé en anglais

Big data as a concept describes datasets that are too large and complex and collected at a pace that is difficult to handle and analyze using traditional statistical methods. It is often described as characterized by the 3 V’s: volume, variety, and velocity, as described initially by Gartner analyst Doug Laney in 2001. It has since been expanded to other attributes like veracity, value, and relationality. The most common examples of big data sources in health care are electronic health record data and associated billing or administrative data sources used by large health care systems and payers. Adding to these sources is the large volume of data being generated through advances in digital health, such as the data generated through smartphones, sensors, operative technologies, and remote monitoring devices. To realize the potential of these big data sources to advance health and health care delivery, new analytic techniques through large-scale informatics and artificial intelligence (machine and deep learning) tools are needed to aid investigators in answering research questions that were not previously possible.