Die Zukunft hat schon begonnen [1] Wie maschinelles Lernen Anästhesie und Intensivmedizin prägt

Artificial intelligence has become an everyday part of modern medicine. Increasing storage capacity and new ways of processing data are leading to ever increasing quantities of data being collected and analysed, especially in the areas of anaesthesia and intensive care medicine, both of which commonly use electronic patient data management systems. Being able to use machine learning on this data requires that it is not simply stored but readily found, accessible, interoperable and reusable in accordance with the FAIR-principles. Analysis utilises a variety of supervised and unsupervised learning methods leading, amongst other things, to hypotheses for prospective randomised trials, analysis of rare complications, risk stratification and development of decision support tools. The aim of this article is to provide an overview of methods and application of machine learning in anaesthesiology and intensive care medicine. In addition, potential pitfalls associated with the technology and possible solutions are discussed. In anaesthesiology and intensive care medicine – as in other areas of medicine – machine learning can help provide individualised care with the aim of avoiding complications and increasing the quality of care provided.