[A primer on machine learning].
Wie funktioniert maschinelles Lernen?
Artificial neural networks
Deep learning
Digital literacy
Machine learning
New technologies
Journal
Der Radiologe
ISSN: 1432-2102
Titre abrégé: Radiologe
Pays: Germany
ID NLM: 0401257
Informations de publication
Date de publication:
Jan 2020
Jan 2020
Historique:
pubmed:
8
12
2019
medline:
8
2
2020
entrez:
8
12
2019
Statut:
ppublish
Résumé
The methods of machine learning and artificial intelligence are slowly but surely being introduced in everyday medical practice. In the future, they will support us in diagnosis and therapy and thus improve treatment for the benefit of the individual patient. It is therefore important to deal with this topic and to develop a basic understanding of it. This article gives an overview of the exciting and dynamic field of machine learning and serves as an introduction to some methods primarily from the realm of supervised learning. In addition to definitions and simple examples, limitations are discussed. The basic principles behind the methods are simple. Nevertheless, due to their high dimensional nature, the factors influencing the results are often difficult or impossible to understand by humans. In order to build confidence in the new technologies and to guarantee their safe application, we need explainable algorithms and prospective effectiveness studies.
Sections du résumé
BACKGROUND
BACKGROUND
The methods of machine learning and artificial intelligence are slowly but surely being introduced in everyday medical practice. In the future, they will support us in diagnosis and therapy and thus improve treatment for the benefit of the individual patient. It is therefore important to deal with this topic and to develop a basic understanding of it.
OBJECTIVES
OBJECTIVE
This article gives an overview of the exciting and dynamic field of machine learning and serves as an introduction to some methods primarily from the realm of supervised learning. In addition to definitions and simple examples, limitations are discussed.
CONCLUSIONS
CONCLUSIONS
The basic principles behind the methods are simple. Nevertheless, due to their high dimensional nature, the factors influencing the results are often difficult or impossible to understand by humans. In order to build confidence in the new technologies and to guarantee their safe application, we need explainable algorithms and prospective effectiveness studies.
Identifiants
pubmed: 31811324
doi: 10.1007/s00117-019-00616-x
pii: 10.1007/s00117-019-00616-x
doi:
Types de publication
Journal Article
Review
Langues
ger
Sous-ensembles de citation
IM
Pagination
24-31Références
Stud Health Technol Inform. 2018;247:581-585
pubmed: 29678027
NPJ Digit Med. 2019 Jul 9;2:65
pubmed: 31388567
Radiologe. 2020 Jan;60(1):32-41
pubmed: 31820014
Nat Med. 2019 Jan;25(1):44-56
pubmed: 30617339
Nature. 2014 Jan 9;505(7482):146-8
pubmed: 24402264