Abstract
Deep learning is a subfield of artificial intelligence (AI) that is concerned with developing large and complex neural networks for various tasks. As of today, there exists a wide variety of DL models yielding promising results in many subfields of AI, such as computer vision (CV) and natural language processing (NLP). In this chapter, we provide an overview of deep learning, elaborating on some common model architectures. Furthermore, we describe the advantages and disadvantages of deep learning compared to machine learning. Afterwards, we discuss the application of deep learning models in various clinical tasks, focusing on clinical imaging, electronic health records and genomics. We also provide a brief overview of prediction tasks in deep learning. The final section of this chapter discusses the limitations and challenges of deploying deep learning models in healthcare and medicine, focusing on the lack of explainability in deep learning models.
Original language | English |
---|---|
Title of host publication | Clinical Applications of Artificial Intelligence in Real-World Data |
Editors | Folkert W. Asselbergs, Spiros Denaxas, Daniel L. Oberski, Jason H. Moore |
Place of Publication | Cham |
Publisher | Springer |
Pages | 189-202 |
Number of pages | 14 |
Edition | 1 |
ISBN (Electronic) | 9783031366789 |
ISBN (Print) | 9783031366772 |
DOIs | |
Publication status | Published - 5 Nov 2023 |
Keywords
- Classification
- Clinical imaging
- Deep learning
- Electronic health records
- Explainable AI (XAI)
- Machine learning
- Regression
- Segmentation