The role of deep learning in improving healthcare

Stefan Thaler, Vlado Menkovski

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

Abstract

Healthcare is transforming through adoption of information technologies (IT) and digitalization. Machine learning (ML) and artificial intelligence (AI) are two of the IT technologies that are leading this transformation. In this chapter we focus on Deep Learning (DL), a subfield of ML that relies on deep artificial neural networks to deliver breakthroughs in long-standing AI problems. DL is about working with high-dimensional data (e.g., images, speech recording, natural language) and learning efficient representations that allow for building successful models. We present a structured overview of DL methods applied to healthcare problems based on their suitability of the different technologies to the available modalities of healthcare data. This data-centric perspective reflects the data-driven nature of DL methods and allows side-by-side comparison with different domains in healthcare. Challenges, in broad adoption of DL, are commonly related to some of its main drawbacks, particularly lack of interpretability and transparency. We discuss the drawbacks and limitations of DL technology that specifically come to light in the domain of healthcare. We also address the need for a considerable amount of data and annotations to successfully build these models that can be a particularly expensive and time-consuming effort. Overall, the chapter offers insights into existing applications of DL to healthcare on their suitability for specific types of data and their limitations.

LanguageEnglish
Title of host publicationData Science for Healthcare
Subtitle of host publicationMethodologies and Applications
EditorsSergio Consoli, Diego Reforgiato Recupero, Milan Petković
Place of PublicationCham
PublisherSpringer
Pages75-116
Number of pages42
ISBN (Electronic)978-3-030-05249-2
ISBN (Print)978-3-030-05248-5
DOIs
StatePublished - 1 Jan 2019

Fingerprint

Learning
Delivery of Health Care
Artificial Intelligence
Technology
Artificial intelligence
Information technology
Learning systems
Deep learning
Transparency
Language
Neural networks
Machine Learning

Cite this

Thaler, S., & Menkovski, V. (2019). The role of deep learning in improving healthcare. In S. Consoli, D. Reforgiato Recupero, & M. Petković (Eds.), Data Science for Healthcare: Methodologies and Applications (pp. 75-116). Cham: Springer. DOI: 10.1007/978-3-030-05249-2_3
Thaler, Stefan ; Menkovski, Vlado. / The role of deep learning in improving healthcare. Data Science for Healthcare: Methodologies and Applications. editor / Sergio Consoli ; Diego Reforgiato Recupero ; Milan Petković. Cham : Springer, 2019. pp. 75-116
@inbook{72ba859ba19348e292a834d3dfddd1b7,
title = "The role of deep learning in improving healthcare",
abstract = "Healthcare is transforming through adoption of information technologies (IT) and digitalization. Machine learning (ML) and artificial intelligence (AI) are two of the IT technologies that are leading this transformation. In this chapter we focus on Deep Learning (DL), a subfield of ML that relies on deep artificial neural networks to deliver breakthroughs in long-standing AI problems. DL is about working with high-dimensional data (e.g., images, speech recording, natural language) and learning efficient representations that allow for building successful models. We present a structured overview of DL methods applied to healthcare problems based on their suitability of the different technologies to the available modalities of healthcare data. This data-centric perspective reflects the data-driven nature of DL methods and allows side-by-side comparison with different domains in healthcare. Challenges, in broad adoption of DL, are commonly related to some of its main drawbacks, particularly lack of interpretability and transparency. We discuss the drawbacks and limitations of DL technology that specifically come to light in the domain of healthcare. We also address the need for a considerable amount of data and annotations to successfully build these models that can be a particularly expensive and time-consuming effort. Overall, the chapter offers insights into existing applications of DL to healthcare on their suitability for specific types of data and their limitations.",
author = "Stefan Thaler and Vlado Menkovski",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-3-030-05249-2_3",
language = "English",
isbn = "978-3-030-05248-5",
pages = "75--116",
editor = "Sergio Consoli and {Reforgiato Recupero}, Diego and Milan Petković",
booktitle = "Data Science for Healthcare",
publisher = "Springer",
address = "Germany",

}

Thaler, S & Menkovski, V 2019, The role of deep learning in improving healthcare. in S Consoli, D Reforgiato Recupero & M Petković (eds), Data Science for Healthcare: Methodologies and Applications. Springer, Cham, pp. 75-116. DOI: 10.1007/978-3-030-05249-2_3

The role of deep learning in improving healthcare. / Thaler, Stefan; Menkovski, Vlado.

Data Science for Healthcare: Methodologies and Applications. ed. / Sergio Consoli; Diego Reforgiato Recupero; Milan Petković. Cham : Springer, 2019. p. 75-116.

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

TY - CHAP

T1 - The role of deep learning in improving healthcare

AU - Thaler,Stefan

AU - Menkovski,Vlado

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Healthcare is transforming through adoption of information technologies (IT) and digitalization. Machine learning (ML) and artificial intelligence (AI) are two of the IT technologies that are leading this transformation. In this chapter we focus on Deep Learning (DL), a subfield of ML that relies on deep artificial neural networks to deliver breakthroughs in long-standing AI problems. DL is about working with high-dimensional data (e.g., images, speech recording, natural language) and learning efficient representations that allow for building successful models. We present a structured overview of DL methods applied to healthcare problems based on their suitability of the different technologies to the available modalities of healthcare data. This data-centric perspective reflects the data-driven nature of DL methods and allows side-by-side comparison with different domains in healthcare. Challenges, in broad adoption of DL, are commonly related to some of its main drawbacks, particularly lack of interpretability and transparency. We discuss the drawbacks and limitations of DL technology that specifically come to light in the domain of healthcare. We also address the need for a considerable amount of data and annotations to successfully build these models that can be a particularly expensive and time-consuming effort. Overall, the chapter offers insights into existing applications of DL to healthcare on their suitability for specific types of data and their limitations.

AB - Healthcare is transforming through adoption of information technologies (IT) and digitalization. Machine learning (ML) and artificial intelligence (AI) are two of the IT technologies that are leading this transformation. In this chapter we focus on Deep Learning (DL), a subfield of ML that relies on deep artificial neural networks to deliver breakthroughs in long-standing AI problems. DL is about working with high-dimensional data (e.g., images, speech recording, natural language) and learning efficient representations that allow for building successful models. We present a structured overview of DL methods applied to healthcare problems based on their suitability of the different technologies to the available modalities of healthcare data. This data-centric perspective reflects the data-driven nature of DL methods and allows side-by-side comparison with different domains in healthcare. Challenges, in broad adoption of DL, are commonly related to some of its main drawbacks, particularly lack of interpretability and transparency. We discuss the drawbacks and limitations of DL technology that specifically come to light in the domain of healthcare. We also address the need for a considerable amount of data and annotations to successfully build these models that can be a particularly expensive and time-consuming effort. Overall, the chapter offers insights into existing applications of DL to healthcare on their suitability for specific types of data and their limitations.

UR - http://www.scopus.com/inward/record.url?scp=85064368668&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-05249-2_3

DO - 10.1007/978-3-030-05249-2_3

M3 - Chapter

SN - 978-3-030-05248-5

SP - 75

EP - 116

BT - Data Science for Healthcare

PB - Springer

CY - Cham

ER -

Thaler S, Menkovski V. The role of deep learning in improving healthcare. In Consoli S, Reforgiato Recupero D, Petković M, editors, Data Science for Healthcare: Methodologies and Applications. Cham: Springer. 2019. p. 75-116. Available from, DOI: 10.1007/978-3-030-05249-2_3