Classifying Process Traces for Stroke Management Quality Assessment: A Deep Learning Approach

Giorgio Leonardi; Stefania Montani; Manuel Striani

doi:10.1007/978-3-030-79161-2_15

Classifying Process Traces for Stroke Management Quality Assessment: A Deep Learning Approach

Giorgio Leonardi, Stefania Montani, Manuel Striani

Department of Science and Technological Innovation

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

Stroke management process trace classification can support quality assessment, since it allows to verify whether better-equipped Stroke Centers actually implement more complete processes, suitable to manage complex patients as well. In this paper, we present an approach to stroke trace classification based on deep learning techniques: in particular, we have tested a traditional architecture, based on Recurrent Neural Networks, as well as novel, more complex ones, which combine recurrent networks with convolutional models. Experimental results have shown the feasibility of the approach, and the superiority of composite architectures, which have led to higher accuracy values.

Original language	English
Title of host publication	Intelligent Systems Reference Library
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	373-387
Number of pages	15
DOIs	https://doi.org/10.1007/978-3-030-79161-2_15
Publication status	Published - 2022

Publication series

Name	Intelligent Systems Reference Library
Volume	211
ISSN (Print)	1868-4394
ISSN (Electronic)	1868-4408

Keywords

Classification
Deep learning
Process traces
Stroke management

Access to Document

10.1007/978-3-030-79161-2_15

Cite this

@inbook{2f84e391c8164e4d894d63712011096d,

title = "Classifying Process Traces for Stroke Management Quality Assessment: A Deep Learning Approach",

abstract = "Stroke management process trace classification can support quality assessment, since it allows to verify whether better-equipped Stroke Centers actually implement more complete processes, suitable to manage complex patients as well. In this paper, we present an approach to stroke trace classification based on deep learning techniques: in particular, we have tested a traditional architecture, based on Recurrent Neural Networks, as well as novel, more complex ones, which combine recurrent networks with convolutional models. Experimental results have shown the feasibility of the approach, and the superiority of composite architectures, which have led to higher accuracy values.",

keywords = "Classification, Deep learning, Process traces, Stroke management",

author = "Giorgio Leonardi and Stefania Montani and Manuel Striani",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.",

year = "2022",

doi = "10.1007/978-3-030-79161-2_15",

language = "English",

series = "Intelligent Systems Reference Library",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "373--387",

booktitle = "Intelligent Systems Reference Library",

address = "Germany",

}

Classifying Process Traces for Stroke Management Quality Assessment: A Deep Learning Approach. / Leonardi, Giorgio ; Montani, Stefania ; Striani, Manuel.
Intelligent Systems Reference Library. Springer Science and Business Media Deutschland GmbH, 2022. p. 373-387 (Intelligent Systems Reference Library; Vol. 211).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

TY - CHAP

T1 - Classifying Process Traces for Stroke Management Quality Assessment

T2 - A Deep Learning Approach

AU - Leonardi, Giorgio

AU - Montani, Stefania

AU - Striani, Manuel

PY - 2022

Y1 - 2022

N2 - Stroke management process trace classification can support quality assessment, since it allows to verify whether better-equipped Stroke Centers actually implement more complete processes, suitable to manage complex patients as well. In this paper, we present an approach to stroke trace classification based on deep learning techniques: in particular, we have tested a traditional architecture, based on Recurrent Neural Networks, as well as novel, more complex ones, which combine recurrent networks with convolutional models. Experimental results have shown the feasibility of the approach, and the superiority of composite architectures, which have led to higher accuracy values.

AB - Stroke management process trace classification can support quality assessment, since it allows to verify whether better-equipped Stroke Centers actually implement more complete processes, suitable to manage complex patients as well. In this paper, we present an approach to stroke trace classification based on deep learning techniques: in particular, we have tested a traditional architecture, based on Recurrent Neural Networks, as well as novel, more complex ones, which combine recurrent networks with convolutional models. Experimental results have shown the feasibility of the approach, and the superiority of composite architectures, which have led to higher accuracy values.

KW - Classification

KW - Deep learning

KW - Process traces

KW - Stroke management

UR - http://www.scopus.com/inward/record.url?scp=85115632423&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-79161-2_15

DO - 10.1007/978-3-030-79161-2_15

M3 - Chapter

T3 - Intelligent Systems Reference Library

SP - 373

EP - 387

BT - Intelligent Systems Reference Library

PB - Springer Science and Business Media Deutschland GmbH

ER -