Improving Early Prognosis of Dementia Using Machine Learning Methods

Research output: Contribution to journalArticleResearchpeer review

Authors

  • Georgios Katsimpras
  • Fotis Aisopos
  • Peter Garrard
  • Maria Esther Vidal
  • Georgios Paliouras

Research Organisations

External Research Organisations

  • National Centre For Scientific Research Demokritos (NCSR Demokritos)
  • St. George's University of London
View graph of relations

Details

Original languageEnglish
Article number30
Number of pages16
JournalACM Transactions on Computing for Healthcare
Volume3
Issue number3
Publication statusPublished - 7 Apr 2022

Abstract

Early and precise prognosis of dementia is a critical medical challenge. The design of an optimal computational model that addresses this issue, and at the same time explains the underlying mechanisms that lead to output decisions, is an ongoing challenge. In this study, we focus on assessing the risk of an individual converting to Dementia in the short (next year) and long (one to five years) term, given only a few early-stage observations. Our goal is to develop a machine learning model that could assist the prediction of dementia from regular clinical data. The results show that combining various machine learning techniques together can successfully define ways to identify the risks of developing dementia over the following five years with accuracies considerably above average rates. These findings suggest that accurately developed models can be considered as a promising tool to improve early dementia prognosis.

Keywords

    Dementia, machine learning, prognosis

ASJC Scopus subject areas

Cite this

Improving Early Prognosis of Dementia Using Machine Learning Methods. / Katsimpras, Georgios; Aisopos, Fotis; Garrard, Peter et al.
In: ACM Transactions on Computing for Healthcare, Vol. 3, No. 3, 30, 07.04.2022.

Research output: Contribution to journalArticleResearchpeer review

Katsimpras, G, Aisopos, F, Garrard, P, Vidal, ME & Paliouras, G 2022, 'Improving Early Prognosis of Dementia Using Machine Learning Methods', ACM Transactions on Computing for Healthcare, vol. 3, no. 3, 30. https://doi.org/10.1145/3502433
Katsimpras, G., Aisopos, F., Garrard, P., Vidal, M. E., & Paliouras, G. (2022). Improving Early Prognosis of Dementia Using Machine Learning Methods. ACM Transactions on Computing for Healthcare, 3(3), Article 30. https://doi.org/10.1145/3502433
Katsimpras G, Aisopos F, Garrard P, Vidal ME, Paliouras G. Improving Early Prognosis of Dementia Using Machine Learning Methods. ACM Transactions on Computing for Healthcare. 2022 Apr 7;3(3):30. doi: 10.1145/3502433
Katsimpras, Georgios ; Aisopos, Fotis ; Garrard, Peter et al. / Improving Early Prognosis of Dementia Using Machine Learning Methods. In: ACM Transactions on Computing for Healthcare. 2022 ; Vol. 3, No. 3.
Download
@article{3d1d92ccbcd14ee4ab4c264d82a89a69,
title = "Improving Early Prognosis of Dementia Using Machine Learning Methods",
abstract = "Early and precise prognosis of dementia is a critical medical challenge. The design of an optimal computational model that addresses this issue, and at the same time explains the underlying mechanisms that lead to output decisions, is an ongoing challenge. In this study, we focus on assessing the risk of an individual converting to Dementia in the short (next year) and long (one to five years) term, given only a few early-stage observations. Our goal is to develop a machine learning model that could assist the prediction of dementia from regular clinical data. The results show that combining various machine learning techniques together can successfully define ways to identify the risks of developing dementia over the following five years with accuracies considerably above average rates. These findings suggest that accurately developed models can be considered as a promising tool to improve early dementia prognosis.",
keywords = "Dementia, machine learning, prognosis",
author = "Georgios Katsimpras and Fotis Aisopos and Peter Garrard and Vidal, {Maria Esther} and Georgios Paliouras",
note = "Funding Information: This article is supported by European Union{\textquoteright}s Horizon 2020 research and innovation programme under Grant Agreement No. 727658, Project IASIS (Integration and analysis of heterogeneous big data for precision medicine and suggested treatments for different types of patients). ",
year = "2022",
month = apr,
day = "7",
doi = "10.1145/3502433",
language = "English",
volume = "3",
number = "3",

}

Download

TY - JOUR

T1 - Improving Early Prognosis of Dementia Using Machine Learning Methods

AU - Katsimpras, Georgios

AU - Aisopos, Fotis

AU - Garrard, Peter

AU - Vidal, Maria Esther

AU - Paliouras, Georgios

N1 - Funding Information: This article is supported by European Union’s Horizon 2020 research and innovation programme under Grant Agreement No. 727658, Project IASIS (Integration and analysis of heterogeneous big data for precision medicine and suggested treatments for different types of patients).

PY - 2022/4/7

Y1 - 2022/4/7

N2 - Early and precise prognosis of dementia is a critical medical challenge. The design of an optimal computational model that addresses this issue, and at the same time explains the underlying mechanisms that lead to output decisions, is an ongoing challenge. In this study, we focus on assessing the risk of an individual converting to Dementia in the short (next year) and long (one to five years) term, given only a few early-stage observations. Our goal is to develop a machine learning model that could assist the prediction of dementia from regular clinical data. The results show that combining various machine learning techniques together can successfully define ways to identify the risks of developing dementia over the following five years with accuracies considerably above average rates. These findings suggest that accurately developed models can be considered as a promising tool to improve early dementia prognosis.

AB - Early and precise prognosis of dementia is a critical medical challenge. The design of an optimal computational model that addresses this issue, and at the same time explains the underlying mechanisms that lead to output decisions, is an ongoing challenge. In this study, we focus on assessing the risk of an individual converting to Dementia in the short (next year) and long (one to five years) term, given only a few early-stage observations. Our goal is to develop a machine learning model that could assist the prediction of dementia from regular clinical data. The results show that combining various machine learning techniques together can successfully define ways to identify the risks of developing dementia over the following five years with accuracies considerably above average rates. These findings suggest that accurately developed models can be considered as a promising tool to improve early dementia prognosis.

KW - Dementia

KW - machine learning

KW - prognosis

UR - http://www.scopus.com/inward/record.url?scp=85140035449&partnerID=8YFLogxK

U2 - 10.1145/3502433

DO - 10.1145/3502433

M3 - Article

AN - SCOPUS:85140035449

VL - 3

JO - ACM Transactions on Computing for Healthcare

JF - ACM Transactions on Computing for Healthcare

SN - 2691-1957

IS - 3

M1 - 30

ER -