A Machine Learning Framework for Predicting Dementia and Mild Cognitive Impairment

Daniel Stamate, Wajdi Alghambdi, Jeremy Ogg, Richard Hoile, Fionn Murtagh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Dementia is one of the most feared illnesses that has a growing year-to-year negative global impact, having a health and social care cost higher than cancer, stroke and chronic heart disease, taken together. Without the availability of a cure, nor a standardised clinical test, the utilisation of machine learning methods to identify individuals that are at risk of developing dementia could bring a new step towards proactive intervention. This study's goal is to carry out a precursor analysis leading to building classification models with enhanced capabilities for differentiating diagnoses of CN (Cognitively Normal), MCI (Mild Cognitive Impairment) and Dementia. The predictive modelling approach we propose is based on the ReliefF method combined with statistical permutation tests for feature selection, and on model training, tuning, and testing based on algorithms such as Random Forests, Support Vector Machines, Gaussian Processes, Stochastic Gradient Boosting, and eXtreme Gradient Boosting. Stability of model performances were studied in computationally intensive Monte Carlo simulations. The results consistently show that our models accurately detect dementia, and also mild cognitive impairment patients by only using the inclusion of baseline measurements as predictors, thus illustrating the importance of baseline measurements. The best results issued from Monte Carlo were achieved by eXtreme Gradient Boosting optimised models, with an accuracy of 0.88 (SD 0.02), a sensitivity of 0.93 (SD 0.02) and a specificity of 0.94 (SD 0.01) for dementia, and a sensitivity of 0.86 (SD 0.02) and a specificity of 0.9 (SD 0.02) for mild cognitive impairment. These results support in particular future developments for a risk-based method that can identify an individual's risk of developing dementia.

Original languageEnglish
Title of host publicationProceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018
EditorsM. Arif Wani, Mehmed Kantardzic, Moamar Sayed-Mouchaweh, Joao Gama, Edwin Lughofer
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages671-678
Number of pages8
ISBN (Electronic)9781538668054
ISBN (Print)9781538668061
DOIs
Publication statusPublished - 17 Jan 2019
Event17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018 - Orlando, United States
Duration: 17 Dec 201820 Dec 2018

Conference

Conference17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018
CountryUnited States
CityOrlando
Period17/12/1820/12/18

Fingerprint

Learning systems
Statistical tests
Random processes
Support vector machines
Feature extraction
Tuning
Dementia
Machine learning
Impairment
Health
Availability
Testing
Costs
Boosting
Gradient
Specificity

Cite this

Stamate, D., Alghambdi, W., Ogg, J., Hoile, R., & Murtagh, F. (2019). A Machine Learning Framework for Predicting Dementia and Mild Cognitive Impairment. In M. A. Wani, M. Kantardzic, M. Sayed-Mouchaweh, J. Gama, & E. Lughofer (Eds.), Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018 (pp. 671-678). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLA.2018.00107
Stamate, Daniel ; Alghambdi, Wajdi ; Ogg, Jeremy ; Hoile, Richard ; Murtagh, Fionn. / A Machine Learning Framework for Predicting Dementia and Mild Cognitive Impairment. Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018. editor / M. Arif Wani ; Mehmed Kantardzic ; Moamar Sayed-Mouchaweh ; Joao Gama ; Edwin Lughofer. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 671-678
@inproceedings{9f0cd28f40ca41578050952e7fe0ae90,
title = "A Machine Learning Framework for Predicting Dementia and Mild Cognitive Impairment",
abstract = "Dementia is one of the most feared illnesses that has a growing year-to-year negative global impact, having a health and social care cost higher than cancer, stroke and chronic heart disease, taken together. Without the availability of a cure, nor a standardised clinical test, the utilisation of machine learning methods to identify individuals that are at risk of developing dementia could bring a new step towards proactive intervention. This study's goal is to carry out a precursor analysis leading to building classification models with enhanced capabilities for differentiating diagnoses of CN (Cognitively Normal), MCI (Mild Cognitive Impairment) and Dementia. The predictive modelling approach we propose is based on the ReliefF method combined with statistical permutation tests for feature selection, and on model training, tuning, and testing based on algorithms such as Random Forests, Support Vector Machines, Gaussian Processes, Stochastic Gradient Boosting, and eXtreme Gradient Boosting. Stability of model performances were studied in computationally intensive Monte Carlo simulations. The results consistently show that our models accurately detect dementia, and also mild cognitive impairment patients by only using the inclusion of baseline measurements as predictors, thus illustrating the importance of baseline measurements. The best results issued from Monte Carlo were achieved by eXtreme Gradient Boosting optimised models, with an accuracy of 0.88 (SD 0.02), a sensitivity of 0.93 (SD 0.02) and a specificity of 0.94 (SD 0.01) for dementia, and a sensitivity of 0.86 (SD 0.02) and a specificity of 0.9 (SD 0.02) for mild cognitive impairment. These results support in particular future developments for a risk-based method that can identify an individual's risk of developing dementia.",
keywords = "Dementia, eXtreme Gradient Boosting, Gaussian Processes, Machine Learning, Monte Carlo Simulations, ReliefF, Statistical Permutation Tests, Stochastic Gradient Boosting, Support Vector Machines",
author = "Daniel Stamate and Wajdi Alghambdi and Jeremy Ogg and Richard Hoile and Fionn Murtagh",
year = "2019",
month = "1",
day = "17",
doi = "10.1109/ICMLA.2018.00107",
language = "English",
isbn = "9781538668061",
pages = "671--678",
editor = "Wani, {M. Arif} and Mehmed Kantardzic and Moamar Sayed-Mouchaweh and Joao Gama and Edwin Lughofer",
booktitle = "Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Stamate, D, Alghambdi, W, Ogg, J, Hoile, R & Murtagh, F 2019, A Machine Learning Framework for Predicting Dementia and Mild Cognitive Impairment. in MA Wani, M Kantardzic, M Sayed-Mouchaweh, J Gama & E Lughofer (eds), Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018. Institute of Electrical and Electronics Engineers Inc., pp. 671-678, 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018, Orlando, United States, 17/12/18. https://doi.org/10.1109/ICMLA.2018.00107

A Machine Learning Framework for Predicting Dementia and Mild Cognitive Impairment. / Stamate, Daniel; Alghambdi, Wajdi; Ogg, Jeremy; Hoile, Richard; Murtagh, Fionn.

Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018. ed. / M. Arif Wani; Mehmed Kantardzic; Moamar Sayed-Mouchaweh; Joao Gama; Edwin Lughofer. Institute of Electrical and Electronics Engineers Inc., 2019. p. 671-678.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A Machine Learning Framework for Predicting Dementia and Mild Cognitive Impairment

AU - Stamate, Daniel

AU - Alghambdi, Wajdi

AU - Ogg, Jeremy

AU - Hoile, Richard

AU - Murtagh, Fionn

PY - 2019/1/17

Y1 - 2019/1/17

N2 - Dementia is one of the most feared illnesses that has a growing year-to-year negative global impact, having a health and social care cost higher than cancer, stroke and chronic heart disease, taken together. Without the availability of a cure, nor a standardised clinical test, the utilisation of machine learning methods to identify individuals that are at risk of developing dementia could bring a new step towards proactive intervention. This study's goal is to carry out a precursor analysis leading to building classification models with enhanced capabilities for differentiating diagnoses of CN (Cognitively Normal), MCI (Mild Cognitive Impairment) and Dementia. The predictive modelling approach we propose is based on the ReliefF method combined with statistical permutation tests for feature selection, and on model training, tuning, and testing based on algorithms such as Random Forests, Support Vector Machines, Gaussian Processes, Stochastic Gradient Boosting, and eXtreme Gradient Boosting. Stability of model performances were studied in computationally intensive Monte Carlo simulations. The results consistently show that our models accurately detect dementia, and also mild cognitive impairment patients by only using the inclusion of baseline measurements as predictors, thus illustrating the importance of baseline measurements. The best results issued from Monte Carlo were achieved by eXtreme Gradient Boosting optimised models, with an accuracy of 0.88 (SD 0.02), a sensitivity of 0.93 (SD 0.02) and a specificity of 0.94 (SD 0.01) for dementia, and a sensitivity of 0.86 (SD 0.02) and a specificity of 0.9 (SD 0.02) for mild cognitive impairment. These results support in particular future developments for a risk-based method that can identify an individual's risk of developing dementia.

AB - Dementia is one of the most feared illnesses that has a growing year-to-year negative global impact, having a health and social care cost higher than cancer, stroke and chronic heart disease, taken together. Without the availability of a cure, nor a standardised clinical test, the utilisation of machine learning methods to identify individuals that are at risk of developing dementia could bring a new step towards proactive intervention. This study's goal is to carry out a precursor analysis leading to building classification models with enhanced capabilities for differentiating diagnoses of CN (Cognitively Normal), MCI (Mild Cognitive Impairment) and Dementia. The predictive modelling approach we propose is based on the ReliefF method combined with statistical permutation tests for feature selection, and on model training, tuning, and testing based on algorithms such as Random Forests, Support Vector Machines, Gaussian Processes, Stochastic Gradient Boosting, and eXtreme Gradient Boosting. Stability of model performances were studied in computationally intensive Monte Carlo simulations. The results consistently show that our models accurately detect dementia, and also mild cognitive impairment patients by only using the inclusion of baseline measurements as predictors, thus illustrating the importance of baseline measurements. The best results issued from Monte Carlo were achieved by eXtreme Gradient Boosting optimised models, with an accuracy of 0.88 (SD 0.02), a sensitivity of 0.93 (SD 0.02) and a specificity of 0.94 (SD 0.01) for dementia, and a sensitivity of 0.86 (SD 0.02) and a specificity of 0.9 (SD 0.02) for mild cognitive impairment. These results support in particular future developments for a risk-based method that can identify an individual's risk of developing dementia.

KW - Dementia

KW - eXtreme Gradient Boosting

KW - Gaussian Processes

KW - Machine Learning

KW - Monte Carlo Simulations

KW - ReliefF

KW - Statistical Permutation Tests

KW - Stochastic Gradient Boosting

KW - Support Vector Machines

UR - http://www.scopus.com/inward/record.url?scp=85062234612&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2018.00107

DO - 10.1109/ICMLA.2018.00107

M3 - Conference contribution

SN - 9781538668061

SP - 671

EP - 678

BT - Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018

A2 - Wani, M. Arif

A2 - Kantardzic, Mehmed

A2 - Sayed-Mouchaweh, Moamar

A2 - Gama, Joao

A2 - Lughofer, Edwin

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Stamate D, Alghambdi W, Ogg J, Hoile R, Murtagh F. A Machine Learning Framework for Predicting Dementia and Mild Cognitive Impairment. In Wani MA, Kantardzic M, Sayed-Mouchaweh M, Gama J, Lughofer E, editors, Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 671-678 https://doi.org/10.1109/ICMLA.2018.00107