Applying Deep Learning to Predicting Dementia and Mild Cognitive Impairment

TY - CHAP

T1 - Applying Deep Learning to Predicting Dementia and Mild Cognitive Impairment

AU - Stamate, Daniel

AU - Smith, Richard

AU - Tsygancov, Ruslan

AU - Vorobev, Rostislav

AU - Langham, John

AU - Stahl, Daniel

AU - Reeves, David

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Dementia has a large negative impact on the global healthcare and society. Diagnosis is rather challenging as there is no standardised test. The purpose of this paper is to conduct an analysis on ADNI data and determine its effectiveness for building classification models to differentiate the categories Cognitively Normal (CN), Mild Cognitive Impairment (MCI), and Dementia (DEM), based on tuning three Deep Learning models: two Multi-Layer Perceptron (MLP1 and MLP2) models and a Convolutional Bidirectional Long Short-Term Memory (ConvBLSTM) model. The results show that the MLP1 and MLP2 models accurately distinguish the DEM, MCI and CN classes, with accuracies as high as 0.86 (SD 0.01). The ConvBLSTM model was slightly less accurate but was explored in view of comparisons with the MLP models, and for future extensions of this work that will take advantage of time-related information. Although the performance of ConvBLSTM model was negatively impacted by a lack of visit code data, opportunities were identified for improvement, particularly in terms of pre-processing.

AB - Dementia has a large negative impact on the global healthcare and society. Diagnosis is rather challenging as there is no standardised test. The purpose of this paper is to conduct an analysis on ADNI data and determine its effectiveness for building classification models to differentiate the categories Cognitively Normal (CN), Mild Cognitive Impairment (MCI), and Dementia (DEM), based on tuning three Deep Learning models: two Multi-Layer Perceptron (MLP1 and MLP2) models and a Convolutional Bidirectional Long Short-Term Memory (ConvBLSTM) model. The results show that the MLP1 and MLP2 models accurately distinguish the DEM, MCI and CN classes, with accuracies as high as 0.86 (SD 0.01). The ConvBLSTM model was slightly less accurate but was explored in view of comparisons with the MLP models, and for future extensions of this work that will take advantage of time-related information. Although the performance of ConvBLSTM model was negatively impacted by a lack of visit code data, opportunities were identified for improvement, particularly in terms of pre-processing.

KW - Artificial Neural Networks

KW - ConvBLSTM

KW - Deep Learning

KW - Dementia prediction

KW - Multi-Layer Perceptron

KW - ReliefF

KW - SMOTE

UR - http://www.scopus.com/inward/record.url?scp=85086182370&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-49186-4_26

DO - 10.1007/978-3-030-49186-4_26

M3 - Chapter

AN - SCOPUS:85086182370

SN - 9783030491857

T3 - IFIP Advances in Information and Communication Technology

SP - 308

EP - 319

BT - Artificial Intelligence Applications and Innovations - 16th IFIP WG 12.5 International Conference, AIAI 2020, Proceedings

A2 - Maglogiannis, Ilias

A2 - Iliadis, Lazaros

A2 - Pimenidis, Elias

PB - SPRINGER

T2 - 16th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2020

Y2 - 5 June 2020 through 7 June 2020

ER -