Applying Deep Learning to Predicting Dementia and Mild Cognitive Impairment

Stamate, Daniel; Smith, Richard; Tsygancov, Ruslan; Vorobev, Rostislav; Langham, John; Stahl, Daniel and Reeves, David. 2020. 'Applying Deep Learning to Predicting Dementia and Mild Cognitive Impairment'. In: Artificial Intelligence Applications and Innovations. Halkidiki, Greece. [Conference or Workshop Item]

[img]
Preview
Text
aiai2020.paper90.gro.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.

Download (783kB) | Preview

Abstract or Description

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.

Item Type:

Conference or Workshop Item (Paper)

Keywords:

Dementia prediction, Artificial Neural Networks, Deep Learning, MultiLayer Perceptron, ConvBLSTM, ReliefF, SMOTE

Departments, Centres and Research Units:

Computing

Dates:

DateEvent
28 March 2020Accepted
29 May 2020Published

Event Location:

Halkidiki, Greece

Item ID:

28808

Date Deposited:

18 Jun 2020 08:52

Last Modified:

11 Jun 2021 19:19

URI:

https://research.gold.ac.uk/id/eprint/28808

View statistics for this item...

Edit Record Edit Record (login required)