Machine Learning for Dementia Prediction: A Systematic Review and Future Research Directions

Abstract

Nowadays, Artificial Intelligence (AI) and machine learning (ML) have successfully provided automated solutions to numerous real-world problems. Healthcare is one of the most important research areas for ML researchers, with the aim of developing automated disease prediction systems. One of the disease detection problems that AI and ML researchers have focused on is dementia detection using ML methods. Numerous automated diagnostic systems based on ML techniques for early prediction of dementia have been proposed in the literature. Few systematic literature reviews (SLR) have been conducted for dementia prediction based on ML techniques in the past. However, these SLR focused on a single type of data modality for the detection of dementia. Hence, the purpose of this study is to conduct a comprehensive evaluation of ML-based automated diagnostic systems considering different types of data modalities such as images, clinical-features, and voice data. We collected the research articles from 2011 to 2022 using the keywords dementia, machine learning, feature selection, data modalities, and automated diagnostic systems. The selected articles were critically analyzed and discussed. It was observed that image data driven ML models yields promising results in terms of dementia prediction compared to other data modalities, i.e., clinical feature-based data and voice data. Furthermore, this SLR highlighted the limitations of the previously proposed automated methods for dementia and presented future directions to overcome these limitations.

Keywords: Deep learning; Dementia prediction; Feature selection; Machine learning.

Fig. 1

Progression of dementia disease with ageing

Fig. 2

Types of dementia disease

Fig. 3

Flow diagram of PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses)

Fig. 4

Selected research articles which are published from 2011 to 2022 regarding data modality

Fig. 5

Accuracy comparison of different ML models based on image modality

Fig. 6

Accuracy comparison of different ML models based on clinical-variable modality

Fig. 7

Accuracy comparison of different ML models based on voice modality

Fig. 8

Accuracy comparison of ML models based on data modality

Fig. 9

Sensitivity and specificity comparison of ML based on modality

Fig. 10

Accuracy comparison of ML models along with number of sample in the dataset based on data modality

Fig. 11

Overall percentage of ML models used in the selected research articles regardless of data modality

Fig. 12

Overall percentage of evaluation metrics of ML models used by the researchers in the selected research articles