Dementia and Alzheimer's disease are characterised by cognitive decline, and diagnoses are predicted to rise due to an ageing population. Psychometric assessments are widely used by clinicians to inform the diagnosis of dementia, however these may not be as accurate or accessible for patients with lower levels of literacy or socioeconomic status. This study explores how machine learning models can detect dementia when trained on combinations of attributes from multi-modal datasets containing psychometric and Magnetic Resonance Imaging (MRI) data. When psychometric testing is not available, results show that the Random Forest classifier achieves a balanced accuracy, sensitivity and specificity of 84.75%, 79.10%, and 90.41% respectively before the dataset was standardised, and 84.34%, 78.27%, and 90.41% after - outperforming identical models trained on data from a single psychometric test.
|Title of host publication||Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2022|
|Number of pages||7|
|Publication status||Published - 29 Jun 2022|
|Event||15th International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2022 - Corfu, Greece|
Duration: 29 Jun 2022 → 1 Jul 2022
|Name||ACM International Conference Proceeding Series|
|Conference||15th International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2022|
|Period||29/06/22 → 1/07/22|
Bibliographical note© 2022 Copyright held by the owner/author(s).
The dataset used in this study (Open Access Series of Imaging Studies (OASIS) ): is publicly available at http://www.oasis-brains.org; has Principal Investigators D. Marcus, R, Buckner, J. Csernansky, and J. Morris; and is supported by grants P50 AG05681, P01 AG03991, P01 AG026276, R01 AG021910, P20 MH071616, and U24 RR021382.
- Dementia Classification
- Machine Learning
- Multi-Modal Data