TY - GEN
T1 - Early detection and prevention of dementia
T2 - Artificial Intelligence Applications and Innovations. AIAI 2025 IFIP WG 12.5 International Workshops, MHDW 2025, ΑΙ4GD 2025, and SilverTech 2025
AU - Huang, Andy
AU - Manias, Georgios
AU - Cordeiro Ferreira, Renato
AU - Sangiovanni, Mirella
AU - Borovits, Nemania
AU - Tamburri, Damian
AU - Ntanasi, Eva
AU - Scarmeas, Nikolaos
AU - van den Heuvel, Willem-Jan
PY - 2025/6/23
Y1 - 2025/6/23
N2 - Dementia is a progressive neurodegenerative condition affecting millions worldwide, highlighting the need for early and accurate detection. This study leverages the Aiginition Longitudinal Biomarker Investigation of Neurodegeneration (ALBION) dataset, integrating cognitive, psychological, physical, socio-demographic, among others, to enhance early diagnosis. In this direction, two approaches are proposed: the Always-Measured Model, which uses a limited set of consistently recorded features, and the Voting-Based Hybrid Model, which utilizes the dataset’s full multimodal and longitudinal scope. While the Always-Measured Model exhibited bias toward the Normal Cognition class (MCC = 0.64), the first-visit model within the ensemble achieved an MCC of 0.83. This demonstrates that initial-visit data alone can enable accurate detection. Additional data from follow-up visits did not improve the performance of the ensemble approach. However, the ensemble proved valuable in high-certainty cases (85.42% of instances), achieving an MCC of 0.94 and showcasing high robustness and accuracy.
AB - Dementia is a progressive neurodegenerative condition affecting millions worldwide, highlighting the need for early and accurate detection. This study leverages the Aiginition Longitudinal Biomarker Investigation of Neurodegeneration (ALBION) dataset, integrating cognitive, psychological, physical, socio-demographic, among others, to enhance early diagnosis. In this direction, two approaches are proposed: the Always-Measured Model, which uses a limited set of consistently recorded features, and the Voting-Based Hybrid Model, which utilizes the dataset’s full multimodal and longitudinal scope. While the Always-Measured Model exhibited bias toward the Normal Cognition class (MCC = 0.64), the first-visit model within the ensemble achieved an MCC of 0.83. This demonstrates that initial-visit data alone can enable accurate detection. Additional data from follow-up visits did not improve the performance of the ensemble approach. However, the ensemble proved valuable in high-certainty cases (85.42% of instances), achieving an MCC of 0.94 and showcasing high robustness and accuracy.
KW - Machine Learning
KW - Mild Cognitive Impairment
KW - Multimodal Classification
KW - Longitudinal Data
KW - Early Detection
KW - Dementia
U2 - 10.1007/978-3-031-97313-0_16
DO - 10.1007/978-3-031-97313-0_16
M3 - Conference contribution
SN - 978-3-031-97312-3
T3 - IFIP Advances in Information and Communication Technology (IFIPAICT)
SP - 199
EP - 212
BT - Artificial intelligence applications and innovations. AIAI 2025 IFIP WG 12.5 International Workshops
A2 - Papaleonidas, Antonios
A2 - Pimenidis, Elias
A2 - Papadopoulos, Harris
A2 - Chochliouros, Ioannis
PB - Springer Cham
CY - Cham
Y2 - 26 June 2025 through 29 June 2025
ER -