Integrative and interpretable framework to unveil the neurophysiological fingerprint of Alzheimer’s disease and mild cognitive impairment: A machine learning-SHAP approach

2026-04-28T19:51:55Zhttps://uvadoc.uva.es/oai/request

oai:uvadoc.uva.es:10324/782102026-01-14T10:38:56Zcom_10324_23459com_10324_954com_10324_894col_10324_23460

Integrative and interpretable framework to unveil the neurophysiological fingerprint of Alzheimer’s disease and mild cognitive impairment: A machine learning-SHAP approach Gutierrez De Pablo, Victor Herrero Tudela, María Sandonís Fernández, Marina Poza Crespo, Jesús Maturana Candelas, Aaron Rodríguez González, Víctor Tola Arribas, Miguel Ángel Cano, Mónica Hoshi, Hideyuki Shigihara, Yoshihito Hornero Sánchez, Roberto Gómez, Carlos Producción Científica Dementia and mild cognitive impairment (MCI) due to Alzheimer’s disease (AD) are neurological pathologies associated with disruptions in brain electromagnetic activity, typically studied using magnetoencephalography (MEG) and electroencephalography (EEG). To quantify diverse brain properties, different families of param- eters can be computed from MEG and EEG (i.e., spectral, non-linear, morphological, functional connectivity, or network structure and organisation). However, studying these characteristics separately overlooks the com- plex nature of brain activity. Integrative frameworks can be useful to unveil the intricate neurophysiological fingerprint, as well as to characterise pathological conditions comprehensively. To that purpose, data fusion methodologies are crucial, despite their interpretational challenges. In this study, Machine Learning (ML) mod- els were trained to discriminate between groups of severity, whereas the SHapley Additive eXplanations (SHAP) algorithm was afterwards utilised to assess the relevance of the input characteristics into the output classifica- tion. Three databases were analysed: MEG (55 healthy controls, HC, 42 MCI patients, and 86 AD patients), EEG1 (51 HC, 52 MCI, and 100 AD), and EEG2 (45 HC, 69 MCI, and 82 AD). The best results for the three-class classi- fication problem were obtained by Gradient Boosting for the MEG database: 3-class Cohen’s kappa coefficient of 0.5452 and accuracy of 72.63 %. Afterwards, using SHAP on Gradient Boosting, it has been shown that spectral features were identified as highly relevant across all databases. Furthermore, morphology measures presented high relevance for the MEG database, whereas EEG1 and EEG2 databases showed functional connectivity and multiplex organisation measures, respectively, as relevant subgroups of parameters. Finally, commonly relevant features across databases were selected using SHAP to generate the neurophysiological fingerprints of AD and MCI. This study highlights the relevance of different MEG and EEG parameters in characterising neurological pathologies. The proposed framework, based on MEG and EEG, can be used to generate interpretable, robust, and accurate neurophysiological fingerprints of AD and MCI. 2025-09-30 2025-09-30 2025 info:eu-repo/semantics/article Biocybernetics and Biomedical Engineering, 2025, vol. 45, n. 3, p. 438-450 0208-5216 https://uvadoc.uva.es/handle/10324/78210 10.1016/j.bbe.2025.05.011 438 3 450 Biocybernetics and Biomedical Engineering 45 eng https://www.sciencedirect.com/science/article/pii/S0208521625000397 info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-nd/4.0/ © 2025 The Author(s) Attribution-NonCommercial-NoDerivatives 4.0 Internacional Elsevier