Identifying biomarkers for tDCS treatment response in Alzheimer's disease patients: a machine learning approach using resting-state EEG classification

Suellen Marinho Andrade; Leandro da Silva-Sauer; Carolina Dias de Carvalho; Elidianne Layanne Medeiros de Araújo; Eloise de Oliveira Lima; Fernanda Maria Lima Fernandes; Karen Lúcia de Araújo Freitas Moreira; Maria Eduarda Camilo; Lisieux Marie Marinho Dos Santos Andrade; Daniel Tezoni Borges; Edson Meneses da Silva Filho; Ana Raquel Lindquist; Rodrigo Pegado; Edgard Morya; Seidi Yonamine Yamauti; Nelson Torro Alves; Bernardino Fernández-Calvo; José Maurício Ramos de Souza Neto

doi:10.3389/fnhum.2023.1234168

Identifying biomarkers for tDCS treatment response in Alzheimer's disease patients: a machine learning approach using resting-state EEG classification

Front Hum Neurosci. 2023 Oct 4:17:1234168. doi: 10.3389/fnhum.2023.1234168. eCollection 2023.

Authors

Suellen Marinho Andrade¹, Leandro da Silva-Sauer¹, Carolina Dias de Carvalho¹, Elidianne Layanne Medeiros de Araújo¹, Eloise de Oliveira Lima¹, Fernanda Maria Lima Fernandes², Karen Lúcia de Araújo Freitas Moreira³, Maria Eduarda Camilo³, Lisieux Marie Marinho Dos Santos Andrade⁴, Daniel Tezoni Borges⁵, Edson Meneses da Silva Filho⁵, Ana Raquel Lindquist⁵, Rodrigo Pegado⁵, Edgard Morya⁶, Seidi Yonamine Yamauti⁶, Nelson Torro Alves⁷, Bernardino Fernández-Calvo^{7

8

9}, José Maurício Ramos de Souza Neto²

Affiliations

¹ Aging and Neuroscience Laboratory, Federal University of Paraíba, João Pessoa, Paraíba, Brazil.
² Center for Alternative and Renewable Energies (CEAR), Department of Electrical Engineering, Federal University of Paraíba, João Pessoa, Paraíba, Brazil.
³ Laboratory of Ergonomics and Health, Department of Physiotherapy, Federal University of Paraíba, João Pessoa, Paraíba, Brazil.
⁴ Department of Information Technology, Federal University of Ceará, Crateús, Brazil.
⁵ Department of Physiotherapy, Federal University of Rio Grande do Norte, Natal, Rio Grande do Norte, Brazil.
⁶ Edmond and Lily Safra International Institute of Neurosciences (IIN-ELS), Macaíba, Rio Grande do Norte, Brazil.
⁷ Department of Psychology, Federal University of Paraíba, João Pessoa, Brazil.
⁸ Department of Psychology, Faculty of Educational Sciences and Psychology, University of Cordoba, Córdoba, Spain.
⁹ Maimonides Biomedical Research Institute of Cordoba (IMIBIC), Córdoba, Spain.

Abstract

Background: Transcranial direct current stimulation (tDCS) is a promising treatment for Alzheimer's Disease (AD). However, identifying objective biomarkers that can predict brain stimulation efficacy, remains a challenge. The primary aim of this investigation is to delineate the cerebral regions implicated in AD, taking into account the existing lacuna in comprehension of these regions. In pursuit of this objective, we have employed a supervised machine learning algorithm to prognosticate the neurophysiological outcomes resultant from the confluence of tDCS therapy plus cognitive intervention within both the cohort of responders and non-responders to antecedent tDCS treatment, stratified on the basis of antecedent cognitive outcomes.

Methods: The data were obtained through an interventional trial. The study recorded high-resolution electroencephalography (EEG) in 70 AD patients and analyzed spectral power density during a 6 min resting period with eyes open focusing on a fixed point. The cognitive response was assessed using the AD Assessment Scale-Cognitive Subscale. The training process was carried out through a Random Forest classifier, and the dataset was partitioned into K equally-partitioned subsamples. The model was iterated k times using K-1 subsamples as the training bench and the remaining subsample as validation data for testing the model.

Results: A clinical discriminating EEG biomarkers (features) was found. The ML model identified four brain regions that best predict the response to tDCS associated with cognitive intervention in AD patients. These regions included the channels: FC1, F8, CP5, Oz, and F7.

Conclusion: These findings suggest that resting-state EEG features can provide valuable information on the likelihood of cognitive response to tDCS plus cognitive intervention in AD patients. The identified brain regions may serve as potential biomarkers for predicting treatment response and maybe guide a patient-centered strategy.

Clinical trial registration: https://classic.clinicaltrials.gov/ct2/show/NCT02772185?term=NCT02772185&draw=2&rank=1, identifier ID: NCT02772185.

Keywords: Alzheimer’s disease; artificial intelligence; electroencephalography; machine learning; transcranial direct current stimulation.

Copyright © 2023 Andrade, da Silva-Sauer, de Carvalho, de Araújo, Lima, Fernandes, Moreira, Camilo, Andrade, Borges, da Silva Filho, Lindquist, Pegado, Morya, Yamauti, Alves, Fernández-Calvo and de Souza Neto.

Associated data

ClinicalTrials.gov/NCT02772185

Grants and funding

BF-C was the recipient of a Senior Distinguished Researcher position (Beatriz Galindo Program) in the Department of Psychology at Universidad de Córdoba (ref. BEAGAL18/00006). The study was supported by a grant from the Brazilian National Council for Scientific and Technological Development (CNPQ) to BF-C (422533/2016-5).