Neuropsychological and resting-state electroencephalographic markers of older adult neurocognitive adaptability

Comparative analysis of machine learning algorithms for Alzheimer's disease classification using EEG signals and genetic information

Alzheimer's disease (AD) is a progressive neurodegenerative disorder characterized by cognitive decline, memory impairments, and behavioral changes. The presence of abnormal beta-amyloid plaques and tau protein tangles in the brain is known to be associated with AD. However, current limitations of imaging technology hinder the direct detection of these substances. Consequently, researchers are exploring alternative approaches, such as indirect assessments involving monitoring brain signals, cognitive decline levels, and blood biomarkers. Recent studies have highlighted the potential of integrating genetic information into these approaches to enhance early detection and diagnosis, offering a more comprehensive understanding of AD pathology beyond the constraints of existing imaging methods. Our study utilized electroencephalography (EEG) signals, genotypes, and polygenic risk scores (PRSs) as features for machine learning models. We compared the performance of gradient boosting (XGB), random forest (RF), and support vector machine (SVM) to determine the optimal model. Statistical analysis revealed significant correlations between EEG signals and clinical manifestations, demonstrating the ability to distinguish the complexity of AD from other diseases by using genetic information. By integrating EEG with genetic data in an SVM model, we achieved exceptional classification performance, with an accuracy of 0.920 and an area under the curve of 0.916. This study presents a novel approach of utilizing real-time EEG data and genetic background information for multimodal machine learning. The experimental results validate the effectiveness of this concept, providing deeper insights into the actual condition of patients with AD and overcoming the limitations associated with single-oriented data.

Ecological validity reconsidered: the Night Out Task versus the D-KEFS

INTRODUCTION

Although executive functioning (EF) correlates with execution of instrumental activities of daily living (IADLs), tests of EF have been criticized for having poor ecological validity. Attempts have been made to develop new tests that approximate naturalistic daily tasks. However, the incremental utility of such tests has not been convincingly demonstrated. The Night Out Task (NOT) is a novel measure designed to increase ecological validity. This study examined whether the NOT correlates with traditional lab- and home-based measures of EF and IADLs, and whether it outperforms traditional measures of EF in predicting IADLs.

METHOD

Participants (50 adults aged 60 to 95) completed (1) the Delis Kaplan Executive Function System (D-KEFS) and IADLs in the laboratory, and (2) ecological momentary assessment of EF and daily IADL tasks at home across three weeks (using the Daily Assessment of Independent Living and Executive Skills protocol; DAILIES).

RESULTS

The NOT correlated with a lab-based measure of EF beyond covariates, and lab-based IADLs beyond covariates and beyond the D-KEFS. However, it was unrelated to at-home variables beyond covariates. In contrast, the D-KEFS was a significant predictor of at-home IADLs, and this association was mediated by at-home EF performance.

CONCLUSION

This study provides a preliminary validation of the NOT as a correlate of office-based performances in a primarily college educated white sample. Despite its high face validity, the NOT does not appear to sufficiently tap EF processes needed for home-based IADLs as measured by the DAILIES, although small sample size limits the interpretability of this negative finding.

Introduction to the special issue: Are modern neuropsychological assessment methods really "modern"? Reflections on the current neuropsychological test armamentarium

OBJECTIVE

We introduce this special issue which focuses on how advances in neuroscience and technology can modernize and transform clinical neuropsychological assessment.

METHOD

We included both invited and solicited papers to reflect on the strengths and weaknesses of currently used, standardized neuropsychological tests and to explore how we might incorporate new technologies and neuroscientific advances to modernize neuropsychological assessment methods.

RESULTS

The papers are organized along the following themes: (1) A critique of the current clinical neuropsychological test armamentarium; (2) A description of new opportunities for collecting neurobehavioral data with technology; (3) Digital science, biomedical big data and the internet; (4) Integrating neuropsychological, neuroimaging, and neurophysiological assessments; (5) Modernization, globalization and culture.

CONCLUSION

The process of modernizing methods of assessment in clinical neuropsychology is laborious and requires a coordinated, sustained effort among clinicians, researchers, and the test industry. While embracing technology is necessary, we must also be aware of unintended consequences as we navigate this exciting new territory.