Search

We report a novel approach to dementia neurobiomarker development from EEG time series using topological data analysis (TDA) methodology and machine learning (ML) tools in the 'AI for social good' application domain, with possible following application to home-based point of care diagnostics and cognitive intervention monitoring. We propose a new approach to a digital dementia neurobiomarker for early-onset mild cognitive impairment (MCI) prognosis. We report the best median accuracies in a range of upper 85% linear discriminant analysis (LDA), as well above 90% for linear SVM and deep fully connected neural network classifier models in leave-one-out-subject cross-validation, which presents very encouraging results in a binary healthy cognitive aging versus MCI stages using TDA features applied to brainwave time series patterns captured from a four-channel EEG wearable.Clinical relevance- The reported study offers an objective dementia early onset neurobiomarker prospect to replace traditional subjective paper and pencil tests with an application of EEG-wearable-based and topological data analysis machine learning tools in a possibly successive home-based point-of-care environment.

An efficient machine learning (ML) implementation in the so-called 'AI for social good' domain shall contribute to dementia digital neuro-biomarker development for early-onset prognosis of a possible cognitive decline. We report encouraging initial developments of wearable EEG-derived theta-band fluctuations examination and a successive classification embracing a time-series complexity examination with a multifractal detrended fluctuation analysis (MFDFA) in the face or emotion video-clip identification short-term oddball memory tasks. We also report findings from a thirty-five elderly volunteer pilot study that EEG responses to instructed to ignore (inhibited) oddball paradigm stimulation results in more informative MFDFA features, leading to better machine learning classification results. The reported pilot project showcases vital social assistance of artificial intelligence (AI) application for an early-onset dementia prognosis. Clinical Relevance- This introduces a candidate for an objective digital neuro-biomarker from theta-band EEG recorded by a wearable for a plausible replacement of biased 'paper & pencil' tests for a mild cognitive impairment (MCI) evaluation.

We discuss the practical employment of a machine learning (ML) technique within AI for a social good application. We present an application for elderly adult dementia onset prognostication. First, the paper explains our encouraging preliminary study results of EEG responses analysis using a signal complexity measure of multiscale entropy (MSE) in reminiscent interior working memory evaluation tasks. Then, we compare shallow and deep learning machine learning models for a digital biomarker of dementia onset detection. The evaluated machine-learning models succeed in the most reliable median accuracies above 80% using random forest and fully connected neural network classifiers in automatic discrimination of normal cognition versus a mild cognitive impairment (MCI) task. The classifier input features consist of MSE patterns only derived from four dry EEG electrodes. Fifteen elderly subjects voluntarily participate in the reported study focusing on EEG-based objective dementia biomarker advancement. The results showcase the essential social advantages of artificial intelligence (AI) application for the dementia prognosis and advance ML for the subsequent use for simple objective EEG-based examination.Clinical relevance- This manuscript introduces an objective biomarker from EEG recorded by a wearable for a plausible replacement of a mild cognitive impairment (MCI) evaluation using usual biased paper and pencil examinations.

We present an efficient utilization of a machine learning (ML) method concentrating on the 'AI for social good' application. We develop a digital dementia biomarker for early-onset dementia forecast. The paper demonstrates encouraging preliminary results of EEG-wearable-based signal analysis and a subsequent classification adopting a signal complexity test of a multifractal detrended fluctuation analysis (MFDFA) in emotional faces working memory training and evaluation tasks. For the digital biomarker of dementia onset detection, we examine shallow- and deep-learning machine learning models. We report the best median accuracies in a range of 90% for random forest and fully connected neural network classifier models in both emotional faces learning and evaluation experimental tasks. In addition, the classifiers are trained in a ten-fold cross-validation regime to discriminate normal versus mild cognitive impairment (MCI) cognition stages using MFDFA patterns from four-channel EEG recordings. Thirty-five volunteer elderly subjects participate in the current study concentrating on simple wearable EEG-based objective dementia biomarker progression. The reported outcomes showcase an essential social benefit of artificial intelligence (AI) employment for early dementia prediction. Furthermore, we improve ML employment for the succeeding application in an uncomplicated and applied EEG-wearable examination.

The presented paper discusses a practical application of machine learning (ML) in the so-called 'AI for social good' domain and in particular concerning the problem of a potential elderly adult dementia onset prediction. An increase in dementia cases is producing a significant medical and economic weight in many countries. Approximately 47 million older adults live with a dementia spectrum of neurocognitive disorders, according to an up-to-date statement of the World Health Organization (WHO), and this amount will triple within the next thirty years. This growing problem calls for possible application of AI-based technologies to support early diagnostics for cognitive interventions and a subsequent mental wellbeing monitoring as well as maintenance with so-called 'digital-pharma' or 'beyond a pill' therapeutical strategies. The paper explains our attempt and encouraging preliminary study results of behavioral responses analysis in a facial emotion implicit-short-term-memory learning and evaluation experiment. We present results of various shallow and deep learning machine learning models for digital biomarkers of dementia progress detection and monitoring. The discussed machine-learning models result in median accuracies right below a 90% benchmark using classical shallow and deep learning approaches for automatic discrimination of normal cognition versus a mild cognitive impairment (MCI). The classifier input features consist of an older adult emotional valence and arousal recognition responses, together with reaction times, as well as with self-reported university-level degree education and age, as obtained from a group of 35 older adults participating voluntarily in the reported dementia biomarker development project. The presented results showcase the inherent social benefits of artificial intelligence (AI) utilization for the elderly and establish a step forward to advance machine learning (ML) approaches for the subsequent employment of simple behavioral examination for MCI and dementia onset diagnostics.Clinical relevance- This manuscript establishes a behavioral and cognitive biomarker candidate potentially substituting a Montreal Cognitive Assessment (MoCA) evaluation without a paper and pencil test.