The Emerging Role of Neurodiagnostic Informatics in Integrated Neurological and Mental Health Care

Abstract

Mental, neurological, and neurodevelopmental (MNN) disorders impose an enormous burden of disease globally. Many MNN disorders follow a developmental trajectory. Thus, defining symptoms of MNN disorders may be conceived as the end product of a long developmental process. Many pharmaceutical therapies are aimed at the end symptoms, essentially attempting to reverse pathological brain function that has developed over a long time. A new paradigm is needed to leverage the developmental trajectory of MNN disorders, based on measuring brain function through the life span. Electroencephalography (EEG) is ideally suited for this task. New developments in several fields, including consumer EEG hardware, ubiquitous access to the Internet and electronic health records, and nonlinear mathematics to extract information from physiological signals have converged to enable new approaches to integrating EEG into routine health care. Research continues to demonstrate that EEG analysis can be used to discover digital biomarkers for a wide range of MNN disorders, including autism, attention-deficit/hyperactivity disorder (ADHD), schizophrenia and dementias, and likely many others. When EEGderived information about brain function is stored with an electronic health record, clinical decision support software may use these data to detect atypical brain development in the earliest stages, thus opening a potential window for early intervention. These developments create an opportunity

Pain phenotypes classified by machine learning using electroencephalography features

“…These algorithms have already been applied in similar contexts, such as detecting traumatic brain injury ( Prichep et al, 2014 ), estimating depth of anesthesia ( Saadeh et al, 2019 ), studying Alzheimer’s disease ( Simpraga et al, 2017 ), and studying seizure activity ( Elahian et al, 2017 ). There is also evidence for using EEG data and an SVM method to predict the diagnosis of complex and variable neurodevelopmental conditions, such as autism spectrum disorder ( Bosl, 2018 ; Bosl et al, 2018 ). Recently, machine learning methods have produced valid and reliable algorithms for predicting pain intensity using high dimensional EEG features.…”

Remote Wearable Neuroimaging Devices for Health Monitoring and Neurophenotyping: A Scoping Review

“…By integrating technologies like wearable neuroimaging devices into everyday settings, researchers can gather more ecologically valid data. This is crucial for understanding the nuanced interplay between brain activity, behavior, and environment [11]. This approach not only enhances the relevance of research findings for real-life situations but also opens new avenues for monitoring and intervention in healthcare and research [12].…”

“…It captures the electrical activity of the brain at various frequency bands, where different frequencies serve as biomarkers of different health conditions. For example, alpha waves, which are in a relatively high frequency range (8)(9)(10)(11)(12), are associated with relaxation and calmness. In contrast, beta waves, which are lower in frequency (with a range of 12-30 Hz), are associated with highly demanding mental activity such as analytical thought and anxiety [15].…”

Towards Decoding of Depersonalisation Disorder Using EEG: A Time Series Analysis Using CDTW

“…3 (B)). As well as its potential to classify several mental tasks [26][27][28], EEG has also shown promising capability in helping with the diagnosis of several mental disorders and psychological conditions [29]. Adler et al [30] recently aimed to investigate DPD using EEG signals and tried to find potential electrophysiological biomarkers associated with DPD symptoms.…”