Abstract
We aimed to develop a machine learning (ML) classifier to detect and compare major psychiatric disorders using electroencephalography (EEG). We retrospectively collected data from medical records, intelligence quotient (IQ) scores from psychological assessments, and quantitative EEG (QEEG) at resting-state assessments from 945 subjects [850 patients with major psychiatric disorders (six large-categorical and nine specific disorders) and 95 healthy controls (HCs)]. A combination of QEEG parameters including power spectrum density (PSD) and functional connectivity (FC) at frequency bands was used to establish models for the binary classification between patients with each disorder and HCs. The support vector machine, random forest, and elastic net ML methods were applied, and prediction performances were compared. The elastic net model with IQ adjustment showed the highest accuracy. The best feature combinations and classification accuracies for discrimination between patients and HCs with adjusted IQ were as follows: schizophrenia = alpha PSD, 93.83%; trauma and stress-related disorders = beta FC, 91.21%; anxiety disorders = whole band PSD, 91.03%; mood disorders = theta FC, 89.26%; addictive disorders = theta PSD, 85.66%; and obsessive–compulsive disorder = gamma FC, 74.52%. Our findings suggest that ML in EEG may predict major psychiatric disorders and provide an objective index of psychiatric disorders.
Highlights
As the standard of clinical practice, the establishment of psychiatric diagnoses is categorically and phenomenologically based
With respect to the prediction of distinguishing patients with main-categorical psychiatric disorders from the healthy controls (HCs), EN showed the highest accuracy, in that the mean area under curve (AUC) for all disorders adjusted for intelligence quotient (IQ) was 87.59 ± 7.92% (SVM = 86.02 ± 8.89% and RF = 87.18 ± 8.08%)
Our current study offers the following clinical insights: higher severity disorders increase the accuracy of the machine learning (ML) discrimination; classifications for specific diagnoses (e.g., PTSD and acute stress disorder) provide higher accuracy than grouping large categories; and each disorder classification model shows different EEG characteristics
Summary
As the standard of clinical practice, the establishment of psychiatric diagnoses is categorically and phenomenologically based. According to the International Classification of Disorders (ICD) and the Diagnostic and Statistical Manual for Mental Disorders (DSM) [1, 2], clinicians interpret explicit and observable signs and symptoms and provide categorical diagnoses based on which those symptoms fall into. This descriptive nosology enhances the simplicity of communication; it is limited by potentially insufficient objectivity as it relies on observation by the clinician and/or the presenting complaints reported by the patient or informant. ML is expected to help or possibly replace clinician decisions such as diagnosis, prediction, and prognosis or treatment outcomes [7]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
