A pilot study to determine whether machine learning methodologies using pre-treatment electroencephalography can predict the symptomatic response to clozapine therapy

• Published in: Clinical neurophysiology Vol. 121; no. 12; pp. 1998 - 2006
• Main Authors: Khodayari-Rostamabad, Ahmad, Hasey, Gary M., MacCrimmon, Duncan J., Reilly, James P., Bruin, Hubert de
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ireland Ltd 01.12.2010; Elsevier
• Subjects: Adult; Adult and adolescent clinical studies; Antipsychotic Agents - therapeutic use; Artificial Intelligence; Biological and medical sciences; Clozapine; Clozapine - therapeutic use; Discrimination (Psychology); EEG; Electrodiagnosis. Electric activity recording; Electroencephalography - methods; Female; Follow-Up Studies; Humans; Investigative techniques, diagnostic techniques (general aspects); Machine learning; Male; Medical sciences; Middle Aged; Nervous system; Neurology; Pilot Projects; Predictive Value of Tests; Psychiatric Status Rating Scales; Psychiatry; Psychology. Psychoanalysis. Psychiatry; Psychopathology. Psychiatry; Psychoses; Reproducibility of Results; Schizophrenia; Schizophrenia - drug therapy; Schizophrenia - physiopathology; Sensitivity and Specificity; Treatment Outcome; Treatment-efficacy prediction; Schizophrenia; Clozapine; Psychiatry; EEG; Treatment-efficacy prediction; Machine learning; Human; Minimum; Methodology; Selection; Prediction; Electrophysiology; Electroencephalography; Representation; Kernel method; Psychosis; Learning; Chronic; Acquisition process; Treatment; Least squares method; Performance
• ISSN: 1388-2457; 1872-8952; 1872-8952
• DOI: 10.1016/j.clinph.2010.05.009

To investigate whether applying advanced machine learning (ML) methodologies to pre-treatment electroencephalography (EEG) data can predict the response to clozapine therapy in adult subjects suffering from chronic schizophrenia. Pre-treatment EEG data are collected in 23 + 14 schizophrenic adults. Treatment outcome, after at least one year follow-up, is determined using clinical ratings by a trained clinician blind to EEG results. First, a feature selection scheme is employed to select a reduced subset of features extracted from the subjects’ EEG that is most statistically relevant to our treatment-response prediction. These features are then entered into a classifier, which is realized in the form of a kernel partial least squares regression method that performs response prediction. Various scales, including the positive and negative syndrome scale (PANSS) are used as treatment-response indicators. We determined that a set of discriminating EEG features do exist. A low-dimensional representation of the feature space showed significant clustering into clozapine responder and non-responder groups. The minimum level of performance of the proposed prediction methodology, tested over a range of conditions using the leave-one-out cross-validation method using the original 23 subjects, with further testing in an independent sample of 14 subjects, was 85%. These findings indicate that analysis of pre-treatment EEG data can predict the clinical response to clozapine in treatment resistant schizophrenia. If replicated in a larger population, this novel approach to EEG analysis may assist the clinician in determining treatment-efficacy.