A machine learning approach using EEG data to predict response to SSRI treatment for major depressive disorder

Khodayari-Rostamabad, Ahmad; Reilly, J.P.; Hasey, Gary; Bruin, Hubert de; MacCrimmon, Duncan J.

doi:10.1016/j.clinph.2013.04.010

Cited by 143 publications

(95 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system could assist MDD patients in choosing suitable treatment according to the EEG data acquired. Furthermore, treatment outcome prediction for the MDD patients, divided into R and NR based on the ML techniques, has shown promise (sensitivity = 94.9%, specificity = 80.9%, accuracy = 87.9%) [125,126]. A similar study was conducted by applying an ML technique to schizophrenia, which achieved a classification accuracy of 85% [127].…”

Section: Techniques For the Prediction Of Treatment Outcomesmentioning

confidence: 97%

Review on EEG and ERP predictive biomarkers for major depressive disorder

Mumtaz

Malik

Yasin

et al. 2015

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Section: Techniques For the Prediction Of Treatment Outcomesmentioning

confidence: 97%

Review on EEG and ERP predictive biomarkers for major depressive disorder

Mumtaz

Malik

Yasin

et al. 2015

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

“…Khodayari-Rostamabad et al [20] collected pretreatment resting state EEG data in 22 treatment-resistant patients prior to 6 weeks of SSRI administration (sertraline in most cases). Response was relatively low in this treatmentresistant sample and improvement was therefore defined by a 30 % improvement or more in the Hamilton Depression Rating Scale (HAM-D), rather than the 50 % cut-off used in most cited studies.…”

Section: Pretreatment Predictorsmentioning

confidence: 99%

Neural Predictors of Treatment Response in Depression

Harmer

2014

Curr Behav Neurosci Rep

View full text Add to dashboard Cite

Depression is a leading cause of disability and treatment response is highly variable between patients. The current review focuses on recent findings from studies exploring neural predictors of treatment response to conventional antidepressant drugs, psychological treatment, and novel candidate interventions. Structural markers of response have revealed that decreased volume of key substrates such as the hippocampus and orbitofrontal cortex are predictive of poor response to antidepressant drug treatment, and diffusion tensor imaging offers potentially relevant information for future studies. Pretreatment measures of rostral anterior cingulate activity (from functional magnetic resonance imaging-and electroencephalogram-based approaches) have also been highlighted as a biomarker for antidepressant drug response. The relative utility of measurements taken at baseline versus early change for refining treatment in individual patients is considered. The response to novel treatments such as scopolamine, ketamine, and deep brain stimulation also offer promise for understanding targets of treatment and predictors for tailoring treatment. There is considerable overlap between neural biomarkers for different treatments although positron emission tomography metabolism in the anterior insula may offer a differential predictor of response to pharmacotherapy versus psychotherapy in depression. These insights provide important information about the potential targets and mechanisms underlying the prediction of treatment effects in depression. Future work needs to explore these different predictors between treatment arms in prospectively defined studies to evaluate whether these markers may have utility in the clinic.

show abstract

“…The researchers also painstakingly recorded patient outcomes, enabling the correlation of specific features of the EEG with known medication outcomes. They found that these correlations proved useful in a prospective clinical setting, and similar studies by other groups in recent years have confirmed these findings 5,6. This research has since been expanded upon through the systematic collection of additional EEGs and associated patient outcomes to treatment.…”

Section: Introductionmentioning

confidence: 56%

The use of the Psychiatric Electroencephalography Evaluation Registry (PEER) to personalize pharmacotherapy

Iosifescu

Neborsky

Valuck

2016

NDT

View full text Add to dashboard Cite

PurposeThis study aims to determine whether Psychiatric Electroencephalography Evaluation Registry (PEER) Interactive (an objective, adjunctive tool based on a comparison of a quantitative electroencephalogram to an existing registry of patient outcomes) is more effective than the current standard of care in treatment of subjects suffering from depression.Patients and methodsThis is an interim report of an ongoing, 2-year prospective, randomized, double blind, controlled study to evaluate PEER Interactive in guiding medication selection in subjects with a primary diagnosis of depression vs standard treatment. Subjects in treatment at two military hospitals were blinded as to study group assignment and their self-report symptom ratings were also blinded. Quick Inventory of Depressive Symptomatology, Self-Report (QIDS-SR16) depression scores were the primary efficacy endpoint. One hundred and fifty subjects received a quantitative electroencephalography exam and were randomized to either treatment as usual or PEER-informed pharmacotherapy. Subjects in the control group were treated according to Veterans Administration/Department of Defense Guidelines, the current standard of care. In the experimental group, the attending physician received a PEER report ranking the subject’s likely clinical response to on-label medications.ResultsIn this post hoc interim analysis subjects were separated into Report Followed and Report Not Followed groups – based on the concordance between their subsequent treatment and PEER medication guidance. We thus evaluated the predictive validity of PEER recommendations. We found significantly greater improvements in depression scores (QIDS-SR16 P<0.03), reduction in suicidal ideation (Concise Health Risk Tracking Scale-SR7 P<0.002), and post-traumatic stress disorder (PTSD) score improvement (PTSD Checklist Military/Civilian P<0.04) for subjects treated with PEER-recommended medications compared to those who did not follow PEER recommendations.ConclusionThis interim analysis suggests that an objective tool such as PEER Interactive can help improve medication selection. Consistent with results of earlier studies, it supports the hypothesis that PEER-guided treatment offers distinct advantages over the current standard of care.

show abstract

A machine learning approach using EEG data to predict response to SSRI treatment for major depressive disorder

Cited by 143 publications

References 59 publications

Review on EEG and ERP predictive biomarkers for major depressive disorder

Review on EEG and ERP predictive biomarkers for major depressive disorder

Neural Predictors of Treatment Response in Depression

The use of the Psychiatric Electroencephalography Evaluation Registry (PEER) to personalize pharmacotherapy

Contact Info

Product

Resources

About