The promise of the quantitative electroencephalogram as a predictor of antidepressant treatment outcomes in major depressive disorder.

Laboratory of Brain, Behavior, and Pharmacology, Semel Institute for Neuroscience and Human Behavior at UCLA, Department of Psychiatry and Biobehavioral Sciences, David Geffen School of Medicine at UCLA, Los Angeles, CA 90024-1759, USA.
Psychiatric Clinics of North America (Impact Factor: 2.13). 04/2007; 30(1):105-24. DOI: 10.1016/j.psc.2006.12.002
Source: PubMed

ABSTRACT Recent studies have shown overall accuracy rates of 72% and 88% using baseline and/or 1-week change in QEEG biomarkers to predict clinical outcome to treatment with various antidepressant medications. In some cases, findings have been replicated across academic institutions and have been studied in the context of randomized, placebo-controlled trials. Recent EEG findings are corroborated by studies that use techniques with greater spatial resolution (eg, PET, MEG) in localizing brain regions pertinent to clinical response. As such, EEG measurements increasingly are validated by other physiologic measurements that have the ability to assess deeper brain structures. Continued progress along these lines may lead to the realized promise of QEEG biomarkers as predictors of antidepressant treatment outcome in routine clinical practice. In the larger context, use of QEEG technology to predict antidepressant response in major depression may mean that more patients will achieve response and remission with less of the trial-and-error approach that currently accompanies antidepressant treatment.

Download full-text


Available from: Andrew F Leuchter, Jun 18, 2015
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: OBJECTIVE: The problem of identifying, in advance, the most effective treatment agent for various psychiatric conditions remains an elusive goal. To address this challenge, we investigate the performance of the proposed machine learning (ML) methodology (based on the pre-treatment electroencephalogram (EEG)) for prediction of response to treatment with a selective serotonin reuptake inhibitor (SSRI) medication in subjects suffering from major depressive disorder (MDD). METHODS: A relatively small number of most discriminating features are selected from a large group of candidate features extracted from the subject's pre-treatment EEG, using a machine learning procedure for feature selection. The selected features are fed into a classifier, which was realized as a mixture of factor analysis (MFA) model, whose output is the predicted response in the form of a likelihood value. This likelihood indicates the extent to which the subject belongs to the responder vs. non-responder classes. The overall method was evaluated using a "leave-n-out" randomized permutation cross-validation procedure. RESULTS: A list of discriminating EEG biomarkers (features) was found. The specificity of the proposed method is 80.9% while sensitivity is 94.9%, for an overall prediction accuracy of 87.9%. There is a 98.76% confidence that the estimated prediction rate is within the interval [75%, 100%]. CONCLUSIONS: These results indicate that the proposed ML method holds considerable promise in predicting the efficacy of SSRI antidepressant therapy for MDD, based on a simple and cost-effective pre-treatment EEG. SIGNIFICANCE: The proposed approach offers the potential to improve the treatment of major depression and to reduce health care costs.
    Clinical neurophysiology: official journal of the International Federation of Clinical Neurophysiology 05/2013; 124(10). DOI:10.1016/j.clinph.2013.04.010 · 2.98 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Recent research aims at developing a biomarker to predict antidepressant treatment outcomes in major depressive disorder. The Antidepressant Treatment Response (ATR) index has been correlated with response to antidepressant medication (, ) but has not been assessed in a placebo-controlled trial. EEGs recorded at pretreatment baseline and after 1 week of randomized treatment were used to calculate ATR index for 23 subjects with major depressive disorder who were treated for 8 weeks with fluoxetine (FLX) 20 mg (n = 12) or placebo (n = 11). The 17-item Hamilton Depression Rating Scale (HamD17) assessed symptom severity; ATR index was assessed as a predictor of percent change in HamD17 score, endpoint response (≥ 50% improvement) and remission (HamD17 score ≤ 7). The ATR index was significantly associated with improvement on FLX (r = 0.64, P = 0.01), with a higher mean ATR index for FLX responders than for nonresponders (t(10) = -2.07, P = 0.03). Receiver operating characteristic analysis found a 0.83 area under the curve (P = 0.03), for ATR index as a predictor for FLX, while an optimized ATR index cutoff of 47.3 yielded 100% sensitivity, 66.7% specificity, 75% positive predictive value, and 100% negative predictive value. Importantly, ATR index did not correlate significantly with placebo outcomes. Results extend ATR index findings to include predictive validity with fluoxetine, suggesting that this biomarker has specificity for drug effects.
    Journal of clinical neurophysiology: official publication of the American Electroencephalographic Society 09/2011; 28(5):478-82. DOI:10.1097/WNP.0b013e318230da8a · 1.60 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The aim of the study was to examine whether the reduction of theta prefrontal quantitative EEG (QEEG) cordance after one week of bupropion administration is a predictor of response to a 4-week treatment in patients that had failed to respond to previous antidepressant treatments. Method: EEG data of 18 inpatients were monitored at baseline and after one week. QEEG cordance was computed at 3 frontal electrodes (Fp1, Fp2, Fz). Response to treatment was defined as a >/=50% reduction of MADRS score. Results: Nine of the eleven responders and one of the seven non-responders showed decreased prefrontal cordance value after the first week of treatment (p=0.01). Positive and negative predictive values of cordance reduction for the prediction of response to the treatment were 0.9 and 0.75, respectively. Conclusion: Similar to other antidepressants, the reduction of prefrontal QEEG cordance might be helpful in the prediction of the acute outcome of bupropion treatment.
    European neuropsychopharmacology: the journal of the European College of Neuropsychopharmacology 07/2010; 20(7):459-66. DOI:10.1016/j.euroneuro.2010.03.007 · 5.40 Impact Factor