Prediction of Individual Response to Electroconvulsive Therapy via Machine Learning on Structural Magnetic Resonance Imaging Data

Redlich, Ronny; Opel, Nils; Grotegerd, Dominik; Dohm, Katharina; Zaremba, Dario; Bürger, Christian; Münker, Sandra; Mühlmann, Lisa; Wahl, Patricia W.; Heindel, Walter; Arolt, Volker; Alferink, Judith; Zwanzger, Peter; Zavorotnyy, Maxim; Kugel, Harald; Dannlowski, Udo

doi:10.1001/jamapsychiatry.2016.0316

Cited by 249 publications

(180 citation statements)

References 46 publications

Supporting

Mentioning

173

Contrasting

Unclassified

Order By: Relevance

“…Several neuroimaging studies have sought to discover MRI markers for predicting outcome of the ECT in mood disorders. These studies have generally demonstrated that resting state connectivity in the dorsomedial PFC and anterior cingulate cortex, 47 intrinsic brain activity in subcallosal cingulate cortex, 48 and gray matter volume in the amygdala, hippocampus, 49 and subgenual cingulate 50, 51 might be associated with individual ECT responses.…”

Section: Discussionmentioning

confidence: 99%

Electroconvulsive therapy-induced brain functional connectivity predicts therapeutic efficacy in patients with schizophrenia: a multivariate pattern recognition study

et al. 2017

View full text Add to dashboard Cite

Previous studies suggested that electroconvulsive therapy can influence regional metabolism and dopamine signaling, thereby alleviating symptoms of schizophrenia. It remains unclear what patients may benefit more from the treatment. The present study sought to identify biomarkers that predict the electroconvulsive therapy response in individual patients. Thirty-four schizophrenia patients and 34 controls were included in this study. Patients were scanned prior to treatment and after 6 weeks of treatment with antipsychotics only (n = 16) or a combination of antipsychotics and electroconvulsive therapy (n = 13). Subject-specific intrinsic connectivity networks were computed for each subject using a group information-guided independent component analysis technique. Classifiers were built to distinguish patients from controls and quantify brain states based on intrinsic connectivity networks. A general linear model was built on the classification scores of first scan (referred to as baseline classification scores) to predict treatment response. Classifiers built on the default mode network, the temporal lobe network, the language network, the corticostriatal network, the frontal-parietal network, and the cerebellum achieved a cross-validated classification accuracy of 83.82%, with specificity of 91.18% and sensitivity of 76.47%. After the electroconvulsive therapy, psychosis symptoms of the patients were relieved and classification scores of the patients were decreased. Moreover, the baseline classification scores were predictive for the treatment outcome. Schizophrenia patients exhibited functional deviations in multiple intrinsic connectivity networks which were able to distinguish patients from healthy controls at an individual level. Patients with lower classification scores prior to treatment had better treatment outcome, indicating that the baseline classification scores before treatment is a good predictor for treatment outcome.

show abstract

Section: Discussionmentioning

confidence: 99%

Electroconvulsive therapy-induced brain functional connectivity predicts therapeutic efficacy in patients with schizophrenia: a multivariate pattern recognition study

et al. 2017

View full text Add to dashboard Cite

show abstract

“…While at least one of the included studies reported a positive correlation between hippocampal volume change and improvement in depression (30), most of the included studies’ individual, patient-level regression analyses also failed to find any correlation (31–36). One additional study (not included in the meta-analysis due to significant differences in methodological approach) did find that changes in the hippocampal-amygdala complex were associated with clinical improvement in depression following ECT (37).…”

Section: Discussionmentioning

confidence: 99%

“…Furthermore, the hippocampus is the most consistently reported brain area to undergo significant volumetric changes pre- and post-ECT. Other studies have variably reported changes in the amygdala (30, 36, 57), the prefrontal cortex (58), and the anterior cingulate cortex (57) following ECT. The amygdala is very proximate to the hippocampus and early imaging studies likely did not have spatial resolution to distinguish between the two structures (26).…”

Section: Discussionmentioning

confidence: 99%

Hippocampal Volume Changes Following Electroconvulsive Therapy: A Systematic Review and Meta-analysis

Wilkinson

Sanacora

Bloch

2017

Biological Psychiatry: Cognitive Neuroscience and Neuroimaging

View full text Add to dashboard Cite

Introduction Reduced hippocampal volume is one of the most consistent morphological findings in Major Depressive Disorder (MDD). Electroconvulsive therapy (ECT) is the most effective therapy for MDD, yet its mechanism of action remains poorly understood. Animal models show that ECT induces several neuroplastic processes, which lead to hippocampal volume increases. We conducted a meta-analysis of ECT studies in humans to investigate its effects on hippocampal volume. Methods PubMed was searched for studies examining hippocampal volume before and after ECT. A random-effects model was used for meta-analysis with standardized mean difference (SMD) of the change in hippocampal volume before and after ECT as the primary outcome. Nine studies involving 174 participants were included. Results Total hippocampal volumes increased significantly following ECT compared to pre-treatment values (SMD=1.10; 95% CI 0.80–1.39; z=7.34; p<0.001; k=9). Both right (SMD=1.01; 95% CI 0.72–1.30; z=6.76; p<0.001; k=7) and left (SMD=0.87; 95% CI 0.51–1.23; z=4.69; p<0.001; k=7) hippocampal volumes were also similarly increased significantly following ECT. We demonstrated no correlation between improvement in depression symptoms with ECT and change in total hippocampal volume (beta=−1.28, 95% CI −4.51–1.95, z=−0.78, p=0.44). Conclusion We demonstrate fairly consistent increases in hippocampal volume bilaterally following ECT treatment. The relationship among these volumetric changes and clinical improvement and cognitive side effects of ECT should be explored by larger, multisite studies with harmonized imaging methods.

show abstract

“…For example, smaller hippocampal volumes in patients with depression predicted a worse illness course compared with patients with larger hippocampal volumes 19 . A recent study confirmed that hippocampal volumes and also sgACC volumes can predict treatment response to ECT in patients with major depression 20 .…”

Section: Functional Neuroimagingmentioning

confidence: 77%

Recent advances in predicting responses to antidepressant treatment

Frodl

2017

F1000Res

View full text Add to dashboard Cite

Major depressive disorder is one of the leading causes of disability in the world since depression is highly frequent and causes a strong burden. In order to reduce the duration of depressive episodes, clinicians would need to choose the most effective therapy for each individual right away. A prerequisite for this would be to have biomarkers at hand that would predict which individual would benefit from which kind of therapy (for example, pharmacotherapy or psychotherapy) or even from which kind of antidepressant class. In the past, neuroimaging, electroencephalogram, genetic, proteomic, and inflammation markers have been under investigation for their utility to predict targeted therapies. The present overview demonstrates recent advances in all of these different methodological areas and concludes that these approaches are promising but also that the aim to have such a marker available has not yet been reached. For example, the integration of markers from different systems needs to be achieved. With ongoing advances in the accuracy of sensing techniques and improvement of modelling approaches, this challenge might be achievable.

show abstract

Prediction of Individual Response to Electroconvulsive Therapy via Machine Learning on Structural Magnetic Resonance Imaging Data

Cited by 249 publications

References 46 publications

Electroconvulsive therapy-induced brain functional connectivity predicts therapeutic efficacy in patients with schizophrenia: a multivariate pattern recognition study

Electroconvulsive therapy-induced brain functional connectivity predicts therapeutic efficacy in patients with schizophrenia: a multivariate pattern recognition study

Hippocampal Volume Changes Following Electroconvulsive Therapy: A Systematic Review and Meta-analysis

Recent advances in predicting responses to antidepressant treatment

Contact Info

Product

Resources

About