Predicting Individual Remission After Electroconvulsive Therapy Based on Structural Magnetic Resonance Imaging: A Machine Learning Approach

Machine Learning in Electroconvulsive Therapy: A Systematic Review

ABSTRACT

Despite years of research, we are still not able to reliably predict who might benefit from electroconvulsive therapy (ECT) treatment. As we exhaust what is possible using traditional statistical analysis, ECT remains a good candidate for machine learning approaches due to the large data sets with data captured through electroencephalography (EEG) and other objective measures. A systematic review of 6 databases led to the full-text examination of 26 articles using machine learning approaches in examining data predicting response to ECT treatment. The identified articles used a wide variety of data types covering structural and functional imaging data (n = 15), clinical data (n = 5), a combination of clinical and imaging data (n = 2), EEG (n = 3), and social media posts (n = 1). The clinical indications in which response prediction was assessed were depression (n = 21) and psychosis (n = 4). Changes in multiple anatomical regions in the brain were identified as holding a predictive value for response to ECT. These primarily centered on the limbic system and associated networks. Clinical features predicting good response to ECT in depression included shorter duration, lower severity, higher medication dose, psychotic features, low cortisol levels, and positive family history. It has also been possible to predict the likelihood of relapse of readmission with psychosis after ECT treatment, including a better response if higher transfer entropy was calculated from EEG signals. A transdisciplinary approach with an international consortium collecting a wide range of retrospective and prospective data may help to refine and extend these outcomes and translate them into clinical practice.

Development and validation of a multimodal neuroimaging biomarker for electroconvulsive therapy outcome in depression: a multicenter machine learning analysis

BACKGROUND

Electroconvulsive therapy (ECT) is the most effective intervention for patients with treatment resistant depression. A clinical decision support tool could guide patient selection to improve the overall response rate and avoid ineffective treatments with adverse effects. Initial small-scale, monocenter studies indicate that both structural magnetic resonance imaging (sMRI) and functional MRI (fMRI) biomarkers may predict ECT outcome, but it is not known whether those results can generalize to data from other centers. The objective of this study was to develop and validate neuroimaging biomarkers for ECT outcome in a multicenter setting.

METHODS

Multimodal data (i.e. clinical, sMRI and resting-state fMRI) were collected from seven centers of the Global ECT-MRI Research Collaboration (GEMRIC). We used data from 189 depressed patients to evaluate which data modalities or combinations thereof could provide the best predictions for treatment remission (HAM-D score ⩽7) using a support vector machine classifier.

RESULTS

Remission classification using a combination of gray matter volume and functional connectivity led to good performing models with average 0.82-0.83 area under the curve (AUC) when trained and tested on samples coming from the three largest centers (N = 109), and remained acceptable when validated using leave-one-site-out cross-validation (0.70-0.73 AUC).

CONCLUSIONS

These results show that multimodal neuroimaging data can be used to predict remission with ECT for individual patients across different treatment centers, despite significant variability in clinical characteristics across centers. Future development of a clinical decision support tool applying these biomarkers may be feasible.

Bifrontal electroconvulsive therapy leads to improvement of cerebral glucose hypometabolism in frontotemporal dementia with comorbid psychotic depression - a case report

BACKGROUND

Differentiating depression and dementia in elderly patients represents a major clinical challenge for psychiatrists. Pharmacological and non-pharmacological treatment options for both conditions are often used cautiously due to fear of adverse effects. If a clinically indicated therapy is not initiated due to fear of adverse effects, the quality of life of affected patients may significantly be reduced.

CASE PRESENTATION

Here, we describe the case of a 65-year-old woman who presented to the department of psychiatry of a university hospital with depressed mood, pronounced anxiety, and nihilistic thoughts. While several pharmacological treatments remained without clinical response, further behavioral observation in conjunction with ¹⁸F-fluoro-2-deoxy-D-glucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) revealed the diagnosis of frontotemporal dementia (FTD). To counter the pharmacological treatment resistance of psychotic depression, we decided to perform electroconvulsive therapy (ECT). Remarkably, ten sessions of ECT yielded an almost complete remission of depressive symptoms. In addition, the patient's delusional ideas disappeared. A follow-up ¹⁸F-FDG PET/CT after the ECT series still showed a frontally and parieto-temporally accentuated hypometabolism, albeit with a clear regression compared to the previous image. The follow-up ¹⁸F-FDG PET/CT thus corroborated the diagnosis of FTD, while on the other hand it demonstrated the success of ECT.

CONCLUSIONS

In this case, ECT was a beneficial treatment option for depressive symptoms in FTD. Also, ¹⁸F-FDG PET/CT should be discussed as a valuable tool in differentiating depression and dementia and as an indicator of treatment response.

Electroconvulsive therapy for treatment-resistant depression

Electroconvulsive therapy (ECT), the oldest brain stimulation procedure in psychiatry, is associated with rapid response and remission in majority of patients with resistant, severe, and sometimes life-threatening depression. ECT has been included as an essential component in the definition of treatment-resistant depression (TRD) to display the course and diversification of TRD. On the other hand, ECT remains the treatment of choice for the most severe incapacitating forms of TRD and is a cost-effective treatment. In this chapter, we reviewed some essential studies, meta-analysis, and expert guidelines regarding ECT in TRD. ECT should not be considered as a treatment of last resort, and its administration should be considered on the basis of individual patient and illness factors. The clinical role of ECT vs other neurostimulation treatments for TRD, that is, repetitive transcranial magnetic stimulation, were also explored. Much effort has been directed toward the clinical and basic research about mechanisms of action of ECT in depression. A thorough understanding of the neurobiological effects of ECT may increase our understanding of its therapeutic effects, ultimately leading to improved patient care. We also showed that the distinct mechanisms of ECT in biological treatments of major depressive disorder (MDD) and some recent approaches to understand this most common psychiatric disorder. ECT should remain a standard part of modern psychiatric medicine. We recommend a more careful and thoughtful application of this traditional but effective technology.

Personalized Diagnosis and Treatment for Neuroimaging in Depressive Disorders

Depressive disorders are highly heterogeneous in nature. Previous studies have not been useful for the clinical diagnosis and prediction of outcomes of major depressive disorder (MDD) at the individual level, although they provide many meaningful insights. To make inferences beyond group-level analyses, machine learning (ML) techniques can be used for the diagnosis of subtypes of MDD and the prediction of treatment responses. We searched PubMed for relevant studies published until December 2021 that included depressive disorders and applied ML algorithms in neuroimaging fields for depressive disorders. We divided these studies into two sections, namely diagnosis and treatment outcomes, for the application of prediction using ML. Structural and functional magnetic resonance imaging studies using ML algorithms were included. Thirty studies were summarized for the prediction of an MDD diagnosis. In addition, 19 studies on the prediction of treatment outcomes for MDD were reviewed. We summarized and discussed the results of previous studies. For future research results to be useful in clinical practice, ML enabling individual inferences is important. At the same time, there are important challenges to be addressed in the future.

Prediction of Facial Emotion Recognition Ability in Patients With First-Episode Schizophrenia Using Amplitude of Low-Frequency Fluctuation-Based Support Vector Regression Model

OBJECTIVE

There were few studies that had attempted to predict facial emotion recognition (FER) ability at the individual level in schizophrenia patients. In this study, we developed a model for the prediction of FER ability in Chinese Han patients with the first-episode schizophrenia (FSZ).

MATERIALS AND METHODS

A total of 28 patients with FSZ and 33 healthy controls (HCs) were recruited. All subjects underwent resting-state fMRI (rs-fMRI). The amplitude of low-frequency fluctuation (ALFF) method was selected to analyze voxel-level spontaneous neuronal activity. The visual search experiments were selected to evaluate the FER, while the support vector regression (SVR) model was selected to develop a model based on individual rs-fMRI brain scan.

RESULTS

Group difference in FER ability showed statistical significance (P < 0.05). In FSZ patients, increased mALFF value were observed in the limbic lobe and frontal lobe, while decreased mALFF value were observed in the frontal lobe, parietal lobe, and occipital lobe (P < 0.05, AlphaSim correction). SVR analysis showed that abnormal spontaneous activity in multiple brain regions, especially in the right posterior cingulate, right precuneus, and left calcarine could effectively predict fearful FER accuracy (r = 0.64, P = 0.011) in patients.

CONCLUSION

Our study provides an evidence that abnormal spontaneous activity in specific brain regions may serve as a predictive biomarker for fearful FER ability in schizophrenia.