1
|
van der Does Y, Turner RJ, Bartels MJH, Hagoort K, Metselaar A, Scheepers F, Grünwald PD, Somers M, van Dellen E. Outcome prediction of electroconvulsive therapy for depression. Psychiatry Res 2023; 326:115328. [PMID: 37429173 DOI: 10.1016/j.psychres.2023.115328] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/15/2023] [Revised: 06/26/2023] [Accepted: 06/30/2023] [Indexed: 07/12/2023]
Abstract
INTRODUCTION We developed and tested a Bayesian network(BN) model to predict ECT remission for depression, with non-response as a secondary outcome. METHODS We performed a systematic literature search on clinically available predictors. We combined these predictors with variables from a dataset of clinical ECT trajectories (performed in the University Medical Center Utrecht) to create priors and train the BN. Temporal validation was performed in an independent sample. RESULTS The systematic literature search yielded three meta-analyses, which provided prior knowledge on outcome predictors. The clinical dataset consisted of 248 treatment trajectories in the training set and 44 trajectories in the test set at the same medical center. The AUC for the primary outcome remission estimated on an independent validation set was 0.686 (95%CI 0.513-0.859) (AUC values of 0.505 - 0.763 observed in 5-fold cross validation of the model within the train set). Accuracy 0.73 (balanced accuracy 0.67), sensitivity 0.55, specificity 0.79, after temporal validation in the independent sample. Prior literature information marginally reduced CI width. DISCUSSION A BN model comprised of prior knowledge and clinical data can predict remission of depression after ECT with reasonable performance. This approach can be used to make outcome predictions in psychiatry, and offers a methodological framework to weigh additional information, such as patient characteristics, symptoms and biomarkers. In time, it may be used to improve shared decision-making in clinical practice.
Collapse
Affiliation(s)
- Yuri van der Does
- Department of Psychiatry, UMC Utrecht Brain Center, University Medical Center Utrecht, Utrecht University, 3584 CX Utrecht, the Netherlands.
| | - Rosanne J Turner
- Department of Psychiatry, UMC Utrecht Brain Center, University Medical Center Utrecht, Utrecht University, 3584 CX Utrecht, the Netherlands; Machine Learning Group, CWI (national research institute for mathematics and computer science), Amsterdam, the Netherlands
| | - Miel J H Bartels
- Department of Psychiatry, UMC Utrecht Brain Center, University Medical Center Utrecht, Utrecht University, 3584 CX Utrecht, the Netherlands
| | - Karin Hagoort
- Department of Psychiatry, UMC Utrecht Brain Center, University Medical Center Utrecht, Utrecht University, 3584 CX Utrecht, the Netherlands
| | - Aäron Metselaar
- Department of Psychiatry, UMC Utrecht Brain Center, University Medical Center Utrecht, Utrecht University, 3584 CX Utrecht, the Netherlands
| | - Floortje Scheepers
- Department of Psychiatry, UMC Utrecht Brain Center, University Medical Center Utrecht, Utrecht University, 3584 CX Utrecht, the Netherlands
| | - Peter D Grünwald
- Machine Learning Group, CWI (national research institute for mathematics and computer science), Amsterdam, the Netherlands; Department of Mathematics, Leiden University, Leiden, Netherlands
| | - Metten Somers
- Department of Psychiatry, UMC Utrecht Brain Center, University Medical Center Utrecht, Utrecht University, 3584 CX Utrecht, the Netherlands
| | - Edwin van Dellen
- Department of Psychiatry, UMC Utrecht Brain Center, University Medical Center Utrecht, Utrecht University, 3584 CX Utrecht, the Netherlands; Department of Neurology, UZ Brussel and Vrije Universiteit Brussel, Brussels, Belgium
| |
Collapse
|
2
|
Wang B, Kang Y, Huo D, Chen D, Song W, Zhang F. Depression signal correlation identification from different EEG channels based on CNN feature extraction. Psychiatry Res Neuroimaging 2023; 328:111582. [PMID: 36565553 DOI: 10.1016/j.pscychresns.2022.111582] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/25/2022] [Revised: 11/24/2022] [Accepted: 12/17/2022] [Indexed: 12/24/2022]
Abstract
Depression is a mental illness and can even lead to suicide if not be diagnosed and treated. Electroencephalograph (EEG) is used to diagnose depression and it is more complexity to extract the features from all the multimodal channel information . In order to simplify the diagnose process and detect clinical depression, the EEG channels with strong depression information should be identified firstly. Therefore, a depression signal correlation identification method based on convolutional neural network (CNN) is proposed. In the method, the labeled multi-channel EEG is used as data. The EEG signals of each channel are divided into neural network training data set and these data is trained by AlexNet network. Then the correlation classification of each channel for depression is identified based on the trained sample. Accuracy and loss functions are used to evaluate classification index.Conversely, the correlation is lower. An experiments is conducted and the results show that the correlation is not consistent. A few of channels are strongly correlated with depression, such as 13, 17, 28, 40, 46, 66 and 69. These EEG channels are selected to diagnose depression.
Collapse
|
3
|
Serum Mature BDNF Level Is Associated with Remission Following ECT in Treatment-Resistant Depression. Brain Sci 2022; 12:brainsci12020126. [PMID: 35203890 PMCID: PMC8870188 DOI: 10.3390/brainsci12020126] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2021] [Revised: 01/07/2022] [Accepted: 01/16/2022] [Indexed: 11/16/2022] Open
Abstract
The search for a biological marker predicting the future failure or success of electroconvulsive therapy (ECT) remains highly challenging for patients with treatment-resistant depression. Evidence suggests that Brain-Derived Neurotrophic Factor (BDNF), a protein known to be involved in brain plasticity mechanisms, can play a key role in both the clinical efficacy of ECT and the pathophysiology of depressive disorders. We hypothesized that mature BDNF (mBDNF), an isoform of BDNF involved in the neural plasticity and survival of neural networks, might be a good candidate for predicting the efficacy of ECT. Total BDNF (tBDNF) and mBDNF levels were measured in 23 patients with severe treatment-resistant depression before (baseline) they received a course of ECT. More precisely, tBDNF and mBDNF measured before ECT were compared between patients who achieved the criteria of remission after the ECT course (remitters, n = 7) and those who did not (non-remitters, n = 16). We found that at baseline, future remitters displayed significantly higher mBDNF levels than future non-remitters (p = 0.04). No differences were observed regarding tBDNF levels at baseline. The multiple logistic regression model controlled for age and sex revealed that having a higher baseline mBDNF level was significantly associated with future remission after ECT sessions (odd ratio = 1.38; 95% confidence interval = 1.07–2.02, p = 0.04). Despite the limitations of the study, current findings provide additional elements regarding the major role of BDNF and especially the mBDNF isoform in the clinical response to ECT in major depression.
Collapse
|
4
|
Wen QH, Liu Y, Chen HD, Wu JL, Liang LJ, He WZ, Wang Y, Huang GP. Relationship Between Depression After Hemorrhagic Stroke and Auditory Event-Related Potentials in a Chinese Patient Group. Neuropsychiatr Dis Treat 2022; 18:1917-1925. [PMID: 36065387 PMCID: PMC9440680 DOI: 10.2147/ndt.s362824] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/02/2022] [Accepted: 08/08/2022] [Indexed: 11/23/2022] Open
Abstract
PURPOSE Post-stroke depression (PSD) is the most common psychiatric sequelae of stroke. Numerous studies revealed that event-related potentials (ERP) can reflect depression severity to a certain extent, while there is almost no research on depression after hemorrhagic stroke. Therefore, we employed a prospective cross-sectional study to explore the relationship between ERP and depression after hemorrhagic stroke. METHODS A total of 74 patients with intracranial hemorrhage were included in this study. Neurological deficits were evaluated using the National Institutes of Health Stroke Scale (NIHSS) on admission. Depression severity and cognitive impairment were measured using the 17-item Hamilton Depression Scale (HAMD-17) and the Chinese version of the Montreal Cognitive Assessment (MoCA) after two weeks of treatment. All patients were conducted auditory Oddball paradigm for event-related potential mismatch negativity (MMN) and P300. RESULTS In total, 36 patients were diagnosed with PSD at the two weeks of treatment, for a percentage of 48.6%. Depression severity of ICH patients correlated positively with both the latency of MMN (r = 0.376, P = 0.001) and P300 (r = 0.325, P = 0.005), and correlated negatively with both the amplitude of MMN (r=-0.385, P = 0.001) and P300 (r=-0.311, P = 0.007). Depression severity was negatively correlated with cognitive function after hemorrhagic stroke (r=-0.347, P = 0.002). CONCLUSION The latency and amplitude of MMN and P300 can well reflect the degree of depression after hemorrhagic stroke, which may help in the early diagnosis and effective treatment of PSD.
Collapse
Affiliation(s)
- Qian-Hui Wen
- Department of Neurosurgery, The Third Hospital of Mianyang, Sichuan Mental Health Center, Mianyang, People's Republic of China.,Faculty of Psychiatry and Mental Health, North Sichuan Medical College, Nanchong, People's Republic of China
| | - Yang Liu
- Department of Neurosurgery, The Third Hospital of Mianyang, Sichuan Mental Health Center, Mianyang, People's Republic of China
| | - Hu-Dan Chen
- Department of Psychiatry, The Third Hospital of Mianyang, Sichuan Mental Health Center, Mianyang, People's Republic of China
| | - Jun-Lin Wu
- Department of Psychiatry, The Third Hospital of Mianyang, Sichuan Mental Health Center, Mianyang, People's Republic of China
| | - Li-Jun Liang
- Faculty of Psychiatry and Mental Health, North Sichuan Medical College, Nanchong, People's Republic of China
| | - Wen-Zhi He
- Faculty of Psychiatry and Mental Health, North Sichuan Medical College, Nanchong, People's Republic of China
| | - Yao Wang
- Faculty of Psychiatry and Mental Health, North Sichuan Medical College, Nanchong, People's Republic of China
| | - Guo-Ping Huang
- Department of Neurosurgery, The Third Hospital of Mianyang, Sichuan Mental Health Center, Mianyang, People's Republic of China.,Faculty of Psychiatry and Mental Health, North Sichuan Medical College, Nanchong, People's Republic of China
| |
Collapse
|