1
|
Delgado-García G, Engbers JDT, Wiebe S, Mouches P, Amador K, Forkert ND, White J, Sajobi T, Klein KM, Josephson CB. Machine learning using multimodal clinical, electroencephalographic, and magnetic resonance imaging data can predict incident depression in adults with epilepsy: A pilot study. Epilepsia 2023; 64:2781-2791. [PMID: 37455354 DOI: 10.1111/epi.17710] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2022] [Revised: 06/30/2023] [Accepted: 07/05/2023] [Indexed: 07/18/2023]
Abstract
OBJECTIVE This study was undertaken to develop a multimodal machine learning (ML) approach for predicting incident depression in adults with epilepsy. METHODS We randomly selected 200 patients from the Calgary Comprehensive Epilepsy Program registry and linked their registry-based clinical data to their first-available clinical electroencephalogram (EEG) and magnetic resonance imaging (MRI) study. We excluded patients with a clinical or Neurological Disorders Depression Inventory for Epilepsy (NDDI-E)-based diagnosis of major depression at baseline. The NDDI-E was used to detect incident depression over a median of 2.4 years of follow-up (interquartile range [IQR] = 1.5-3.3 years). A ReliefF algorithm was applied to clinical as well as quantitative EEG and MRI parameters for feature selection. Six ML algorithms were trained and tested using stratified threefold cross-validation. Multiple metrics were used to assess model performances. RESULTS Of 200 patients, 150 had EEG and MRI data of sufficient quality for ML, of whom 59 were excluded due to prevalent depression. Therefore, 91 patients (41 women) were included, with a median age of 29 (IQR = 22-44) years. A total of 42 features were selected by ReliefF, none of which was a quantitative MRI or EEG variable. All models had a sensitivity > 80%, and five of six had an F1 score ≥ .72. A multilayer perceptron model had the highest F1 score (median = .74, IQR = .71-.78) and sensitivity (84.3%). Median area under the receiver operating characteristic curve and normalized Matthews correlation coefficient were .70 (IQR = .64-.78) and .57 (IQR = .50-.65), respectively. SIGNIFICANCE Multimodal ML using baseline features can predict incident depression in this population. Our pilot models demonstrated high accuracy for depression prediction. However, overall performance and calibration can be improved. This model has promise for identifying those at risk for incident depression during follow-up, although efforts to refine it in larger populations along with external validation are required.
Collapse
Affiliation(s)
- Guillermo Delgado-García
- Department of Clinical Neurosciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada
| | | | - Samuel Wiebe
- Department of Clinical Neurosciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada
- Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- O'Brien Institute for Public Health, University of Calgary, Calgary, Alberta, Canada
- Clinical Research Unit, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Pauline Mouches
- Department of Radiology, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Kimberly Amador
- Department of Radiology, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Nils D Forkert
- Department of Clinical Neurosciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada
- Department of Radiology, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - James White
- Department of Radiology, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Libin Cardiovascular Institute, University of Calgary, Calgary, Alberta, Canada
- Department of Cardiac Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Tolulope Sajobi
- Department of Clinical Neurosciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada
- Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- O'Brien Institute for Public Health, University of Calgary, Calgary, Alberta, Canada
| | - Karl Martin Klein
- Department of Clinical Neurosciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada
- Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Department of Medical Genetics, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Alberta Children's Hospital Research Institute, University of Calgary, Calgary, Alberta, Canada
| | - Colin B Josephson
- Department of Clinical Neurosciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada
- Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- O'Brien Institute for Public Health, University of Calgary, Calgary, Alberta, Canada
- Centre for Health Informatics, University of Calgary, Calgary, Alberta, Canada
| |
Collapse
|
2
|
Cai L, He Q, Luo H, Gui X, Wei L, Lu Y, Liu J, Sun A. Is depression in patients with temporal lobe epilepsy related to hippocampal sclerosis? A meta-analysis. Clin Neurol Neurosurg 2023; 225:107602. [PMID: 36689793 DOI: 10.1016/j.clineuro.2023.107602] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2022] [Revised: 12/14/2022] [Accepted: 01/16/2023] [Indexed: 01/19/2023]
Abstract
OBJECTIVE To systematically evaluate the association between hippocampal sclerosis (HS) and depression in patients with temporal lobe epilepsy (TLE) through a meta-analysis. METHODS Chinese and English databases, such as the China National Knowledge Infrastructure (CNKI), Chinese Scientific Journals (VIP), WanFang, the Chinese Biomedical Literature Service System (SinoMed), PubMed and the Web of Science, were searched. RESULTS Two evaluators independently screened the literature, extracted data and evaluated the risk of bias in the included studies in accordance with the inclusion and exclusion criteria. RevMan 5.1 was used to analyze the data. A total of 786 patients with epilepsy were included in the study, including 82 depressive patients with HS and 64 depressive patients without HS. The results showed that the TLE patients with HS were more likely to develop depression than those without HS (odds ratio (OR)= 2.14, 95% confidence interval (CI) [1.45, 3.16], Z = 3.85, p = 0.0001). CONCLUSION HS can be considered a high-risk factor for depression in patients with TLE, and the correlation is significant. However, the sample size included in the study was small; additional high-quality studies are needed in the future.
Collapse
Affiliation(s)
- Lun Cai
- Department of Neurology, The First Affiliated Hospital of Guangxi University of Chinese Medicine, Guangxi University of Chinese Medicine, Nanning 530023, PR China
| | - Qianchao He
- Department of Neurology, The First Affiliated Hospital of Guangxi University of Chinese Medicine, Guangxi University of Chinese Medicine, Nanning 530023, PR China
| | - Huazheng Luo
- Department of Neurology, The First Affiliated Hospital of Guangxi University of Chinese Medicine, Guangxi University of Chinese Medicine, Nanning 530023, PR China
| | - Xiongbin Gui
- Department of Surgery, The First Affiliated Hospital of Guangxi University of Chinese Medicine, Guangxi University of Chinese Medicine, Nanning 530023, PR China.
| | - Liping Wei
- Department of Surgery, The First Affiliated Hospital of Guangxi University of Chinese Medicine, Guangxi University of Chinese Medicine, Nanning 530023, PR China
| | - Yongjing Lu
- Department of Nuclear Medicine, Guangxi Minzu Hospital, Nanning 530001, PR China
| | - Jie Liu
- Department of Neurology, The First Affiliated Hospital of Guangxi University of Chinese Medicine, Guangxi University of Chinese Medicine, Nanning 530023, PR China
| | - Anna Sun
- Department of Neurology, The First Affiliated Hospital of Guangxi University of Chinese Medicine, Guangxi University of Chinese Medicine, Nanning 530023, PR China
| |
Collapse
|
3
|
Fei Y, Shi R, Song Z. Adjunctive Treatment With Eslicarbazepine Acetate for Adults and Children With Focal-Onset Epilepsy: A Meta-Analysis. Front Neurol 2022; 13:909471. [PMID: 35911890 PMCID: PMC9337800 DOI: 10.3389/fneur.2022.909471] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2022] [Accepted: 06/17/2022] [Indexed: 11/13/2022] Open
Abstract
BackgroundThe efficacy and tolerability of eslicarbazepine acetate (ESL) in adults and children with focal-onset epilepsy (FOE) according to the dose remain to be validated. A meta-analysis based on randomized controlled trials (RCTs) was therefore conducted as a summary.MethodsRelevant RCTs were collected by systematic searching the electronic databases of PubMed, Cochrane's Library, Embase, Wanfang and CNKI from inception to May 16, 2022. The random-effect model was adopted to pool the results by incorporating the possible heterogeneity. Efficacy outcomes including responsive rate and effective rate, defined as cases with 50 and ≥75% reduction in seizure frequency compared to baseline, were determined, respectively. Incidence of severe adverse events (AE) leading to drug discontinuation was also evaluated.ResultsTen studies including 2,565 people with epilepsy contributed to the meta-analysis. For adults, ESL 400 mg/d did not improve the response rate or the effective rate; ESL 800 mg/d was associated with improved response rate (odds ratio [OR] 2.16, 95% confidence interval [CI]: 1.65–2.83, p < 0.001) and effective rate (OR 2.16, 95% CI: 1.41–3.30, p < 0.001) without significantly increased severe AE (OR 1.58, 95% CI: 0.90–2.78, p = 0.11); ESL 1,200 mg/d improved response rate (OR 2.49, p < 0.001) and effective rate (OR 3.09, p = 0.04), but significantly increased severe AE (OR 3.72, p < 0.001). For children, ESL also did not significantly improve the response rate (OR 1.76, p = 0.22) or the effective rate (OR 2.17, p = 0.13).ConclusionESL 800 mg/d is effective and well-tolerated as adjuvants for adults with FOE. Efficacy of ESL in children with FOE should be further evaluated.
Collapse
Affiliation(s)
- Yanqing Fei
- Department of Neurology, Third Xiangya Hospital, Central South University, Changsha, China
| | - Ruting Shi
- Department of Rehabilitation, Third Xiangya Hospital, Central South University, Changsha, China
| | - Zhi Song
- Department of Neurology, Third Xiangya Hospital, Central South University, Changsha, China
- *Correspondence: Zhi Song
| |
Collapse
|
4
|
Shen S, Dong Z, Zhang Q, Xiao J, Zhou D, Li J. The overlapping relationship among depression, anxiety, and somatic symptom disorder and its impact on the quality of life of people with epilepsy. Ther Adv Neurol Disord 2022; 15:17562864221138147. [PMID: 36518552 PMCID: PMC9742685 DOI: 10.1177/17562864221138147] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2022] [Accepted: 10/24/2022] [Indexed: 12/13/2022] Open
Abstract
Background: Emotional disorder is an important indicator for assessing the quality of life (QOL) of people with epilepsy (PWE). Depression, somatic symptom disorder (SSD) and anxiety are among the most frequently occurring mental disorders and overlap with each other. Objectives: This study examines the overlap of these three emotional disorders and their effects separately and in combination on the QOL of PWE. Design: Cross-sectional study. Data Sources and Methods: Adults attending our epilepsy clinic between 1 July 2020 and 1 May 2022 were consecutively enrolled. They were screened for depression, SSD, and anxiety by structured interviews, and demographic, epilepsy-related and QOL indicators were collected. Multivariate analysis, propensity score matching (PSM) and stratified analysis were used to explore the effects of their respective and combined effects on QOL. Results: Among the 749 patients, 189 patients (25%) were diagnosed with depression, 183 patients (24%) were diagnosed with SSD, and 157 patients (21%) were diagnosed with anxiety. The frequency of occurrence of each emotional disorder together with other emotional disorders was higher than the frequency of occurrence of an emotional disorder alone. Depression, SSD, and anxiety all had an independent effect on QOL of PWE ( p < 0.001). Depression had the greatest effect, followed by SSD, and then anxiety ( β: multivariate analysis, −11.0 versus –7.8 versus –6.5; PSM, −14.7 versus –9.4 versus –6.8). The QOL of PWE decreased more significantly with the increasing number of comorbid emotional disorders ( β: –12.1 versus –20.7 versus –23.0). Conclusion: It is necessary to screen for three emotional disorders, that is, depression, SSD, and anxiety, in PWE. Attention should be paid to people with multiple comorbid emotional disorders.
Collapse
Affiliation(s)
- Sisi Shen
- Department of Neurology, West China Hospital, Sichuan University, Chengdu, China
| | - Zaiquan Dong
- Mental Health Centre, West China Hospital, Sichuan University, Chengdu, China
| | - Qi Zhang
- Department of Neurology, West China Hospital, Sichuan University, Chengdu, China
| | - Jing Xiao
- Department of Neurology, West China Hospital, Sichuan University, Chengdu, China
| | - Dong Zhou
- Department of Neurology, West China Hospital, Sichuan University, No. 37 GuoXue Alley, Chengdu 610041, China
| | - Jinmei Li
- Department of Neurology, West China Hospital, Sichuan University, No. 37 GuoXue Alley, Chengdu 610041, China
| |
Collapse
|