Point prevalence of depression in persons with active epilepsy and impact of methodological moderators: A systematic review and meta-analysis

Machine learning using multimodal clinical, electroencephalographic, and magnetic resonance imaging data can predict incident depression in adults with epilepsy: A pilot study

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.

Is depression in patients with temporal lobe epilepsy related to hippocampal sclerosis? A meta-analysis

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.

Adjunctive Treatment With Eslicarbazepine Acetate for Adults and Children With Focal-Onset Epilepsy: A Meta-Analysis

Background

The 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.

Methods

Relevant 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.

Results

Ten 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).

Conclusion

ESL 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.

The overlapping relationship among depression, anxiety, and somatic symptom disorder and its impact on the quality of life of people with epilepsy

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.