Differences in course of illness between patients with bipolar II disorder with and without epileptiform discharges or other sharp activity on electroencephalograms: a cross-sectional study

Abnormal Electroencephalogram Findings and Its Correlation With Clinical Features From Pediatric Patients in Psychiatric Clinic

Objective: We aimed to evaluate the occurrence of electroencephalogram (EEG) abnormalities in pediatric patients attending an outpatient psychiatry clinic at a tertiary center. We examined the rates of abnormalities and specific findings based on demographics, specific diagnoses, and clinical severity. Methods: This study included pediatric patients who underwent EEG at the outpatient psychiatry clinic. Patient demographics, psychiatric diagnosis, intellectual disability, intelligent quotient (IQ) score, family history of psychiatric disorders, and Clinical Global Impression-Severity (CGI-S) score were obtained through retrospective electronic health record analysis. The rate of EEG abnormalities was calculated, and specific abnormal findings were reviewed. Relationships between the rate of EEG abnormalities and diagnosis, severity, IQ, and age at EEG examination were analyzed. Results: Of 319 patients who underwent EEG, 21.3% (68 patients) of patients exhibited abnormalities, including background abnormalities (14.7%, 47 patients), interictal epileptiform discharges (IEDs) (10.3%, 33 patients), and a slow posterior dominant rhythm (3.8%, 10 patients). The frontal region was the most commonly affected area. Neurodevelopmental disorders (NDDs) had the most frequent abnormalities (29.8%), followed by anxiety (16.7%), sleep (14.3%), mood (11.7%), psychotic (5%), and conduct disorders (0%). Disease severity did not correlate with the rate of EEG abnormalities. Adjusted for age, sex, severity, and family history, patients with EEG abnormalities exhibited lower IQ scores. Conclusion: EEG abnormalities were common in pediatric patients with psychiatric disorders, with background abnormalities detected as frequently as IEDs. Disease severity was not associated with EEG abnormality, while IQ scores showed a negative correlation.

A characteristic cerebellar biosignature for bipolar disorder, identified with fully automatic machine learning

Background

Transcriptomic profile differences between patients with bipolar disorder and healthy controls can be identified using machine learning and can provide information about the potential role of the cerebellum in the pathogenesis of bipolar disorder.With this aim, user-friendly, fully automated machine learning algorithms can achieve extremely high classification scores and disease-related predictive biosignature identification, in short time frames and scaled down to small datasets.

Method

A fully automated machine learning platform, based on the most suitable algorithm selection and relevant set of hyper-parameter values, was applied on a preprocessed transcriptomics dataset, in order to produce a model for biosignature selection and to classify subjects into groups of patients and controls. The parent GEO datasets were originally produced from the cerebellar and parietal lobe tissue of deceased bipolar patients and healthy controls, using Affymetrix Human Gene 1.0 ST Array.

Results

Patients and controls were classified into two separate groups, with no close-to-the-boundary cases, and this classification was based on the cerebellar transcriptomic biosignature of 25 features (genes), with Area Under Curve 0.929 and Average Precision 0.955. The biosignature includes both genes connected before to bipolar disorder, depression, psychosis or epilepsy, as well as genes not linked before with any psychiatric disease. Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis revealed participation of 4 identified features in 6 pathways which have also been associated with bipolar disorder.

Conclusion

Automated machine learning (AutoML) managed to identify accurately 25 genes that can jointly - in a multivariate-fashion - separate bipolar patients from healthy controls with high predictive power. The discovered features lead to new biological insights. Machine Learning (ML) analysis considers the features in combination (in contrast to standard differential expression analysis), removing both irrelevant as well as redundant markers, and thus, focusing to biological interpretation.

Epilepsy and other seizure disorders in acute psychiatric inpatients

BACKGROUND

It is well known that patients with epilepsy have a high rate of psychiatric comorbidity. However, studies exploring epilepsy in psychiatric cohorts are scarce. The aim of this study was to examine the prevalence of seizure disorders in acute psychiatric inpatients.

METHODS

This is a cross-sectional study performed in a catchment-area based acute psychiatric department. All patients (age > 18) admitted during September 2011 - March 2012 were eligible for inclusion. Consenting patients were screened for a life-time history of epilepsy or seizures using self-reported questionnaire data and diagnostic codes for epilepsy in hospital and National registries. Patients scoring positive to one or more of these screening criteria underwent a thorough diagnostic validation (chart review), and the seizure disorders were classified as epilepsy, acute symptomatic seizures and/or psychogenic non-epileptic seizures according to current definitions.

RESULTS

A total of 380 out of 591 (64.3%) consecutively admitted patients consented to participate in the study. Eighty-nine patients (23.4%) scored positive to one or more screening criteria. Fifteen (3.9%) were classified with epilepsy, 21 (5.5%) with acute symptomatic seizures and 9 (2.4%) with psychogenic non-epileptic seizures.

CONCLUSIONS

This is the first study to report on the prevalence of seizure disorders in acute psychiatric inpatients. The life-time prevalence of epilepsy in this cohort of patients is five - six times as high as reports in the general population. These findings underscore the need for the clinical psychiatrist to have comprehensive knowledge on the interface between epileptology and psychiatry.

TRIALS REGISTRATION

ClinicalTrials.gov identifier NCT01415323 .