Stress research is a rapidly emerging area in the field of electroencephalography (EEG) signal processing. The use of EEG as an objective measure for cost effective and personalized stress management becomes important in situations like the nonavailability of mental health facilities. In this study, long-term stress was classified with machine learning algorithms using resting state EEG signal recordings. The labeling for the stress and control groups was performed using two currently accepted clinical practices: (i) the perceived stress scale score and (ii) expert evaluation. The frequency domain features were extracted from five-channel EEG recordings in addition to the frontal and temporal alpha and beta asymmetries. The alpha asymmetry was computed from four channels and used as a feature. Feature selection was also performed to identify statistically significant features for both stress and control groups (via t-test). We found that support vector machine was best suited to classify long-term human stress when used with alpha asymmetry as a feature. It was observed that the expert evaluation-based labeling method had improved the classification accuracy by up to 85.20%. Based on these results, it is concluded that alpha asymmetry may be used as a potential bio-marker for stress classification, when labels are assigned using expert evaluation.
Aims1) To determine the pooled prevalence of overweight and obesity in people with severe mental illness (SMI), overall and by type of SMI, geographical region, and year of data collection; and 2) to assess the likelihood of overweight and obesity, in people with SMI compared with the general population.MethodsPubMed, Medline, EMBASE, and PsycINFO databases were searched to identify observational studies assessing the prevalence of obesity in adults with SMI. Screening, data extraction and risk of bias assessments were performed independently by two co-authors. Random effect estimates for the pooled prevalence of overweight and obesity and the pooled odds of obesity in people with SMI compared with the general population were calculated. Subgroup analyses were conducted for types of SMI, setting, antipsychotic medication, region of the world, country income classification, date of data collection and sex. We assessed publication bias and performed a series of sensitivity analyses, excluding studies with high risk of bias, with low sample size and those not reporting obesity according to WHO classification.Result120 studies from 43 countries were included, the majority were from high income countries. The pooled prevalence of obesity in people with SMI was 25.9% (95% C.I. = 23.3-29.1) and the combined pooled prevalence of overweight and obesity was 60.1% (95% C.I. = 55.8-63.1). Sub-Saharan Africa (13.0%, 95%C.I. = 6.7-25.1) and South Asia (17.7%, 95%C.I. = 10.5-28.5) had the lowest prevalence of obesity whilst North Africa and the Middle East (35.8%, 95%C.I. = 23.8-44.8) reported the highest prevalence. People with SMI were 3.04 more likely (95% C.I. = 2.42-3.82) to have obesity than the general population, but there was no difference in the prevalence of overweight. Women with schizophrenia were 1.44 (95% C.I. = 1.25-1.67) times more likely than men with schizophrenia to live with obesity; however, no gender differences were found among those with bipolar disorder.ConclusionPeople with SMI have a markedly high prevalence and higher odds of obesity than the general population. This may contribute to the very high prevalence of physical health conditions and mortality in this group. People with SMI around the world would likely benefit from interventions to reduce and prevent obesity.
Introduction People with severe mental illness (SMI) are more likely to have obesity and engage in health risk behaviours than the general population. The aims of this study are (1) evaluate the effectiveness of interventions that focus on body weight, smoking cessation, improving sleeping patterns, and alcohol and illicit substance abuse; (2) Compare the number of interventions addressing body weight and health risk behaviours in low- and middle-income countries (LMICs) v. those reported in published systematic reviews focusing on high-income countries (HICs). Methods Intervention studies published up to December 2020 were identified through a structured search in the following database; OVID MEDLINE (1946–December 2020), EMBASE (1974–December 2020), CINAHL (1975–2020), APA PsychoINFO (1806–2020). Two authors independently selected studies, extracted study characteristics and data and assessed the risk of bias. and risk of bias was assessed using the Cochrane risk of bias tool V2. We conducted a narrative synthesis and, in the studies evaluating the effectiveness of interventions to address body weight, we conducted random-effects meta-analysis of mean differences in weight gain. We did a systematic search of systematic reviews looking at cardiometabolic and health risk behaviours in people with SMI. We compared the number of available studies of LMICs with those of HICs. Results We assessed 15 657 records, of which 9 met the study inclusion criteria. Six focused on healthy weight management, one on sleeping patterns and two tested a physical activity intervention to improve quality of life. Interventions to reduce weight in people with SMI are effective, with a pooled mean difference of −4.2 kg (95% CI −6.25 to −2.18, 9 studies, 459 participants, I2 = 37.8%). The quality and sample size of the studies was not optimal, most were small studies, with inadequate power to evaluate the primary outcome. Only two were assessed as high quality (i.e. scored ‘low’ in the overall risk of bias assessment). We found 5 reviews assessing the effectiveness of interventions to reduce weight, perform physical activity and address smoking in people with SMI. From the five systematic reviews, we identified 84 unique studies, of which only 6 were performed in LMICs. Conclusion Pharmacological and activity-based interventions are effective to maintain and reduce body weight in people with SMI. There was a very limited number of interventions addressing sleep and physical activity and no interventions addressing smoking, alcohol or harmful drug use. There is a need to test the feasibility and cost-effectiveness of context-appropriate interventions to address health risk behaviours that might help reduce the mortality gap in people with SMI in LMICs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.