Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 63
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
1.
Neurosci Lett ; 721: 134804, 2020 Jan 31.
Artigo em Inglês | MEDLINE | ID: mdl-32014516

RESUMO

Because depression has high prevalence and cause enduring disability, it is important to predict onset of depression among community dwelling adults. In this study, we aimed to build a machine learning-based predictive model for future onset of depression. We used nationwide survey data to construct training and hold-out test set. The class imbalance was dealt with the Synthetic Minority Over-sampling Technique. A tree-based ensemble method, random forest, was used to build a predictive model. Depression was defined by 9 or more on the Center for Epidemiologic Studies - Depression Scale 11 items version. Hyperparameters were tuned throughout the 10-fold cross-validation. A total of 6,588 (6,067 of non-depression and 521 of depression) participants were included in the study. The area under receiver operating characteristics curve was 0.870. The overall accuracy, sensitivity, and specificity were 0.862, 0.730, and 0.866, respectively. Satisfactions for leisure, familial relationship, general, social relationship, and familial income had importance in building predictive model for the onset of future depression. Our study demonstrated that predicting future onset of depression by using survey data could be possible. This predictive model is expected to be used for early identification of individuals at risk for depression and secure time to intervention.

2.
Psychiatry Res Neuroimaging ; 297: 111032, 2020 Jan 25.
Artigo em Inglês | MEDLINE | ID: mdl-32028105

RESUMO

The neurobiological causes underlying suicidal behaviors in major depressive disorder (MDD) have not been identified. This study was performed to investigate the differences in brain cortical thickness, surface area, and volume between suicide attempters and non-attempters with MDD. We performed magnetic resonance imaging (MRI) in 38 MDD patients (18-65 years old; 18 male, 20 female) with and without a history of suicide attempts. FreeSurfer software was used to compare the cortical thickness, surface area, and volume of 19 suicide attempters with MDD and 19 suicide non-attempters with MDD, while controlling for age, sex, mean area (or volume), and severity of depression. Compared with suicide non-attempters, suicide attempters with MDD exhibited a larger surface area in the left postcentral area and left lateral occipital area and a larger cortical volume in the left postcentral area and left lateral orbitofrontal area. Suicide attempters exhibited a smaller surface area in the left superior frontal area than suicide non-attempters. The present findings provide evidence for neuroanatomical risk factors of suicide in MDD. Further research to replicate these results and determine the mechanisms underlying these findings is needed.

5.
Adv Exp Med Biol ; 1192: 3-15, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31705487

RESUMO

The modern society is a so-called era of big data. Whereas nearly everybody recognizes the "era of big data", no one can exactly define how big the data is a "big data". The reason for the ambiguity of the term big data mainly arises from the widespread of using that term. Along the widespread application of the digital technology in the everyday life, a large amount of data is generated every second in relation with every human behavior (i.e., measuring body movements through sensors, texts sent and received via social networking services). In addition, nonhuman data such as weather and Global Positioning System signals has been cumulated and analyzed in perspectives of big data (Kan et al. in Int J Environ Res Public Health 15(4), 2018 [1]). The big data has also influenced the medical science, which includes the field of psychiatry (Monteith et al. in Int J Bipolar Disord 3(1):21, 2015 [2]). In this chapter, we first introduce the definition of the term "big data". Then, we discuss researches which apply big data to solve problems in the clinical practice of psychiatry.


Assuntos
Big Data , Psiquiatria , Humanos , Pesquisa
6.
BMC Public Health ; 19(1): 1328, 2019 Oct 22.
Artigo em Inglês | MEDLINE | ID: mdl-31640652

RESUMO

BACKGROUND: Parkinson's disease (PD) and drug-induced parkinsonism (DIP) are the major diseases of parkinsonism. To better understand parkinsonism, we aimed to assess the prevalence and incidence of PD and DIP in Korea from 2012 to 2015. METHODS: We used the Health Insurance Review and Assessment Service database, which covers the entire population in Korea. We used claims during 2011-2015 to assess epidemiology of PD and DIP during 2012-2015. Retrospective cross-sectional study design was employed to assess prevalence, whereas retrospective cohort study design was used to determine incidence. Patients with at least one claim with ICD-10 G20 and who received antiparkinsonian drugs for at least 60 days were classified as having PD. We excluded patients with antiparkinsonian drugs that can be used for indications other than PD. Patients with at least one claim with ICD-10 G211 or G251 during the prescription period of drugs that are frequently related with DIP were classified as having DIP. Incident cases had a disease-free period of 1 year before diagnosis. To evaluate the significance of changes in the prevalence or incidence over time, Poisson regression was used to determine p for trend. RESULTS: The prevalence of PD increased from 156.9 per 100,000 persons in 2012 to 181.3 per 100,000 persons in 2015 (p for trend< 0.0001). The incidence of PD decreased steadily from 35.4 per 100,000 person-years in 2012 to 33.3 per 100,000 person-years in 2015 (p for trend< 0.0001). The prevalence of DIP increased from 7.3 per 100,000 persons in 2012 to 15.4 per 100,000 persons in 2015 (p for trend< 0.0001) and the incidence of DIP increased from 7.1 per 100,000 person-years in 2012 to 13.9 per 100,000 person-years in 2015 (p for trend< 0.0001). CONCLUSIONS: Our study suggests that the incidence of PD has gradually decreased whereas, the incidence of DIP increased from 2012 to 2015. Further studies are warranted to examine possible causes of increased DIP incidence in order to develop management strategy for parkinsonism.


Assuntos
Doença de Parkinson/diagnóstico , Doença de Parkinson/epidemiologia , Idoso , Estudos Transversais , Bases de Dados Factuais , Feminino , Humanos , Incidência , Masculino , Pessoa de Meia-Idade , Programas Nacionais de Saúde , Doença de Parkinson Secundária/diagnóstico , Doença de Parkinson Secundária/epidemiologia , Prevalência , República da Coreia/epidemiologia , Estudos Retrospectivos
9.
PLoS One ; 14(6): e0217639, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31170212

RESUMO

OBJECTIVE: Suicide in adolescents is a major problem worldwide and previous history of suicide ideation and attempt represents the strongest predictors of future suicidal behavior. The aim of this study was to develop prediction model to identify Korean adolescents of high risk suicide (= who have history of suicide ideation/attempt in previous year) using machine learning techniques. METHODS: A nationally representative dataset of Korea Youth Risk Behavior Web-based Survey (KYRBWS) was used (n = 59,984 of middle and high school students in 2017). The classification process was performed using machine learning techniques such as logistic regression (LR), random forest (RF), support vector machine (SVM), artificial neural network (ANN), and extreme gradient boosting (XGB). RESULTS: A total of 7,443 adolescents (12.4%) had a previous history of suicidal ideation/attempt. In the multivariable analysis, sadness (odds ratio [OR], 6.41; 95% confidence interval [95% CI], 6.08-6.87), violence (OR, 2.32; 95% CI, 2.01-2.67), substance use (OR, 1.93; 95% CI, 1.52-2.45), and stress (OR, 1.63; 95% CI, 1.40-1.86) were associated factors. Taking into account 26 variables as predictors, the accuracy of models of machine learning techniques to predict the high-risk suicidal was comparable with that of LR; the accuracy was best in XGB (79.0%), followed by SVM (78.7%), LR (77.9%), RF (77.8%), and ANN (77.5%). CONCLUSIONS: The machine leaning techniques showed comparable performance with LR to classify adolescents who have previous history of suicidal ideation/attempt. This model will hopefully serve as a foundation for decreasing future suicides as it enables early identification of adolescents at risk of suicide and modification of risk factors.

12.
Sci Rep ; 9(1): 3335, 2019 Mar 04.
Artigo em Inglês | MEDLINE | ID: mdl-30833698

RESUMO

The early detection of cognitive impairment is a key issue among the elderly. Although neuroimaging, genetic, and cerebrospinal measurements show promising results, high costs and invasiveness hinder their widespread use. Predicting cognitive impairment using easy-to-collect variables by non-invasive methods for community-dwelling elderly is useful prior to conducting such a comprehensive evaluation. This study aimed to develop a machine learning-based predictive model for future cognitive impairment. A total of 3424 community elderly without cognitive impairment were included from the nationwide dataset. The gradient boosting machine (GBM) was exploited to predict cognitive impairment after 2 years. The GBM performance was good (sensitivity = 0.967; specificity = 0.825; and AUC = 0.921). This study demonstrated that a machine learning-based predictive model might be used to screen future cognitive impairment using variables, which are commonly collected in community health care institutions. With efforts of enhancing the predictive performance, such a machine learning-based approach can further contribute to the improvement of the cognitive function in community elderly.

13.
J Occup Environ Med ; 61(5): e191-e199, 2019 May.
Artigo em Inglês | MEDLINE | ID: mdl-30829888

RESUMO

OBJECTIVE: This study aims to build a predictive model for "return to work" (RTW) after sick leave by using a machine-learning algorithm. METHODS: Panel data of 2000 participants (1686 males and 314 females) from the Labor Welfare Research Institute of the Korea Workers' Compensation & Welfare Service were used. A gradient boosting machine (GBM) was used to build the predictive model. RESULTS: The GBM showed excellent performance in a binary classification (returned to work vs not working). However, the model of the three-group classification showed suboptimal performance. CONCLUSIONS: Although machine-learning algorithms using common predictive factors can accurately predict whether one can work after sick leave, they cannot differentiate the form of returning to work. Future research with detailed information based on the injury or disease is warranted.

14.
Suicide Life Threat Behav ; 49(2): 393-400, 2019 04.
Artigo em Inglês | MEDLINE | ID: mdl-29349806

RESUMO

Many studies have reported that suicides tend to occur on Mondays. However, owing to a lack of controls, conclusive findings on the potential effects of a day of the week on suicides have been lacking. We analyzed public data for causes of death from 1997 to 2015 in the Republic of Korea. Accidental death was used as a control group. The probability of suicide on each day of the week according to age group was calculated. A total of 377,204 deaths (188,601 suicides and 188,603 accidental deaths) were used. The frequency of suicide was highest on Monday and decreased throughout the week until Saturday. Accidental death was highest on Saturday and showed no variations according to weekday. For people in their teens and 20s, the probabilities of suicide on Monday were 9% and 10% higher, respectively, than those on Sunday. As age increased, the differences in suicide probability according to the day of the week were attenuated. The so-called Blue Monday effect is real, particularly for people in their teens and 20s. Suicide prevention strategies that aim to attenuate the burden and stress of Mondays should be planned.


Assuntos
Suicídio/tendências , Adolescente , Adulto , Estudos de Casos e Controles , Bases de Dados Factuais , Feminino , Humanos , Masculino , Fatores Desencadeantes , República da Coreia , Fatores de Tempo , Adulto Jovem
15.
Psychiatry Res Neuroimaging ; 282: 18-23, 2018 12 30.
Artigo em Inglês | MEDLINE | ID: mdl-30384146

RESUMO

Many studies have revealed that the oxytocin receptor gene (OXTR) is associated with emotional salience and depression among females. Hippocampus is closely associated with the pathophysiology of major depressive disorder (MDD). However, little is known of the interaction effects of OXTR and MDD on hippocampal volume. We sought to investigate the interaction effects of OXTR (rs53576) allelic variants and MDD on hippocampal volumes which also including subfield volumes. The OXTR rs53576 genotype groups were categorized as minor G allele carriers and A allele homozygotes. A total of 47 female patients with depression and 30 healthy females were included in this study. There were significant interactions between OXTR allele type and diagnosis of MDD on the 7 hippocampal subfield volumes, such as left presubiculum, left subiculum, left molecular, right cornus ammonis 1, right granule cells in the molecular layer of the dentate gyrus, right molecular layer, and right subiculum. There were no differences in the hippocampal volumes between MDD vs healthy controls or OXTR A vs G alleles. Our results demonstrate the importance of the interactions between OXTR and MDD on hippocampal volume. Future studies with large sample size should expand those interactions in the whole brain volumes.


Assuntos
Transtorno Depressivo Maior/diagnóstico por imagem , Transtorno Depressivo Maior/genética , Hipocampo/diagnóstico por imagem , Polimorfismo de Nucleotídeo Único/genética , Receptores de Ocitocina/genética , Adulto , Feminino , Humanos , Imagem por Ressonância Magnética/métodos , Masculino , Pessoa de Meia-Idade , Tamanho do Órgão
16.
Nord J Psychiatry ; 72(7): 534-541, 2018 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-30444158

RESUMO

BACKGROUND: Magnesium (Mg2+), an endogenous N-methyl-D-aspartate receptor antagonist, has received increased attention recently because of its role in the pathophysiology of and treatment response in depression. However, whether Mg2+ level is decreased in depression is not firmly established. We aimed to conduct a systematic review and meta-analysis to help making consensus for the association between Mg2+ levels and depression. METHODS: A systematic search was conducted in the electronic database resources PubMed and Embase. After a careful selection of relevant studies, a meta-analysis using the random effects model was conducted in each measuring source, such as serum, plasma, and cerebrospinal fluid (CSF). RESULTS: A total of 18 studies were included in this study. Among 11 studies that measured Mg2+ in the serum, Mg2+ level was lower in patients with depression than in controls (weighted mean difference = -.088, 95% confidence interval = -.164 to -.012). In the sensitivity analysis by removing studies one by one, 2 out of the 11 studies obliterated such significant differences. There were no significant differences in the Mg2+ levels in the studies for plasma and CSF. CONCLUSIONS: Despite some evidence supporting an association between decreased Mg2+ levels and depression from studies with serum, the results of our meta-analysis urge to use caution when associating Mg2+ levels and depression. Future studies are needed to establish a consensus for the role of low Mg2+ levels in depression.


Assuntos
Depressão/sangue , Depressão/diagnóstico , Magnésio/sangue , Biomarcadores/sangue , Depressão/psicologia , Humanos , Autoimagem
17.
J Nerv Ment Dis ; 206(10): 770-775, 2018 10.
Artigo em Inglês | MEDLINE | ID: mdl-30273273

RESUMO

Because suicide is irreversible, prevention is paramount. For the optimal strategy to reduce lethal means, we sought to investigate age- and sex-associated variations in suicide methods. Data on annual causes of death from 1991 to 2015 in the Republic of Korea were used. Major sociodemographic correlates of the five suicide methods were analyzed by multiple multinominal logistic regression analysis. Among a total of 239,565 suicides from 1991 to 2015, hanging was most common. Gas poisoning sharply increased from 2007 to 2015. The gap between hanging and the second most common method of suicide has increased from 659 in 2004 to 4,433 in 2015. Charcoal burning was most commonly used by males younger than 45 years of age, whereas pesticide was commonly used by both sexes ages 55 years and older. Our results suggest that age- and sex-specific suicide prevention strategies are needed, particularly for gas and pesticide poisoning.


Assuntos
Suicídio/estatística & dados numéricos , Adulto , Fatores Etários , Idoso , Escolaridade , Feminino , Humanos , Masculino , Estado Civil , Pessoa de Meia-Idade , República da Coreia/epidemiologia , Fatores Sexuais , Adulto Jovem
18.
J Am Acad Child Adolesc Psychiatry ; 57(7): 508-514.e1, 2018 07.
Artigo em Inglês | MEDLINE | ID: mdl-29960696

RESUMO

OBJECTIVE: The postdischarge suicide rate in children and adolescents ever hospitalized for a psychiatric illness is much higher than that of children and adolescents in the general population. We aimed to investigate the postdischarge death and suicide among children and adolescents hospitalized for a psychiatric illness using the Korean National Health Insurance database and causes of death statistics from the National Statistics Office. METHOD: We identified children and adolescents less than 18 years of age who experienced at least one psychiatric hospitalization from 2008 to 2013 with a principal diagnosis of a psychiatric disorder based on the International Classification of Diseases, 10th Revision, Code Fxx.x). Postdischarge deaths (all-cause death or suicide) after the first psychiatric hospitalization were investigated. RESULTS: The total number of patients hospitalized for a psychiatric illness was 14,097, and the numbers of all-cause deaths and suicide deaths after discharge were 93 and 64, respectively. The rates of suicide according by diagnostic group were 440.1 (per 100,000 person-years) for psychosis, 248.8 for depression, 155.4 for conduct disorder, 153.6 for bipolar disorder, 103.4 for posttraumatic stress disorder, 93.0 for anxiety disorder, and 38.4 for attention-deficit/hyperactivity disorder. CONCLUSION: As suicide is the main cause of postdischarge death, there is an urgent need to develop and implement effective prevention strategies after psychiatric hospitalization.


Assuntos
Causas de Morte , Hospitais/estatística & dados numéricos , Transtornos Mentais/mortalidade , Alta do Paciente/estatística & dados numéricos , Suicídio/estatística & dados numéricos , Adolescente , Bases de Dados Factuais , Feminino , Humanos , Masculino , Transtornos Mentais/terapia , República da Coreia , Estudos Retrospectivos
19.
Psychiatry Investig ; 15(7): 663-669, 2018 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-29945429

RESUMO

Objective: The purpose of this study was to determine the key components of Korean disaster psychiatric assistant teams (K-DPATs), to set up new mental health service providing system for the disaster victims. Methods: We conducted an analytic hierarchy process (AHP) involving disaster mental health experts, using a pairwise comparison questionnaire to compare the relative importance of the key components of the Korean disaster mental health response system. In total, 41 experts completed the first online survey; of these, 36 completed the second survey. Ten experts participated in panel meetings and discussed the results of the survey and AHP process. Results: It was agreed that K-DPATs should be independent of the existing mental health system (70.1%), funding for K-DPATs should be provided by the Ministry of Public Safety, and the system should be managed by the Ministry of Health (65.8%). Experts shared the view that K-DPAT leaders would be suitable key decision makers for all types of disaster, with the exception of those involving infectious diseases. Conclusion: K-DPAT, a new model for disaster mental health response systems could improve the insufficiency of the current system, address problems such as fragmentation, and fulfill disaster victims' unmet need for early professional intervention.

20.
Psychiatry Investig ; 15(7): 701-709, 2018 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-29898579

RESUMO

Objective: This study investigated the proposed association between restless legs syndrome (RLS) and the prevalence of hypertension. Methods: A meta-analysis was conducted based on searches of the PUBMED, EMBASE, Cochrane Library, and Korean electronic databases. Cohort and cross-sectional studies reporting the incidence of hypertension in individuals with RLS were included. Dichotomous data were pooled to obtain an odds ratio (OR) and 95% confidence interval (CI) for the prevalence of hypertension in individuals with RLS. The main outcome measure of the study was prevalence of hypertension in patients with RLS compared with a control group. Results: One cohort study and eight cross-sectional studies were included in the meta-analysis. Individuals with RLS had an increased prevalence of hypertension (all studies: OR=1.13, 95% CI=1.04-1.23; cross-sectional studies: OR=1.12, 95% CI=1.01-1.24). However, in subgroup analyses controlling for cardiovascular risk factors, such as diabetes mellitus and dyslipidemia, the differences in the prevalence of hypertension between RLS and control patients were no longer significant. Conclusion: Patients with RLS may have a higher prevalence of hypertension, according to a pooled analysis, but the results remain to be confirmed in well-designed prospective studies.

SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA