Advanced Daily Prediction Model for National Suicide Numbers with Social Media Data

OBJECTIVE: Suicide is a significant public health concern worldwide. Social media data have a potential role in identifying high suicide risk individuals and also in predicting suicide rate at the population level. In this study, we report an advanced daily suicide prediction model using social media data combined with economic/meteorological variables along with observed suicide data lagged by 1 week. METHODS: The social media data were drawn from weblog posts. We examined a total of 10,035 social media keywords for suicide prediction. We made predictions of national suicide numbers 7 days in advance daily for 2 years, based on a daily moving 5-year prediction modeling period. RESULTS: Our model predicted the likely range of daily national suicide numbers with 82.9% accuracy. Among the social media variables, words denoting economic issues and mood status showed high predictive strength. Observed number of suicides one week previously, recent celebrity suicide, and day of week followed by stock index, consumer price index, and sunlight duration 7 days before the target date were notable predictors along with the social media variables. CONCLUSION: These results strengthen the case for social media data to supplement classical social/economic/climatic data in forecasting national suicide events.

Extrapyramidal Signs and Risk of Progression from Mild Cognitive Impairment to Dementia: A Clinical Research Center for Dementia of South Korea Study

OBJECTIVE: Extrapyramidal signs (EPS) are common in patients with mild cognitive impairment (MCI). However, few studies have assessed the effect of EPS on the clinical course of MCI. We aimed to evaluate whether patients with EPS show more frequent progression from MCI to Alzheimer's disease (AD) and to other types of dementia. METHODS: Participants (n=882) with MCI were recruited, and were followed for up to 5 years. The EPS positive group was defined by the presence of at least one EPS based on a focused neurologic examination at baseline. RESULTS: A total of 234 converted to dementia during the follow-up period. The risk of progression to AD was lower in the patients with EPS after adjusting for potential confounders [hazard ratio (HR)=0.70, 95% confidence interval (CI)=0.53–0.93, p=0.01]. In contrast, the patients with EPS had a six-fold elevated risk of progression to dementia other than AD (HR=6.33, 95%CI=2.30–17.39, p < 0.001). CONCLUSION: EPS in patients with MCI is a strong risk factor for progression of MCI to non-Alzheimer dementia. The careful neurologic examination for EPS in patients with MCI can yield important clinical information for prognosis.

Association between the BDNF Val66Met Polymorphism and Chronicity of Depression

OBJECTIVE: Both clinical and biological factors influence the course of depressive disorders. This study tested for associations between the brain-derived neurotrophic factor (BDNF) gene at the Val66Met locus and the course of major depressive disorder (MDD). METHODS: Three hundred ten Korean subjects (209 patients, 101 controls) were genotyped for rs6265 at nucleotide 196 (G/A), which produces an amino acid substitution at codon 66 (Val66Met) of the gene for BDNF. Course of illness was evaluated both by chronicity of current episode (episode duration >24 months) and by the lifetime history of recurrences. RESULTS: Patients with the Met/Met BDNF genotype had a significantly higher rate of chronic depression than all others. There was a significant dose effect of the Met allele on chronicity. Compared with the Val/Val genotype, the relative risk of chronicity was 1.67 for the Val/Met genotype, and 2.58 for the Met/Met genotype. Lifetime history of recurrent episodes was not related to BDNF genotypes but was significantly associated with younger age of onset and with a history of depression in first degree relatives. CONCLUSION: BDNF genotyping may be informative for anticipating chronicity in major depression.