Deep Learning-Based Stroke Disease Prediction System Using Real-Time Bio Signals.

The emergence of an aging society is inevitable due to the continued increases in life expectancy and decreases in birth rate. These social changes require new smart healthcare services for use in daily life, and COVID-19 has also led to a contactless trend necessitating more non-face-to-face health services. Due to the improvements that have been achieved in healthcare technologies, an increasing number of studies have attempted to predict and analyze certain diseases in advance. Research on stroke diseases is actively underway, particularly with the aging population. Stroke, which is fatal to the elderly, is a disease that requires continuous medical observation and monitoring, as its recurrence rate and mortality rate are very high. Most studies examining stroke disease to date have used MRI or CT images for simple classification. This clinical approach (imaging) is expensive and time-consuming while requiring bulky equipment. Recently, there has been increasing interest in using non-invasive measurable EEGs to compensate for these shortcomings. However, the prediction algorithms and processing procedures are both time-consuming because the raw data needs to be separated before the specific attributes can be obtained. Therefore, in this paper, we propose a new methodology that allows for the immediate application of deep learning models on raw EEG data without using the frequency properties of EEG. This proposed deep learning-based stroke disease prediction model was developed and trained with data collected from real-time EEG sensors. We implemented and compared different deep-learning models (LSTM, Bidirectional LSTM, CNN-LSTM, and CNN-Bidirectional LSTM) that are specialized in time series data classification and prediction. The experimental results confirmed that the raw EEG data, when wielded by the CNN-bidirectional LSTM model, can predict stroke with 94.0% accuracy with low FPR (6.0%) and FNR (5.7%), thus showing high confidence in our system. These experimental results demonstrate the feasibility of non-invasive methods that can easily measure brain waves alone to predict and monitor stroke diseases in real time during daily life. These findings are expected to lead to significant improvements for early stroke detection with reduced cost and discomfort compared to other measuring techniques.

Reversed Hand Movement during Sleep in Patients with Obstructive Sleep Apnea.

OBJECTIVE: Previous findings suggest that hand movement laterality is reversed during sleep. The present study aimed to verify this phenomenon and evaluate whether the extent of reversal is correlated with the severity of sleep apnea. METHODS: A total of 184 participants (mean age: 44.5±13.0 years; 81.5% males) wore actigraphs on both hands during sleep, and nocturnal polysomnography was simultaneously performed. RESULTS: Actigraphic indices of hand movement were significantly higher for the left hand than those for the right hand (p<0.001), including total activity score, mean activity score, mean score in active periods and fragmentation index. Additionally, calculated differences between the fragmentation index for the left versus right hands were significantly correlated with the apnea-hypopnea index (AHI, r=0.149, p=0.032). The AHI was not significantly correlated with differences in hand movement between both hands movement assessed by total activity score (r=0.004, p=0.957), mean activity score (r=0.011, p=0.876), mean score in active periods (r=-0.080, p=0.255). CONCLUSION: More severe symptoms of obstructive sleep apnea was associated with larger degree of hand movement reversal at night. This result support the theory that homeostatic deactivation occurs in the dominant hemisphere during sleep.

Attitudes toward the mentally ill among community health-related personnel in South Korea.

BACKGROUND AND AIMS: Prejudice and negative attitudes toward mental illness are major obstacles in the rehabilitation and functional recovery of patients. The objective of this study was to evaluate the attitudes of health-related personnel toward mentally ill patients in a local urban community in South Korea. MATERIALS AND METHODS: In total, 401 participants (men, 132; women, 269; mean age, 37.3 ± 9.5 years) were recruited. The participants were health-related personnel in a district of Seoul, who were recruited from three different workplaces: a local administration office, a public health center, and a community welfare center. Sociodemographic data were gathered, and the community attitudes toward the mentally ill (CAMI) inventory were administered. Comparisons of the CAMI subscales were conducted among participants using statistical analysis. RESULTS: Community welfare center workers showed more authoritarianism and social restriction and less community mental health ideology than the other two groups. Among the demographic variables, a shorter working career, higher education, female gender, and younger age were also related to a more negative attitude toward mentally ill patients. CONCLUSION: Community health-related personnel who have contact with patients with mental illness should be encouraged to have a fair, hospitable, and open-minded attitude. It is advisable for these workers to receive interventions such as regular educational programs early in their careers.

The Severity of Sleep Disordered Breathing Induces Different Decrease in the Oxygen Saturation During Rapid Eye Movement and Non-Rapid Eye Movement Sleep.

OBJECTIVE: To investigate how differences in oxygen saturation between non-REM (NREM) and REM sleep in patients according to the severity of sleep apnea. METHODS: We studied 396 male patients diagnosed with simple snoring or obstructive sleep apnea syndrome (OSAS) on nocturnal polysomnography. Patients were divided into groups by the OSAS severity. We compared the average oxygen saturation between REM and NREM sleep in each group. RESULTS: In the simple snoring group, average oxygen saturation was significantly greater during REM than during NREM sleep. In the severe OSA group alone, average oxygen saturation was greater in NREM than in REM sleep. The difference of NREM-REM average oxygen saturation correlated significantly with AHI in the severe OSA group. CONCLUSION: More severe hypoxemia was seen in REM than NREM sleep in the severe OSAS group. The differential oxygen decrease between REM and NREM sleep is likely due to the differentially occurring sleep breathing events in each sleep stage according to the SDB severity. The more AHI increases in the severe OSAS patients, the more prominent the hypoxemia of REM sleep compared with NREM sleep is likely to appear. This suggests that the pressure of continuous positive airway pressure should be increased to control the hypoxemia of REM sleep in extremely severe OSAS.

The Relationship between Type D Personality and Suicidality in Low-Income, Middle-Aged Adults.

OBJECTIVE: Low-income adults are considered to be a group at high risk for suicide. We sought to examine the effect of type D personality and other socio-demographic factors on suicidality in low-income, middle-aged Koreans. METHODS: In total, 306 low-income, middle-aged Koreans [age: 49.16±5.24 (40-59) years, 156 males, 150 females] were enrolled from the Korean National Basic Livelihood Security System. Socio-demographic data, including employment status, income, health, marital status, and educational attainment, were gathered. Beck's 19-item Scale for Suicidal Ideation (SSI) was applied to evaluate suicidality, and the DS14 was used to assess type D personality. RESULTS: Unemployment (p<0.01) and absence of spouse (p=0.03) predicted higher SSI scores independent of other socioeconomic factors. All type D personality scores [i.e., negative affectivity (NA), social inhibition (SI), and total score] predicted higher SSI scores independent of all socioeconomic factors (all, p<0.001). Subjects with type D personality had higher SSI scores (p<0.001), and the association between suicidality and socio-demographic factors (employment or physical health) could be found only in subjects without type D personality. CONCLUSION: Type D personality was a risk factor for suicide in low-income Koreans, independently from socio-economic factors. In addition, the socio-demographic factors were less prominently associated with suicidality in those with type D personality.

Three-Dimensional Electroencephalographic Changes on Low-Resolution Brain Electromagnetic Tomography (LORETA) During the Sleep Onset Period.

Electroencephalographic (EEG) patterns during sleep are markedly different from those measured during the waking state, but the process of falling asleep is not fully understood in terms of biochemical and neurophysiological aspects. We sought to investigate EEG changes that occur during the transitional period from wakefulness to sleep in a 3-dimensional manner to gain a better understanding of the physiological meaning of sleep for the brain. We examined EEG 3-dimensionally using LORETA (low-resolution electromagnetic tomography), to localize the brain region associated with changes that occur during the sleep onset period (SOP). Thirty-channel EEG was recorded in 61 healthy subjects. EEG power spectra and intracortical standardized LORETA were compared between 4 types of 30-second states, including the wakeful stage, transition stage, early sleep stage 1, and late sleep stage 1. Sleep onset began with increased delta and theta power and decreased alpha-1 power in the occipital lobe, and increased theta power in the parietal lobe. Thereafter, global reductions of alpha-1 and alpha-2 powers and greater increases of theta power in the occipito-parietal lobe occurred. As sleep became deeper in sleep stage 1, beta-2 and beta-3, powers decreased mainly in the frontal lobe and some regions of the parieto-temporo-limbic area. These findings suggest that sleep onset includes at least 3 steps in a sequential manner, which include an increase in theta waves in the posterior region of the brain, a global decrease in alpha waves, and a decrease in beta waves in the fronto-central area.

Path analysis of suicide ideation in older people.

BACKGROUND: Suicide among older people is one of the most rapidly emerging healthcare issues. The objective of this study was to identify the factors associated with suicide ideation in the aged population in South Korea. METHODS: The study recruited 684 subjects older than 65 years old (males = 147, females = 537, mean age = 78.20±7.02 years), and trained interviewers performed the interviews. The study was performed as part of a community mental health suicide prevention program. The subjects' socio-demographic data, physical health, alcohol problems, social relationships, psychological well-being, and depression severity were all considered. The Korean version of the Beck Scale for Suicide Ideation (K-BSI) was used to evaluate the intensity of suicide ideation. Correlation and hierarchical multiple regression analyses were performed to identify the factors associated with the K-BSI. The study results were tested using a path analysis. RESULTS: Depression severity was positively correlated with suicide ideation, and economic status, psychological well-being, and social relationships were negatively correlated with suicide ideation. Depression severity had the largest direct impact, and economic status and social relationships had indirect impacts on suicide ideation. Psychological well-being exerted both direct and indirect influences. CONCLUSION: Depression severity was the most important predictor of suicide ideation among older people. Other direct and indirect factors played secondary roles. Effective suicide prevention strategies should focus on early detection and active intervention for depression. Socio-economic programs may also indirectly reduce suicide ideation among the aged population.

Usefulness of Young's Internet addiction test for clinical populations.

BACKGROUND: Young's Internet Addiction Test (IAT) is one of the most widely used scales for assessing Internet addiction. AIMS: The purpose of the current study was to investigate the value of IAT for subjects clinically diagnosed with Internet addiction. METHODS: A total of 52 subjects, whose chief complaint and most serious behavioral problem was Internet addiction, were enrolled at an Internet-addiction clinic associated with a university hospital. The IAT was administered to assess the existence and severity of Internet addiction. Subjects were classified according to the severity guidelines of the Diagnostic and Statistical Manual of Mental Disorders, 4th edition, text revision (DSM-IV-TR) and according to the duration of their Internet addiction. RESULTS: The mean IAT score of our clinical subjects was 62.8 ± 18.2, which was below 70, the cut-off point indicating significant problems. The IAT detected only 42% of the clinical subjects as having significant problems with Internet addiction. No significant differences in IAT scores among those with mild, moderate and severe degrees of Internet addition were found, and no association between IAT scores and duration of illness was observed. CONCLUSIONS: IAT scores were not significant correlated with clinical severity and duration of illness in a clinical population. This instrument had limited clinical utility for evaluating the severity of Internet addiction. Considerable caution is required in interpretations of IAT scores.

The effect of aging and severity of sleep apnea on heart rate variability indices in obstructive sleep apnea syndrome.

OBJECTIVE: This study aims to analyze how much heart rate variability (HRV) indices discriminatively respond to age and severity of sleep apnea in the obstructive sleep apnea syndrome (OSAS). METHODS: 176 male OSAS patients were classified into four groups according to their age and apnea-hypopnea index (AHI). The HRV indices were compared via analysis of covariance (ANCOVA). In particular, the partial correlation method was performed to identify the most statistically significant HRV indices in the time and frequency domains. Stepwise multiple linear regressions were further executed to examine the effects of age, AHI, body mass index (BMI), systolic blood pressure (SBP), diastolic blood pressure (DBP), and sleep parameters on the significant HRV indices. RESULTS: The partial correlation analysis yielded the NN50 count (defined as the number of adjacent R-wave to R-wave intervals differing by more than 50 ms) and low frequency/high frequency (LF/HF) ratio to be two most statistically significant HRV indices in both time and frequency domains. The two indices showed significant differences between the groups. The NN50 count was affected by age (p<0.001) and DBP (p=0.039), while the LF/HF ratio was affected by AHI (p<0.001), the amount of Stage 2 sleep (p=0.005), and age (p=0.021) in the order named in the regression analysis. CONCLUSION: The NN50 count more sensitively responded to age than to AHI, suggesting that the index is mainly associated with an age-related parasympathetic system. On the contrary, the LF/HF ratio responded to AHI more sensitively than to age, suggesting that it is mainly associated with a sympathetic tone likely reflecting the severity of sleep apnea.

Onset of Manic Episode during Chemotherapy with 5-Fluorouracil.

The authors report a case of 5-Fluorouracil (5-FU) induced manic episode in an elderly female without any previous psychiatric history. The patient presented manic symptoms after 4th cycle of 5-FU chemotherapy after surgery of rectal cancer. After cessation of chemotherapy and administration of olanzapine and divalproex sodium, symptoms were subsided within 10 days.

Persistence of neuropsychiatric symptoms over six months in mild cognitive impairment in community-dwelling Korean elderly.

BACKGROUND: Several studies of patients with mild cognitive impairment (MCI) have revealed that this population, like people with dementia, have neuropsychiatric symptoms (NPS) as well as memory impairment. No study has reported on the natural history and course of NPS in MCI although this is important in terms of management. We aimed to determine the persistence of NPS over six months in participants with MCI. METHOD: The Neuropsychiatric Inventory (NPI) was used to rate the severity of NPS in 241 consecutive referrals with MCI from a Korean clinic at baseline and in 220 patients at 6-month follow-up. We also collected information about the cognition and quality of life of patients and their caregivers. RESULTS: Ninety-seven (44.1%) MCI participants who completed the 6-month follow-up exhibited at least one NPS at baseline; 60 (27.3%) were clinically significant NPS. Seventy (72.1%) of those with any symptom had at least one persistent NPS at 6-month follow-up, and 44 (73.3%) of those with clinically significant symptoms had at least one significant and persistent NPS at 6-month follow-up. Those with persistent symptoms had more severe baseline symptoms. Both patients and caregivers had a poorer quality of life when the patient had at least one clinically significant symptom. CONCLUSIONS: NPS were highly persistent overall in older people with MCI. Persistence was predicted by having more severe symptoms at baseline. Clinically significant levels of NPS were associated with decreased quality of life. We conclude that clinicians should be aware that NPS symptoms in MCI usually persist.

Changes in the expression of transthyretin and protein kinase Cγ genes in the prefrontal cortex in response to naltrexone.

Naltrexone, an opioid receptor antagonist, has been approved for clinical use in the treatment of alcohol dependence. In the present study, we examined the underlying mechanisms of naltrexone by investigating the pharmacogenomic variations in the brain regions associated with alcohol consumption. A complementary DNA microarray analysis was used to profile gene expression changes in the hippocampus and prefrontal cortex (PFC) of C57BL/6 mice injected with naltrexone following ethanol treatment. Intraperitoneal administration of 200µl (16mg/kg) of naltrexone for 4 weeks caused alterations in the expression of a wide range of hippocampal (394) and PFC (566) genes in ethanol-treated mice. Ingenuity Pathway Analysis (IPA) software was used to search for biological pathways and interrelationships between gene networks in the subsets of candidate genes that were altered in the naltrexone-treated PFC and hippocampus. We found gene networks associated with cell morphology, cell death, nervous system development and function, and neurological disease. Confirmation studies using quantitative reverse transcription-polymerase chain reaction (qRT-PCR) revealed that the expression of transthyretin (TTR) and protein kinase C (PKC)γ were increased in the PFC but not in the hippocampus of naltrexone-treated mice. In conclusion, the present study demonstrates a pharmacogenomic response to naltrexone in the brains of ethanol-consuming mice. These findings provide a basis for conducting pharmacogenetic research on the effect of naltrexone in specific brain areas, which would enhance our understanding of the underlying causes and possible treatments of alcohol use disorders.

The Effects of Venlafaxine and Dexamethasone on the Expression of HSP70 in Rat C6 Glioma Cells.

OBJECTIVE: The present study aimed to determine the intracellular action of the antidepressant, venlafaxine, in C6 glioma cells using heat shock protein 70 (HSP70) immunocytochemistry and HSP70 Western blots; HSP70 is known to be associated with stress and depression. METHODS: The extent of HSP70 expression was measured after rat C6 glioma cells were treated with 1) dexamethasone only, 2) venlafaxine only, 3) simultaneous venlafaxine and dexamethasone, or 4) dexamethasone after venlafaxine pretreatment. Dexamethasone (10 microM, 6 hours) did not affect the level of HSP70 expression relative to control. RESULTS: Short-term (1 hour) venlafaxine treatment significantly increased the level of HSP 70 expression. Simultaneous long-term (72 hours) venlafaxine and dexamethasone treatment significantly reduced the level of HSP70 expression. Dexamethasone treatment administered following long-term (24 and 72 hours) pretreatment with venlafaxine also significantly reduced the level of HSP70 expression. CONCLUSION: Short-term treatment with venlafaxine increases the expression of HSP70, but prolonged treatment with dexamethasone suppresses the venlafaxine-induced expression of HSP70. These findings suggest that HSP70 and dexamethasone play a significant role in the pathophysiology of depression.

Characteristics of excessive cellular phone use in Korean adolescents.

Abstract The objective of this study was to evaluate the possible psychological problems related to excessive cellular phone use in adolescents. Results from 595 participants showed that the potentially excessive user group had a tendency to identify themselves with their cellular phones and to have difficulties in controlling usage. They expressed more depressive symptoms, higher interpersonal anxiety, and lower self-esteem. A positive correlation was also observed between excessive cellular phone use and Internet addiction.

Correlation between the severity of obstructive sleep apnea and heart rate variability indices.

The risk of cardiovascular disease is known to be increased in obstructive sleep apnea syndrome (OSAS). Its mechanism can be explained by the observation that the sympathetic tone increases due to repetitive apneas accompanied by hypoxias and arousals during sleep. Heart rate variability (HRV) representing cardiac autonomic function is mediated by respiratory sinus arrhythmia, baroreflex-related fluctuation, and thermoregulation-related fluctuation. We evaluated the heart rate variability of OSAS patients during night to assess their relationship with the severity of the symptoms. We studied overnight polysomnographies of 59 male untreated OSAS patients with moderate to severe symptoms (mean age 45.4+/- 11.7 yr, apnea-hypopnea index [AHI]=43.2+/-23.4 events per hour, and AHI >15). Moderate (mean age 47.1+/-9.4 yr, AHI=15-30, n=22) and severe (mean age 44.5 +/-12.9 yr, AHI >30, n=37) OSAS patients were compared for the indices derived from time and frequency domain analysis of HRV, AHI, oxygen desaturation event index (ODI), arousal index (ArI), and sleep parameters. As a result, the severe OSAS group showed higher mean powers of total frequency (TF) (p=0.012), very low frequency (VLF) (p= 0.038), and low frequency (LF) (p=0.002) than the moderate OSAS group. The LF/HF ratio (p=0.005) was higher in the severe group compared to that of the moderate group. On the time domain analysis, the HRV triangular index (p=0.026) of severe OSAS group was significantly higher. AHI was correlated best with the LF/HF ratio (r(p))=0.610, p<0.001) of all the HRV indices. According to the results, the frequency domain indices tended to reveal the difference between the groups better than time domain indices. Especially the LF/HF ratio was thought to be the most useful parameter to estimate the degree of AHI in OSAS patients.

Tramadol versus buprenorphine for the management of acute heroin withdrawal: a retrospective matched cohort controlled study.

Many medications have been used over the past thirty years for the treatment of opioid withdrawal, including propoxyphene, methadone, clonidine, parenteral buprenorphine, and, more recently, sublingual buprenorphine. Each has been found to have clinical strengths and limitations. Tramadol is a centrally acting synthetic analgesic with opiate activity primarily due to the binding of a metabolite to the micro receptor. Despite this micro receptor activity, tramadol appears to have low abuse potential and is a non-scheduled analgesic. The pharmacologic profile of tramadol makes it a candidate for opiate withdrawal treatment. A chart review was undertaken to retrospectively compare treatment outcomes of heroin-dependent patients when detoxified with parenteral buprenorphine (1996-1997) versus tramadol (1999-2000). Inclusion criteria for this study were heroin as drug of choice, current opioid physical dependence (ie, withdrawal symptoms), no current abuse of oral opioid analgesics, and no alcohol or benzodiazepine withdrawal symptoms. Patient cases that met inclusion criteria were group-matched between buprenorphine and tramadol on the basis of age, sex, and amount of heroin used (bags/day). Charts were audited for patient demographics, daily heroin use at admission, withdrawal symptoms, and discharge status. In total, 129 patient charts were reviewed, and 115 met all inclusion criteria and were group-matched (45 patients in the buprenorphine group, seventy in the tramadol group). There were no differences in demographics between the two groups of patients. Fifty-six percent of the buprenorphine group and 71% of the tramadol group completed detoxification; tramadol-treated patients had significantly higher average withdrawal symptoms when compared to the buprenorphine group and a greater reduction in withdrawal symptoms over time. Finally, the number of side effects was small and did not differ between the groups. The results of this study are consistent with previous pilot reports that indicated few clinical differences between parenteral buprenorphine and oral tramadol protocols when used in the management of acute heroin withdrawal. As a consequence, tramadol shows some promise as an opioid withdrawal management medication.

Tramadol versus buprenorphine for the treatment of opiate withdrawal: a retrospective cohort control study.

Various drugs have been used for the treatment of opioid withdrawal, e.g., methadone, buprenorphine, and clonidine. Tramadol is a centrally acting synthetic analgesic agent with opiate activity due to low affinity binding of the parent compound and higher affinity binding of the O-demethylated metabolite M1 to mu opioid receptors. As a consequence, there may be a role for the use of tramadol in the treatment of opiate withdrawal. We attempt to assess the efficacy of tramadol in treating moderate heroin withdrawal through a retrospective cohort control study, conducted in a detoxification unit in a community teaching hospital. Out of 100 heroin abusers admitted for detoxification during the review period, 64 patients who were treated either with buprenorphine or tramadol, were included in this study, with 20 participants in the buprenorphine group and 44 in the tramadol group. Both groups were matched for age, sex, and self-reported average quantity of heroin used per day. In the tramadol group, the average CINA maximum was 9.0, and in the buprenorphine group it was 11.2 (P = 0.07). The use of oral clonidine per patient in the tramadol group was 1.6 tablets, and in the buprenorphine group 0.1 tablets (P = 0.002). The length of stay was 3.7 days in the tramadol group and 4.1 days in the buprenorphine group (P = 0.5). Four participants in the tramadol group received three or more doses of buprenorphine because their symptoms were not controlled, and were considered as treatment failures. These preliminary data suggest that tramadol may be comparable to buprenorphine in the management of mild to moderately severe heroin withdrawal. These findings, if reproduced in larger studies with stronger research designs, have potentially great implications for the management of opioid withdrawal in both the inpatient and outpatient setting.

The use of tramadol for acute heroin withdrawal: a comparison to clonidine.

Using a retrospective chart review, 59 patients detoxified with tramadol were compared to 85 patients detoxified with clonidine on rates of leaving against medical advice (AMA) and control of withdrawal symptoms. Patients detoxified with tramadol had 23% (95% CI, 0.09-0.59; P < .01) the risk of leaving AMA and scored an average of 0.24 points lower (95% CI, 0.08-0.41; P < .01) on a 0-3 point withdrawal symptom scale compared to patients detoxified with clonidine. This preliminary study indicates that tramadol is more effective in managing withdrawal than clonidine, and may be especially useful in outpatient detoxification.