Screening for suicide risk in adult sleep patients

Bored to death: Artificial Intelligence research reveals the role of boredom in suicide behavior

Background

Recent advancements in Artificial Intelligence (AI) contributed significantly to suicide assessment, however, our theoretical understanding of this complex behavior is still limited.

Objective

This study aimed to harness AI methodologies to uncover hidden risk factors that trigger or aggravate suicide behaviors.

Methods

The primary dataset included 228,052 Facebook postings by 1,006 users who completed the gold-standard Columbia Suicide Severity Rating Scale. This dataset was analyzed using a bottom-up research pipeline without a-priory hypotheses and its findings were validated using a top-down analysis of a new dataset. This secondary dataset included responses by 1,062 participants to the same suicide scale as well as to well-validated scales measuring depression and boredom.

Results

An almost fully automated, AI-guided research pipeline resulted in four Facebook topics that predicted the risk of suicide, of which the strongest predictor was boredom. A comprehensive literature review using APA PsycInfo revealed that boredom is rarely perceived as a unique risk factor of suicide. A complementing top-down path analysis of the secondary dataset uncovered an indirect relationship between boredom and suicide, which was mediated by depression. An equivalent mediated relationship was observed in the primary Facebook dataset as well. However, here, a direct relationship between boredom and suicide risk was also observed.

Conclusion

Integrating AI methods allowed the discovery of an under-researched risk factor of suicide. The study signals boredom as a maladaptive 'ingredient' that might trigger suicide behaviors, regardless of depression. Further studies are recommended to direct clinicians' attention to this burdening, and sometimes existential experience.

Self-Reported Mood and Lifestyle-Related Physical Activity of Young Adults With Major Depressive Disorder

We investigated whether mood and lifestyle-related indicators of physical health are differentially expressed according to self-reported levels of depressive symptoms among young adults with a current episode of major depression. In a cross-sectional study, we recruited 94 young adults (females = 67, 71.3%; males = 27, 28.7%; aged 18-35 years) with a current episode of major depression. We assessed their mood with the Profile of Mood States (POMS), and Beck Anxiety Inventory-(BAI), sleep with the Pittsburgh Sleep Quality Index (PSQI), physical activity with the Simple Physical Activity Questionnaire (SIMPAQ), and their cardiorespiratory fitness. Participants' depression levels were classified as follows using established cut-points: (a) Mild Depressive Symptoms (MIDS, BDI-II 14-19 points, n = 17), (b) Moderate Depressive Symptoms (MODS, BDI-II 20-28 points, n = 37) or (c) Severe Depressive Symptoms (SEDS, BDI-II 29-63 points, n = 40). As expected, we found that young adults with SEDS, when compared to those with MODS and MIDS, showed higher depressive mood on the POMS, and they exhibited greater anxiety symptoms, lower reported 'vigor' on physical activity measures, worse sleep quality as expressed by their global score sleep; daytime dysfunction; and sleep disturbance, and they showed lower cardiorespiratory fitness. Those with moderate depressive symptoms only differed from those with mild symptoms with respect to hostility, fatigue and mood disturbance. Although there was a gradient whereby worse mental and physical health indicators were more closely related to the SEDS depression categorization, while healthier indicators were associated with the MIDS category, some parameters were not different between the MDD severity groups, particularly when comparing MIDS and MODS. Clinicians treating patients with MDD should consider these factors when designing lifestyle-based interventions.

Nighttime Sleep Quality and Daytime Sleepiness Predicts Suicide Risk in Adults Admitted to an Inpatient Psychiatric Hospital

As sleep problems have been identified as an important, yet understudied, predictor of suicide risk, the present study analyzed the relationship between daytime sleepiness and nighttime sleep disturbance in a high-risk population of adults admitted to an inpatient psychiatric hospital. Objectives were to (1) examine the time course of subjective daytime sleepiness, nighttime sleep disturbance, and suicide risk throughout inpatient psychiatric treatment, (2) examine pre- to post-treatment changes in sleep disturbance with treatment as usual in an inpatient psychiatric setting, and (3) investigate whether daytime sleepiness and nighttime sleep disturbance predicted suicide risk above and beyond anxiety and depression. Participants were 500 consecutively admitted adults admitted to an intermediate length of stay (4-6 weeks) inpatient psychiatric hospital (47% female; 18-87 years of age). Measures of sleep, suicide risk, depression, and anxiety were completed at admission, weeks 1 through 4, and at discharge. Latent growth curve modeling (LGM) and hierarchal linear modeling (HLM) were conducted. The LGM analysis demonstrated that daytime sleepiness, nighttime sleep disturbance, and suicide risk all improved throughout inpatient treatment. Further, HLM showed that daytime sleepiness predicted suicide risk above and beyond symptoms of anxiety, depression, major sleep medications, and prior suicidal ideation and attempts, while nighttime sleep disturbance predicted suicide risk above and beyond symptoms of anxiety, major sleep medications, and prior suicidal ideation and attempts. Findings indicate the need to reevaluate safety protocols that may impact sleep, particularly that may increase daytime sleepiness, and to develop evidence-based sleep interventions for individuals admitted to inpatient psychiatric hospitals.

Association between hospital-diagnosed sleep disorders and suicide: a nationwide cohort study

STUDY OBJECTIVES

Sleep disorders are related to mental disorders. Yet few studies have examined their association with suicide. We examined whether males and females diagnosed with sleep disorders had higher rates of suicide than individuals not diagnosed with sleep disorders.

METHODS

In a cohort study, nationwide data on all males and females aged over 15 years living in Denmark during 1980-2016 were analyzed. Sleep disorders were identified through diagnoses recorded during contacts to somatic hospitals. Incidence rate ratios (IRR) were estimated using Poisson regression models and adjusted for covariates.

RESULTS

In all, 3 674 563 males and 3 688 164 females were included, of whom 82 223 (2.2%, mean age: 50.2 years, SD: 17.5) males and 40 003 (1.1%, mean age: 50.6 years, SD: 19.9) females had sleep disorder diagnoses. Compared with those with no sleep disorders, the adjusted IRR for suicide were 1.6 (95% CI, 1.4 to 1.7) and 2.2 (95% CI, 1.8 to 2.6) for males and females with sleep disorders, respectively. Excess rates for narcolepsy were found for males (IRR: 1.2, 95% CI, 1.0 to 1.5) and females (IRR: 3.3, 95% CI, 3.0 to 4.1), and for sleep apnea in males (IRR: 1.8, 95% CI, 1.5 to 2.2). A difference with respect to age and sex was observed (p < 0.001) between males and females. Males and females had IRR of 4.1 (95% CI, 3.1 to 5.5) and 7.0 (95% CI, 4.8 to 10.1), during the first 6 months after being diagnosed with a sleep disorder.

CONCLUSIONS

Sleep disorders were associated with higher suicide rates even after adjusting for preexisting mental disorders. Our findings suggest attention toward suicidality in patients with sleep disorders is warranted.

Self-reported sleep and exercise patterns in patients admitted with suicidal attempts: a cross-sectional comparative study

BACKGROUND

There is evidence that sleep disturbances and exercise are risk factors for suicide attempts; however, whether sleep disturbances are independently associated with suicide attempts is debatable. We compared the sleep and exercise patterns of individuals who attempted suicide to those of the general population and investigated whether sleep disturbances were independently associated with suicide attempts.

METHODS

Over a year, individuals presented to the emergency department at Hamad General Hospital and Mental Health Services in Doha with suicide attempts (n = 127) filled out questionnaires on sleep and exercise, demographics, and clinical measures. A control group (n = 126) from two primary care centers filled out the same questionnaires during the same period.

RESULTS

Subjects in the suicide group were significantly younger, single, had a lower level of education, and showed considerably more early insomnia, daytime tiredness, interrupted sleep, and no regular exercise. The most common diagnoses seen with suicidality were adjustment disorder and major depression, and the most common method used to attempt suicide was an overdose. After multiple regression analysis, being Arab, belonging to the category "other nationalities," unemployment, and early insomnia were significantly associated with an increased risk of suicide attempts.

CONCLUSION

This is the first comparative study on suicide in the Arabian Gulf. Individuals in Qatar with acute stress, depressive symptoms, sleep disturbances, and lack of exercise are at increased risk of attempting suicide. Thus, clinicians need to routinely screen for sleep and physical activity because of their significant contribution to physical and mental well-being.

Prescription medications for insomnia are associated with suicidal thoughts and behaviors in two nationally representative samples

STUDY OBJECTIVES

Z-drugs (eszopiclone, zolpidem, and zaleplon) are commonly used for insomnia but are also associated with suicide risk. However, it is unclear if this association is unique to Z-drugs. Therefore, the present study estimated the associations between multiple prescription insomnia medications and suicidal thoughts and behaviors.

METHODS

Data were acquired from the National Survey on Drug Use and Health for 2015-2018 and the National Health and Nutrition Examination Survey for 2005-2018. Samples were balanced on sociodemographic and mental health covariates using inverse probability of treatment weighting. Associations of Z-drugs, trazodone, and sedative benzodiazepines (temazepam, triazolam, flurazepam) with suicidal ideation, planning, and attempts were estimated using binomial logistic regression.

RESULTS

In the National Survey on Drug Use and Health, Z-drugs were associated with suicidal ideation (odds ratio [OR], 1.32; 95% confidence interval [CI], 1.14-1.54]), suicide planning (OR, 1.44; 95% CI, 1.19-1.75), and suicide attempts (OR, 1.45; 95% CI, 1.13-1.86) after adjusting for age, sex, race/ethnicity, income, depression, illicit substance use, and the 6-item Kessler Psychological Distress Scale and World Health Organization Disability Assessment Schedule II scores. When analyses accounted for the same factors, sedative benzodiazepines were associated with suicide attempts (OR, 1.76; 95% CI, 1.06-2.87) but not suicidal ideation (OR, 1.37; 95% CI, 0.99-1.88) or suicide planning (OR, 1.39; 95% CI, 0.97-2.00). In the National Health and Nutrition Examination Survey, Z-drugs were associated with suicidal ideation (OR, 2.44; 95% CI, 1.41-4.22), as was trazodone (OR, 2.33; 95% CI, 1.45-3.75), after analyses adjusted for age, sex, race/ethnicity, and exposure to various psychotropic medications.

CONCLUSIONS

Multiple classes of prescription insomnia medications are associated with suicidal thinking and behaviors, even after analyses adjusted for measures of mental health.

Clinical features of the patients with major depressive disorder co-occurring insomnia and hypersomnia symptoms: a report of NSSD study

BACKGROUND

The co-occurrence of insomnia and hypersomnia symptoms in patients with major depressive disorder (MDD) is associated with suicidal ideation and functional impairment. The relationship between sleep disturbances and clinical features and outcomes may not be adequately studied. In this study, we measured the functional impairments and clinical features of co-occurring insomnia and hypersomnia symptoms in Chinese patients with MDD.

METHODS

A post-hoc analysis was performed on data from the National Survey on Symptomatology of Depression (NSSD), which assessed the MDD patients in 32 hospitals by a clinician-rating questionnaire. The clinical features and outcomes were compared among the following four groups: insomnia symptom only, hypersomnia symptom only, both insomnia and hypersomnia symptoms, no sleep disturbance, respectively.

RESULTS

Totally, 234 (7.15%) of 3275 participants with MDD co-occurred insomnia and hypersomnia symptoms. They had more depressive symptoms (27.41 ± 9.123), higher rate of suicide ideation (39.7%), more severe impairment in physical (58.1%), economic (32.9%), work (55.1%), and relationship with families (29.5%). Patients with both sleep disturbances were more likely to excessive worry about sleep, have suicidal ideation, the distress of social disharmony, more somatic symptoms, lack of energy, hyperphagia, loss of mood reactivity, and diurnal change, whereas less likely to have anxious mood.

LIMITATIONS

Sleep disorders were not diagnosed by current standard diagnostic criteria.

CONCLUSIONS

Patients co-occurring with both sleep disturbances are associated with a higher rate of suicide risk and poorer social function. Our study could provide implications for suicidal risk evaluation and the development of therapeutic strategies for depression.

Deep neural networks detect suicide risk from textual facebook posts

Detection of suicide risk is a highly prioritized, yet complicated task. Five decades of research have produced predictions slightly better than chance (AUCs = 0.56–0.58). In this study, Artificial Neural Network (ANN) models were constructed to predict suicide risk from everyday language of social media users. The dataset included 83,292 postings authored by 1002 authenticated Facebook users, alongside valid psychosocial information about the users. Using Deep Contextualized Word Embeddings for text representation, two models were constructed: A Single Task Model (STM), to predict suicide risk from Facebook postings directly (Facebook texts → suicide) and a Multi-Task Model (MTM), which included hierarchical, multilayered sets of theory-driven risk factors (Facebook texts → personality traits → psychosocial risks → psychiatric disorders → suicide). Compared with the STM predictions (0.621 ≤ AUC ≤ 0.629), the MTM produced significantly improved prediction accuracy (0.697 ≤ AUC ≤ 0.746), with substantially larger effect sizes (0.729 ≤ d ≤ 0.936). Subsequent content analyses suggested that predictions did not rely on explicit suicide-related themes, but on a range of text features. The findings suggest that machine learning based analyses of everyday social media activity can improve suicide risk predictions and contribute to the development of practical detection tools.

Increased Global PSQI Score Is Associated with Depressive Symptoms in an Adult Population from the United States

BACKGROUND

Although sleep problems are associated with a wide range of mental problems, it remains uncertain whether the global Pittsburgh Sleep Quality Index (PSQI) score is related to depressive symptoms in an adult population.

PATIENTS AND METHODS

Data from the Midlife in the United States (MIDUS) study, including a general adult population, were obtained. A total of 1002 individuals (aged 34-84 years) were included in this study. Linear regression and logistic regression analyses were performed to investigate the association between sleep parameters from the PSQI score and depressive symptoms.

RESULTS

The median age of all participants was 53.0 years old, and 45.2% of them were male. After adjustments were made for sociodemographic characteristics, lifestyle factors, currently diagnosed diseases and inflammatory markers, global PSQI score was significantly associated with depression score in the linear regression model (0.298 [0.207-0.389], P<0.001; Model 3). A higher global PSQI score was independently and significantly associated with depressive symptoms (score ≥16) in the logistic regression model (1.235 [1.150-1.325], P<0.001; Model 3). Stratified analysis showed that the independent association between global PSQI score and depressive symptoms was affected by hypnotics use, but not antidepressants use.

CONCLUSIONS

A higher global PSQI score is significantly associated with a higher risk of depressive symptoms in an adult population from the United States. Future longitudinal and interventional studies are warranted to assess whether reducing the global PSQI score may improve symptoms of depression.

The Relationship Between Global Sleep Score And Inflammatory Markers In Obese Adults From The United States

BACKGROUND

Poor sleep is a risk factor for cardiovascular diseases (CVDs). The underlying pathogenesis is not clear. Levels of inflammatory markers, such as C-reactive protein (CRP), interleukin-6 (IL-6) and tumor necrosis factor-ɑ (TNF-ɑ), have been found to be elevated in patients with CVDs.

AIM

The study aimed to investigate the associations between sleep quality and serum inflammatory markers in a cohort of obese adults.

METHODS

This was a second analysis of the data from the Midlife in the United States (MIDUS) study, a longitudinal study of a national (US) sample of adults. A total of 1255 participants completed comprehensive biological assessments. The associations between global sleep score and serum levels of inflammatory markers were analyzed.

RESULTS

Univariate analysis showed that a higher global sleep score was correlated with lower age (r = -0.079, P= 0.009), higher BMI (r = 0.100, P= 0.001) and heavier perceived stress (r = 0.335, P<0.001). Multivariate linear regression analysis showed that the global sleep score was positively related to levels of IL-6 (Sβ=0.074, P=0.009), IL-8 (Sβ=0.089, P=0.002), TNF-ɑ (Sβ=0.0.082, P=0.005), E-selectin (Sβ=0.071, P=0.016) and intercellular adhesion molecule-1 (ICAM-1, Sβ=0.117, P<0.001) after adjustments were made for age, gender, race, marital status, education, current smoking status, physician-diagnosed CVDs and respiratory diseases, BMI and perceived stress. However, the global sleep score was not associated with serum IL-10 (Sβ=-0.021, P=0.463) and CRP (Sβ=0.035, P=0.059) levels after adjustments were made for these confounding factors.

CONCLUSION

Poor sleep is positively associated with serum inflammatory marker levels among obese adults. Sufficient sleep may be particularly important for obese adults to prevent CVDs.