Levels Of Suicide Risk Research Articles

Вплив задоволеності засуджених та ув’язнених міжособистісними відносинами на їх суїцидальні схильності

The purpose of the study is to reveal the impact of prisoners and convicts’ satisfaction on their relationship with closer environment on their suicidal tendencies, as well as on feeling of hopelessness as a predictor of suicide. Methodology. The interrogation of 181 imprisoned persons in penal institutions (pre-trial detention centers) located in 21 oblasts of Ukraine was conducted in order to clarify the indicators and the relationships between them. The following methods were used: 1) test “SR-45” (by Yunatskevych) that reveals a tendency to suicide risk; 2) Beck’s “Hopelessness” scale that reveals the level of hopelessness; 3) questionnaire of measuring the satisfaction with interpersonal relations that influences the level of the convicts relationship with the three groups that make up the social environment: relatives (family), employees of penal institutions (pre-trial detention centers) and other convicts. A five-point Likert scale was used in the questionnaire. Results. The study revealed an impact on the level of suicide risk regarding the relationship with personnel of the penal institutions (p≤0.01) – bad relations with the personnel increase the susceptibility of convicts to suicide. The influence of the level of convicts’ satisfaction with relationship with the personnel (p≤0.01) and with their relatives (p≤0.01) on the feeling of hopelessness was also revealed – the higher the satisfaction, the lower the hopelessness. No statistically significant effects of convicts’ satisfaction with relationships with other convicts on the level of suicidal reactions and on the hopelessness were found. Practical implications. The obtained results indicate the need for preventive measures aimed at raising awareness of the personnel of the penal institution and pre-trial detention centers on the aspects of convicts’ suicidal behavior and the socio-psychological competence in general, promoting the preservation of prisoners’ relationship with their relatives. Originality/value. The research was conducted by the authors in September 2020 – March 2021. This is the first attempt in Ukrainian psychological science to study empirically the impact of prisoners and convicts’ satisfaction with their relationship with the social environment on their suicidal intentions. Key words: imprisoned, convicts, suicide, suicidal behavior, relationship satisfaction, administration, family and relatives.

Evaluating and Improving Engagement in Care After High-Intensity Stays for Mental or Substance Use Disorders.

This interrupted time-series analysis examined whether activating a quality measure, supported by education and a population management tool, was associated with higher postdischarge engagement (PDE) in outpatient care after inpatient and residential stays for mental or substance use disorder care. Discharges from October 2016 to May 2019 were identified from national Veterans Health Administration (VHA) records representing all 140 VHA health care systems. Engagement was defined as multiple mental or substance use disorder outpatient visits in the 30 days postdischarge. The number of such visits required to meet the engagement definition depended on a patient's suicide risk and acuity level of inpatient or residential treatment. Health care system-level performance was calculated as the percentage of qualifying discharges with 30-day PDE. A segmented mixed-effects linear regression model tested whether monthly health care system performance changed significantly after activation of the PDE measure (activation rollout period, October-December 2017). A total of 322,344 discharges qualified for the measure. In the regression model, average health care system performance was 65.6% at the beginning of the preactivation period (October 2016) and did not change significantly in the following 12 months. Average health care system performance increased by 5.7% (SE=0.8%, p<0.001) after PDE measure activation and did not change significantly thereafter-a difference representing 11,464 more patients engaging in care than would have without activation of the measure. Results support use of this measure, along with education, technical assistance, and population management tools, to improve engagement after discharge from residential and inpatient mental and substance use disorder treatment.

Suicidality, self-efficacy and mental health help-seeking in lesbian, gay, bisexual and transgender adults in Taiwan: A cross-sectional study.

The study aimed to investigate the associations of suicide risk, self-efficacy and mental health help-seeking among the lesbian, gay, bisexual and transgender (LGBT). The LGBT individuals were found to have higher risk of suicide. However, mental health promotion and suicide prevention strategies were lacking in this population. A cross-sectional survey with two-group comparison. The LGBT group was recruited through snowballing method, which was then age-matched with the comparison group as the reference. The questionnaire contained demographics, self-rated health, suicide risk assessment and help-seeking indicators including formal (e.g. medical or psychiatric services) and informal (e.g. family or friends) help sought. Chi-square tests, t-tests, two-way ANOVA and multivariable regression were performed to test the differences between two groups. The methods followed STROBE criteria. The LGBT group had a significantly higher prevalence of lifetime/recent suicide ideation, prior suicide attempts and mental distress or depressive symptoms. Their self-rated health and health-related self-efficacy were poorer than those of the comparison group and were associated with increased suicide risk levels. Among the 27.1% of LGBT who intended to seek help for depression, one in five visited psychiatric services. The LGBT were 2-4 times more likely than the comparison group to disclose their distress or seek informal help. However, psychiatric and medical service contacts were relatively low for suicide high-risk individuals in the LGBT group. The LGBT individuals had a lower level of self-efficacy and higher suicidal risks than the general public. Healthcare professionals and the public should be aware of their informal help-seeking signals such as disclosure of suicide ideation to friends/relatives and connect them to proper mental health resources for further assessment. The LGBT with suicide risks require early detection and proper referrals by first-line nurses to promote suicide prevention in this population.

Impulsiveness and suicide in male offenders: Examining the buffer roles of regulatory emotional self-efficacy and flourishing.

Although impulsiveness has been recognized as a risk factor for suicide, few studies have explored how to protect offenders with impulsiveness from the risk of suicide. This study aims to examine the relationships among impulsiveness, suicide risk, regulatory emotional self-efficacy (RESE), and flourishing, focusing on the moderating effects of RESE and flourishing in the relationship between impulsiveness and suicide risk. This is a cross-sectional study of 941 male offenders. All participants were requested to provide some items of demographic information and to complete a package of self-reported questionnaires measuring impulsiveness, suicide risk, RESE, and flourishing. The results indicate that impulsiveness is positively correlated with suicide risk, while RESE and flourishing are negatively correlated with impulsiveness and suicide risk. Most importantly, both RESE and its dimension managing negative affect (NEG) negatively moderate the relationship between impulsiveness and suicide risk. Flourishing and the RESE dimension expressing positive affect (POS) show no significant moderating effect on impulsiveness-suicide risk link. Regulatory emotional self-efficacy, especially its NEG dimension, can buffer the impact of impulsiveness on suicide risk in male offenders, indicating that these factors might be useful supplements in suicide prevention. Offender with higher level of RESE and flourishing show lower level of impulsiveness and suicide risk. High level of RESE and its NEG dimension can buffer the effect of impulsiveness on suicide risk. RESE, especially its NEG dimension might be a useful supplement for suicide prevention in offenders with high impulsiveness.

Treating Veterans at Risk for Suicide: An Examination of the Safety, Tolerability, and Outcomes of Cognitive Processing Therapy.

Individuals with posttraumatic stress disorder (PTSD) are at increased risk for suicidal thoughts and behaviors; however, clinicians often report apprehension about recommending trauma-focused therapy to patients with an increased risk of suicide. The present study aimed to evaluate the safety, tolerability, and response to cognitive processing therapy (CPT) among a sample of military veterans with PTSD and increased suicide risk. A secondary aim was to provide a clinically useful definition of high suicide risk. Chart review was used to classify the suicide risk level of 290 veterans who participated in CPT at a Veterans Affairs clinic. Treatment outcomes in veterans with different suicide risk levels were also gathered and compared. Over 50% (n = 155) of the sample demonstrated increased suicide risk, and 1.0% (n = 3) engaged in suicidal behavior after initiating treatment. To date, hospital records show no suicide deaths since 2016 among clinic patients who received CPT. Suicide risk level was not associated with CPT tolerability, and PTSD symptom change was equivalent across groups, ps = .085-.976. Veterans across groups reported clinically significant reductions in PTSD symptoms. The tested suicide risk categorization schemes performed similarly in differentiating the odds of CPT completion and PTSD symptom reduction. These results suggest that veterans with PTSD and an increased risk of suicide, including those with previous suicide attempts and current ideation, can tolerate and benefit from CPT. Additional variables must be considered to truly determine the acute and imminent suicide risk that would deem CPT to be contraindicated.

Convolutional Neural Network–Based Deep Learning Model for Predicting Differential Suicidality in Depressive Patients Using Brain Generalized q-Sampling Imaging

Suicide is a priority health problem. Suicide assessment depends on imperfect clinician assessment with minimal ability to predict the risk of suicide. Machine learning/deep learning provides an opportunity to detect an individual at risk of suicide to a greater extent than clinician assessment. The present study aimed to use deep learning of structural magnetic resonance imaging (MRI) to create an algorithm for detecting suicidal ideation and suicidal attempts. We recruited 4 groups comprising a total of 186 participants: 33 depressive patients with suicide attempt (SA), 41 depressive patients with suicidal ideation (SI), 54 depressive patients without suicidal thoughts (DP), and 58 healthy controls (HCs). The confirmation of depressive disorder, SA and SI was based on psychiatrists' diagnosis and Mini-International Neuropsychiatric Interview (MINI) interviews. In the generalized q-sampling imaging (GQI) dataset, indices of generalized fractional anisotropy (GFA), the isotropic value of the orientation distribution function (ISO), and normalized quantitative anisotropy (NQA) were separately trained in convolutional neural network (CNN)-based deep learning and DenseNet models. From the results of 5-fold cross-validation, the best accuracies of the CNN classifier for predicting SA, SI, and DP against HCs were 0.916, 0.792, and 0.589, respectively. In SA-ISO, DenseNet outperformed the simple CNNs with a best accuracy from 5-fold cross-validation of 0.937. In SA-NQA, the best accuracy was 0.915. The results showed that a deep learning method based on structural MRI can effectively detect individuals at different levels of suicide risk, from depression to suicidal ideation and attempted suicide. Further studies from different populations, larger sample sizes, and prospective follow-up studies are warranted to confirm the utility of deep learning methods for suicide prevention and intervention.

Medical-Level Suicide Risk Analysis: A Novel Standard and Evaluation Model

The frequent occurrence of suicides in modern society constitutes a serious public health issue. While the motives, methods, and consequences of suicide are quite complicated, if people at risk of suicide can be identified and intervened in time, the loss of life can be reduced. Through analyses based on combining a large number of suicide texts and professional medical literature, a dictionary of potential suicide risk impact factors has been established in this article. Based on this dictionary, a novel medical-level suicide risk standard is proposed to monitor suicide risk from point-to-surface under the timeline baseline. In order to solve the problem of insufficient Chinese suicide data sets, the manually assisted method based on knowledge perception is adopted to annotate the data set with corresponding to risk level. At the same time, a Bert evaluation model based on knowledge perception was established for the classification of risk level. The experimental results showed that proposed method has a 56% recognition accuracy in the prediction of 10-Label suicide risk level proposed in this article, and the classification performance is better than traditional machine learning algorithms. Therefore, the results showed that the classification standard and evaluation model can be effectively used for the identification and early warning of suicide risk, which can discover high suicide risk groups to reduce the occurrence of suicide. It is of great significance to people’s emotion care monitoring.

Features of the Sovereignty of Psychological Space in Adolescents with Different Levels of Suicidal Risk

In the framework of this work, the features of the sovereignty of the psychological space of adolescents with different levels of suicidal risk were investigated. Most adolescents have an average level of suicidal risk. Adolescents with a high level of suicidal risk are characterized by deprivation of the psychological space.

Estudio cualitativo sobre el bienestar en adolescentes con y sin riesgo suicida

Objetivo. Conocer y comprender las nociones y estrategias de bienestar presentes en adolescentes con altos y bajos niveles de riesgo suicida. Metodología. Este estudio exploratorio con enfoque cualitativo, mediante el cual se analizaron las diferencias entre las nociones de bienestar y las estrategias recurrentes en 40 adolescentes con puntuaciones altas y bajas de riesgo suicida. Resultados. Indican la existencia de nociones asociadas a la salud, a la visión integradora y a una perspectiva subjetiva. En cuanto a las estrategias usadas por los adolescentes para promover su propio bienestar las categorías que emergieron se centraron en la interacción social, el hedonismo, el control, la redefinición y proyección subjetiva positiva, y la orientación al cambio. Conclusión. Se discuten los resultados sobre la orientación de estrategias de intervención en adolescentes con alto riesgo suicida basados en sus propias nociones.

Discriminating Suicide Attempters and Predicting Suicide Risk Using Altered Frontolimbic Resting-State Functional Connectivity in Patients With Bipolar II Disorder.

Bipolar II disorder (BD-II) major depression episode is highly associated with suicidality, and objective neural biomarkers could be key elements to assist in early prevention and intervention. This study aimed to integrate altered brain functionality in the frontolimbic system and machine learning techniques to classify suicidal BD-II patients and predict suicidality risk at the individual level. A cohort of 169 participants were enrolled, including 43 BD-II depression patients with at least one suicide attempt during a current depressive episode (SA), 62 BD-II depression patients without a history of attempted suicide (NSA), and 64 demographically matched healthy controls (HCs). We compared resting-state functional connectivity (rsFC) in the frontolimbic system among the three groups and explored the correlation between abnormal rsFCs and the level of suicide risk (assessed using the Nurses' Global Assessment of Suicide Risk, NGASR) in SA patients. Then, we applied support vector machines (SVMs) to classify SA vs. NSA in BD-II patients and predicted the risk of suicidality. SA patients showed significantly decreased frontolimbic rsFCs compared to NSA patients. The left amygdala-right middle frontal gyrus (orbital part) rsFC was negatively correlated with NGASR in the SA group, but not the severity of depressive or anxiety symptoms. Using frontolimbic rsFCs as features, the SVMs obtained an overall 84% classification accuracy in distinguishing SA and NSA. A significant correlation was observed between the SVMs-predicted NGASR and clinical assessed NGASR (r = 0.51, p = 0.001). Our results demonstrated that decreased rsFCs in the frontolimbic system might be critical objective features of suicidality in BD-II patients, and could be useful for objective prediction of suicidality risk in individuals.

A Feasibility Study Using a Machine Learning Suicide Risk Prediction Model Based on Open-Ended Interview Language in Adolescent Therapy Sessions.

Background: As adolescent suicide rates continue to rise, innovation in risk identification is warranted. Machine learning can identify suicidal individuals based on their language samples. This feasibility pilot was conducted to explore this technology’s use in adolescent therapy sessions and assess machine learning model performance. Method: Natural language processing machine learning models to identify level of suicide risk using a smartphone app were tested in outpatient therapy sessions. Data collection included language samples, depression and suicidality standardized scale scores, and therapist impression of the client’s mental state. Previously developed models were used to predict suicidal risk. Results: 267 interviews were collected from 60 students in eight schools by ten therapists, with 29 students indicating suicide or self-harm risk. During external validation, models were trained on suicidal speech samples collected from two separate studies. We found that support vector machines (AUC: 0.75; 95% CI: 0.69–0.81) and logistic regression (AUC: 0.76; 95% CI: 0.70–0.82) lead to good discriminative ability, with an extreme gradient boosting model performing the best (AUC: 0.78; 95% CI: 0.72–0.84). Conclusion: Voice collection technology and associated procedures can be integrated into mental health therapists’ workflow. Collected language samples could be classified with good discrimination using machine learning methods.

Longitudinal study of PTSD and depression in a war-exposed sample – comorbidity increases distress and suicide risk

Background Major depressive disorder (MDD) and post-traumatic stress disorder (PTSD) are the most common mental disorders following traumatic experiences. The aim of this study was to investigate the extent to which PTSD and depression co-occurred in Serbian general population at baseline and 1 year after the follow-up, as well as how this co-occurrence was associated with sociodemographic factors, personal distress, suicidality and quality of life. Subjects and methods The sample consisted of 159 subjects, who fulfilled the IES criteria for PTSD, and were taken from a larger sample of 640 participants, which was chosen by a random walk technique in five regions of the country affected by major trauma. The assessment was carried out by the following instruments: Mini International Neuropsychiatric Interview 5 (MINI 5), Life Stressor Checklist-Revised (BSC-R), Brief Symptom Inventory (BSI), Impact of Event Scale-Revised (IES-R) and Manchester Short Assessment of Quality of Life Scale (MANSA). The follow-up study was carried out 1 year after the baseline. Results In the initial phase, PTSD was found in 100 out of 159 participants (62.9%), while 81 (51%) fulfilled the diagnostic criteria for MDD. Comorbidity of PTSD and depression was identified in 65 (40.9%) subjects of the sample. After 1 year, PTSD was found in 56 (35.2%) and MDD in 73 (45.9%) participants. Comorbidity of PTSD and depression in the follow-up phase was identified in 41 (25.8%) subjects of the sample. The subjects with comorbidity had significantly higher level of post-traumatic stress symptoms, general psychological distress as well as suicide risk and lower level of quality of life than participants with either condition alone. Conclusion PTSD–depression comorbidity is a common post-traumatic condition. Complex psychopathology, severity of symptoms and their consequences, both at individual and community levels, require attention to be paid to early diagnostics and treatment of affected persons.

Suicide Risk Management Protocol for a Randomized Controlled Trial of Cardiac Patients Reporting Hopelessness.

Investigators conducting studies that include potentially suicidal individuals are obligated to develop a suicide risk management (SRM) protocol. There is little available in the literature to guide researchers in SRM protocol development. The aim of the study was to describe an SRM protocol developed for a randomized controlled trial (RCT) currently enrolling cardiac patients who report moderate to severe levels of hopelessness. The SRM protocol identifies suicidal ideation and measures ideation severity through use of the Columbia-Suicide Severity Rating Scale risk factor questions. Based on responses, study participants are deemed safe or at low, moderate, or high risk for suicide. The SRM protocol guides research staff through a plan of action based on risk level. The protocol further guides staff through a plan over the course of this prospective study-from hospital enrollment to home-based visits. Research staff are well trained to identify suicidal ideation risk factors, initiate specific questioning about suicidal intent, determine level of risk, identify protective factors and a safe environment, and make referrals if needed. Of the 51 patients hospitalized with cardiac disease who reported moderate to severe hopelessness, 43 scored at a safe suicide risk level and 8 scored at low risk. Thirty-five of the 51 patients enrolled in the RCT. Of the 35 participants who received home visits to date, there have been three instances of low and one instance of moderate suicide risk. The SRM protocol has been consistently and accurately used by research personnel in both hospital and home settings. One modification has been made to the protocol since study activation, namely, the addition of an assessment of counseling history and encouragement of continued counseling. Booster training sessions of research staff will continue throughout the course of the RCT. Use of the SRM protocol identifies study participants who are safe or at risk for suicide in both hospital and home settings, and research staff can refer participants accordingly. The SRM protocol developed for this RCT can serve as a model in the development of SRM protocols for future research in acute care, community, or home-based settings.

Routinized categorization of suicide risk into actionable strata: Establishing the validity of an existing suicide risk assessment framework in an outpatient sample.

The Suicide Risk Assessment and Management Decision Tree (DT) is a clinician-administered assessment that leads to risk categorizations that correspond with actionable strata. This study investigated the construct validity and test-retest reliability of the DT risk categories across two time points. Outpatients (N = 731) completed a battery of self-report measures. Spearman's correlations were used to examine the relationships between DT suicide risk level and suicidal symptoms, theory-based risk factors, psychiatric correlates, and DT suicide risk level at Timepoint 2. Correlations were analyzed for significant differences to examine the divergent validity of the DT. Results, overall, were in line with hypotheses, with the exception of depression and thwarted belongingness. Findings provide evidence for the reliability, convergent validity, and discriminant validity of the DT. This clinician-administered suicide risk assessment may be useful for standardization of the assessment and management of suicide risk in outpatient clinical settings.

Suicide assessment and treatment in pediatric primary care settings.

TopicThis article will briefly review screening for depression and suicidal ideation in primary care and school‐based clinics, with a focus on in‐depth screening for imminent suicide risk, developing a safety plan, and incorporating handoffs to urgent and emergency mental health care personnel. The article will cover current definitions of levels of suicidal risk and clinic‐based protocols for a team approach to adolescents in crisis.PurposeTo provide primary care and behavioral health nurses with evidence‐based suicide risk screening and assessment tools and best practices for using them in patient‐centered encounters with adolescents with suicidal thinking or behavior.Sources UsedJournal articles, books, and reports.ConclusionPast studies have shown that many individuals who died by suicide had seen a primary care provider in 30 days before their deaths. Nurses in primary care settings should develop clinic‐based protocols for screening all adolescents for suicide risk, developing safety plans, and providing suicidal youth and families with monitoring, appropriate referrals, follow‐up, and support.

Just in time crisis response: suicide alert system for telemedicine psychotherapy settings

Objective: To design a Natural Language Processing (NLP) algorithm capable of detecting suicide content from patients’ written communication to their therapists, to support rapid response and clinical decision making in telehealth settings. Method: A training dataset of therapy transcripts for 1,864 patients was established by detecting patient content endorsing suicidality using a proxy-model anchored on therapists’ suicide prevention interventions; human expert raters then assessed the level of suicide risk endorsed by patients identified by the proxy-model (i.e., no risk, risk factors, ideation, method, or plan). A bag-of-words classification model was then iteratively built using the annotations from the expert raters to detect suicide risk level in 85,216 labeled patients’ sentences from the training dataset. Results: The final NLP model identified risk-related content from non-risk content with good accuracy (AUC = 82.78). Conclusions: Risk for suicide could be reliably identified by the NLP algorithm. The risk detection model could assist telehealth clinicians in providing crisis resources in a timely manner. This modeling approach could also be applied to other psychotherapy research tasks to assist in the understanding of how the psychotherapy process unfolds for each patient and therapist.

University students presenting for psychiatric emergency services: Socio-demographic and clinical factors related to service utilization and suicide risk

Objective Given increases in mental health utilization among college and university students, this study examines clinical and socio-demographic characteristics in students presenting to psychiatric emergency services. Participants: University students (N = 725; Mage = 22 years, SD = 4.0; 67% White) visiting psychiatric emergency services at a large academic health system between July 1, 2012 and June 30, 2016. Methods: A retrospective review of students’ electronic medical records, which included responses to the Columbia-Suicide Severity Rating Scale, was conducted. Results: Levels of suicide risk varied by students’ self-identified race. Nonwhite students were more likely to endorse a suicide attempt in the past week and less likely to be taking psychiatric medications than White students. International students were more likely to report a lifetime history of multiple attempts. Conclusions: Disparities related to college student psychiatric emergencies warrant specific attention to specific racial/ethnic groups and international students to reduce and manage mental health crises.

Relationship Between Buddhist Belief and Suicide Risk in Chinese Persons Undergoing Methadone Maintenance Therapy for Heroin Dependence.

BackgroundIn western countries, there is a negative association between religious belief and suicide risk, while in China this association is positive. Nevertheless, few data are available on the association between one specific type of religion and suicide risk, which might be different from the overall positive religion-suicide association in China. This study examined the association between Buddhist belief and suicide risk in Chinese persons receiving methadone maintenance therapy (MMT) for heroin dependence.MethodsIn total, 61 Buddhist believers and 425 age, gender, and clinic frequency-matched non-religious believers were selected from a sample of patients with heroin dependence treated in three MMT clinics in Wuhan, China. The suicidality module of the Chinese version of the Mini-international Neuropsychiatric Interview 5.0 was used to assess current suicide risk. Patients' demographic and clinical characteristics were also collected. Multiple ordinary logistic regression was used to analyze the association between Buddhist belief and current suicide risk, controlling for the confounding effects of demographic and clinical factors.ResultsIn Chinese patients receiving MMT for heroin dependence, Buddhist believers had significantly higher levels of current suicide risk than non-religious believers (low: 45.9% vs. 24.7%, medium: 4.9% vs. 3.5%, high: 19.7% vs. 12.5%, P < 0.001). After adjusting for demographic and clinical covariates (including depressive symptoms), Buddhist belief was still significantly associated with an increase in the level of current suicide risk (OR: 2.98, P < 0.001).ConclusionBuddhist belief is significantly associated with elevated current suicide risk in Chinese patients receiving MMT for heroin independence. In Chinese MMT clinics, patients with Buddhist belief may have a high current suicide risk and a timely psychiatric assessment and crisis intervention (when necessary) should be provided to these patients.

Longitudinal study of PTSD and depression in a war-exposed sample – comorbidity increases distress and suicide risk

Abstract Background Major depressive disorder (MDD) and post-traumatic stress disorder (PTSD) are the most common mental disorders following traumatic experiences. The aim of this study was to investigate the extent to which PTSD and depression co-occurred in Serbian general population at baseline and 1 year after the follow-up, as well as how this co-occurrence was associated with sociodemographic factors, personal distress, suicidality and quality of life. Subjects and methods The sample consisted of 159 subjects, who fulfilled the IES criteria for PTSD, and were taken from a larger sample of 640 participants, which was chosen by a random walk technique in five regions of the country affected by major trauma. The assessment was carried out by the following instruments: Mini International Neuropsychiatric Interview 5 (MINI 5), Life Stressor Checklist-Revised (BSC-R), Brief Symptom Inventory (BSI), Impact of Event Scale-Revised (IES-R) and Manchester Short Assessment of Quality of Life Scale (MANSA). The follow-up study was carried out 1 year after the baseline. Results In the initial phase, PTSD was found in 100 out of 159 participants (62.9%), while 81 (51%) fulfilled the diagnostic criteria for MDD. Comorbidity of PTSD and depression was identified in 65 (40.9%) subjects of the sample. After 1 year, PTSD was found in 56 (35.2%) and MDD in 73 (45.9%) participants. Comorbidity of PTSD and depression in the follow-up phase was identified in 41 (25.8%) subjects of the sample. The subjects with comorbidity had significantly higher level of post-traumatic stress symptoms, general psychological distress as well as suicide risk and lower level of quality of life than participants with either condition alone. Conclusion PTSD–depression comorbidity is a common post-traumatic condition. Complex psychopathology, severity of symptoms and their consequences, both at individual and community levels, require attention to be paid to early diagnostics and treatment of affected persons.

Moodable: On feasibility of instantaneous depression assessment using machine learning on voice samples with retrospectively harvested smartphone and social media data

Abstract Depression is a leading cause of disability and is associated with suicide risk. However, a quarter of patients with major depression remain undiagnosed. Prior work has demonstrated that a smartphone user's depression level can be detected by analyzing data gathered from their smartphone's sensors or from their social media posts over a few weeks after enrollment in a user study. These studies typically utilize a prospective study design, which is burdensome as it requires participants smartphone data to be gathered for prolonged periods before their depression level can be assessed. In contrast, we present a feasibility study of our Mood Assessment Capable Framework (Moodable) that facilitates almost instantaneous mood assessment by analyzing instantaneous voice samples provided by the user as well as historical sensor data harvested (scraped) from their smartphone and recent social media posts. Our retrospective, low-burden approach means that Moodable no longer requires study participants to engage with their phone for weeks before a depression score can be inferred. Moodable has the potential to minimize user data collection burden, increase user compliance, avoid study awareness bias and offer a near instantaneous depression screening. To lay a solid foundation for Moodable, we first surveyed 202 volunteer participants about their willingness to share voice samples and various smartphone and social media data types for mental health assessment. Based on these findings, we then developed the Moodable app. Thereafter, we utilized Moodable to collect short voice samples, and a rich array of retrospectively harvested data from users' smartphones (location, browser history, call logs) and social media accounts (instagram, twitter and facebook), with appropriate permissions, of 335 volunteer participants who also responded to 9 depression related questions of the Patient Health Questionaire (PHQ-9). Moodable then used machine learning to build classification models and classify the user's depression and suicidal ideation, for users which scores where unknown to the models. Results of Moodable's screening capability are promising. In particular, for the depression classification task we achieved F1 scores (the harmonic mean of the precision and recall) of 0.766, sensitivity of 0.750, and specificity of 0.792. For the suicidal ideation task we achieved F1 scores of 0.848, sensitivity of 0.864, and specificity of 0.725. This work could significantly increase depression-screening at the population level and opens numerous avenues for further research into this newly proposed paradigm of instantaneously screening depression and suicide risk levels from voice samples and retrospective smartphone and social media data.