Associations Between PTSD Symptom Custers and Longitudinal Changes in Suicidal Ideation: Comparison Between 4-Factor and 7-Factor Models of DSM-5 PTSD Symptoms

Virtually screening adults for depression, anxiety, and suicide risk using machine learning and language from an open-ended interview

Background

Current depression, anxiety, and suicide screening techniques rely on retrospective patient reported symptoms to standardized scales. A qualitative approach to screening combined with the innovation of natural language processing (NLP) and machine learning (ML) methods have shown promise to enhance person-centeredness while detecting depression, anxiety, and suicide risk from in-the-moment patient language derived from an open-ended brief interview.

Objective

To evaluate the performance of NLP/ML models to identify depression, anxiety, and suicide risk from a single 5-10-min semi-structured interview with a large, national sample.

Method

Two thousand four hundred sixteen interviews were conducted with 1,433 participants over a teleconference platform, with 861 (35.6%), 863 (35.7%), and 838 (34.7%) sessions screening positive for depression, anxiety, and suicide risk, respectively. Participants completed an interview over a teleconference platform to collect language about the participants' feelings and emotional state. Logistic regression (LR), support vector machine (SVM), and extreme gradient boosting (XGB) models were trained for each condition using term frequency-inverse document frequency features from the participants' language. Models were primarily evaluated with the area under the receiver operating characteristic curve (AUC).

Results

The best discriminative ability was found when identifying depression with an SVM model (AUC = 0.77; 95% CI = 0.75-0.79), followed by anxiety with an LR model (AUC = 0.74; 95% CI = 0.72-0.76), and an SVM for suicide risk (AUC = 0.70; 95% CI = 0.68-0.72). Model performance was generally best with more severe depression, anxiety, or suicide risk. Performance improved when individuals with lifetime but no suicide risk in the past 3 months were considered controls.

Conclusion

It is feasible to use a virtual platform to simultaneously screen for depression, anxiety, and suicide risk using a 5-to-10-min interview. The NLP/ML models performed with good discrimination in the identification of depression, anxiety, and suicide risk. Although the utility of suicide risk classification in clinical settings is still undetermined and suicide risk classification had the lowest performance, the result taken together with the qualitative responses from the interview can better inform clinical decision-making by providing additional drivers associated with suicide risk.

Trauma-related guilt as a mediator between post-traumatic stress disorder and suicidal ideation

Background

As a mental health issue, suicide is a growing global concern, with patients who have post-traumatic stress disorder (PTSD) being at particularly high risk. This study aimed to investigate whether the link between PTSD and suicidal ideation is mediated by trauma-related guilt.

Methods

Data were obtained from Wave 1, Time 1 (November 2016), and Time 2 (March 2017) of the National Survey for Stress and Health (NSSH) in Japan. The NSSH is an online longitudinal survey conducted on Japan's national population aged 18 years and older. The cumulative response rate of the survey was 66.7% at Time 2. A total of 1,005 patients with PTSD were included for analyses. The severity of PTSD symptoms was assessed with PTSD DSM-5 Checklist, and the trauma-related guilt were assessed using the two subscales (hindsight-bias/responsibility and global guilt scale) of the trauma-related guilt inventory (TRGI). Suicidal ideation was evaluated using the suicidal ideation attributes scale (SIDAS). Pearson's correlation was used to investigate the associations among PTSD symptoms, TRGI scores, and SIDAS scores. Causal mediation analysis was applied to evaluate the causal relationship between PTSD, trauma-related guilt, and suicidal ideation.

Results

Pearson's correlation did not show patients' age, gender, and household income significantly associated with SIDAS scores. On the other hand, severities of PTSD symptoms (r = 0.361, p < 0.001) and trauma-related guilt (r = 0.235, p < 0.001) were positively associated with SIDAS scores. After adjusting for age, gender, and household income, the mediation analysis revealed that trauma-related guilt significantly mediates the effects of PTSD symptoms on suicidal ideation.

Conclusion

Our results implied that trauma-related guilt may represent a critical link between PTSD and suicidal ideation, which may be a noteworthy target for therapeutic intervention.

Risk for PTSD symptom worsening during new PTSD treatment episode in a nationally representative sample of treatment-seeking U.S. veterans with subthreshold PTSD

Previous research has examined risk factors associated with poorer treatment outcomes for military Veterans with PTSD. However, work has not examined risk for symptom worsening among Veterans with subthreshold PTSD. The aim of this study was to examine demographic, psychiatric, physical health, and pre-treatment PTSD symptom clusters associated with clinically significant worsening of PTSD among a nationally representative sample of United States (U.S.) Veterans with subthreshold PTSD. Participants were Veterans (weighted N = 3162; unweighted N = 236) with subthreshold PTSD entering a new episode of treatment at U.S. Veterans Affairs PTSD specialty clinics during fiscal years 2018 and 2019. Data was collected as part of the Veterans Outcome Assessment, a yearly baseline and 3-month follow-up telephone survey. Analyses used weighted calculations to support the use of VOA data to draw inferences about all eligible Veterans, and binary logistic regression was used to examine risk factors for symptom worsening. Over 1/3 (37.7%) of Veterans with subthreshold PTSD experienced clinically significant symptom worsening from baseline to follow-up. Adjusted analyses revealed several risk factors for symptom worsening, including demographic (e.g., male sex, White race), psychiatric (personality and anxiety disorders), health care utilization (e.g., more primary care encounters in the previous year), physical health disability, and specific baseline PTSD symptom clusters (negative affect and anxious arousal). Findings suggest that Veterans with subthreshold symptoms seeking treatment for PTSD are at risk for symptom worsening, and highlight the importance of assessment, prevention, and treatment in targeting veterans with PTSD symptoms below the diagnostic threshold.

Efficacy and Tolerability of Repetitive Transcranial Magnetic Stimulation on Suicidal Ideation: A Systemic Review and Meta-Analysis

OBJECTIVE

This study aimed to investigate the efficacy of repetitive transcranial magnetic stimulation (rTMS) in treating suicidal ideation in patients with mental illness.

METHOD

We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Major electronic databases were systematically searched from the time of their inception until July 22, 2021. The primary outcome was the mean change in the scores for suicidal ideation. The secondary outcome was the mean change in depression severity.

RESULTS

Ten randomized controlled trials were eligible with 415 participants in the active treatment group (mean age = 53.78 years; mean proportion of women = 54.5%) and 387 participants in the control group (mean age = 55.52 years; mean proportion of women = 51.78%). rTMS significantly reduced suicidal ideation (k = 10, n = 802, Hedges' g = -0.390, 95% confidence interval [CI] = -0.193 to -0.588, p <.001) and severity of depressive symptoms (k = 9, n = 761, Hedges' g = -0.698, 95% CI = -1.023 to -0.372, p < 0.001) in patients with major mental disorders. In the subgroup analysis, rTMS reduced suicidal ideation among patients with non-treatment-resistant depression (non-TRD) (-0.208) but not in those with TRD. rTMS as combination therapy had a larger effect than did monotherapy (-0.500 vs. -0.210). Suicidal ideation significantly reduced in patients receiving more than ten treatment sessions (-0.255). Importantly, the rTMS group showed favorable tolerability without major adverse events.

CONCLUSION

The study showed that rTMS was effective and well-tolerated in reducing suicidal ideation and depression severity in patients with major mental disorders.

A machine-learning model to predict suicide risk in Japan based on national survey data

OBJECTIVE

Several prognostic models of suicide risk have been published; however, few have been implemented in Japan using longitudinal cohort data. The aim of this study was to identify suicide risk factors for suicidal ideation in the Japanese population and to develop a machine-learning model to predict suicide risk in Japan.

MATERIALS AND METHODS

Data was obtained from Wave1 Time 1 (November 2016) and Time 2 (March 2017) of the National Survey for Stress and Health in Japan, were incorporated into a suicide risk prediction machine-learning model, trained using 65 items related to trauma and stress. The study included 3,090 and 2,163 survey respondents >18 years old at Time 1 and Time 2, respectively. The mean (standard deviation, SD) age was 44.9 (10.9) years at Time 1 and 46.0 (10.7) years at Time 2. We analyzed the participants with increased suicide risk at Time 2 survey. Model performance, including the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity, were also analyzed.

RESULTS

The model showed a good performance (AUC = 0.830, 95% confidence interval = 0.795-0.866). Overall, the model achieved an accuracy of 78.8%, sensitivity of 75.4%, specificity of 80.4%, positive predictive value of 63.4%, and negative predictive value of 87.9%. The most important risk factor for suicide risk was the participants' Suicidal Ideation Attributes Scale score, followed by the Sheehan Disability Scale score, Patient Health Questionnaire-9 scores, Cross-Cutting Symptom Measure (CCSM-suicidal ideation domain, Dissociation Experience Scale score, history of self-harm, Generalized Anxiety Disorder-7 score, Post-Traumatic Stress Disorder check list-5 score, CCSM-dissociation domain, and Impact of Event Scale-Revised scores at Time 1.

CONCLUSIONS

This prognostic study suggests the ability to identify patients at a high risk of suicide using an online survey method. In addition to confirming several well-known risk factors of suicide, new risk measures related to trauma and trauma-related experiences were also identified, which may help guide future clinical assessments and early intervention approaches.