1
|
Wright-Berryman J, Cohen J, Haq A, Black DP, Pease JL. Virtually screening adults for depression, anxiety, and suicide risk using machine learning and language from an open-ended interview. Front Psychiatry 2023; 14:1143175. [PMID: 37377466 PMCID: PMC10291825 DOI: 10.3389/fpsyt.2023.1143175] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/12/2023] [Accepted: 05/22/2023] [Indexed: 06/29/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- Jennifer Wright-Berryman
- Department of Social Work, College of Allied Health Sciences, University of Cincinnati, Cincinnati, OH, United States
| | | | - Allie Haq
- Clarigent Health, Mason, OH, United States
| | | | - James L. Pease
- Department of Social Work, College of Allied Health Sciences, University of Cincinnati, Cincinnati, OH, United States
| |
Collapse
|
2
|
Chou PH, Wang SC, Wu CS, Ito M. Trauma-related guilt as a mediator between post-traumatic stress disorder and suicidal ideation. Front Psychiatry 2023; 14:1131733. [PMID: 37056401 PMCID: PMC10086326 DOI: 10.3389/fpsyt.2023.1131733] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/26/2022] [Accepted: 03/13/2023] [Indexed: 04/15/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- Po-Han Chou
- Department of Psychiatry, China Medical University Hsinchu Hospital, China Medical University, Taichung, Taiwan
- Department of Psychiatry, China Medical University Hospital, China Medical University, Taichung, Taiwan
- *Correspondence: Po-Han Chou, ;
| | - Shao-Cheng Wang
- Department of Psychiatry, Taoyuan General Hospital, Ministry of Health and Welfare, Taoyuan, Taiwan
- Department of Mental Health, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, United States
- Department of Medical Laboratory Science and Biotechnology, Chung Hwa University of Medical Technology, Tainan, Taiwan
- Department of Nurse-Midwifery and Women Health, National Taipei University of Nursing and Health Sciences, Taipei, Taiwan
| | - Chi-Shin Wu
- National Center for Geriatrics and Welfare Research, National Health Research Institutes, Miaoli, Taiwan
- Department of Psychiatry, National Taiwan University Hospital Yunlin Branch, Yunlin, Taiwan
- Chi-Shin Wu,
| | - Masaya Ito
- National Center for Cognitive-Behavior Therapy and Research, National Center of Neurology and Psychiatry, Hsinchu, Miaoli, Taiwan
| |
Collapse
|
3
|
Gross GM, Pietrzak RH, Hoff RA, Katz IR, Harpaz-Rotem I. Risk for PTSD symptom worsening during new PTSD treatment episode in a nationally representative sample of treatment-seeking U.S. veterans with subthreshold PTSD. J Psychiatr Res 2022; 151:304-310. [PMID: 35526446 DOI: 10.1016/j.jpsychires.2022.04.040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/29/2021] [Revised: 03/03/2022] [Accepted: 04/28/2022] [Indexed: 10/18/2022]
Abstract
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.
Collapse
Affiliation(s)
- Georgina M Gross
- VA Connecticut Healthcare System, West Haven, CT, USA; Yale University School of Medicine, Department of Psychiatry, New Haven, CT, USA; Northeast Program Evaluation Center, VA Office of Mental Health and Suicide Prevention, West Haven VA Medical Center, West Haven, CT, USA.
| | - Robert H Pietrzak
- VA Connecticut Healthcare System, West Haven, CT, USA; Yale University School of Medicine, Department of Psychiatry, New Haven, CT, USA; U.S. Department of Veterans Affairs National Center for PTSD, West Haven, CT, USA
| | - Rani A Hoff
- Yale University School of Medicine, Department of Psychiatry, New Haven, CT, USA; Northeast Program Evaluation Center, VA Office of Mental Health and Suicide Prevention, West Haven VA Medical Center, West Haven, CT, USA
| | - Ira R Katz
- VA Office of Mental Health and Suicide Prevention, Department of Veterans Affairs, Washington, DC, USA; Philadelphia VA Medical Center, Philadelphia, PA, USA
| | - Ilan Harpaz-Rotem
- VA Connecticut Healthcare System, West Haven, CT, USA; Yale University School of Medicine, Department of Psychiatry, New Haven, CT, USA; U.S. Department of Veterans Affairs National Center for PTSD, West Haven, CT, USA; Northeast Program Evaluation Center, VA Office of Mental Health and Suicide Prevention, West Haven VA Medical Center, West Haven, CT, USA
| |
Collapse
|
4
|
Chen GW, Hsu TW, Ching PY, Pan CC, Chou PH, Chu CS. Efficacy and Tolerability of Repetitive Transcranial Magnetic Stimulation on Suicidal Ideation: A Systemic Review and Meta-Analysis. Front Psychiatry 2022; 13:884390. [PMID: 35599760 PMCID: PMC9120615 DOI: 10.3389/fpsyt.2022.884390] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/26/2022] [Accepted: 04/14/2022] [Indexed: 11/29/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Guan-Wei Chen
- Department of Psychiatry, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan
| | - Tien-Wei Hsu
- Department of Psychiatry, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan
| | - Pao-Yuan Ching
- Department of Psychiatry, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan
| | - Chih-Chuan Pan
- Department of Psychiatry, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan
| | - Po-Han Chou
- Department of Psychiatry, China Medical University Hsinchu Hospital, China Medical University, Hsinchu, Taiwan
| | - Che-Sheng Chu
- Department of Psychiatry, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan.,Center for Geriatric and Gerontology, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan.,Non-invasive Neuromodulation Consortium for Mental Disorders, Society of Psychophysiology, Taipei, Taiwan.,Graduate Institute of Medicine, College of Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan
| |
Collapse
|
5
|
Chou PH, Wang SC, Wu CS, Horikoshi M, Ito M. A machine-learning model to predict suicide risk in Japan based on national survey data. Front Psychiatry 2022; 13:918667. [PMID: 35990064 PMCID: PMC9387201 DOI: 10.3389/fpsyt.2022.918667] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/12/2022] [Accepted: 07/11/2022] [Indexed: 11/13/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Po-Han Chou
- Department of Psychiatry, China Medical University Hsinchu Hospital, China Medical University, Hsinchu, Taiwan.,Department of Psychiatry, China Medical University Hospital, China Medical University, Taichung, Taiwan
| | - Shao-Cheng Wang
- Department of Psychiatry, Taoyuan General Hospital, Ministry of Health and Welfare, Taoyuan, Taiwan.,Department of Mental Health, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, United States.,Department of Medical Laboratory Science and Biotechnology, Chung Hwa University of Medical Technology, Tainan, Taiwan
| | - Chi-Shin Wu
- National Center for Geriatrics and Welfare Research, National Health Research Institutes, Zhunan Town, Yunlin County, Taiwan.,Department of Psychiatry, National Taiwan University Hospital, Douliu, Taiwan
| | - Masaru Horikoshi
- National Center for Cognitive-Behavior Therapy and Research, National Center of Neurology and Psychiatry, Tokyo, Japan
| | - Masaya Ito
- National Center for Cognitive-Behavior Therapy and Research, National Center of Neurology and Psychiatry, Tokyo, Japan
| |
Collapse
|