4 results
A practical risk calculator for suicidal behavior among transitioning U.S. Army soldiers: results from the Study to Assess Risk and Resilience in Servicemembers-Longitudinal Study (STARRS-LS)
- Jaclyn C. Kearns, Emily R. Edwards, Erin P. Finley, Joseph C. Geraci, Sarah M. Gildea, Marianne Goodman, Irving Hwang, Chris J. Kennedy, Andrew J. King, Alex Luedtke, Brian P. Marx, Maria V. Petukhova, Nancy A. Sampson, Richard W. Seim, Ian H. Stanley, Murray B. Stein, Robert J. Ursano, Ronald C. Kessler
-
- Journal:
- Psychological Medicine / Volume 53 / Issue 15 / November 2023
- Published online by Cambridge University Press:
- 09 March 2023, pp. 7096-7105
-
- Article
- Export citation
-
Background
Risk of suicide-related behaviors is elevated among military personnel transitioning to civilian life. An earlier report showed that high-risk U.S. Army soldiers could be identified shortly before this transition with a machine learning model that included predictors from administrative systems, self-report surveys, and geospatial data. Based on this result, a Veterans Affairs and Army initiative was launched to evaluate a suicide-prevention intervention for high-risk transitioning soldiers. To make targeting practical, though, a streamlined model and risk calculator were needed that used only a short series of self-report survey questions.
MethodsWe revised the original model in a sample of n = 8335 observations from the Study to Assess Risk and Resilience in Servicemembers-Longitudinal Study (STARRS-LS) who participated in one of three Army STARRS 2011–2014 baseline surveys while in service and in one or more subsequent panel surveys (LS1: 2016–2018, LS2: 2018–2019) after leaving service. We trained ensemble machine learning models with constrained numbers of item-level survey predictors in a 70% training sample. The outcome was self-reported post-transition suicide attempts (SA). The models were validated in the 30% test sample.
ResultsTwelve-month post-transition SA prevalence was 1.0% (s.e. = 0.1). The best constrained model, with only 17 predictors, had a test sample ROC-AUC of 0.85 (s.e. = 0.03). The 10–30% of respondents with the highest predicted risk included 44.9–92.5% of 12-month SAs.
ConclusionsAn accurate SA risk calculator based on a short self-report survey can target transitioning soldiers shortly before leaving service for intervention to prevent post-transition SA.
Development of a model to predict antidepressant treatment response for depression among Veterans
- Victor Puac-Polanco, Hannah N. Ziobrowski, Eric L. Ross, Howard Liu, Brett Turner, Ruifeng Cui, Lucinda B. Leung, Robert M. Bossarte, Corey Bryant, Jutta Joormann, Andrew A. Nierenberg, David W. Oslin, Wilfred R. Pigeon, Edward P. Post, Nur Hani Zainal, Alan M. Zaslavsky, Jose R. Zubizarreta, Alex Luedtke, Chris J. Kennedy, Andrea Cipriani, Toshiaki A. Furukawa, Ronald C. Kessler
-
- Journal:
- Psychological Medicine / Volume 53 / Issue 11 / August 2023
- Published online by Cambridge University Press:
- 15 July 2022, pp. 5001-5011
-
- Article
- Export citation
-
Background
Only a limited number of patients with major depressive disorder (MDD) respond to a first course of antidepressant medication (ADM). We investigated the feasibility of creating a baseline model to determine which of these would be among patients beginning ADM treatment in the US Veterans Health Administration (VHA).
MethodsA 2018–2020 national sample of n = 660 VHA patients receiving ADM treatment for MDD completed an extensive baseline self-report assessment near the beginning of treatment and a 3-month self-report follow-up assessment. Using baseline self-report data along with administrative and geospatial data, an ensemble machine learning method was used to develop a model for 3-month treatment response defined by the Quick Inventory of Depression Symptomatology Self-Report and a modified Sheehan Disability Scale. The model was developed in a 70% training sample and tested in the remaining 30% test sample.
ResultsIn total, 35.7% of patients responded to treatment. The prediction model had an area under the ROC curve (s.e.) of 0.66 (0.04) in the test sample. A strong gradient in probability (s.e.) of treatment response was found across three subsamples of the test sample using training sample thresholds for high [45.6% (5.5)], intermediate [34.5% (7.6)], and low [11.1% (4.9)] probabilities of response. Baseline symptom severity, comorbidity, treatment characteristics (expectations, history, and aspects of current treatment), and protective/resilience factors were the most important predictors.
ConclusionsAlthough these results are promising, parallel models to predict response to alternative treatments based on data collected before initiating treatment would be needed for such models to help guide treatment selection.
Development of a model to predict psychotherapy response for depression among Veterans
- Hannah N. Ziobrowski, Ruifeng Cui, Eric L. Ross, Howard Liu, Victor Puac-Polanco, Brett Turner, Lucinda B. Leung, Robert M. Bossarte, Corey Bryant, Wilfred R. Pigeon, David W. Oslin, Edward P. Post, Alan M. Zaslavsky, Jose R. Zubizarreta, Andrew A. Nierenberg, Alex Luedtke, Chris J. Kennedy, Ronald C. Kessler
-
- Journal:
- Psychological Medicine / Volume 53 / Issue 8 / June 2023
- Published online by Cambridge University Press:
- 11 February 2022, pp. 3591-3600
-
- Article
- Export citation
-
Background
Fewer than half of patients with major depressive disorder (MDD) respond to psychotherapy. Pre-emptively informing patients of their likelihood of responding could be useful as part of a patient-centered treatment decision-support plan.
MethodsThis prospective observational study examined a national sample of 807 patients beginning psychotherapy for MDD at the Veterans Health Administration. Patients completed a self-report survey at baseline and 3-months follow-up (data collected 2018–2020). We developed a machine learning (ML) model to predict psychotherapy response at 3 months using baseline survey, administrative, and geospatial variables in a 70% training sample. Model performance was then evaluated in the 30% test sample.
Results32.0% of patients responded to treatment after 3 months. The best ML model had an AUC (SE) of 0.652 (0.038) in the test sample. Among the one-third of patients ranked by the model as most likely to respond, 50.0% in the test sample responded to psychotherapy. In comparison, among the remaining two-thirds of patients, <25% responded to psychotherapy. The model selected 43 predictors, of which nearly all were self-report variables.
ConclusionsPatients with MDD could pre-emptively be informed of their likelihood of responding to psychotherapy using a prediction tool based on self-report data. This tool could meaningfully help patients and providers in shared decision-making, although parallel information about the likelihood of responding to alternative treatments would be needed to inform decision-making across multiple treatments.
Contributors
-
- By Ghazi Al-Rawas, Vazken Andréassian, Tianqi Ao, Stacey A. Archfield, Berit Arheimer, András Bárdossy, Trent Biggs, Günter Blöschl, Theresa Blume, Marco Borga, Helge Bormann, Gianluca Botter, Tom Brown, Donald H. Burn, Sean K. Carey, Attilio Castellarin, Francis Chiew, François Colin, Paulin Coulibaly, Armand Crabit, Barry Croke, Siegfried Demuth, Qingyun Duan, Giuliano Di Baldassarre, Thomas Dunne, Ying Fan, Xing Fang, Boris Gartsman, Alexander Gelfan, Mikhail Georgievski, Nick van de Giesen, David C. Goodrich, Hoshin V. Gupta, Khaled Haddad, David M. Hannah, H. A. P. Hapuarachchi, Hege Hisdal, Kamila Hlavčová, Markus Hrachowitz, Denis A. Hughes, Günter Humer, Ruud Hurkmans, Vito Iacobellis, Elena Ilyichyova, Hiroshi Ishidaira, Graham Jewitt, Shaofeng Jia, Jeffrey R. Kennedy, Anthony S. Kiem, Robert Kirnbauer, Thomas R. Kjeldsen, Jürgen Komma, Leonid M. Korytny, Charles N. Kroll, George Kuczera, Gregor Laaha, Henny A. J. van Lanen, Hjalmar Laudon, Jens Liebe, Shijun Lin, Göran Lindström, Suxia Liu, Jun Magome, Danny G. Marks, Dominic Mazvimavi, Jeffrey J. McDonnell, Brian L. McGlynn, Kevin J. McGuire, Neil McIntyre, Thomas A. McMahon, Ralf Merz, Robert A. Metcalfe, Alberto Montanari, David Morris, Roger Moussa, Lakshman Nandagiri, Thomas Nester, Taha B. M. J. Ouarda, Ludovic Oudin, Juraj Parajka, Charles S. Pearson, Murray C. Peel, Charles Perrin, John W. Pomeroy, David A. Post, Ataur Rahman, Liliang Ren, Magdalena Rogger, Dan Rosbjerg, José Luis Salinas, Jos Samuel, Eric Sauquet, Hubert H. G. Savenije, Takahiro Sayama, John C. Schaake, Kevin Shook, Murugesu Sivapalan, Jon Olav Skøien, Chris Soulsby, Christopher Spence, R. ‘Sri’ Srikanthan, Tammo S. Steenhuis, Jan Szolgay, Yasuto Tachikawa, Kuniyoshi Takeuchi, Lena M. Tallaksen, Dörthe Tetzlaff, Sally E. Thompson, Elena Toth, Peter A. Troch, Remko Uijlenhoet, Carl L. Unkrich, Alberto Viglione, Neil R. Viney, Richard M. Vogel, Thorsten Wagener, M. Todd Walter, Guoqiang Wang, Markus Weiler, Rolf Weingartner, Erwin Weinmann, Hessel Winsemius, Ross A. Woods, Dawen Yang, Chihiro Yoshimura, Andy Young, Gordon Young, Erwin Zehe, Yongqiang Zhang, Maichun C. Zhou
- Edited by Günter Blöschl, Technische Universität Wien, Austria, Murugesu Sivapalan, University of Illinois, Urbana-Champaign, Thorsten Wagener, University of Bristol, Alberto Viglione, Technische Universität Wien, Austria, Hubert Savenije, Technische Universiteit Delft, The Netherlands
-
- Book:
- Runoff Prediction in Ungauged Basins
- Published online:
- 05 April 2013
- Print publication:
- 18 April 2013, pp ix-xiv
-
- Chapter
- Export citation