Objectives The US Veterans Health Administration (VHA) has begun using predictive modeling to identify Veterans at high suicide risk to target care. Initial analyses are reported here. Methods A penalized logistic regression model was compared with an earlier proof-of-concept logistic model. Exploratory analyses then considered commonly-used machine learning algorithms. Analyses were based on electronic medical records for all 6,360 individuals classified in the National Death Index as having died by suicide in fiscal years 2009–2011 who used VHA services the year of their death or prior year and a 1% probability sample of time-matched VHA service users alive at the index date (n = 2,112,008). Results A penalized logistic model with 61 predictors had sensitivity comparable to the proof-of-concept model (which had 381 predictors) at target thresholds. The machine learning algorithms had relatively similar sensitivities, the highest being for Bayesian additive regression trees, with 10.7% of suicides occurred among the 1.0% of Veterans with highest predicted risk and 28.1% among the 5.0% of with highest predicted risk. Conclusions Based on these results, VHA is using penalized logistic regression in initial intervention implementation. The paper concludes with a discussion of other practical issues that might be explored to increase model performance.
Objective: Veterans are believed to be at high risk of suicide. However, research comparing suicide rates between veterans and nonveterans is limited, and even less is known regarding differences by history of Veterans Health Administration (VHA) service use. This study directly compared veteran and nonveteran suicide risk while for the first time differentiating veterans by VHA service use. Methods:The cross-sectional study analyzed data from 173,969 adult suicide decedents from 23 states (2000)(2001)(2002)(2003)(2004)(2005)(2006)(2007)(2008)(2009)(2010) included in the U.S. Department of Veterans Affairs suicide data archive. Annual standardized mortality ratios (SMRs) were computed for veterans compared with nonveterans and for veterans who used VHA services compared with veterans who did not, overall and separately for males and females.Results: After the analysis controlled for age and gender differences, the number of observed veteran suicides was approximately 20% higher than expected in 2000 (SMR=1.19, 95% confidence interval [CI]=1.10-1.28), and this increased to 60% higher by 2010 (SMR=1.63, CI=1.58-1.68). The elevated risk for female veterans (2010 SMR=5.89) was higher than that observed for male veterans (2010 SMR=1.54). Trends for non-VHA-utilizing veterans mirrored those of the veteran population as a whole, and the SMR for VHA-utilizing veterans declined. Since 2003, the number of suicides among VHAutilizing veterans was less than expected when compared directly with the suicide rate among non-VHA-utilizing veterans.Conclusions: Veterans are members of the community and, as such, are an important part of observed increases in U.S. suicide rates. Not all veterans are at equal or increasing risk of suicide, however. VHA-utilizing veterans appear to have declining absolute and relative suicide rates.
Our findings suggest that sleep problems may be an important but under-recognized problem in children with DS. Sleep problems appear to be correlated with prevalent comorbidities, which may provide guidance to augment current practice guidelines to evaluate sleep problems in this population.
Objectives: The US Department of Veterans Affairs' Suicide Prevention Applications Network (SPAN) is a national system for suicide event tracking and case management. The objective of this study was to assess data on suicide attempts among people using Veterans Health Administration (VHA) services. Methods:We assessed the degree of data overlap on suicide attempters reported in SPAN and the VHA's medical records from October 1, 2010, to September 30, 2014-overall, by year, and by region. Data on suicide attempters in the VHA's medical records consisted of diagnoses documented with E95 codes from the International Classification of Diseases, Ninth Revision. Results: Of 50 518 VHA patients who attempted suicide during the 4-year study period, data on fewer than half (41%) were reported in both SPAN and the medical records; nearly 65% of patients whose suicide attempt was recorded in SPAN had no data on attempted suicide in the VHA's medical records. Conclusion:Evaluation of administrative data suggests that use of SPAN substantially increases the collection of data on suicide attempters as compared with the use of medical records alone, but neither SPAN nor the VHA's medical records identify all suicide attempters. Further research is needed to better understand the strengths and limitations of both systems and how to best combine information across systems. Keywords veterans, suicide, preventionEffective surveillance systems are the cornerstone of public health: they (1) inform the development of prevention strategies tailored to the characteristics and needs of established or newly emerging high-risk populations and (2) evaluate the impact of newly implemented programs. The 2012 National Strategy for Suicide Prevention and the resulting research agenda emphasized a need for improved data to inform suicide prevention.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.