John F McCarthy1, Robert M Bossarte1, Ira R Katz1, Caitlin Thompson1, Janet Kemp1, Claire M Hannemann1, Christopher Nielson1, Michael Schoenbaum1. 1. John F. McCarthy and Claire M. Hannemann are with the Serious Mental Illness Treatment Resource and Evaluation Center, Office of Mental Health Operations, Department of Veterans Affairs, Washington DC. Robert M. Bossarte is with the Epidemiology Program, Office of Public Health; Ira R. Katz is with the Office of Mental Health Operations; Caitlin Thompson is with the Suicide Prevention Program, Mental Health Services; and Christopher Nielson is with Predictive Analytics, Office of Business Intelligence and Analytics, Department of Veterans Affairs. Janet Kemp is with the VISN 2 Center of Excellence for Suicide Prevention, Department of Veterans Affairs, Canandaigua, NY. Michael Schoenbaum is with the Office of Science Policy, Planning, and Communications, National Institute of Mental Health, Rockville, MD.
Abstract
OBJECTIVES: The Veterans Health Administration (VHA) evaluated the use of predictive modeling to identify patients at risk for suicide and to supplement ongoing care with risk-stratified interventions. METHODS: Suicide data came from the National Death Index. Predictors were measures from VHA clinical records incorporating patient-months from October 1, 2008, to September 30, 2011, for all suicide decedents and 1% of living patients, divided randomly into development and validation samples. We used data on all patients alive on September 30, 2010, to evaluate predictions of suicide risk over 1 year. RESULTS: Modeling demonstrated that suicide rates were 82 and 60 times greater than the rate in the overall sample in the highest 0.01% stratum for calculated risk for the development and validation samples, respectively; 39 and 30 times greater in the highest 0.10%; 14 and 12 times greater in the highest 1.00%; and 6.3 and 5.7 times greater in the highest 5.00%. CONCLUSIONS: Predictive modeling can identify high-risk patients who were not identified on clinical grounds. VHA is developing modeling to enhance clinical care and to guide the delivery of preventive interventions.
OBJECTIVES: The Veterans Health Administration (VHA) evaluated the use of predictive modeling to identify patients at risk for suicide and to supplement ongoing care with risk-stratified interventions. METHODS: Suicide data came from the National Death Index. Predictors were measures from VHA clinical records incorporating patient-months from October 1, 2008, to September 30, 2011, for all suicide decedents and 1% of living patients, divided randomly into development and validation samples. We used data on all patients alive on September 30, 2010, to evaluate predictions of suicide risk over 1 year. RESULTS: Modeling demonstrated that suicide rates were 82 and 60 times greater than the rate in the overall sample in the highest 0.01% stratum for calculated risk for the development and validation samples, respectively; 39 and 30 times greater in the highest 0.10%; 14 and 12 times greater in the highest 1.00%; and 6.3 and 5.7 times greater in the highest 5.00%. CONCLUSIONS: Predictive modeling can identify high-risk patients who were not identified on clinical grounds. VHA is developing modeling to enhance clinical care and to guide the delivery of preventive interventions.
Authors: Ronald C Kessler; Christopher H Warner; Christopher Ivany; Maria V Petukhova; Sherri Rose; Evelyn J Bromet; Millard Brown; Tianxi Cai; Lisa J Colpe; Kenneth L Cox; Carol S Fullerton; Stephen E Gilman; Michael J Gruber; Steven G Heeringa; Lisa Lewandowski-Romps; Junlong Li; Amy M Millikan-Bell; James A Naifeh; Matthew K Nock; Anthony J Rosellini; Nancy A Sampson; Michael Schoenbaum; Murray B Stein; Simon Wessely; Alan M Zaslavsky; Robert J Ursano Journal: JAMA Psychiatry Date: 2015-01 Impact factor: 21.596
Authors: Mark A Ilgen; Amy S B Bohnert; Rosalinda V Ignacio; John F McCarthy; Marcia M Valenstein; H Myra Kim; Frederic C Blow Journal: Arch Gen Psychiatry Date: 2010-11
Authors: Hyungjin Myra Kim; Eric G Smith; Dara Ganoczy; Heather Walters; Clare M Stano; Mark A Ilgen; Amy S B Bohnert; Marcia Valenstein Journal: J Clin Psychiatry Date: 2012-10 Impact factor: 4.384
Authors: Marcia Valenstein; Hyungjin Myra Kim; Dara Ganoczy; John F McCarthy; Kara Zivin; Karen L Austin; Katherine Hoggatt; Daniel Eisenberg; John D Piette; Frederic C Blow; Mark Olfson Journal: J Affect Disord Date: 2008-10-22 Impact factor: 4.839
Authors: John F McCarthy; Marcia Valenstein; H Myra Kim; Mark Ilgen; Kara Zivin; Frederic C Blow Journal: Am J Epidemiol Date: 2009-02-27 Impact factor: 4.897
Authors: Peter C Britton; Kipling M Bohnert; Mark A Ilgen; Cathleen Kane; Brady Stephens; Wilfred R Pigeon Journal: Soc Psychiatry Psychiatr Epidemiol Date: 2017-04-11 Impact factor: 4.328
Authors: Brian K Ahmedani; Edward L Peterson; Yong Hu; Rebecca C Rossom; Frances Lynch; Christine Y Lu; Beth E Waitzfelder; Ashli A Owen-Smith; Samuel Hubley; Deepak Prabhakar; L Keoki Williams; Nicole Zeld; Elizabeth Mutter; Arne Beck; Dennis Tolsma; Gregory E Simon Journal: Am J Prev Med Date: 2017-06-12 Impact factor: 5.043
Authors: Gregory E Simon; Eric Johnson; Jean M Lawrence; Rebecca C Rossom; Brian Ahmedani; Frances L Lynch; Arne Beck; Beth Waitzfelder; Rebecca Ziebell; Robert B Penfold; Susan M Shortreed Journal: Am J Psychiatry Date: 2018-05-24 Impact factor: 18.112
Authors: Austin B Frakt; Julia C Prentice; Steven D Pizer; A Rani Elwy; Melissa M Garrido; Amy M Kilbourne; David Atkins Journal: Health Serv Res Date: 2018-06-03 Impact factor: 3.402
Authors: Gregory E Simon; Susan M Shortreed; Eric Johnson; Arne Beck; Karen J Coleman; Rebecca C Rossom; Ursula S Whiteside; Belinda H Operskalski; Robert B Penfold Journal: Depress Anxiety Date: 2017-04-25 Impact factor: 6.505