Search

The 2013 US Veterans Administration/Department of Defense Clinical Practice Guidelines (VA/DoD CPG) require comprehensive suicide risk assessments for VA/DoD patients with mental disorders but provide minimal guidance on how to carry out these assessments. Given that clinician-based assessments are not known to be strong predictors of suicide, we investigated whether a precision medicine model using administrative data after outpatient mental health specialty visits could be developed to predict suicides among outpatients. We focused on male nondeployed Regular US Army soldiers because they account for the vast majority of such suicides. Four machine learning classifiers (naive Bayes, random forests, support vector regression and elastic net penalized regression) were explored. Of the Army suicides in 2004-2009, 41.5% occurred among 12.0% of soldiers seen as outpatient by mental health specialists, with risk especially high within 26 weeks of visits. An elastic net classifier with 10-14 predictors optimized sensitivity (45.6% of suicide deaths occurring after the 15% of visits with highest predicted risk). Good model stability was found for a model using 2004-2007 data to predict 2008-2009 suicides, although stability decreased in a model using 2008-2009 data to predict 2010-2012 suicides. The 5% of visits with highest risk included only 0.1% of soldiers (1047.1 suicides/100 000 person-years in the 5 weeks after the visit). This is a high enough concentration of risk to have implications for targeting preventive interventions. An even better model might be developed in the future by including the enriched information on clinician-evaluated suicide risk mandated by the VA/DoD CPG to be recorded.

The 2013 US Veterans Administration/Department of Defense Clinical Practice Guidelines (VA/DoD CPG) require comprehensive suicide risk assessments for VA/DoD patients with mental disorders but provide minimal guidance on how to carry out these assessments. Given that clinician-based assessments are not known to be strong predictors of suicide, we investigated whether a precision medicine model using administrative data after outpatient mental health specialty visits could be developed to predict suicides among outpatients. We focused on male nondeployed Regular US Army soldiers because they account for the vast majority of such suicides. Four machine learning classifiers (naive Bayes, random forests, support vector regression and elastic net penalized regression) were explored. Of the Army suicides in 2004-2009, 41.5% occurred among 12.0% of soldiers seen as outpatient by mental health specialists, with risk especially high within 26 weeks of visits. An elastic net classifier with 10-14 predictors optimized sensitivity (45.6% of suicide deaths occurring after the 15% of visits with highest predicted risk). Good model stability was found for a model using 2004-2007 data to predict 2008-2009 suicides, although stability decreased in a model using 2008-2009 data to predict 2010-2012 suicides. The 5% of visits with highest risk included only 0.1% of soldiers (1047.1 suicides/100 000 person-years in the 5 weeks after the visit). This is a high enough concentration of risk to have implications for targeting preventive interventions. An even better model might be developed in the future by including the enriched information on clinician-evaluated suicide risk mandated by the VA/DoD CPG to be recorded.

The study objective was to determine whether sleep extension (a) improves alertness and performance during subsequent sleep restriction and (b) mediates the rate at which alertness and performance are restored by post-restriction recovery sleep. Twenty-four healthy adult participants (ages 18-39) were randomly assigned to an Extended [10 hours time in bed (TIB)] or Habitual [mean (SD) = 7.09 (0.7)] sleep group for one week, followed by one Baseline (10 hours or habitual TIB), seven Sleep Restriction (3 hours TIB), and five Recovery Sleep nights (8 hours TIB) with performance [Psychomotor Vigilance Task (PVT)] and alertness [Maintenance of Wakefulness Test (MWT); Stanford Sleepiness Scale (SSS)] tests administered hourly throughout. We conclude that the extent to which sleep restriction impairs alertness and performance, and the rate at which these impairments are subsequently reversed by recovery sleep, varies as a function of the amount of nightly sleep obtained prior to the sleep restriction period., See also ADM002187. Presented at the Army Science Conference (26th) held in Orlando, FL on 1-4 Dec 2008.

Analyses of applied military data is often complex for two reasons. First, many performance and health variables of interest are non-normally distributed. Second, data typically have a complex nested or partially crossed structure. Recent advances in applied statistics make it possible to address both complexities within a single unified statistical framework., Presented at the Army Science Conference (25th), "Transformational Army Science and Technology - Charting the future of S&T for the Soldier," held in Orlando, Florida on 27-30 Nov 2006. Published in proceedings of the same. See also ADM002075. The original document contains color images.