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.

We 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.

Twelve-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.

An 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.

Data on best practices for evacuating an intensive care unit (ICU) during a disaster are limited. The impact of Hurricane Sandy on New York City area hospitals provided a unique opportunity to learn from the experience of ICU providers about their preparedness, perspective, roles, and activities.

We conducted a cross-sectional survey of nurses, respiratory therapists, and physicians who played direct roles during the Hurricane Sandy ICU evacuations.

Sixty-eight health care professionals from 4 evacuating hospitals completed surveys (35% ICU nurses, 21% respiratory therapists, 25% physicians-in-training, and 13% attending physicians). Only 21% had participated in an ICU evacuation drill in the past 2 years and 28% had prior training or real-life experience. Processes were inconsistent for patient prioritization, tracking, transport medications, and transport care. Respondents identified communication (43%) as the key barrier to effective evacuation. The equipment considered most helpful included flashlights (24%), transport sleds (21%), and oxygen tanks and respiratory therapy supplies (19%). An evacuation wish list included walkie-talkies/phones (26%), lighting/electricity (18%), flashlights (10%), and portable ventilators and suction (16%).

ICU providers who evacuated critically ill patients during Hurricane Sandy had little prior knowledge of evacuation processes or vertical evacuation experience. The weakest links in the patient evacuation process were communication and the availability of practical tools. Incorporating ICU providers into hospital evacuation planning and training, developing standard evacuation communication processes and tools, and collecting a uniform dataset among all evacuating hospitals could better inform critical care evacuation in the future. (Disaster Med Public Health Preparedness. 2016;10:20–27)