Military Servicemembers and Veterans are at elevated risk for suicide, but rarely self-identify to their leaders or clinicians regarding their experience of suicidal thoughts. We developed an algorithm to identify posts containing suicide-related content on a military-specific social media platform.

Publicly-shared social media posts (n = 8449) from a military-specific social media platform were reviewed and labeled by our team for the presence/absence of suicidal thoughts and behaviors and used to train several machine learning models to identify such posts.

The best performing model was a deep learning (RoBERTa) model that incorporated post text and metadata and detected the presence of suicidal posts with relatively high sensitivity (0.85), specificity (0.96), precision (0.64), F1 score (0.73), and an area under the precision-recall curve of 0.84. Compared to non-suicidal posts, suicidal posts were more likely to contain explicit mentions of suicide, descriptions of risk factors (e.g. depression, PTSD) and help-seeking, and first-person singular pronouns.

Our results demonstrate the feasibility and potential promise of using social media posts to identify at-risk Servicemembers and Veterans. Future work will use this approach to deliver targeted interventions to social media users at risk for suicide.

To detect an outbreak-related source of Legionella, control the outbreak, and prevent additional Legionella infections from occurring.

Epidemiologic investigation of an acute outbreak of hospital-associated Legionnaires disease among outpatients and visitors to a Wisconsin hospital.

Patients with laboratory-confirmed Legionnaires disease who resided in southeastern Wisconsin and had illness onsets during February and March 2010.

Patients with Legionnaires disease were interviewed using a hypothesis-generating questionnaire. On-site investigation included sampling of water and other potential environmental sources for Legionella testing. Case-finding measures included extensive notification of individuals potentially exposed at the hospital and alerts to area healthcare and laboratory personnel.

Laboratory-confirmed Legionnaires disease was diagnosed in 8 patients, all of whom were present at the same hospital during the 10 days prior to their illness onsets. Six patients had known exposure to a water wall-type decorative fountain near the main hospital entrance. Although the decorative fountain underwent routine cleaning and maintenance, high counts of Legionella pneumophila serogroup 1 were isolated from cultures of a foam material found above the fountain trough.

This outbreak of Legionnaires disease was associated with exposure to a decorative fountain located in a hospital public area. Routine cleaning and maintenance of fountains does not eliminate the risk of bacterial contamination. Our findings highlight the need to evaluate the safety of water fountains installed in any area of a healthcare facility.

Infect Control Hosp Epidemiol 2012;33(2):185-191