Purpose: Monitoring suicide risk in clinical practice requires valid and reliable assessment instruments. This study evaluated the psychometric properties of the 7-item version of the Concise Health Risk Tracking Self-Report, CHRT-SR 7 in a primarily rural population. Methods: The sample comprised 788 participants (81.7% female) of an effectiveness trial of an internet-based self-help intervention for depression. Participants completed self-report questionnaires, including the CHRT-SR 7 , Patient Health Questionnaire-9, Generalized Anxiety Disorder-7, Work and Social Adjustment Scale, Connor-Davidson Resilience Scale-10, and Barriers to Seeking Mental Health Care. Four-week testretest reliability was calculated for a subsample of 147 participants randomized to a waitlist control group. Findings:The CHRT-SR 7 internal consistency was α = 0.80 (total sample), α = 0.80 (women), and α = 0.83 (men). The 4-week test-retest reliability was strong for women (r = 0.78) and moderate for men (r = 0.66). Confirmatory factor analysis supported the original 3-factor solution: Hopelessness (2 items), Perceived Lack of Social Support (2 items), and Current Suicidal Thoughts and Plans (3 items), which was invariant across gender and rural status. Convergent and divergent validity was supported as reflected in significant correlations of the CHRT-SR 7 and its subscales with measures of depression, anxiety, adjustment, and resilience. Limitations include the limited demographic diversity (mostly non-Hispanic White women) and reliance on self-report data. Conclusions:Our findings complement those reported in prior studies of patients with severe depression and support the use of the CHRT-SR 7 for measuring suicide risk in rural adults; future studies should further test the instrument's psychometric properties in racial or ethnic minority rural residents.

BioNLP Open Shared Tasks (BioNLP-OST) is an international competition organized to facilitate development and sharing of computational tasks of biomedical text mining and solutions to them. For BioNLP-OST 2019, we introduced a new mental health informatics task called "RDoC Task", which is composed of two subtasks: information retrieval and sentence extraction through National Institutes of Mental Health's Research Domain Criteria framework. Five and four teams around the world participated in the two tasks, respectively. According to the performance on the two tasks, we observe that there is room for improvement for text mining on brain research and mental illness.