A Machine Learning Approach to Identifying the Thought Markers of Suicidal Subjects: A Prospective Multicenter Trial

Death by suicide demonstrates profound personal suffering and societal failure. While basic sciences provide the opportunity to understand biological markers related to suicide, computer science provides opportunities to understand suicide thought markers. In this novel prospective, multimodal, multicenter, mixed demographic study, we used machine learning to measure and fuse two classes of suicidal thought markers: verbal and nonverbal. Machine learning algorithms were used with the subjects’ words and vocal characteristics to classify 379 subjects recruited from two academic medical centers and a rural community hospital into one of three groups: suicidal, mentally ill but not suicidal, or controls. By combining linguistic and acoustic characteristics, subjects could be classified into one of the three groups with up to 85% accuracy. The results provide insight into how advanced technology can be used for suicide assessment and prevention.     

Women Derive Collective Self-Esteem from Their Feminist Identity

Women's self-esteem is more strongly related to social acceptance and inclusion than to accomplishments. We investigated the extent to which women derive self-esteem from being women, that is, from their membership in a collective gender group. We hypothesized and found that women's collective self-esteem (i.e., self-esteem derived from their gender group) would systematically vary for women showing differing degrees of feminist development. Thus, women's self-esteem derived from womanhood seems to depend on the "meaning" of womanhood to the individual woman.     

Food, mood, and attitude: reducing risk for eating disorders in college women.

Food, Mood, and Attitude (FMA) is a CD-ROM prevention program developed to decrease risk for eating disorders in college women. Female 1st-year students (N = 240) were randomly assigned to the intervention (FMA) or control group. Equal numbers of students at risk and of low risk for developing an eating disorder were assigned to each condition. Participants in the FMA condition improved on all measures relative to controls. Significant 3-way interactions (Time x Condition x Risk Status) were found on measures of internalization of sociocultural attitudes about thinness, shape concerns, and weight concerns, indicating that at-risk participants in the intervention group improved to a greater extent than did low-risk participants. At follow-up, significantly fewer women in the FMA group reported overeating and excessive exercise relative to controls.