Finding warning markers: Leveraging natural language processing and machine learning technologies to detect risk of school violence.

INTRODUCTION: School violence has a far-reaching effect, impacting the entire school population including staff, students and their families. Among youth attending the most violent schools, studies have reported higher dropout rates, poor school attendance, and poor scholastic achievement. It was noted that the largest crime-prevention results occurred when youth at elevated risk were given an individualized prevention program. However, much work is needed to establish an effective approach to identify at-risk subjects. OBJECTIVE: In our earlier research, we developed a risk assessment program to interview subjects, identify risk and protective factors, and evaluate risk for school violence. This study focused on developing natural language processing (NLP) and machine learning technologies to automate the risk assessment process. MATERIAL AND METHODS: We prospectively recruited 131 students with or without behavioral concerns from 89 schools between 05/01/2015 and 04/30/2018. The subjects were interviewed with two risk assessment scales and a questionnaire, and their risk of violence were determined by pediatric psychiatrists based on clinical judgment. Using NLP technologies, different types of linguistic features were extracted from the interview content. Machine learning classifiers were then applied to predict risk of school violence for individual subjects. A two-stage feature selection was implemented to identify violence-related predictors. The performance was validated on the psychiatrist-generated reference standard of risk levels, where positive predictive value (PPV), sensitivity (SEN), negative predictive value (NPV), specificity (SPEC) and area under the ROC curve (AUC) were assessed. RESULTS: Compared to subjects' sociodemographic information, use of linguistic features significantly improved classifiers' predictive performance (P < 0.01). The best-performing classifier with n-gram features achieved 86.5 %/86.5 %/85.7 %/85.7 %/94.0 % (PPV/SEN/NPV/SPEC/AUC) on the cross-validation set and 83.3 %/93.8 %/91.7 %/78.6 %/94.6 % (PPV/SEN/NPV/SPEC/AUC) on the test data. The feature selection process identified a set of predictors covering the discussion of subjects' thoughts, perspectives, behaviors, individual characteristics, peers and family dynamics, and protective factors. CONCLUSIONS: By analyzing the content from subject interviews, the NLP and machine learning algorithms showed good capacity for detecting risk of school violence. The feature selection uncovered multiple warning markers that could deliver useful clinical insights to assist personalizing intervention. Consequently, the developed approach offered the promise of an accurate and scalable computerized screening service for preventing school violence.

An Atypical Presentation of Pediatric Acute Neuropsychiatric Syndrome Responding to Plasmapheresis Treatment.

Here we report a case of a 15-year-old female who had originally been diagnosed and treated unsuccessfully for schizophrenia, psychosis, severe anxiety, and depression. More in-depth history revealed an abrupt onset of her symptoms with remote acute infections and many exhibited characteristics of obsessive compulsive disorder with rituals. Work-up for underlying infectious, immunodeficiency, and autoimmune causes was unrevealing except for very high levels of anti-neuronal antibodies which have been linked to Pediatric Acute-onset Neuropsychiatric Syndrome (PANS). Treatment options were discussed with the family and it was decided to use a course of plasmapheresis based on previous studies demonstrating efficacy and its safety profile. After course of therapy, there was a dramatic resolution of her psychosis, OCD traits, and anxiety. She was able to stop all of her antipsychotic and anxiety medications and resume many of her previous normal daily activities. The effect of this treatment has been sustained to the present time. This case emphasizes the importance of exploring nontraditional treatments for severe, treatment-resistant mental illness which requires a multidisciplinary approach. Further research is warranted in larger populations to investigate pathomechanisms and treatment of PANs/PANDAs.

Automated Risk Assessment for School Violence: a Pilot Study.

School violence has increased over the past ten years. This study evaluated students using a more standard and sensitive method to help identify students who are at high risk for school violence. 103 participants were recruited through Cincinnati Children's Hospital Medical Center (CCHMC) from psychiatry outpatient clinics, the inpatient units, and the emergency department. Participants (ages 12-18) were active students in 74 traditional schools (i.e. non-online education). Collateral information was gathered from guardians before participants were evaluated. School risk evaluations were performed with each participant, and audio recordings from the evaluations were later transcribed and manually annotated. The BRACHA (School Version) and the School Safety Scale (SSS), both 14-item scales, were used. A template of open-ended questions was also used. This analysis included 103 participants who were recruited from 74 different schools. Of the 103 students evaluated, 55 were found to be moderate to high risk and 48 were found to be low risk based on the paper risk assessments including the BRACHA and SSS. Both the BRACHA and the SSS were highly correlated with risk of violence to others (Pearson correlations>0.82). There were significant differences in BRACHA and SSS total scores between low risk and high risk to others groups (p-values <0.001 under unpaired t-test). In particular, there were significant differences in individual SSS items between the two groups (p-value <0.001). Of these items, Previous Violent Behavior (Pearson Correlation = 0.80), Impulsivity (0.69), School Problems (0.64), and Negative Attitudes (0.61) were positively correlated with risk to others. The novel machine learning algorithm achieved an AUC of 91.02% when using the interview content to predict risk of school violence, and the AUC increased to 91.45% when demographic and socioeconomic data were added. Our study indicates that the BRACHA and SSS are clinically useful for assessing risk for school violence. The machine learning algorithm was highly accurate in assessing school violence risk.

Eye Gaze Patterns Associated with Aggressive Tendencies in Adolescence.

Social information processing theory hypothesizes that aggressive children pay more attention to cues of hostility and threat in others' behavior, consequently leading to over-interpretation of others' behavior as hostile. While there is abundant evidence of aggressive children demonstrating hostile attribution biases, less well documented is whether such biases stem from over-attendance and hypersensitivity to hostile cues in social situations. Over-attendance to hostile cues would be typified by deviations at any stage of the multi-stage process of social information processing models. While deviations at later stages in social information processing models are associated with aggressive behavior in children, the initial step of encoding has historically been difficult to empirically measure, being a low level automatic process unsuitable for self-report. We employed eye-tracking methodologies to better understand the visual encoding of such social information. Eye movements of ten 13-18 year-old children referred from clinical and non-clinical populations were recorded in real time while the children viewed scenarios varying between hostile, non-hostile and ambiguous social provocation. In addition, the children completed a brief measure of risk of aggression. Aggressive children did attend more to the social scenarios with hostile cues, in particular attending longest to those hostile scenarios where the actor in the scenario had a congruent emotional response. These findings corroborate social information processing theory and the traditional bottom-up processing hypotheses that aggressive behavior relates to increased attention to hostile cues.

A Pilot Study on Developing a Standardized and Sensitive School Violence Risk Assessment with Manual Annotation.

School violence has increased over the past decade and innovative, sensitive, and standardized approaches to assess school violence risk are needed. In our current feasibility study, we initialized a standardized, sensitive, and rapid school violence risk approach with manual annotation. Manual annotation is the process of analyzing a student's transcribed interview to extract relevant information (e.g., key words) to school violence risk levels that are associated with students' behaviors, attitudes, feelings, use of technology (social media and video games), and other activities. In this feasibility study, we first implemented school violence risk assessments to evaluate risk levels by interviewing the student and parent separately at the school or the hospital to complete our novel school safety scales. We completed 25 risk assessments, resulting in 25 transcribed interviews of 12-18 year olds from 15 schools in Ohio and Kentucky. We then analyzed structured professional judgments, language, and patterns associated with school violence risk levels by using manual annotation and statistical methodology. To analyze the student interviews, we initiated the development of an annotation guideline to extract key information that is associated with students' behaviors, attitudes, feelings, use of technology and other activities. Statistical analysis was applied to associate the significant categories with students' risk levels to identify key factors which will help with developing action steps to reduce risk. In a future study, we plan to recruit more subjects in order to fully develop the manual annotation which will result in a more standardized and sensitive approach to school violence assessments.