Prospective Development and Validation of the Computerized Adaptive Screen for Suicidal Youth

Abstract

The rate of suicide among adolescents is rising in the US, yet many adolescents at risk are unidentified and receive no mental health services.OBJECTIVE To develop and independently validate a novel computerized adaptive screen for suicidal youth (CASSY) for use as a universal screen for suicide risk in medical emergency departments (EDs). DESIGN, SETTING, AND PARTICIPANTSStudy 1 of this prognostic study prospectively enrolled adolescent patients at 13 geographically diverse US EDs in the Pediatric Emergency Care Applied Research Network. They completed a baseline suicide risk survey and participated in 3-month telephone follow-ups. Using 3 fixed Ask Suicide-Screening Questions items as anchors and additional items that varied in number and content across individuals, we derived algorithms for the CASSY. In study 2, data were collected from patients at

Risk factors for nonfatal self‐harm and suicide among adolescents: two nested case–control studies conducted in the UK Clinical Practice Research Datalink

“…The use of routinely collected information in primary care may also be harnessed to identify those at risk. For example, emerging evidence from machine learning paradigms has indicated that systems trained on routinely collected clinical data may help clinicians identify individuals at elevated self‐harm repetition risk (King et al., 2021; Su et al., 2020).…”

Comparing the predictive value of screening to the use of electronic health record data for detecting future suicidal thoughts and behavior in an urban pediatric emergency department: A preliminary analysis

“…While our sample had high ASQ compliance rates, previous studies have shown lower compliance rates indicating a need for ongoing monitoring and quality improvement efforts (Betz et al, 2016). Notwithstanding, screening for suicide risk has shown promise at identifying patients at risk for suicide (Ballard et al, 2017;DeVylder et al, 2019;King et al, 2021).…”

Suicide Screening Tools for Pediatric Emergency Department Patients: A Systematic Review

“…A positive is usually defined as a yes to any recent ideation or yes to suicide attempt, though one paper excluded passive ideation from its definition of a positive ( 33 ). The full C-SSRS assessment (used in King et al ( 41 ), Horwitz et al ( 37 ), Manning et al ( 45 ), Gipson et al, ( 26 ), Czyz et al, ( 21 )) is more detailed: in addition to assessing the level of recent ideation, it assesses ideation at the patient's worst point, as well as assessing its intensity, frequency, duration, controllability, deterrents, and reasons. For behavior, the full assessment breaks behavior into actual, interrupted attempt, aborted, and preparatory behavior, and its lethality.…”

“…The optimal cut-off for that item was 6.5/10, which generated a sensitivity of 79% and specificity of 76%; this item was also the strongest predictor of time-to-suicide attempt. King et al ( 41 ) developed and validated the Computerized Adaptive Screen for Suicidal Youth in two larges samples of pediatric ED patients. They found high predictive accuracy of the tool for future suicide attempts, with areas under the curve of 0.87–0.89.…”

“…Those with a positive ASQ result were more likely to be admitted (6,14,22,48) and more likely to re-present with to the ED (6), especially with a suicide-related complaint (14,20,27). In studies that examined criterion validity, the ASQ had acceptable sensitivity (60-93%) and specificity (43-92%) in predicting future attempts (6,14,20,27,41). It also performed well against the longer SIQ with a sensitivity of 97% and specificity of 88% (36).…”