Health and Well-Being at the Transition to Adulthood Among Individuals With Disabilities: An Analysis of the Panel Study of Income Dynamics.

PURPOSE: To describe positive mental health, or "flourishing," and self-reported health trajectories among transition-aged young adults (TAYA) with developmental/learning and physical disabilities over a 12-year period, utilizing a population-based sample. METHODS: This study features a secondary analysis of national data from the Panel Study of Income Dynamics Transition to Adulthood Supplement. The analytic sample included all TAYA with (n = 487) and without (n = 810) disabilities, including developmental/learning disabilities (DD/LD), attention deficit hyperactivity disorder (ADHD), and speech, hearing, and vision impairments who participated in 2017 Transition to Adulthood Supplement data collection (n = 1,297; M age = 24.5, standard deviation = 2.40). We utilized linear mixed modeling to retrospectively describe flourishing and self-reported health trajectories across 12 years among TAYA with and without disabilities between ages 18 to 28, adjusting for demographic and developmental characteristics. RESULTS: Relative to TAYA without disabilities, TAYA with speech [0.10, 0.85] and vision impairments [0.10, 0.92], DD/LD [0.38, 1.11], and ADHD [0.27, 0.97] demonstrated lower flourishing. TAYA with speech [0.07, 0.36] and vision impairments [0.08, 0.38], DD/LD [0.15, 0.411], and ADHD [0.14, 0.93] reported lower health. Relative to TAYA with other disabilities, TAYA with ADHD [0.14, 0.93] and DD/LD [0.01, 0.29] reported lower flourishing and health, respectively. Interaction effects and descriptive analyses revealed distinct patterns of change for TAYA with ADHD. DISCUSSION: TAYA with disabilities report lower flourishing and health, relative to TAYA without disabilities. TAYA with specific disabilities differ in their flourishing and health trajectories. Findings can inform the development of interventions for TAYA with disabilities.

Assessing Detection of Children With Suicide-Related Emergencies: Evaluation and Development of Computable Phenotyping Approaches.

BACKGROUND: Although suicide is a leading cause of death among children, the optimal approach for using health care data sets to detect suicide-related emergencies among children is not known. OBJECTIVE: This study aimed to assess the performance of suicide-related International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) codes and suicide-related chief complaint in detecting self-injurious thoughts and behaviors (SITB) among children compared with clinician chart review. The study also aimed to examine variations in performance by child sociodemographics and type of self-injury, as well as develop machine learning models trained on codified health record data (features) and clinician chart review (gold standard) and test model detection performance. METHODS: A gold standard classification of suicide-related emergencies was determined through clinician manual review of clinical notes from 600 emergency department visits between 2015 and 2019 by children aged 10 to 17 years. Visits classified with nonfatal suicide attempt or intentional self-harm using the Centers for Disease Control and Prevention surveillance case definition list of ICD-10-CM codes and suicide-related chief complaint were compared with the gold standard classification. Machine learning classifiers (least absolute shrinkage and selection operator-penalized logistic regression and random forest) were then trained and tested using codified health record data (eg, child sociodemographics, medications, disposition, and laboratory testing) and the gold standard classification. The accuracy, sensitivity, and specificity of each detection approach and relative importance of features were examined. RESULTS: SITB accounted for 47.3% (284/600) of the visits. Suicide-related diagnostic codes missed nearly one-third (82/284, 28.9%) and suicide-related chief complaints missed more than half (153/284, 53.9%) of the children presenting to emergency departments with SITB. Sensitivity was significantly lower for male children than for female children (0.69, 95% CI 0.61-0.77 vs 0.84, 95% CI 0.78-0.90, respectively) and for preteens compared with adolescents (0.66, 95% CI 0.54-0.78 vs 0.86, 95% CI 0.80-0.92, respectively). Specificity was significantly lower for detecting preparatory acts (0.68, 95% CI 0.64-0.72) and attempts (0.67, 95% CI 0.63-0.71) than for detecting ideation (0.79, 95% CI 0.75-0.82). Machine learning-based models significantly improved the sensitivity of detection compared with suicide-related codes and chief complaint alone. Models considering all 84 features performed similarly to models considering only mental health-related ICD-10-CM codes and chief complaints (34 features) and models considering non-ICD-10-CM code indicators and mental health-related chief complaints (53 features). CONCLUSIONS: The capacity to detect children with SITB may be strengthened by applying a machine learning-based approach to codified health record data. To improve integration between clinical research informatics and child mental health care, future research is needed to evaluate the potential benefits of implementing detection approaches at the point of care and identifying precise targets for suicide prevention interventions in children.

Detection of Suicidal Behavior and Self-harm Among Children Presenting to Emergency Departments: A Tree-based Classification Approach.

Suicide is the second leading cause of death of U.S. children over 10 years old. Application of statistical learning to structured EHR data may improve detection of children with suicidal behavior and self-harm. Classification trees (CART) were developed and cross-validated using mental health-related emergency department (MH-ED) visits (2015-2019) of children 10-17 years (N=600) across two sites. Performance was compared with the CDC Surveillance Case Definition ICD-10-CM code list. Gold-standard was child psychiatrist chart review. Visits were suicide-related among 284/600 (47.3%) children. ICD-10-CM detected cases with sensitivity 70.7 (95%CI 67.0-74.3), specificity 99.0 (98.8-100), and 85/284 (29.9%) false negatives. CART detected cases with sensitivity 85.1 (64.7-100) and specificity 94.9 (89.2-100). Strongest predictors were suicide-related code, MH- and suicide-related chief complaints, site, area deprivation index, and depression. Diagnostic codes miss nearly one-third of children with suicidal behavior and self-harm. Advances in EHR-based phenotyping have the potential to improve detection of childhood-onset suicidality.