Individualized Prospective Prediction of Opioid Use Disorder.

OBJECTIVE: Opioid use disorder (OUD) is a chronic relapsing disorder with a problematic pattern of opioid use, affecting nearly 27 million people worldwide. Machine learning (ML)-based prediction of OUD may lead to early detection and intervention. However, most ML prediction studies were not based on representative data sources and prospective validations, limiting their potential to predict future new cases. In the current study, we aimed to develop and prospectively validate an ML model that could predict individual OUD cases based on representative large-scale health data. METHOD: We present an ensemble machine-learning model trained on a cross-linked Canadian administrative health data set from 2014 to 2018 (n = 699,164), with validation of model-predicted OUD cases on a hold-out sample from 2014 to 2018 (n = 174,791) and prospective prediction of OUD cases on a non-overlapping sample from 2019 (n = 316,039). We used administrative records of OUD diagnosis for each subject based on International Classification of Diseases (ICD) codes. RESULTS: With 6409 OUD cases in 2019 (mean [SD], 45.34 [14.28], 3400 males), our model prospectively predicted OUD cases at a high accuracy (balanced accuracy, 86%, sensitivity, 93%; specificity 79%). In accord with prior findings, the top risk factors for OUD in this model were opioid use indicators and a history of other substance use disorders. CONCLUSION: Our study presents an individualized prospective prediction of OUD cases by applying ML to large administrative health datasets. Such prospective predictions based on ML would be essential for potential future clinical applications in the early detection of OUD.

Risk factors for developmental vulnerability: Insight from population-level surveillance using the Early Development Instrument.

Objectives: Population-level studies may elucidate the most promising intervention targets to prevent negative outcomes of developmental vulnerability in children. This study aims to bridge the current literature gap on identifying population-level developmental vulnerability risk factors using combined social and biological/health information. Methods: This study assessed developmental vulnerability among kindergarten children using the 2016 Early Development Instrument (EDI) and identified risk factors of developmental vulnerability using EDI data cross-linked to a population-wide administrative health dataset. A total number of 23,494 children aged 5-6 were included (48% female). Prenatal, neonatal, and early childhood risk factors for developmental vulnerability were investigated, highlighting the most important ones contributing to early development. Results: The main risk factors for developmental vulnerability were children with a history of mental health diagnosis (risk ratio = 1.46), biological sex-male (risk ratio = 1.51), and poor socioeconomic status (risk ratio = 1.58). Conclusion: Our study encompasses both social and health information in a populational-level representative sample of Alberta, Canada. The results confirm evidence established in other geographic regions and jurisdictions and demonstrate the association between perinatal risk factors and developmental vulnerability. Based on these results, we argue that the health system should adopt a multilevel prevention and intervention strategy, targeting individual, family, and community together.

Croup presentations to emergency departments in Alberta, Canada: a large population-based study.

BACKGROUND: Croup is a common pediatric respiratory illness. While croup is generally a mild disease, exacerbations may be seen in the Emergency Department (ED) setting. The objective of this study was to describe the epidemiology of croup presentations to EDs made by infants (