Prediction of sustained opioid use in children and adolescents using machine learning.

BACKGROUND: Opioid misuse in the paediatric population is understudied. This study aimed to develop a machine learning classifier to differentiate between occasional and sustained opioid users among children and adolescents in outpatient settings. METHODS: Data for 29,335 patients under 19 yr with recorded opioid purchases were collected from medical records. Machine learning methods were applied to predict sustained opioid use within 1, 2, or 3 yr after first opioid use, using sociodemographic information, medical history, and healthcare usage variables collected near the time of first prescription fulfilment. The models' performance was evaluated with classification and calibration metrics, and a decision curve analysis. An online tool was deployed for model self-exploration and visualisation. RESULTS: The models demonstrated good performance, with a 1-yr follow-up model achieving a sensitivity of 0.772, a specificity of 0.703, and an ROC-AUC of 0.792 on an independent test set, with calibration intercept and slope of 0.00 and 1.02, respectively. Decision curve analysis revealed the clinical benefit of using the model relative to other strategies. SHAP analysis (SHapley Additive exPlanations) identified influential variables, including the number of diagnoses, medical images, laboratory tests, and type of opioid used. CONCLUSIONS: Our model showed promising performance in predicting sustained opioid use among paediatric patients. The online risk prediction tool can facilitate compliance to such tools by clinicians. This study presents the potential of machine learning in identifying at-risk paediatric populations for sustained opioid use, potentially contributing to secondary prevention of opioid abuse.

Coping mechanisms and burnout among checkpoint soldiers in the IDF: a salutogenic perspective.

While many military positions are characterized by rigorous routines and long-hour shifts, some positions also require the practice of sensitivity and empathy alongside diligence and attention. Prolonged exposure to such conditions may promote emotional exhaustion, depersonalization and diminished self-accomplishment perception, all part of work-related burnout which may affect soldiers' ability to practice their duty. The service in the Israel Defense Forces (IDF) checkpoint unit is an example of such conditions due to the soldiers' constant interaction with civilian population. In this questionnaire-based cross-sectional study which included 404 responders from the IDF checkpoint battalions, we examined the effects of demographical, situational and personal variables on soldiers' burnout. A hierarchical multivariate linear regression (R2 = 0.47) identified sense of coherence, the core concept in the salutogenic model of health, as the most prominent protective factor, followed by service motivation and perceived well-being (WB). Taken together, the results revealed several factors associated with military work-related burnout. These findings can serve as a base for burnout prevention programs, which may potentially improve not only the soldiers' WB but also the interfaces between military and civilian populations.

Opioid trends and risk factors for sustained use among children and adolescents in Israel: a retrospective cohort study.

ABSTRACT: Despite growing global concern over opioids, little is known about the epidemiology of opioid use in children and adolescents. This retrospective study investigated opioid use trends and identified risk factors associated with sustained opioid use among outpatient children and adolescents in Israel. Electronic health records of 110,955 children and adolescents were used to establish opioid purchase trends in outpatient settings between 2003 and 2021. Of these, data from 2012 to 2021, n = 32,956, were included in a Cox proportional hazards analysis to identify demographic, clinical, and pharmacological risk factors for sustained opioid use. An increase in opioid use was observed, with a notable rise among strong opioids, peripheral areas, and noncancer patients. Prevalence of sustained opioid users was approximately 2.5%. Risk factors with significant adjusted hazard ratios for sustained use included history of frequent doctor visits 1.82 (95% CI [1.50-2.22]) and drug purchases 1.30 (95% CI [1.07-1.58]), malignancy 1.50 (95% CI [1.07-2.09]), history of cardiovascular (1.44 (95% CI [1.04-1.98]) and pain-related conditions 1.34 (95% CI [1.14-1.58]), and different opioid substances (relative to codeine use): tramadol 2.38 (95% CI [1.73-3.27]), oxycodone 4.29 (95% CI [3.00-6.16]), and "other strong opioids" 6.05 (95% CI [3.59-10.2]). Awareness of observed increase in opioid purchases is crucial for doctors and public health practitioners. Additional monitoring and secondary prevention of children and adolescents possessing the identified risk factors should facilitate where appropriate reducing sustained opioid use when it is unnecessary.

Strength in Numbers - Identifying a Significant Association Between High Serum Ferritin Levels and Newly diagnosed Malignancy in a Large Health Organization Cohort.

BACKGROUND: Ferritin, an iron storage protein and acute phase reactant, has been implicated in various aspects of human health and disease, including cancer. Previous studies have identified elevated serum ferritin (SF) levels in several cancer types, but a comprehensive examination across different malignancies remains lacking. This study aims to fill this gap by utilizing anonymized data from Maccabi Health Services (MHS), one of Israel's largest health organizations, to explore the association between elevated SF levels and the diagnosis of different malignancies. METHODS: An extensive dataset from MHS, comprising 2.7 million members, including 1.3 million individuals who underwent SF level testing, was analyzed. Odds Ratios (OR) and 95% confidence intervals (CI) were calculated to assess the association between high SF levels and cancer diagnosis. Subgroup analysis was conducted to investigate variations across different malignancies. RESULTS: The analysis revealed a significant association between elevated SF levels and cancer diagnosis among MHS members, with an OR of 1.9 (95% CI 1.71-2.15). Sub- group analysis unveiled differences in the association across malignancy types, with hematological, hepatobiliary and respiratory malignancies more strongly associated with high SF levels. CONCLUSIONS: This study provides further support for the link between elevated SF levels and malignancy, leveraging a vast dataset from MHS, underscoring potential utilities of elevated SF levels as a potential indicator for cancer with a variable role among different malignancy types. IMPACT: The identification of elevated SF levels as a potential indicator for underlying malignancy for seemingly-healthy individuals.

False-positive HIV screening tests during the COVID-19 pandemic, a passing trend?

False-positive fourth-generation HIV screening tests are rare and are usually associated with various infections and autoimmune diseases. SARS-CoV-2 infection and vaccination were recently linked with false-positive HIV screening test results. However, little is known about false-positives in people who performed HIV screening tests after outbreaks of different SARS-CoV-2 strains and vaccination campaigns. Here, we examined the false-positive rates in samples collected by the Israeli AIDS Task Force in 2018--2022, with respect to such factors.

Community Vs. hospital HIV testing sites in Jerusalem, Israel - who's tested and who's at risk?

BACKGROUND: After decades of constant increase in HIV diagnoses among men who have sex with men (MSM), a gradual decrease has been reported in recent years. Timely detection of HIV leads to early treatment and behavioral changes which decrease further transmissions. This cross-sectional study aimed to assess demographic and behavioral characteristics of individuals who were tested for HIV in Jerusalem, Israel. METHODS: This study compared individuals who were tested at Hadassah AIDS Center (HAC) with those tested at the Jerusalem Open House (JOH) - an LGBTQ community center. Participants completed anonymous questionnaires regarding their demographic, HIV-testing history, and sexual behaviors. High-risk sexual behavior (HRSB) was defined as a diagnosis of sexually transmitted disease or condomless anal/vaginal sex during the last year. RESULTS: Among 863 participants, 104 (12.1%) were tested in HAC and 759 (87.9%) in JOH. Of those, 19 (18.3%) and 227 (29.9%) were HRSB, respectively. Two MSM were tested positive in JOH. JOH received more MSM, HRSB and individuals who were previously tested for HIV, while HAC received more migrants and health-care workers. HRSB-participants were more commonly younger, males, non-Jewish, with lower income, previously tested for HIV, reported more sexual partners, payed for sex or used drugs. CONCLUSIONS: MSM and HRSB-individuals were more likely to be tested in JOH, while migrants and health-care workers in HAC, possibly due to the geographic location, reputation and specific atmosphere. In order to encourage HIV-tests among HRSB and non-Jews, additional interventions should be employed, including outreach activities, extending opening hours and reducing testing costs should be employed.