{"title":"Machine learning models to detect opioid misuse in emergency department patients at triage","authors":"Chirag Chhablani , Usman Shahid , Natalie Parde , Sami Muslmani , Huiyi Hu , Dillon Thorpe , Majid Afshar , Niranjan Karnik , Neeraj Chhabra","doi":"10.1016/j.ajem.2026.02.037","DOIUrl":"10.1016/j.ajem.2026.02.037","url":null,"abstract":"<div><h3>Objective</h3><div>Emergency department (ED) encounters represent valuable opportunities to initiate evidence-based treatments for patients with opioid misuse, but few receive such care. Universal manual screening has been proposed to improve patient identification but is uncommon due to its time and resource-intensive nature. We sought to determine the feasibility of identifying patients with opioid misuse at the time of ED triage using machine learning (ML).</div></div><div><h3>Methods</h3><div>We conducted a retrospective cohort study of 1123 ED encounters (September 2020 – March 2023) at a tertiary hospital. Encounters were enriched for opioid misuse, manually annotated, and chronologically split for training, validation, and testing. Candidate triage-time features included patient demographics, Emergency Severity Index, arrival time of day, chief complaint, comorbidities, and chronic medications. Model performance was evaluated using F1 score, area under the precision–recall curve (AUPRC), accuracy, recall, and AUROC. Post-hoc explainability analyses included SHapley Additive exPlanations (SHAP) and feature importance.</div></div><div><h3>Results</h3><div>All models performed comparably to opioid-related diagnosis codes placed at any time during the encounter. Random Forest (F1 = 0.75 [95%CI 0.70–0.83], AUPRC = 0.88 [0.81–0.93], accuracy = 0.79 [0.70–0.83]) and Gradient Boosting (F1 = 0.77 [0.71–0.82], AUPRC = 0.89 [0.85–0.93], accuracy = 0.81 [0.720.84]) had among the highest F1 score and AUPRC but confidence intervals overlapped with other methods. Explainability analyses highlighted prior drug-use diagnosis codes, triage acuity, and age as top predictors.</div></div><div><h3>Conclusion</h3><div>ML classifiers leveraging routinely collected triage data offer a feasible and scalable alternative to manual screening in flagging opioid misuse before physician evaluation, potentially enabling early harm-reduction interventions. Prospective multi-site validation, calibration, and bias assessments are warranted.</div></div>","PeriodicalId":55536,"journal":{"name":"American Journal of Emergency Medicine","volume":"104 ","pages":"Pages 17-23"},"PeriodicalIF":2.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147367374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Finn Erland Nielsen , Osama Bin Abdullah , Lana Chafranska , Thomas Andersen Schmidt , Rune Husås Sørensen
{"title":"Temperature at admission and mortality in older adults with infection: Limited prognostic value in non-sepsis cases","authors":"Finn Erland Nielsen , Osama Bin Abdullah , Lana Chafranska , Thomas Andersen Schmidt , Rune Husås Sørensen","doi":"10.1016/j.ajem.2026.01.045","DOIUrl":"10.1016/j.ajem.2026.01.045","url":null,"abstract":"<div><h3>Background</h3><div>Temperature abnormalities are established prognostic markers in sepsis, but their predictive value in older adults with infection without sepsis remains unclear.</div></div><div><h3>Objective</h3><div>To examine the association between arrival temperature and 28-day all-cause mortality among emergency department patients aged ≥65 years with infection, stratified by sepsis status.</div></div><div><h3>Methods</h3><div>We performed a post-hoc analysis of a prospective cohort from a Danish emergency department. Sepsis was defined as infection plus an acute ≥2 point increase in the Sequential Organ Failure Assessment (SOFA) score. Propensity score matching balanced covariates between groups. The restricted cubic spline regression modelled non-linear temperature-mortality associations. Sensitivity analyses excluded patients with comorbidities that affected baseline SOFA and used the National Early Warning Score (NEWS2) to classify <em>likely sepsis</em>.</div></div><div><h3>Results</h3><div>Among 1431 patients (median age 78.9 years; 49.3% male), 545 (38.1%) met sepsis criteria. In non-sepsis patients, mortality was stable across 36–41 °C with no statistically significant association (global spline <em>p</em> = 0.320), although a modest increase was observed below 36 °C. In sepsis, hypothermia (<36 °C) was associated with higher mortality, whereas fever (>38 °C) was protective. At temperature extremes (<36 °C and > 39 °C), confidence intervals widened substantially due to sparse data. Findings were consistent across sensitivity analyses.</div></div><div><h3>Conclusions</h3><div>In older adults with infection but without sepsis, arrival temperature did not predict 28-day mortality. In sepsis, hypothermia was associated with higher mortality, and fever with lower mortality. The prognostic interpretation of very low or very high temperatures remains uncertain, suggesting clinical caution in these temperature ranges.</div></div>","PeriodicalId":55536,"journal":{"name":"American Journal of Emergency Medicine","volume":"103 ","pages":"Pages 1-8"},"PeriodicalIF":2.2,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146081747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Clinical differences between metformin-associated lactic acidosis and metformin-unrelated lactic acidosis: A descriptive study","authors":"Yuji Okazaki MD , Fumiya Inoue MD , Toshihisa Ichiba MD , Akira Namera PhD","doi":"10.1016/j.ajem.2026.01.027","DOIUrl":"10.1016/j.ajem.2026.01.027","url":null,"abstract":"<div><h3>Background</h3><div>The extent to which metformin contributes to lactic acidosis in metformin-treated patients presenting to the emergency department (ED) remains unclear, particularly when blood metformin concentrations are unavailable. This study aimed to clarify the clinical differences between metformin-associated lactic acidosis (MALA) and metformin-unrelated lactic acidosis (MULA) on ED admission.</div></div><div><h3>Methods</h3><div>We conducted a retrospective study at a tertiary care hospital from January 1, 2023 to July 31, 2025. We included adult patients receiving metformin who presented to the ED with lactic acidosis, defined as pH < 7.35 and lactate ≥5 mmol/L. Patients were classified as having MALA if their serum metformin concentration at ED admission was ≥5 mg/L; others were categorized as MULA.</div></div><div><h3>Results</h3><div>Among 14 patients with available serum metformin concentrations, 3 were classified as MALA and 11 as MULA. MALA patients presented with lower blood pressure at ED admission (median 65/36 versus 130/74 mmHg), more profound acidemia (median pH 7.03 [IQR 6.89–7.06] versus 7.22 [IQR 7.20–7.32]), and higher lactate levels (median 14.8 mmol/L [IQR 14.3–19.0] versus 7.3 mmol/L [IQR 5.7–12.5]). Serum creatinine was also higher in the MALA group (median 2.65 mg/dL [IQR 2.26–6.35]) than in the MULA group (median 1.16 mg/dL [IQR 0.97–1.39]).</div></div><div><h3>Conclusions</h3><div>Although the sample size was small, three clinical clues for identifying MALA may include severe acidemia with hyperlactatemia, kidney impairment, and hypotension. Clinicians may consider MALA when these findings coexist in the absence of measured blood metformin concentrations. Further large-scale studies are warranted to confirm our findings.</div></div>","PeriodicalId":55536,"journal":{"name":"American Journal of Emergency Medicine","volume":"103 ","pages":"Pages 9-13"},"PeriodicalIF":2.2,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146081746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A simple instrument-ring technique for rapid localization of scalp bleeding in the emergency department.","authors":"Huseyin Cahit Halhalli, Emrah Celik","doi":"10.1016/j.ajem.2026.04.031","DOIUrl":"https://doi.org/10.1016/j.ajem.2026.04.031","url":null,"abstract":"","PeriodicalId":55536,"journal":{"name":"American Journal of Emergency Medicine","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147790258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Esra Türe, Ahmet Kağan Özkaya, Elif Nur İldeş, Serhat İldeş
{"title":"Divergence between guidelines: Management of diabetic ketoacidosis in transition-age patients.","authors":"Esra Türe, Ahmet Kağan Özkaya, Elif Nur İldeş, Serhat İldeş","doi":"10.1016/j.ajem.2026.04.022","DOIUrl":"https://doi.org/10.1016/j.ajem.2026.04.022","url":null,"abstract":"","PeriodicalId":55536,"journal":{"name":"American Journal of Emergency Medicine","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147789055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ali Pourmand, Michael Gottlieb, Rachel E Bridwell, Brit Long
{"title":"Practice changing articles: Multidose ondansetron after emergency visits in children with gastroenteritis.","authors":"Ali Pourmand, Michael Gottlieb, Rachel E Bridwell, Brit Long","doi":"10.1016/j.ajem.2026.04.016","DOIUrl":"https://doi.org/10.1016/j.ajem.2026.04.016","url":null,"abstract":"","PeriodicalId":55536,"journal":{"name":"American Journal of Emergency Medicine","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147789273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}