Background: Carbon monoxide (CO) poisoning is a leading cause of toxicological emergencies worldwide. Although carboxyhemoglobin (COHb) levels are traditionally used to confirm exposure, they often fail to reflect clinical severity. This study aimed to evaluate the diagnostic performance of serum lactate and hematological parameters in predicting the need for hyperbaric oxygen therapy (HBOT) among patients with acute CO poisoning. Materials and methods: This retrospective cross-sectional study included 292 adult patients with confirmed CO poisoning admitted to a tertiary emergency department between 2020 and 2024. Patients were categorized according to HBOT administration. Laboratory values including lactate, COHb, and hematologic parameters and indices were analyzed. Multivariable logistic regression and ROC curve analysis were used to assess predictive performance. Results: Of the 292 patients, 94 (32.2%) received HBOT. Serum lactate and COHb were significantly higher in the HBOT group ( p < 0.001 for both) and were identified as independent predictors of HBOT requirement (lactate OR = 2.04; COHb OR = 1.32). AUC for lactate alone was 0.754; combining lactate with hematologic markers modestly improved AUC to 0.769. The most robust model, incorporating lactate and COHb, achieved an AUC of 0.936. Hematologic markers alone showed limited predictive value. Conclusion: Serum lactate, particularly when combined with COHb, provides strong diagnostic value in predicting HBOT need in CO poisoning. The integration of these readily available biomarkers may improve triage decisions in emergency care.

OBJECTIVES: Although the reliability of e-point septal separation (EPSS) and caval index (CI) is proven in the diagnosis of acute heart failure (AHF), how much they contribute to the initial clinical impression is unclear. This study aimed to determine the diagnostic contribution of EPSS and CI to the initial clinical impression of AHF. METHODS: This is a prospective observational study conducted in an academic emergency department (ED). The patients admitted to the ED with acute undifferentiated dyspnea were included. Primary diagnosis was made after an initial clinical evaluation, and a secondary diagnosis was made after EPSS and CI measurements. Independent cardiologists made the final diagnosis. The primary outcome was the diagnostic contribution of EPSS and CI to the primary diagnosis. RESULTS: A total of 182 patients were included in the study. The primary diagnosis was found with a sensitivity of 0.55 and specificity of 0.84 and the secondary diagnosis was determined with a sensitivity of 0.78 and specificity of 0.83 in predicting the final diagnosis. The agreement coefficient between the primary and final diagnosis was 0.44 and between the secondary diagnosis and the final diagnosis was 0.61. When the primary diagnosis was coherent with secondary diagnosis, sensitivity and specificity were found to be 0.74 and 0.90, respectively. CONCLUSION: Although a detailed history and physical examination are the essential factors in shaping clinical perception, CI and EPSS combined significantly contribute to the initial clinical impression.

Background: Accurate burn size and depth assessment at first contact guides fluid resuscitation, referral, and operative planning, yet both tasks show meaningful inter-clinician variability. General-purpose multimodal large language models may offer scalable, image-based decision support in emergency care, but prospective benchmarking against clinicians and a robust reference standard remains limited. Methods: We conducted a prospective, single-centre diagnostic accuracy and agreement study in a tertiary emergency department (22 July–8 September 2025). Consecutive acute burn presentations (< 24 h) were screened; protocol-conformant cases contributed standardized three-view photographs per anatomically distinct burn region. A multimodal large language model generated region-level estimates of total body surface area (TBSA) contribution and burn depth class. Eighteen emergency physicians independently rated the same images and minimal metadata, blinded to model and reference outputs. A three-member expert panel served as the reference standard by consensus. The primary endpoint was non-inferiority of the model versus the physician median for region-level absolute TBSA error relative to the panel, with a pre-specified margin of 3 percentage points, using patient-level cluster bootstrap for inference. Secondary endpoints included TBSA agreement and depth agreement (quadratic-weighted kappa). Results: Of 413 screened presentations, 52 patients were enrolled, yielding 64 analyzable burn region-cases (35 pediatric, 29 adult). The model’s mean absolute TBSA error versus the panel was 1.40 percentage points (median 1.00); 87.5% of cases were within ± 3 percentage points and 98.4% within ± 5. The physician median had a mean absolute error of 0.89 percentage points (median 0.75). The paired non-inferiority analysis met the pre-specified criterion (Hodges–Lehmann median Δ = 0.25; one-sided 95% upper bound = 0.50), indicating the model was non-inferior to physicians for TBSA estimation. In contrast, depth agreement versus the panel was slight for the model (quadratic-weighted kappa 0.14), with systematic underestimation of deeper burns, while physician consensus showed substantially higher agreement (quadratic-weighted kappa 0.65). Conclusions: In this prospective emergency department evaluation, a general-purpose multimodal model achieved non-inferior performance to emergency physicians for region-level TBSA estimation but performed substantially worse for burn depth classification. These findings support a narrowly defined adjunct role for TBSA estimation, while depth-dependent decisions should remain clinician-led and require further method development and external validation.