ABSTRACT Objective Evaluate the diagnostic accuracy of an artificial intelligence (AI) model for identifying urgent computed tomography brain (CTB) findings in consecutive emergency department (ED) patients and estimate the proportion eligible for expedited disposition. Methods We retrospectively analysed 3424 consecutive non‐contrast CTB scans from adults presenting to a quaternary ED in 2024. The AI model (Harrison Enterprise CTB) classified each scan as “urgent” or “non‐urgent.” The reference standard was the index consultant radiologist report alone, classified independently by two emergency physicians with disagreements resolved by a blinded consultant radiologist tiebreak, all blinded to AI output. In a separate post hoc analysis, false negatives were re‐adjudicated by a single unblinded assessor with access to the medical record and any subsequent imaging. Results Of 3424 scans, 253 (7.4%) had urgent findings on the reference standard. AI sensitivity was 85.4% (95% CI 80.0%–89.0%), specificity 69.1% (95% CI 67.0%–71.0%) and negative predictive value (NPV) 98.3% (95% CI 98.0%–99.0%). An estimated 64.0% of encounters were true negatives potentially eligible for expedited disposition. Of 37 false negatives, independent adjudication reclassified 24 as non‐urgent, yielding a post hoc sensitivity of 94.3% and NPV of 99.4%. The 13 remaining cases were small or subtle findings. None of the 13 cases required urgent intervention during the index ED presentation. Conclusion The AI model demonstrated high NPV for urgent CTB findings, with no false negative requiring urgent intervention during the index ED presentation. Preliminary results provide the safety rationale to proceed with a prospective trial aiming to incorporate this technology into ED workflows.
ABSTRACT Objective This study sought to characterise the demographics, arrest characteristics, clinical outcomes and ED access variables for out‐of‐hospital cardiac arrest (OHCA) presentations to the Victorian Heart Hospital (VHH), Australia's first dedicated cardiac hospital. Methods A retrospective audit of OHCA presentations to the VHH Cardiac Emergency Department from June 2024 to June 2025 was undertaken. Survival to hospital discharge was the primary outcome. Categorical variables associated with survival were assessed using Fisher's exact test with odds ratios; continuous variables associated with survival were assessed by Mann–Whitney U test. Results One hundred and twenty‐one patients were included; 70.2% male, median age 66 years (IQR 59–75). Shockable rhythms accounted for 61.2% of presentations and prehospital ROSC was documented in 92.6%. The primary outcome of survival to hospital discharge was 50.4% and 30‐day survival was 40.0%. Shockable rhythm (OR 3.46, 95% CI 1.55–7.73), cardiac aetiology (OR 3.40, 95% CI 1.32–8.74) and prehospital ROSC (OR 9.23, 95% CI 1.12–76.3) were significant categorical variables associated with survival. Interhospital transfer was required in 24.0% of patients primarily due to a noncardiac aetiology of arrest requiring continuity of care at an affiliated centre. Conclusions In this selected postresuscitation OHCA cohort, survival to hospital discharge was 50.4%, with high rates of prehospital ROSC, shockable rhythm and witnessed arrest. These findings should not be interpreted as evidence of superiority over population‐based OHCA cohorts. ED access variables, including a 24.0% interhospital transfer rate, represent novel system‐level findings warranting prospective investigation.
