Background Triage is an essential part of Emergency Medicine, which may be assisted by AI models due to limited availability of medical staff. However, AI models for aiding triage have difficulty in identifying levels that are difficult or ambiguous for human clinicians to distinguish. This study aims to develop a more reliable triage model that improves the accuracy of classification, especially for cases with moderate acuity. Methods We developed a new triage model called KUTS, a foundational classification model for emergency triage, which leverages a knowledge prompt-tuning encoder and an uncertainty-based classifier. KUTS takes tabular data and chief complaints as input, and then assign different acuity levels to patients based on their condition acuity. We trained and tested the model on multiple real-world emergency department datasets. Results Here we show that on the most difficult level for human to distinguish (moderate acuity level), our KUTS substantially outperforms the previous shallow single-modal methods, deep single-modal methods and deep multi-modal methods on AUC score, by an average of 0.19, 0.35, and 0.13 (from 0.76, 0.60, 0.82 to 0.95), respectively. Besides, on all the triage levels, our KUTS also outperforms the previous shallow single-modal methods, deep single-modal methods and deep multi-modal methods on AUC score, by an average of 0.14, 0.20 and 0.06 (from 0.82, 0.76, 0.90 to 0.96), respectively. Conclusions KUTS provides a foundational framework and paradigm for the study of emergency triage, and facilitates the development of more efficient triage systems.

Background: Sepsis commonly causes acute respiratory distress syndrome (ARDS), and ARDS contributes to poor prognosis in sepsis patients. Early prediction of ARDS for sepsis patients remains a clinical challenge. This study aims to develop and validate chest computed tomography (CT) radiomic-based signatures for early prediction of ARDS and assessment of individual severity in sepsis patients. Methods: In this ambispective observational cohort study, a deep learning model, a sepsis-induced acute respiratory distress syndrome (SI-ARDS) prediction neural network, will be developed to extract radiomics features of chest CT from sepsis patients. The datasets will be collected from these retrospective and prospective cohorts, including 400 patients diagnosed with sepsis-3 definition during a period from 1 May 2015 to 30 May 2022. 160 patients of the retrospective cohort will be selected as a discovering group to reconstruct the model and 40 patients of the retrospective cohort will be selected as a testing group for internal validation. Additionally, 200 patients of the prospective cohort from two hospitals will be selected as a validating group for external validation. Data pertaining to chest CT, clinical information, immune-associated inflammatory indicators and follow-up will be collected. The primary outcome is to develop and validate the model, predicting in-hospital incidence of SI-ARDS. Finally, model performance will be evaluated using the area under the curve (AUC) of receiver operating characteristic (ROC), sensitivity and specificity, using internal and external validations. Discussion: Present studies reveal that early identification and classification of the SI-ARDS is essential to improve prognosis and disease management. Chest CT has been sought as a useful diagnostic tool to identify ARDS. However, when characteristic imaging findings were clearly presented, delays in diagnosis and treatment were impossible to avoid. In this ambispective cohort study, we hope to develop a novel model incorporating radiomic signatures and clinical signatures to provide an easy-to-use and individualized prediction of SI-ARDS occurrence and severe degree in patients at early stage.

Out-of-hospital cardiac arrest (OHCA) is a significant global public health issue, few studies describe characteristics and trends in China. This study examines OHCA features and trends in Shenzhen, one of the fastest-growing cities. This retrospective study analysed data from the Shenzhen Emergency Center database (2011–2018), including ambulance dispatch and pre-hospital medical records. Descriptive statistics and temporal trends were used to examine the incidence, patients characteristics, pre-hospital treatment, and outcome. Among 18,772 medical cause OHCA cases, the crude incidence rate was 17.4 per 100,000 population, with an age-standardised rate of 38.4. Incidence increased over time. Resuscitation was attempted in 43.8% of cases, with a median patient age of 56 years and 73.5% being male. Most arrest (69.0%) occurred at home, and 82% were presumed to be cardiac cause.The median response time was 11.2 min. Bystander cardiopulmonary resuscitation (CPR) rates increased from 4.6% in 2011 to 14.5% in 2018, while bystander automated external defibrillator (AED) use remained low (0.2%). Pre-hospital electrocardiogram (ECG) recording improved from 40.6% to 91.9%, with shockable rhythms 2.2%. Intravenous access was established in 69.7% of patients, 51.9% received epinephrine, 19.29% received pre-hospital defibrillation, and 16.4% underwent advanced airway management. The pre-hospital Return of Spontaneous Circulation (ROSC) rate increased from 2.7% to 5.8%, with a total ROSC rate of 3.11%. OHCA incidence in Shenzhen is lower than both domestic and international levels but increasing. Low bystander intervention rated and prolonged response times contribute to poor outcome, underscoring the need for system improvements.

Despite the rising disease mortality rates, there is a dearth of studies on the incidence and trends of out-of-hospital cardiac arrests (OHCA) in China. This study aims to investigate the incidence and temporal trends of presumed cardiac origin OHCA in Guangzhou, Southern China, from 2011 to 2020. In this population-based retrospective cohort study, pre-hospital data from the Guangzhou Emergency Medical Service (GZ-EMS) from 2011 to 2020 were analyzed. Crude incidence rates and age-standardized incidence rates (ASIRs) were calculated respectively. ASIRs were calculated using the 2000 national census population as the standard population. The Joinpoint software was used to calculate the Annual Percent Change (APC) and Average Annual Percent Change (AAPC) in the incidence of OHCA over the study period. From 2011 to 2020, 44,375 EMS-assessed OHCAs of presumed cardiac origin were recorded. Overall, the crude incidence rate of OHCA was 53.1 per 100,000 on average. AAPC was 7.0% (95% CI: 4.3%–9.8%). Age-standardized incidence rate(ASIR) was 38.4 per 100,000 on average, with an average annual increase of 4.8% (95% CI: 2.4%–7.3%). The crude and ASIR of OHCA increased in men, while the ASIR changed more moderately in women. The age group of ≥80 years had the highest rate of increase. The 20–29 and 70–79 age groups also demonstrated notable increases. From 2011 to 2020, Guangzhou experienced a notable upward trend in both crude and ASIR of OHCA, with significant variations observed across gender and age demographics. This trend calls for a deeper investigation into the underlying factors.

Sepsis-Induced Acute Respiratory Distress Syndrome (SI-ARDS) presents significant diagnostic and prognostic challenges due to its complex clinical manifestations and high mortality rate. We developed a deep Knowledge-Driven multi-Modal Fusion (KDMF) framework for the accurate diagnosis and prognosis of SI-ARDS. The model leverages multi-modal data, including CT images, CT reports, and laboratory indicators, alongside a disease-specific knowledge graph. KDMF achieves superior performance in predicting SI-ARDS incidence (AUC 0.930) and time to 28-day mortality (AUC 0.843, C-index 0.833). Comprehensive error analysis and ablation studies demonstrate the critical contributions of each data modality and the integrated knowledge graph. The results highlight the potential of KDMF to enhance early intervention and treatment strategies, underscoring the robustness and interpretability of the framework in clinical applications.