OBJECTIVES:To evaluate the cost-effectiveness of implementing an extracorporeal cardiopulmonary resuscitation (ECPR) strategy for refractory out-of-hospital cardiac arrest (OHCA) compared with current practice in Singapore, where it is not routinely used. DESIGN:We performed a simulation-based cost-effectiveness analysis using a decision tree to model acute phase and a Markov model for long-term outcomes over a lifetime horizon, from a healthcare provider perspective. SETTING:Singapore healthcare system. PATIENTS:Nontraumatic adult OHCA patients from Singapore with initial shockable rhythm and no prehospital return of spontaneous circulation were analyzed. INTERVENTIONS:We modeled the implementation of an ECPR strategy and compared it with current practice using only conventional cardiopulmonary resuscitation. Transition probabilities of existing practice were derived from the nationwide Singapore OHCA registry (Pan-Asian Resuscitation Outcomes Study: PAROS), (2010-2016), while ECPR outcomes were based on the Comprehensive Registry of Intensive Care for OHCA Survival in Osaka (Osaka CRITICAL study) (2012-2019). Costs and quality-adjusted life-years (QALYs) were compared between strategies, with scenario analyses conducted to assess the impact of lower age eligibility thresholds and increased transport time to extracorporeal membrane oxygenation-capable hospitals. Incremental cost-effectiveness ratios (ICERs) were estimated using a willingness-to-pay threshold of S$45,000 per QALY. MEASUREMENTS AND MAIN RESULTS:A total of 1462 OHCA cases from Singapore were analyzed; the mean age of patients was 57 years (sd, 11 yr), and 87% were male. In base-case analysis, ICER was estimated at $34,320/QALY, with a positive net monetary benefit of $8,532. Scenario analyses demonstrated that an age-restricted ECPR strategy (< 65 yr) yielded a similar ICER ($33,469/QALY) to the base case. In contrast, incorporating a 10-minute transport extension slightly exceeded the willingness-to-pay threshold ($47,158/QALY). CONCLUSIONS:In this modeling study, adopting an ECPR strategy for OHCA in Singapore was likely to be cost-effective across different age-based eligibility thresholds; however, it was sensitive to delays in transport time. Further implementation research is important to guide scale-up and policy decisions.

Background: Survival analysis is essential for studying time-to-event outcomes and providing a dynamic understanding of the probability of an event occurring over time. Various survival analysis techniques, from traditional statistical models to state-of-the-art machine learning algorithms, support healthcare intervention and policy decisions. However, there remains ongoing discussion about their comparative performance. Methods: We conducted a comparative study of several survival analysis methods, including the accelerated failure time, Cox proportional hazards (CoxPH), stepwise CoxPH, elastic net penalized Cox model, random survival forests, gradient boosting machine learning, AutoScore-Survival, DeepSurv, time-dependent Cox model based on neural network, and DeepHit survival neural network. We applied the concordance index (C-index) for model discrimination, and the integrated Brier scores (IBSs) for calibration, and considered the model interpretability. The prediction performance was independently evaluated in the inpatient dataset of Singapore General Hospital (SGH) from 2017 to 2019 and Asian patients from the MIMIC-IV Clinical Database (MIMIC-IV). The outcome was to predict 90-d all-cause mortality based on patient demographics, clinicopathological features, and historical data. Results: The results of the C-index indicate that deep learning achieved comparable performance, with DeepSurv producing the best discrimination in both SGH (C-index: 0.893) and MIMIC-IV (C-index: 0.794). The calibration of DeepSurv also performed the best, with the IBS of 0.0406 in SGH and 0.1473 in MIMIC-IV, all using the full variables. Moreover, AutoScore-Survival, using a minimal variable subset, is easy to interpret and can achieve good discrimination (C-index in SGH: 0.867; MIMIC-IV: 0.788) and calibration (IBS in SGH: 0.0439; MIMIC-IV: 0.1263). Conclusion: All survival models were satisfactory in predicting mortality after hospital admission. This study provides recommendations for selection based on the characteristics of different models.

The use of artificial intelligence (AI) tools by learners in healthcare presents both substantial opportunities and significant risks. When deployed appropriately, AI systems have been shown to improve diagnostic accuracy, enhance medication safety, and expand access to specialist expertise. However, early and uncritical reliance on AI during formative training may give rise to a distinct and under-recognized risk: never-skilling. Never-skilling occurs when learners substitute AI-generated outputs for the cognitive effort required to develop foundational clinical reasoning skills. Unlike 'de-skilling' in experienced senior clinicians, never-skilling prevents the initial formation of the foundational cognitive framework needed for clinical reasoning among medical students and early trainees. While direct causal evidence remains limited, preliminary signals from non-clinical studies suggest potential risks warrant early intervention. Never-skilling's impact extends beyond individual competency to threaten global healthcare equity, potentially creating AI-dependent physicians who can only practice in resource-rich settings, and raises questions about how independent competency is verified and documented for medical licensure, workforce readiness, and international physician mobility. To prevent and safeguard against never-skilling, we identify three interconnected challenges: competency acquisition failure when AI bypasses productive struggle, calibration deficits that prevent accurate self-assessment, and metacognitive erosion that threatens professional identity formation. To address these risks, we propose a precautionary three-phase framework for medical education and clinical training: establishing baseline AI-independent clinical competency with mandatory assessment constraints, using adversarial pedagogy to train learners to identify AI errors, and supervised integration of AI. This framework addresses this gap, given the absence of longitudinal data tracking competency development in AI-native learners.

Multi-site collaboration can power survival models that no single hospital could fit alone, but privacy rules and protected computing environments block patient-level data sharing and the persistent server connections required by iterative federated methods. We present DiSAH (Distributed Survival via Additive Hazards), a federated algorithm for time-to-event analysis whose closed-form, non-iterative structure removes the need for a dedicated central server. Coordination requires only aggregation of summary statistics, which any site can perform, with no patient-level data leaving the site. DiSAH is the first federated method to estimate hazard differences, the absolute change in event rate attributable to each risk factor, providing an actionable scale for triage, resource allocation, and health-economic evaluation. Across simulations and 47,778 emergency-department patients from the United States and Singapore, DiSAH matches centralized analysis in accuracy and discrimination, recovers mortality risk factors no individual site was powered to detect, and outperforms meta-analysis and local models.

Deploying clinical prediction models across healthcare systems often fails when key training covariates are unavailable at deployment and labeled outcomes are limited in the target domain. For example, high-performing models for out-of-hospital cardiac arrest (OHCA) rely on detailed prehospital measurements routinely collected in high-resource settings but unavailable in many international registries. Existing methods either discard missing covariates, sacrificing predictive information, or rely on untestable assumptions about their target distribution. We propose DRUM (Distributionally Robust Unsupervised transfer learning with structurally Missing covariates), a framework that transfers prediction models to target populations where certain covariates are structurally absent and outcome labels are unavailable. DRUM partitions covariates into shared components (X), observed across all settings, and missing components (A), observed only in the source. Rather than imputing missing covariates, DRUM optimizes worst-case predictive performance over the unknown target distribution of A | X using a neural network generator, with a robustness parameter controlling allowable deviation from the source conditional. We further develop a bias correction procedure that reduces sensitivity to nuisance estimation error. Simulations show substantial improvements in both mean and worst-case prediction error under distribution shift. Applied to cross-national OHCA prediction, transferring models from a US registry to multiple Asian registries where prehospital variables are unrecorded, DRUM yields better-calibrated predictions and improved clinical classification performance across sites.

Background/Objectives: Alcohol-related frequent attenders (ARFAs) constitute a small but resource-intensive emergency department (ED) population. Methods: Following PRISMA-ScR guidelines, we searched MEDLINE, PsycINFO, CINAHL Complete, and EMBASE from inception to May 2025 for empirical studies examining ED frequent attendance with alcohol involvement. Definitions had high heterogeneity; therefore, narrative synthesis was conducted. Results: A total of 73 studies were included, most retrospective (57.5%), encompassing sample sizes from 14 to over 4.1 million participants: 59 frequent attender (FA) studies with alcohol subgroup analyses and 14 pure ARFA studies. Research was concentrated in North America and Europe (56/73, 76.7%), with limited Asia-Pacific representation (21.9%). Seven distinct definition threshold categories were identified (≥2 to ≥20 visits annually); 31.5% utilised different definitions. Qualitative studies (n = 6) identified push factors (dependence, mental health crises, housing instability, fragmented services) and pull factors (24/7 access, crisis care model, immediate service) driving frequent attendance. Eight studies evaluated interventions; all employed non-randomised designs examining case management, integrated pathways, and community-based treatments. Conclusions: Critical gaps include the absence of standardised definitions for comparison across studies, a concentration of research in Western settings limiting global applicability, and insufficient rigorous intervention evidence. Priorities include developing empirically validated definitions, expanding non-Western research, and conducting randomised controlled trials with adequate follow-up.

Quality-of-life is reduced in older patients surviving major blunt trauma. Pre-injury frailty, chronic illness, low falls, or head injury, increase the risk of unplanned healthcare utilization and post-discharge mortality. However, post-hospitalization needs and experiences of patients and caregivers from this high-risk group are not well-understood. This mixed-methods longitudinal study aims to understand participants’ perspectives on needs, prognosis, quality-of-life and end-of-life planning, during the post-injury trajectory. High-risk patients > 55-years-old, and their caregivers, were recruited from three hospitals after surviving blunt trauma. All participants allowed the study team access to medical records, including unplanned readmission and death, for 36 months. Participants who consented to longitudinal follow-up were assessed for quality-of-life and caregiver burden at regular intervals. If unplanned readmission or death occurred, the longitudinal group participants were contacted for a semi-structured interview. Out of 155 participants recruited, 71 patients experienced > = 1 unplanned readmission and 33 died. Twelve semi-structured interviews were conducted after unplanned readmission or death. Five unmet needs were extrapolated from qualitative interviews: uncertainty of prognosis; access to financial support; unaddressed social needs; inconsistent access to healthcare and inadequate structural support. Qualitative findings corroborated with and provided context for the quantitative analysis. Patients with high (> = 2) unplanned readmissions, higher co-morbidities or poorer function had lower quality-of-life. For caregiver burden, high-readmission caregivers experienced increasing financial stress over time, but other domain trajectories were similar between high- and low-readmission groups. The study was limited by recruitment and access difficulties caused by the COVID-19 pandemic, and over-representation of the ethnic majority. Older high-risk blunt trauma survivors and caregivers need better support to mitigate uncertainties in their disease trajectory. Future directions include a system-level prompt to identify at-risk patients at discharge, offering access to designated care teams at different time-points to support the patients and caregivers to navigate the many uncertainties in their healthcare journeys.

OBJECTIVE:This study integrates a machine learning (ML) based Score for Emergency Risk Prediction (SERP), developed using objective mortality endpoints with the Patient Acuity Category Scale (PACS) and evaluated its effectiveness in clinical use. METHODS:This single-centre, retrospective cohort study included all ED patients from a large tertiary hospital between 1 January 2018 and 31 December 2019. Using a reclassification framework, SERP was incorporated into PACS to derive two enhanced triage models. PACS+ model 1 downtriaged patients with low predicted 30-day mortality risk and up-triaged those with high risk. PACS+ model 2 up-triaged only high-risk patients, while low-risk patients retained their original category. Predictive performance in the test cohort was assessed using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). RESULTS:The derivation cohort included 97,188 ED visits, and test cohort included 97,212 ED visits. In the derivation set, the mean (SD) age of patients was 58.97 (18.41) years old and 47,993 (49.4%) were females. Of all patients, 19.9%, 57.5%, 22.5%, and 0.2% were triaged to PACS categories 1-4 respectively. The 30-day mortality rate in the derivation set was 2.8% and 2.7% in the validation cohort. For 30-day mortality prediction, PACS+ model 1 (AUC 0.828 [95% CI 0.820-0.836]) and PACS+ model 2 (AUC 0.812 [95% CI 0.805-0.818]) outperformed PACS (AUC 0.722 [95% CI 0.714-0.729]). PACS+ model 1 consistently achieved greater net benefit across the range of clinical thresholds. CONCLUSION:Integrating ML-based SERP with PACS improved 30-day mortality prediction in ED triage.

Background Informed consent depends on patients' understanding of anaesthesia risk, yet comprehension remains poor despite routine preoperative consultation. Conversational artificial intelligence (AI) could establish patient-reported understanding before clinician contact, but whether such systems can achieve patient-reported understanding comparable to clinician-delivered education remains unknown. Methods We conducted a randomised equivalence trial (n = 130) of PEAR (Preoperative Education of Anaesthesia Risks), a multilingual retrieval-augmented conversational AI grounded in institutional consent materials, versus standard preoperative consultation in adults undergoing elective surgery. Results A total of 130 adults (mean age 52.4 +/- 14.5 years) were enrolled. Post-consultation understanding scores in the PEAR group met the pre-specified equivalence criterion compared with standard consultation across all three primary measures. Patients who interacted with PEAR before clinician contact achieved understanding scores comparable to those receiving standard face-to-face consultation alone. PEAR reduced documentation and consultation time, corresponding to a projected annual net benefit of approximately SGD 0.99 million (USD 0.78 million) at a single tertiary centre. Conclusions A retrieval-augmented conversational AI achieved patient-reported understanding of anaesthesia risk equivalent to standard preoperative consultation while substantially improving workflow efficiency. These findings support supervised deployment of conversational AI within perioperative care pathways while preserving clinician oversight for verification and patient-specific decision-making. ### Competing Interest Statement The authors have declared no competing interest. ### Clinical Trial NCT06949462 ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: The protocol was approved by the SingHealth Centralised Institutional Review Board (CIRB 2025/0673) and registered at ClinicalTrials.gov ([NCT06949462][1]). All participants provided written informed consent. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present study are available upon reasonable request to the authors. [1]: /lookup/external-ref?link_type=CLINTRIALGOV&access_num=NCT06949462&atom=%2Fmedrxiv%2Fearly%2F2026%2F05%2F26%2F2026.05.24.26353997.atom

Access to trustworthy artificial intelligence (AI) for clinical applications is uneven, especially in low-resource settings with limited and inconsistent data. Models from high-resource settings often fail to generalize. Transfer learning (TL) can adapt established models to new settings. Using neurological outcome prediction for out-of-hospital cardiac arrest (OHCA) as a proof of concept, we adapted a model trained on a large cohort to Vietnam (243 patients) and Singapore (15,916 patients) using the Pan-Asian Resuscitation Outcomes Study registry. The external model performed poorly on the Vietnam cohort, with an area under the receiver operating characteristic curve (AUROC) of 0.467 (95

The modern-day population with more chronic, complex medical and social comorbidities is increasing ambulance utilisation and conveyance to emergency departments (ED). This contributes to ambulance ramping, ED overcrowding and increased hospital bed utilisation. This scoping review aims to identify alternative care paths for patients calling for ambulance services. A total of 4902 articles were identified through four databases and the gray literature. The terms ‘paramedic’, ‘ambulance’ and ‘non-conveyance’, ‘alternative’ and ‘community care’ were combined to yield the search terms. The population studied includes individuals calling the national emergency number while the intervention focuses on prehospital services designed to avoid ED conveyance. Independent researchers screened the titles, abstracts and full texts, yielding 59 relevant articles which were then meta-synthesised. Five themes of care were identified - hear and treat, hear and refer, see and treat, see and refer and see and convey to a non-ED facility. Low-acuity patients, older patients, palliative and psychiatric patients, as well as those facing exacerbation of chronic conditions, alcoholic and frequent attenders appear to benefit from these alternative care service pathways (ACSPs). Allied health professionals such as nurses, social workers, occupational therapists, and physiotherapists collaborate with paramedics to frontload the care of these patients in the prehospital setting. Alternative conveyance destinations include general practices, geriatric wards, toxicology units, sobering centres and community hospitals. Implementing ACSPs and integrating healthcare approaches to enhance service efficiency and patient outcomes can alleviate pressure on emergency services by providing timely care and directing patients to appropriate services.

Background:The current landscape of emergency care (EC) is marked by high demand, leading to issues such as emergency department boarding, overcrowding, and subsequent delays that impact the quality and safety of patient care. Integrating data science into EC can enhance decision-making with predictive, preventative, personalized, and participatory approaches. However, gaps in adherence to fairness, accountability, interpretability, and responsibility are evident, particularly due to barriers to data-sharing, which often result in a lack of transparency and robust oversight in these applications. Objective:The FAIR-EC (Fair, Accountable, Interpretable, and Responsible-Emergency Care) collaboration adapts the existing Fair, Accountable, Interpretable, and Responsible principles to address emerging challenges as data science integrates with EC. This initiative aims to transform EC by establishing ethical artificial intelligence standards specifically tailored for this integration. By bridging the gap between EC professionals, data scientists, and other stakeholders, the collaboration promotes international cooperation that leverages advanced data science techniques to enhance EC outcomes across different care settings. Methods:We propose a federated research design to analyze extensive datasets from various global institutions without compromising patient privacy. This approach transforms epidemiological research with advanced data science techniques, emphasizing the harmonization of data for comprehensive analyses across different health care systems. Results:The FAIR-EC initiative has facilitated the identification and harmonization of datasets from diverse geographical regions, enabling the examination of regional variations in EC practices. As of paper submission, participating sites have identified retrospective EC datasets totaling >2 million records (eg, Duke Health >400,000 and Singapore General Hospital >1.7 million records). Initial projects have demonstrated feasibility and operational readiness, including implementation of federated workflows and ongoing development of a federated scoring system, cross-site evaluation, and adaptation of association studies and predictive models across various regions. Cross-site harmonization and pilot analyses are underway (with local ethics approvals in progress), and first multisite results are expected to be submitted in mid-late 2026, with additional project-level publications anticipated in 2027. These efforts highlight the feasibility of leveraging advanced data science techniques to address the complexities of EC while preserving patient privacy without centralizing individual-level data. This project was funded from September 1, 2022, to August 31, 2023. Conclusions:FAIR-EC integrates data science ethically and effectively into EC, addressing challenges such as fragmented data, real-time handoffs, and public health crises. Its federated design harmonizes diverse data streams while preserving privacy, and its emphasis on ethical artificial intelligence aligns with the dynamic nature of EC. Despite challenges in data variability and system complexity, FAIR-EC establishes a strong foundation for innovation in global EC.

The global AI divide in healthcare is widening. While high-resource settings increasingly deploy sophisticated clinical AI, low-resource settings, where disease burdens are often greatest, remain underrepresented in training datasets and underserved by the infrastructure and expertise that underpin model development. AI models trained on narrow or geographically concentrated datasets consequently underperform in the very populations where they are most needed. Without deliberate efforts to advance AI as a digital public good, these technologies risk perpetuating rather than reducing health inequities. Privacy-enhancing technologies (PETs), though well-established, remain underutilized in global health. By enabling collaborative model development without the routine movement of sensitive individual-level data, PETs allow algorithms to learn from diverse populations while respecting data sovereignty, local and international regulations, and institutional policies. However, many PETs remain difficult to implement in settings with limited computational infrastructure, technical expertise, and workforce capacity. In this Perspective, we examine the PET landscape for health research and implementation, emphasizing that techniques must be matched to local capacity and use case. We also address emerging challenges as large language models enter healthcare, particularly where third-party Application Programming Interface (API)-based architectures conflict with data protection and sovereignty requirements. We propose four priorities for equitable implementation: governance that recognizes data sovereignty, guidelines that accommodate privacy-preserving collaboration, investment in lightweight and locally deployable AI infrastructure, and partnerships built on trust and mutual benefit. Technical solutions alone are insufficient; successful implementation also requires trust, mutual benefit, and alignment across diverse legal, cultural, and institutional contexts. Together, these measures can support more equitable development and deployment of AI for global health.

Background/Objectives: Missing data in clinical observational studies, such as out-of-hospital cardiac arrest (OHCA) registries, can compromise statistical validity. Single imputation methods are simple alternatives to complete-case analysis (CCA) but do not account for imputation uncertainty. Multiple imputation (MI) is the standard for handling missing-at-random (MAR) data, yet its implementation remains challenging. This study evaluated the performance of MI in association analysis compared with CCA and single imputation methods. Methods: Using a simulation framework with real-world Singapore OHCA registry data (N = 13,274 complete cases), we artificially introduced 20%, 30%, and 40% missingness under MAR. MI was implemented using predictive mean matching (PMM), random forest (RF), and classification and regression trees (CART) algorithms, with 5-20 imputations. Performance was assessed based on bias and precision in a logistic regression model evaluating the association between alert issuance and bystander CPR. Results: CART outperformed PMM, providing more accurate β coefficients and stable CIs across missingness levels. Although K-Nearest Neighbours (KNN) produced similar point estimates, it underestimated imputation uncertainty. PMM showed larger bias, wider and less stable CIs, and in some settings performed similarly to CCA. MI methods produced wider CIs than single imputation, appropriately capturing imputation uncertainty. Increasing the number of imputations had minimal impact on point estimates but modestly narrowed CIs. Conclusions: MI performance depends strongly on the chosen algorithm. CART and RF methods offered the most robust and consistent results for OHCA data, whereas PMM may not be optimal and should be selected with caution. MI using tree-based methods (CART/RF) remains the preferred strategy for generating reliable conclusions in OHCA research.

Despite continuous advances in medical technology, the global distribution of health care resources remains uneven. The development of large language models (LLMs) has transformed the landscape of medicine and holds promise for improving health care quality and expanding access to medical information globally. However, existing LLMs are primarily trained on high-resource languages, limiting their applicability in global medical scenarios. To address this gap, we constructed GlobMed, a large multilingual medical dataset, containing over 500,000 entries spanning 12 languages, including four low-resource languages. Building on this, we established GlobMed-Bench, which systematically assesses 56 state-of-the-art proprietary and open-weight LLMs across multiple multilingual medical tasks, revealing significant performance disparities across languages, particularly for low-resource languages. Additionally, we introduced GlobMed-LLMs, a suite of multilingual medical LLMs trained on GlobMed, with parameters ranging from 1.7B to 8B. GlobMed-LLMs achieved an average performance improvement of over 40

INTRODUCTION:Singapore is among the fastest-ageing nations in the world, and studies have shown a steady rise in emergency department (ED) utilisation among older adults. This study aimed to describe trends and characteristics of ED use in Singapore over a 12-year period and to assess differences in utilisation across age groups. METHODS:Data from 2008 to 2019 on ED visits, admissions, patient characteristics and principal ED diagnoses were extracted from the electronic health records of a tertiary hospital. The primary outcome was admissions through ED, and the secondary outcome was the proportion of high-acuity visits. The Wilcoxon rank-sum test was used to assess trends. Multivariable logistic regression was used to assess factors associated with ED admissions and proportions of high-acuity visits, as well as test the interaction between year and age group. RESULTS:Although the number of ED visits decreased from 108,838 in 2008 to 102,890 in 2019, the ED admission rate increased from 35.1% to 47.0%. Across all age groups, older adults aged ≥80 years showed a greater increase in ED admissions over time compared to adults aged 18-64 years. In the same period, the proportion of high-acuity ED visits increased across all age groups, although age-related differences diminished over time. Some fluctuations were observed in the most common ED diagnoses. CONCLUSION:Our study showed that ED admission rates, particularly among older adults, increased from 2008 to 2019. This highlights the growing care needs of older patients and underscore the importance of geriatric-friendly EDs and evidence-based programmes to ensure high-quality care.

Aim:To compare the prehospital outcomes of out-of-hospital cardiac arrest (OHCA) across different emergency medical service (EMS) system organizational models in China. Methods:This is a retrospective analysis of data from the Baseline Investigation of Out-of-Hospital Cardiac Arrest (BASIC-OHCA) (August 1, 2019-December 31, 2020) in China. Two EMS models were compared. One is independent model, in which all stations are directly established and managed by an independent public agency. The other one is hospital-based model, in which the stations are affiliated to hospitals. The primary outcome was ROSC sustained until arrival at the emergency department and transfer of care (survived event). Association were analyzed using multivariable logistic regression. Results:A total of 24,814 OHCA patients from 10 EMS systems were included. The overall survived event rate was 2.05%, which was higher in the independent model than the hospital-based model (2.23% vs. 1.40%; P < 0.001). After adjustment, the independent model remained associated with higher odds of survived event (adjusted odds ratio 2.32; 95% CI, 1.71-3.17). The independent model had longer EMS response times (median 12.00 vs. 10.00 min; P < 0.001) but higher rates of epinephrine administration (85.02% vs. 73.26%; P < 0.001) and advanced airway placement (49.24% vs. 21.48%; P < 0.001) than the hospital-based model. Conclusions:In this study, the independent model was associated with a statistically higher survived event rate than the hospital-based model in China. However, considering the small absolute difference, future efforts should be taken to explore broader, system-level best practices to achieve more clinically meaningful improvements in OHCA outcomes.