Injury Prevention最新文献

{"title":"Ethnic variation in access to publicly funded care for unintentional injuries in older adults in Aotearoa New Zealand: a retrospective study.","authors":"Alana Cavadino, Braden Te Ao, Ngaire Kerse, Bridget Kool, John Parsons, Joanna Hikaka","doi":"10.1136/ip-2023-045168","DOIUrl":"10.1136/ip-2023-045168","url":null,"abstract":"<p><strong>Background: </strong>Māori (the Indigenous people of Aotearoa New Zealand (NZ)) are more likely to experience injury than non-Māori, but less likely to have effective access to publicly funded injury care services. It is unknown if this pattern extends into older age. This retrospective study analysed Accident Compensation Corporation (ACC; national no-fault injury compensation scheme) claims data to investigate ethnic variation in unintentional injury claims and related costs for older adults (≥50 years).</p><p><strong>Methods: </strong>Injury claims data for older adults residing in two regions of NZ between January 2014 and December 2018 were reviewed. Age-standardised claims rates (per person year) standardised rate ratios were calculated and compared between Māori and non-Māori. ACC claim costs (medical treatment; earning-related compensation) were estimated, with total and average costs per claim compared between the two groups.</p><p><strong>Results: </strong>There were 149 275 ACC claims (18 369 Māori; 130 906 non-Māori) among 64 238 individuals (9284 Māori; 54 954 non-Māori). The age-standardised rate of ACC claims for unintentional injury was 46% higher among non-Māori (95% CI 44% to 48%) than Māori. The ACC spend for non-Māori was NZ$155 277 962 compared with NZ$30 446 673 for Māori. Māori had a significantly higher average cost per claim (NZ$1658 vs NZ$1186, p<0.001).</p><p><strong>Conclusions: </strong>Results of this study highlight differences in the manner in which different groups of older adults access injury compensation in NZ, indicating the need to invest in injury prevention initiatives that target older Māori, as well as initiatives supporting improved ACC access for older Māori.</p>","PeriodicalId":13682,"journal":{"name":"Injury Prevention","volume":" ","pages":"66-72"},"PeriodicalIF":2.5,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141071031","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":"Did 'long COVID' increase road deaths in the USA?","authors":"Leon Robertson","doi":"10.1136/ip-2023-045136","DOIUrl":"10.1136/ip-2023-045136","url":null,"abstract":"<p><strong>Objective: </strong>To examine data on COVID-19 disease associated with a 10% increase in US road deaths from 2020 to 2021 that raises the question of the potential effect of pandemic stress and neurological damage from COVID-19 disease.</p><p><strong>Methods: </strong>Poisson regression was used to estimate the association of recent COVID-19 cases, accumulated cases, maximum temperatures, truck registrations and gasoline prices with road deaths monthly among US states in 2021. Using the regression coefficients, changes in each risk factor from 2020 to 2021 were used to calculate expected deaths in 2021 if each factor had remained the same as in 2020.</p><p><strong>Results: </strong>Corrected for the other risk factors, road deaths were associated with accumulated COVID-19 cases but not concurrent cases. More than 20 700 road deaths were associated with the changes in accumulated COVID-19 cases but were substantially offset by about 19 100 less-than-expected deaths associated with increased gasoline prices.</p><p><strong>Conclusions: </strong>The lingering effects of COVID-19 on neurological function may be a risk factor for behaviour leading to road deaths.</p>","PeriodicalId":13682,"journal":{"name":"Injury Prevention","volume":" ","pages":"18-20"},"PeriodicalIF":2.5,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140131319","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":"Cost-effectiveness of the 'Stay One Step Ahead' Home Safety programme for the prevention of injuries among children under 5 years.","authors":"Matthew Jones, Elizabeth Orton, Michael James Taylor, Clare Timblin, Rachel Clarke, Michael Craig Watson, Mike Hayes, Tina Patel, Carol Coupland, Denise Kendrick","doi":"10.1136/ip-2024-045236","DOIUrl":"10.1136/ip-2024-045236","url":null,"abstract":"<p><strong>Background: </strong>Unintentional injuries are a common cause of morbidity and mortality in the under-5s, but undertaking home safety practices can reduce injury risk. Stay One Step Ahead (SOSA) is an evidence-based standardised home safety programme. This study evaluates the cost-effectiveness of SOSA versus usual care in Nottingham, UK.</p><p><strong>Methods: </strong>Cost-effectiveness analysis from a National Health Service and personal social services perspective. SOSA activity data, injury occurrence and associated short-term healthcare costs were collected within a controlled before-and-after study from 2017 to 2020. The primary outcome was the incremental cost-effectiveness ratio (ICER) per additional home adopting three key safety practices (working smoke alarm, safe poisons storage and fitted stair gate). Secondary outcomes were ICERs per injury avoided and quality-adjusted life-years (QALYs) gained.</p><p><strong>Results: </strong>SOSA costs £30 per child but reduces short-term healthcare expenditure by £42. SOSA increased the number of homes with three key safety practices by 0.02 per child, reduced injuries per child by 0.15 and gained 0.0036 QALYs per child. SOSA was dominant as it was cheaper and more effective than current practice. ICERs were -£590 per additional home deemed safe, -£77 per injury avoided and -£3225 per QALY gained. Focusing on healthcare expenditure alone, SOSA saved £1.39 for every pound spent.</p><p><strong>Conclusions: </strong>SOSA is a cost-saving intervention. Commissioners should consider implementing SOSA.</p>","PeriodicalId":13682,"journal":{"name":"Injury Prevention","volume":" ","pages":"45-51"},"PeriodicalIF":2.5,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11874428/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142107054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gun violence exposure and population health inequality: a conceptual framework.","authors":"Daniel C Semenza, Nicole Kravitz-Wirtz","doi":"10.1136/ip-2023-045197","DOIUrl":"10.1136/ip-2023-045197","url":null,"abstract":"<p><p>This essay establishes a conceptual framework to understand how direct, secondar and community exposures to gun violence converge to influence population health. Our framework asserts that persistent gun violence in structurally disadvantaged communities enacts broad consequences for mental, physical and behavioural health, operating as a key driver of racial and socioeconomic health disparities. We discuss the applications of this framework for research and improved data collection with a focus on establishing timely and accurate measures of gun violence alongside individual and community health measures. We then address the policy implications of the framework, emphasising the need for long-term, institutional investment in gun violence prevention and intervention, survivor service provision and evidence-based policies at all levels of government.</p>","PeriodicalId":13682,"journal":{"name":"Injury Prevention","volume":" ","pages":"1-8"},"PeriodicalIF":2.5,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11874337/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142365154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Non-reporting of sport-related concussion symptoms: a cross-sectional study of community rugby league players in the UK.","authors":"Daniel Isaac Tadmor, Lucy Chesson, Kevin Till, Gemma Phillips, Laura Fairbank, James Brown, Matt Cross, Andrew J Gardner, Rich D Johnston, Cameron Owen, Sharief Hendricks, Keith A Stokes, Ben Jones","doi":"10.1136/ip-2023-045108","DOIUrl":"10.1136/ip-2023-045108","url":null,"abstract":"<p><p>Recognising and removing players with suspected sport-related concussions is crucial for community sports.</p><p><strong>Objectives: </strong>Quantify rates and factors associated with non-reporting of concussion symptoms in community rugby league.</p><p><strong>Methods: </strong>Overall, 484 community rugby league players aged ≥18 years and 965 parents of rugby league players aged <18 years completed an online survey, regarding concussion history, knowledge, prevalence and reasons for non-reporting of concussion, long-term implications and perceptions of concussion.</p><p><strong>Results: </strong>Thirty-five percent of players aged ≥18 years and 22% of parents of players aged <18 years reported at least one concussion in the last two seasons. Forty-three percent of players aged ≥18 years and 5% of parents of players aged<18 years surveyed stated they did not report concussion-related symptoms sustained during 2020 and 2021 seasons. The two most common reasons for non-reporting of concussion symptoms were <i>'didn't want to be ruled out of a match'</i> and <i>'didn't want to let down the team'</i>. Players aged ≥18 years who received external coaching pressures around concussion were more likely to not report concussion symptoms. Over 40% of parents and players were concerned about the potential long-term implications. Ten percent of players aged ≥18 years and 7% of parents of players aged <18 years would encourage their family members/children to not play rugby league.</p><p><strong>Conclusions: </strong>Non-reporting rates of suspected concussion symptoms in adult community players were twice as high as in professional rugby league, with similar reasons (wanting to play and not letting the team down). Engaging coaches to prioritise brain health and providing broader and appropriate education on concussion should be focused on, given the concerns reported by community players and parents.</p>","PeriodicalId":13682,"journal":{"name":"Injury Prevention","volume":" ","pages":"81-87"},"PeriodicalIF":2.5,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141765947","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":"Community and multisector partner engagement in US Vision Zero plan development.","authors":"Sylvia Greer, Tabitha Combs, Rebecca B Naumann, Elyse Keefe, Seth LaJeunesse, Kelly R Evenson","doi":"10.1136/ip-2023-045148","DOIUrl":"10.1136/ip-2023-045148","url":null,"abstract":"<p><strong>Background: </strong>Vision Zero aims to eliminate serious and fatal road injuries using a Safe System approach. Safe System principles establish that safety is a shared responsibility; this involves both multisector partners and community engagement. This descriptive study explored multisector partners and community engagement in the development of municipal Vision Zero plans.</p><p><strong>Methods: </strong>We reviewed all first edition Vision Zero plans published by US municipalities from 2014 to 2022. Using a structured coding tool, we abstracted partner involvement and community engagement strategies used in the development of Vision Zero plans.</p><p><strong>Results: </strong>We identified, reviewed and abstracted 64 plans. The average number of partner groups per plan was 11.5 (12.0 for municipalities with a population ≥150 000; 10.1 for municipalities <150 000) and was higher for later plans (11.9 for plans published 2019-2022; 10.0 for plans published 2014-2018). Common partner groups engaged in the plan were law enforcement (85.9% of plans), local transportation planning (78.3%), mayor/city council/city manager (78.1%), engineering/public works (78.1%) and schools (73.4%). Community engagement strategies were reported in 71.9% of the plans and were more frequent among municipalities with a population ≥150 000 (76.1%) compared with a population <150 000 (61.1%), and in those with more recent plans (82.1%) versus earlier ones (56.0%). The most common community engagement strategies were public meetings, online surveys and map mark-ups.</p><p><strong>Conclusions: </strong>These findings highlight the extent to which Vision Zero plans were aligned with core Safe System tenets regarding diverse partner involvement and community engagement. Plan developers should consider the translation of Safe System principles in Vision Zero plan development.</p>","PeriodicalId":13682,"journal":{"name":"Injury Prevention","volume":" ","pages":"60-65"},"PeriodicalIF":2.5,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11830399/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142107053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Global, regional and national burdens of occupational injuries, 1990-2019: a systematic analysis for the Global Burden of Disease Study 2019.","authors":"Jianqiang Lai, Xianmin Li, Wei Liu, Qian Liufu, Chengfan Zhong","doi":"10.1136/ip-2023-045149","DOIUrl":"10.1136/ip-2023-045149","url":null,"abstract":"<p><strong>Objectives: </strong>Occupational injuries pose a significant challenge to global health and development. This study aimed to quantify the international and regional burdens of occupational injuries from 1990 to 2019, stratified by specific causes.</p><p><strong>Methods: </strong>We analysed global trends in deaths, disability-adjusted life years (DALYs), age-standardised mortality rates (ASMR) and age-standardised DALY rates (ASDR) related to occupational injuries. Specific injuries, including animal contact, drowning, mechanical forces, falls, fire, heat, hot substances, foreign bodies, poisoning and road injuries, were evaluated. Age-stratified and regional analyses were also performed.</p><p><strong>Results: </strong>Globally, the number of deaths, DALYs, ASMR and ASDR related to occupational injuries declined from 1990 to 2019. The middle Socio-demographic Index (SDI) region exhibited the highest burden, whereas the high SDI region showed the least burden. China and India had the highest occupational injury-related death rates in 2019. Males, particularly those aged 25-44 years, were found to be more vulnerable. Road injuries were the leading cause of death in all age groups. Compared with 1990, mortality numbers and rates decreased significantly by 2019, with the highest burdens experienced in East Asia, South Asia and Southeast Asia.</p><p><strong>Conclusion: </strong>The global decline in occupational injuries is promising; however, certain regions and demographics remain disproportionately affected. Targeted interventions in high-burden areas are crucial to further reduce the impact of occupational injuries.</p>","PeriodicalId":13682,"journal":{"name":"Injury Prevention","volume":" ","pages":"52-59"},"PeriodicalIF":2.5,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141093208","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":"Physical and psychological factors related to injury, illness and tactical performance in law enforcement recruits: a systematic review.","authors":"Myles Murphy, Nicole Merrick, Gill Cowen, Vanessa Sutton, Garth Allen, Nicolas H Hart, Andrea B Mosler","doi":"10.1136/ip-2023-045150","DOIUrl":"10.1136/ip-2023-045150","url":null,"abstract":"<p><strong>Objective: </strong>There are inconsistent reports of factors relating to injury, illness and tactical performance in law enforcement recruits. Our objectives were to: (1) report physical and psychological risk factors and protective factors for injury and illness and (2) report physical and psychological risk factors and protective factors for tactical performance success.</p><p><strong>Design: </strong>Systematic epidemiological review.</p><p><strong>Methods: </strong>Searches of six databases were conducted on 13 December 2022. We included cohorts that assessed physical and psychological factors for injury, illness and tactical performance success. Study quality was assessed using the Joanna Briggs Institute Quality Assessment Checklist for Prevalence Studies and certainty assessed using the Grading of Recommendations Assessment, Development and Evaluation.</p><p><strong>Results: </strong>30 studies were included, and quality assessment was performed. Very low certainty of evidence exists for physical variables related to injury risk, and we found no studies that investigated psychological variables as a risk factor for injury. Low-certainty evidence found older age, poorer performance with push-up reps to failure, poorer arm ergometer revolutions, poorer beep test, poorer 75-yard pursuit and the 1.5 miles run tests to be associated with reduced tactical performance. Very low certainty of evidence exists that the psychological variables of intelligence and anger are associated with tactical performance.</p><p><strong>Conclusions: </strong>We identified a lack of high-level evidence for factors associated with injury, illness and performance. Interventions based on this research will be suboptimal. We suggest context-specific factors related to injury, illness and performance in law enforcement populations are used to inform current practice while further, high-quality research into risk factors is performed.</p><p><strong>Prospero registration number: </strong>CRD42022381973.</p>","PeriodicalId":13682,"journal":{"name":"Injury Prevention","volume":" ","pages":"9-17"},"PeriodicalIF":2.5,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141859556","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":"Trends in alcohol, MDMA, methylamphetamine and THC in injured and deceased motor vehicle drivers and motorcyclists over a decade (2010-2019) in Victoria, Australia.","authors":"Jennifer Schumann, Matthew Di Rago, Noel Woodford, Linda Glowacki, John Fitzpatrick, Michael Kelly, Ben Beck, Olaf H Drummer, Dimitri Gerostamoulos, Joanna F Dipnall","doi":"10.1136/ip-2024-045342","DOIUrl":"https://doi.org/10.1136/ip-2024-045342","url":null,"abstract":"<p><strong>Background: </strong>Driving under the influence of alcohol and other drugs contributes significantly to road traffic crashes worldwide. This study explored trends of alcohol, methylamphetamine (MA), 3,4-methylenedioxy-N-methylamphetamine (MDMA) and Δ9-tetrahydrocannabinol (THC), in road crashes from 2010 to 2019 in Victoria, Australia.</p><p><strong>Methods: </strong>We conducted a cross-sectional analysis using data from the Victorian Institute of Forensic Medicine and Victoria Police, examining proscribed drug detections in road crashes. Time series graphs per substance explored indicative trends and comparisons between road users. Negative binomial regression models, with robust SEs and adjusted for exposure (kilometres travelled, Victorian licence holders), modelled the incidence rate ratio, with a Bonferroni-adjusted α=0.007 for multiple comparisons.</p><p><strong>Results: </strong>There were 19 843 injured drivers and 1596 fatally injured drivers. MA had the highest prevalence (12.3% of fatalities and 9.1% of injured drivers), demonstrating an increase over time. Overall, 16.8% of car drivers and motorcyclists tested positive for one or more drugs, with 14% of crashes involving a blood alcohol concentration (BAC)≥0.05%. MA and THC were the most common drugs in fatalities. Between 2015 and 2019, MA was detected in 27.9% of motorcyclist fatalities, followed by THC (18.3%) and alcohol ≥0.05% (14.2%), with similar but lower frequencies among injured motorcyclists. Alcohol detections (≥0.05% BAC) in fatalities declined, but increased in injured motorcyclists and car drivers until plateauing in 2017. THC detections rose among injured drivers until 2018, detected in 8.1% and 15.2% of injured and fatal drivers, respectively. MDMA-positive driving decreased among injured drivers and remained stable at ~1% of fatalities.</p><p><strong>Conclusions: </strong>Despite enhanced road safety measures in Victoria, drug-driving persists, indicating a need for revised prevention strategies targeting this growing issue.</p>","PeriodicalId":13682,"journal":{"name":"Injury Prevention","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143004950","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":"Predicting 90-day return to the emergency department in orthopaedic trauma patients in the Southeastern USA: a machine-learning approach.","authors":"Bruno Valan, Aaron Therien, Emily Peairs, Solomon Ayehu, Joshua Taylor, Daniel Zeng, Steven Olson, Rachel Reilly, Christian Pean, Malcolm DeBaun","doi":"10.1136/ip-2024-045358","DOIUrl":"https://doi.org/10.1136/ip-2024-045358","url":null,"abstract":"<p><strong>Introduction: </strong>Return-to-acute-care metrics, such as early emergency department (ED) visits, are key indicators of healthcare quality, with ED returns following surgery often considered avoidable and costly events. Proactively identifying patients at high risk of ED return can support quality improvement efforts, allowing interventions to target vulnerable patients. With its predictive capabilities, machine learning (ML) has shown potential in forecasting various clinical outcomes but remains underutilised in orthopaedic trauma. This study uses a random forest model to predict 90-day ED return in orthopaedic trauma patients, aiming to identify high-risk individuals and elucidate risk factors associated with returns. This study hypothesised that a highly accurate model could be developed to predict patients at high risk of ED return within 90 days of surgery.</p><p><strong>Purpose: </strong>To develop and validate an ML model that predicts 90-day ED returns after orthopaedic trauma surgery using input data readily available in the electronic health record.</p><p><strong>Methods: </strong>This is a retrospective model development and validation study. The study used data from a registry that includes information on all orthopaedic surgeries conducted at a level 1 academic medical centre. Patients who underwent orthopaedic trauma between 1 January 2017 and 1 March 2023 were identified using common procedural terminology code. The model used demographic, comorbid and perioperative variables. Return to the ED was captured as a binary outcome. Model performance was evaluated using the area under the receiver operator curve (AUROC).</p><p><strong>Results: </strong>A total of 12 069 patients met the inclusion criteria. Patients were predominantly female (53%) and white (70%), with a median age of 55. The 90-day ED return rate was 14% (table 1). The random forest model identified body mass index, distance from the patient's residence to the hospital, age, length of hospital stay and complexity of procedure (work relative value unit) as significant predictors of ED return, each accounting for greater than 10% of the total importance across all features in the model (table 2). Further, the model displayed strong discrimination of patients returning to the ED (AUROC=0.74) (figure 1).</p><p><strong>Conclusions: </strong>The random forest model demonstrated predictive discrimination of 90-day ED returns. Critical predictors such as patient distance from the hospital suggest considering geographical and socioeconomic factors in postdischarge care planning. Operational factors such as length of stay or complexity of the procedure also predicted return to the ED. The study lays the groundwork for future predictive models in clinical decision-making and healthcare resource utilisation.</p><p><strong>Level of evidence: </strong>Level III, retrospective model development and validation study.</p>","PeriodicalId":13682,"journal":{"name":"Injury Prevention","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143004966","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}