Archives of Academic Emergency Medicine最新文献

{"title":"The Role of Artificial Intelligence in Diagnosing Pulmonary Embolism: A Systematic Review and Meta-analysis.","authors":"Alireza Farzaei, Fateme Hajzeinolabedini, Babak Sharif Kashani, Mohamad Sadegh Keshmiri, Alireza Khodayari Javazm, Yasaman Farzaei, Mohamad Fereidooni, Behrouz Emamjomeh, Amir Nezami-Asl","doi":"10.22037/aaem.v13i1.2720","DOIUrl":"10.22037/aaem.v13i1.2720","url":null,"abstract":"<p><strong>Introduction: </strong>Missed or delayed diagnosis of pulmonary embolism (PE) is associated with increased morbidity, mortality, and longer hospitalizations. This study aimed to evaluate the diagnostic accuracy of Artificial Intelligence (AI) models in detecting PE across imaging.</p><p><strong>Methods: </strong>We systematically searched PubMed/MEDLINE, Scopus, Embase and Web of Science from inception to 1 January 2025 without language or regional limits. After removing duplicate results, the remaining records were screened through titles/abstracts, and two reviewers independently assessed full texts. Risk of bias was evaluated in duplicate with the QUADAS-2 tool. Pooled sensitivity, specificity, positive and negative likelihood ratios, diagnostic odds ratio and area under the ROC curve were calculated with random-effects models in STATA 17. Heterogeneity was quantified with Cochran's Q and I², while we explored its sources using subgroup analyses (for categorical moderators) and meta-regression (for continuous moderators). Publication bias was assessed with Deeks' funnel plot and trim-and-fill, and we examined robustness through leave-one-out sensitivity analyses.</p><p><strong>Results: </strong>A total of 1,432 records were identified through database searches, with 654 duplicates removed. After screening titles and abstracts of 787 articles, 256 full-text articles were assessed for eligibility, and 28 studies met the inclusion criteria. Internal validation phases included 43,330 participants (4,866 PE-positive, 38,463 PE-negative), while external validation phases comprised 3,588 participants (1,699 PE-positive, 1,889 PE-negative). In the internal validation phase, the pooled sensitivity and specificity of AI in PE diagnosis across imaging were 0.91 (95% confidence interval (CI): 0.88-0.95; I²=9%) and 0.94 (95% CI: 0.86-0.98; I²=99.78%), respectively. The positive likelihood ratio (PLR) was 16.08, and the negative likelihood ratio (NLR) was 0.09, both statistically significant (P < 0.001). The pooled diagnostic odds ratio (DOR) was 163.55 (95% CI: 71.30-375.14, I<sup>2</sup>: 96.1), and the area under the curve (AUC) was 0.95 (95% CI: 0.93 to 0.97), indicating excellent accuracy. In external validation, the pooled sensitivity and specificity were slightly lower at 0.89 (95% CI: 0.79-0.95; I²=95.60%) and 0.88 (95% CI: 0.80-0.93; I²=91.48%), respectively. The DOR was 59.65 (95% CI: 23.53 to 151.17, I<sup>2</sup>: 89.6) and AUC was 0.94 (95% CI: 0.92 to 0.96, I<sup>2</sup>: 89.6). There was no significant publication bias detected.</p><p><strong>Conclusion: </strong>AI models achieved high diagnostic accuracy in detecting PE through imaging. However, this performance tends to decrease from internal to external validation, highlighting limitations in generalizability. Additionally, substantial heterogeneity was observed across studies, as indicated by high I² values, which should be considered when interpreting the pooled estimates.</p","PeriodicalId":8146,"journal":{"name":"Archives of Academic Emergency Medicine","volume":"13 1","pages":"e86"},"PeriodicalIF":2.0,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12883040/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146148949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting the Risk of Opioid-induced Respiratory Depression Using ChatGPT-4o and Machine Learning Techniques.","authors":"Mohammad Meshkini, Sayed Masoud Hosseini, Peyman Erfan Talab Evini, Mitra Rahimi, Babak Mostafazadeh, Pooya Eini, Nahal Babaeian Amini, Amirhossein Faghihi, Farhad Esmailsorkh, Sajede Karimi, Mohammad Asadi, Hadi Jalilvand, Nasibeh Rady Raz, Iman Alidadyani, Hadi Jafari, Faraz Zandiyeh, Kiandokht Khorshidi, Maryam Ahadi, Shayesteh Ashrafi-Esfahani, Shahin Shadnia","doi":"10.22037/aaem.v13i1.2832","DOIUrl":"10.22037/aaem.v13i1.2832","url":null,"abstract":"<p><strong>Introduction: </strong>Opioid-induced respiratory depression is a life-threatening complication of opioid overdose. This study aimed to develop a model for predicting the risk of respiratory depression following opioid overdose using ChatGPT-4o.</p><p><strong>Methods: </strong>A retrospective cross-sectional study was conducted on 2,005 patients admitted following opioid overdose at Loghman Hakim Hospital, Tehran, Iran, from February 2021 to February 2024. Demographic data, clinical presentations, interventions, and outcomes of patients were extracted from electronic medical records and a predictive model was developed using a no-code methodology with the assistance of ChatGPT-4o.</p><p><strong>Results: </strong>2,005 patients with the mean age of 32.97 ± 14.86 (Range: 1-100) years were studied (74.5% male). Respiratory depression was observed in 18% of patients upon admission. Naloxone was administered to 37.6% of patients, with higher usage in those requiring intubation. Key predictors included low oxygen saturation (SpO₂), low respiratory rate (RR), and increased heart rate (HR). The predictive model achieved an accuracy of 94.4% (95% confidence interval (CI): 87.0-96.3), a recall of 81.0% (95% CI: 78.0-84.0) for respiratory depression, and an area under the curve (AUC) of 0.98 (95% CI: 0.95-0.99).</p><p><strong>Conclusion: </strong>The study highlights critical clinical predictors of respiratory depression risk in opioid overdose patients and demonstrates the potential of machine learning models in enhancing early detection and intervention.</p>","PeriodicalId":8146,"journal":{"name":"Archives of Academic Emergency Medicine","volume":"13 1","pages":"e85"},"PeriodicalIF":2.0,"publicationDate":"2025-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12883042/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146148897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accuracy and Clinical Utility of Clinical Predictive Models for Identifying Dizziness with Central Causes; A Retrospective Diagnostic Accuracy Study.","authors":"Shunsuke Soma, Katsunori Ito, Tsukasa Kamitani","doi":"10.22037/aaem.v13i1.2787","DOIUrl":"10.22037/aaem.v13i1.2787","url":null,"abstract":"<p><strong>Introduction: </strong>Although several clinical prediction models (CPMs) have been developed for identifying acute dizziness with central causes, their application in clinical practice remains unclear. This study aimed to evaluate the accuracy and clinical utility of four CPMs in identifying dizziness with central lesions.</p><p><strong>Methods: </strong>This single-center, retrospective, diagnostic accuracy study was conducted at the ED of Aomori Hospital, Japan, from April to March 2023. The area under the receiver operating characteristic curve (AUROC) of four risk stratification models (ABCD2, TriAGe+, PCI, and Sudbury) in predicting dizziness with central causes were evaluated considering the brain imaging (computed tomography (CT) scan and magnetic resonance imaging (MRI)) findings, interpreted by a neurologist or neurosurgeon, as the gold standard. Calibration was evaluated visually using calibration plots. Additionally, analyses of efficacy, safety, and clinical utility using a decision curve were conducted.</p><p><strong>Results: </strong>Of the 3,606 patients identified, 2,958 with the mean age of 65.3 ± 16.4 (range: 15-97.) years were included in the final analysis (64.7% female). 155 (5.2 %) were diagnosed with central lesions. The AUROCs were 0.67 (95% confidence interval (CI): 0.62-0.71) for ABCD2, 0.80 (95% CI: 0.76-0.84) for TriAGe+, 0.82 (0.78-0.86) for PCI, and 0.85 (95% CI: 0.82-0.88) for Sudbury. TriAGe+, PCI, and Sudbury demonstrated good calibration. Among these, the Sudbury model demonstrated the highest diagnostic efficiency, was the only model to meet safety criteria, and provided the highest net benefit in decision curve analysis, particularly at lower predicted prevalence thresholds.</p><p><strong>Conclusion: </strong>The TriAGe+, PCI, and Sudbury models demonstrated strong discriminatory performance and reliable calibration when applied during ED admission at a community hospital. Particularly, the Sudbury model may reduce false-negative outcomes for central lesions, thereby potentially minimizing the need for unnecessary neuroimaging in patients identified as low-risk.</p>","PeriodicalId":8146,"journal":{"name":"Archives of Academic Emergency Medicine","volume":"13 1","pages":"e84"},"PeriodicalIF":2.0,"publicationDate":"2025-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12883870/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146155871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Identifying the Key Factors Influencing Risk Perception Among Healthcare Workers in the Context of Disasters; A Systematic Review.","authors":"Raziyeh Bakhshi Giv, Mohammadreza Amiresmaili, Hojjat Farahmandnia, Ali Sadatmoosavi, Seyed Mobin Moradi, Seyyed Mohammad Reza Hosseini, Samaneh Alinejad","doi":"10.22037/aaem.v13i1.2909","DOIUrl":"10.22037/aaem.v13i1.2909","url":null,"abstract":"<p><strong>Introduction: </strong>Risk perception is a cognitive, multidimensional process through which individuals identify and assess potential threats. This study aimed to systematically review the recent research to identify the key factors influencing the risk perception within healthcare workers operating in critical and disaster scenarios.</p><p><strong>Methods: </strong>This study was conducted as a systematic review in accordance with PRISMA guidelines. A search was performed for articles published between January 2014 and July 2025 in the PubMed/MEDLINE, Scopus, Web of Science, and Google Scholar databases. Of the 2,154 initial articles, 10 eligible studies were included in the analysis following screening and quality assessment. Quantitative, qualitative, and mixed-methods studies addressing factors influencing healthcare workers' risk perception during disasters were selected, and the data were coded and categorized using thematic analysis.</p><p><strong>Results: </strong>The analysis of the 10 selected studies identified a central theme titled \"Factors Influencing Risk Perception,\" which was further divided into five key domains: 1) Demographic and individual factors, 2) Experience and exposure to risk, 3) Knowledge resources and information capital, 4) Cognitive-emotional attitudes and beliefs, and 5) Protective behaviors and measures.</p><p><strong>Conclusion: </strong>This review demonstrates that healthcare workers' risk perception during disasters is a multifaceted phenomenon shaped by the interaction of individual, experiential, knowledge-based, emotional, and behavioral factors. Understanding these dimensions is crucial for explaining responses and designing interventions to enhance resilience and preparedness among healthcare workers. Based on the conceptual framework, it is recommended that educational programs and organizational policies consider demographic differences, experiences, and the psychosocial needs of staff.</p>","PeriodicalId":8146,"journal":{"name":"Archives of Academic Emergency Medicine","volume":"13 1","pages":"e83"},"PeriodicalIF":2.0,"publicationDate":"2025-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12883041/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146148977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of 10- and 30-minute Hepatic Ischemia on Total Protein, Albumin, Globulin Fractions, and LDH of Male Albino Rates; An Experimental Study.","authors":"Shalala Garib Ismayilova, Zumrud Amirgulu Abaszade, AygunVugar Kazimli, Nigar Taryel Guliyeva, Hijran Faramaz Khidirova, Maryam Rauf Abbasova, Kamil Sahib Alkishiev","doi":"10.22037/aaem.v13i1.2887","DOIUrl":"https://doi.org/10.22037/aaem.v13i1.2887","url":null,"abstract":"<p><strong>Introduction: </strong>Hepatic ischemia results in the dysrhythmia of the intrahepatic hemodynamics. This study aimed to evaluate the changes occurring in the protein metabolism and serum lactate dehydrogenase (LDH) level after hepatic ischemia and assess the effects of antioxidant therapy in this regard.</p><p><strong>Methods: </strong>In this experimental study (with manipulation of ischemia time and antioxidant therapy) 120 male rats were divided into groups of acute hepatic ischemia; acute hepatic ischemia +antioxidant; chronic ischemia using tetra chloromethane; and sham or intact control to evaluate the changes occurring in the protein metabolism (total protein, albumin, and globulin fractions) and LDH level 3, 7, 15, and 30 days after 10- or 30-minute hepatic ischemia induction and effects of antioxidant therapy in this regard.</p><p><strong>Results: </strong>In the 10-minute ischemia group, total protein decreased to 34.69 ± 2.49 g/L at 3 days, while albumin fell to 12.36 ± 0.85 g/L. The inflammatory response was evident through elevated α1-globulin (9.02 ± 1.50 g/L) and LDH (3476.37 ± 324.89 U/L) at day 3, which gradually normalized by day 30. In the 30-minute ischemia group, the effects were more pronounced, with total protein reaching 54.57 ± 1.93 g/L and albumin 34.33 ± 2.20 g/L at day 3, alongside marked increases in α1-globulin (10.35 ± 1.30 g/L), α2-globulin (3.19 ± 0.43 g/L), β-globulin (8.09 ± 2.27 g/L), γ-globulin (5.64 ± 1.08 g/L), and LDH (2301.44 ± 80.07 U/L). After 10- and 30-minute ischemia, α1, α2, β, and γ globulins as well as LDH level were significantly increased at the post-ischemic recovery. The group that received antioxidant showed significantly lower increases in the globulin fractions and LDH level at 3, 7, 15, and 30 days after the procedure.</p><p><strong>Conclusion: </strong>Based on the findings, 10- and 30-minute acute hepatic ischemia had a profound negative effect on protein metabolism, which was reflected in decreased total protein and albumin, and increased globulin fractions and LDH, indicating the presence of continuous hepatocellular injury and a significant inflammatory reaction. Riditox antioxidant therapy had a consistent, albeit incomplete, hepatoprotective effect, which attenuated these biochemical imbalances.</p>","PeriodicalId":8146,"journal":{"name":"Archives of Academic Emergency Medicine","volume":"13 1","pages":"e82"},"PeriodicalIF":2.0,"publicationDate":"2025-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12928732/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147281974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Challenging Dilemma regarding Cardiac Advanced Life Support in Patients with Minimally Invasive Cardiac Surgery: A Letter to Editor.","authors":"Mahmood Hosseinzadeh Maleki, Mohsen Yaghubi","doi":"10.22037/aaem.v14i1.2876","DOIUrl":"10.22037/aaem.v14i1.2876","url":null,"abstract":"<p><p>Cardiac Advanced Life Support (CALS) differs from conventional Advanced Cardiac Life Support (ACLS) in utilizing targeted resuscitation protocols designed explicitly for post-cardiac surgery patients. The hallmark of CALS is the performance of prompt re-sternotomy and internal cardiac massage within 5 minutes of cardiac arrest if the patient is unresponsive to external chest compressions and rapid defibrillation. The standardized algorithms for ACLS, fundamental to managing cardiac arrest, present a significant and potentially dangerous dilemma when applied to patients who have undergone minimally invasive cardiac surgery (MICS). While MICS offers benefits like reduced trauma and faster recovery, it creates a unique physiological landscape that conflicts with conventional resuscitation. This letter highlights the urgent need to re-evaluate the ACLS protocol for this growing patient population. We advocate for the immediate development of a specialized MICS-specific resuscitation guideline that moves beyond a one-size-fits-all approach to in-hospital cardiac arrest.</p>","PeriodicalId":8146,"journal":{"name":"Archives of Academic Emergency Medicine","volume":"14 1","pages":"e5"},"PeriodicalIF":2.0,"publicationDate":"2025-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12883173/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146148931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neutrophil to Lymphocyte Ratio as a Predictive Factor of Unfavorable Outcomes in Traumatic Spinal Cord Injury: A Systematic Review and Meta-analysis.","authors":"Amirreza Peyrovinasab, Hamed Zarei, Mahrokh Janmohamadi, Mehra Fekri, Farzin Tahmasbi Arashlow, Alireza Ghorbani, Pantea Gharin, Pardis Soroush, Saeed Safari, Mahmoud Yousefifard","doi":"10.22037/aaem.v14i1.2766","DOIUrl":"10.22037/aaem.v14i1.2766","url":null,"abstract":"<p><strong>Introduction: </strong>There are a number of biomarkers connected to inflammation that affect spinal cord injury (SCI) outcomes. This systematic review and meta-analysis was conducted to evaluate the prognostic value of the Neutrophil-to-lymphocyte ratio (NLR) in patients diagnosed with traumatic SCI.</p><p><strong>Methods: </strong>Observational studies evaluating the association between baseline NLR and severity or neurological improvement in traumatic SCI patients were systematically identified using Medline, Embase, Scopus, and Web of Science databases on March 4, 2025. The risk of bias among the included studies was assessed using the National Heart, Lung, and Blood Institute (NHLBI) tool. A random-effects model was employed for meta-analyses. Effects sizes were reported as odds ratios (ORs) or standardized mean difference (SMD), along with their 95% confidence intervals (CIs).</p><p><strong>Results: </strong>Six retrospective cohort studies involving 1,564 participants were included, with five eligible for meta-analysis. Blood samples were collected within 72 hours of admission. Meta-analysis showed that patients without neurological improvement had significantly higher NLR values (SMD: 0.98; 95% CI: 0.08-1.87; I² = 94.36%). Additionally, elevated NLR was independently associated with no neurological improvement (adjusted OR: 1.12; 95% CI: 1.06-1.17; I² = 0.04%). Qualitative synthesis further indicated that higher NLR values were consistently associated with greater injury severity in acute traumatic SCI.</p><p><strong>Conclusion: </strong>Elevated NLR is associated with greater injury severity and poorer neurological recovery in patients with acute traumatic SCI. These findings suggest that NLR may serve as a useful early prognostic biomarker in the clinical assessment of mentioned patients.</p>","PeriodicalId":8146,"journal":{"name":"Archives of Academic Emergency Medicine","volume":"14 1","pages":"e4"},"PeriodicalIF":2.0,"publicationDate":"2025-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12884672/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146155888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Effects of Using Prehospital Calcium Gluconate During Cardiopulmonary Resuscitation: A Retrospective Study.","authors":"Thongpitak Huabbangyang, Agasak Silakoon, Suchanaree Soimongkolchai, Punyawee Dangsawasd, Siravit Phankhot, Piyada Yomklang, Chunlanee Sangketchon","doi":"10.22037/aaem.v13i1.2870","DOIUrl":"10.22037/aaem.v13i1.2870","url":null,"abstract":"<p><strong>Introduction: </strong>Calcium gluconate (CG) administration during cardiopulmonary resuscitation (CPR) has not been recommended in routine clinical practice. This study examined the impact of prehospital CG administration on outcomes of out-of-hospital cardiac arrest (OHCA) cases.</p><p><strong>Methods: </strong>This retrospective cohort study collected data on adult patients aged >18 years who experienced non-traumatic OHCA and were transported by the emergency medical service (EMS) to the emergency department. Data on return of spontaneous circulation (ROSC) at the scene, survival to hospital admission, and survival to hospital discharge were obtained from EMS reports and electronic medical records and compared between OHCA cases who received or didn't receive CG.</p><p><strong>Results: </strong>In total, 215 adult patients with non-traumatic OHCA were enrolled in this study. Among them, 107 received CG and 108 didn't receive. In particular, CG administration was associated with a lower rate of ROSC at the scene compared with cases without its administration (8.6% lower). The likelihood of ROSC at the scene was 0.75 times that of those who did not receive CG. CG administration was associated with a lower survival to hospital admission (16.48% lower). The likelihood of survival to hospital admission was 0.42 times that of patients who did not receive CG. In addition, survival to hospital discharge was 7.37% lower in patients who received CG, and the likelihood of survival to hospital discharge was 0.21 times that of those who did not receive CG.</p><p><strong>Conclusions: </strong>Prehospital CG administration by the EMS team did not improve ROSC in the scene, survival to hospital admission, or survival to hospital discharge. The findings highlight the need for selective use of calcium based on guideline-recommended indications rather than empirical administration.</p>","PeriodicalId":8146,"journal":{"name":"Archives of Academic Emergency Medicine","volume":"13 1","pages":"e81"},"PeriodicalIF":2.0,"publicationDate":"2025-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12883869/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146155910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning-Based Prognostic Prediction Models in Calcium Channel Blockers Poisoning.","authors":"Babak Mostafazadeh, Sayed Masoud Hosseini, Shahin Shadnia, Mahdi Mehmandoost, Mahsa Taremi, Seyed Ali Mohtarami, Peyman Erfan Talab Evini, Mitra Rahimi, Pooya Eini, Amirreza Taherkhani, Nahal Babaeian Amini, Elmira Heidarli, Mohammad Meshkini, Leena Amine, Hafedh Thabet","doi":"10.22037/aaem.v13i1.2804","DOIUrl":"10.22037/aaem.v13i1.2804","url":null,"abstract":"<p><strong>Introduction: </strong>Calcium channel blocker (CCB) poisoning is a critical toxicological emergency that can result in severe complications, particularly cardiovascular effects. This study aimed to evaluate the accuracy of Machine learning (ML) models in predicting the outcomes of CCB poisoning.</p><p><strong>Methods: </strong>This retrospective cross-sectional study analyzed the medical records of patients diagnosed with CCB poisoning at Loghman Hakim Hospital between 2019 and 2024. The accuracy of machine learning (ML) models in predicting the outcomes of CCB poisoning and identifying its predictive factors was evaluated. Various ML models, including XGBoost, CatBoost, Random Forest, and AdaBoost, were trained on clinical and laboratory data. Then, feature selection was performed to identify the most relevant variables. The hold-out set was randomly selected to avoid selection bias. Model performance was assessed using accuracy, precision, recall, F1-score, and macro-averaged area under the receiver operating characteristic (ROC) curve (AUC).</p><p><strong>Results: </strong>274 CCB poisoning cases with the mean age of 31.99± 17.47 (range: 1.5 to 89) years were evaluated (70.4% female). Feature selection identified 18 key prognostic factors, including body temperature, whole bowel irrigation, need for cardiology consultation, arterial oxygen saturation, Glasgow coma scale (GCS)-eye response, electrocardiography (ECG) findings, serum level of alkaline phosphatase (ALP), pH-venous blood gas (VBG), HCO₃-VBG, serum level of lactate dehydrogenase (LDH), blood sugar, pulse rate, fraction of inspired oxygen (FiO2), time elapsed from ingestion to admission, troponin, serum level of alanine aminotransferase (ALT), serum level of creatinine, and serum level of potassium. Among the ML models, XGBoost and CatBoost demonstrated the highest predictive performance, with macro-averaged AUC values of 0.9899 (95%confidence interval (CI): 0.98-0.99) and 0.9983 (95%CI: 0.997-0.999), respectively. These models outperformed traditional statistical approaches, providing enhanced risk stratification for patients with CCB poisoning.</p><p><strong>Conclusion: </strong>This study highlights the potential of ML-based models for predicting outcomes in CCB poisoning, offering a data-driven framework for early risk stratification. The superior performance of XGBoost and CatBoost suggests their clinical applicability. Future research should focus on external validation in multi-center settings and real-time integration into clinical decision-making systems.</p>","PeriodicalId":8146,"journal":{"name":"Archives of Academic Emergency Medicine","volume":"13 1","pages":"e79"},"PeriodicalIF":2.0,"publicationDate":"2025-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12702512/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145762018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mechanical versus Manual Chest Compressions for Cardiopulmonary Resuscitation in Emergency Department: A Comparative Study.","authors":"Ali Vafaei, Parvin Kashani, Amir Heidari, Abbas Hasanzadeh","doi":"10.22037/aaem.v13i1.2849","DOIUrl":"10.22037/aaem.v13i1.2849","url":null,"abstract":"<p><strong>Introduction: </strong>Mechanical chest compression devices provide consistent depth and reduced pauses during cardiopulmonary resuscitation (CPR), but their clinical impact on routine practice in emergency department (ED) remains uncertain. This study aimed to compare the outcomes of mechanical versus manual compressions among adults with in-hospital cardiac arrest managed in ED.</p><p><strong>Methods: </strong>A single-center, comparative study of consecutive adult cardiac arrests in the ED (n = 372) was carried out. Patients were allocated by time period to either manual CPR (n = 195) during the retrospective phase (September 2024 to January 2025) or mechanical CPR (n = 177) with LUCAS-3 during the prospective phase (January to June 2025). The primary outcome was return of spontaneous circulation (ROSC). Secondary outcomes were survival at 6 hours and 24 hours post-arrest. Baseline differences were summarized with standardized mean differences, and survival was described with Kaplan-Meier curves (0-24 h). Logistic regression estimated odds ratios (ORs) for ROSC and 6-hour survival.</p><p><strong>Results: </strong>Mechanical and manual chest compression groups comprised 177 and 195 patients, respectively. Unadjusted outcomes favored mechanical CPR. ROSC occurred in 54 (30.5%) versus 32 (16.4%), with an absolute risk difference of 14.1% and Six-hour survival was 25 (14.1%) versus 5 (2.6%). After adjustment, mechanical CPR remained associated with higher odds of ROSC (OR = 2.44, 95% confidence interval (CI): 1.18-4.42) and 6-hour survival (OR = 6.71, 95% CI: 2.94-18.94). By 24 hours, no patient survived in the mechanical group, whereas one patient (0.5) survived in the manual group (P>0.05). Kaplan-Meier curves showed early separation that narrowed by 24 hours.</p><p><strong>Conclusion: </strong>It seems that mechanical chest compression during CPR is associated with increased ROSC and better early survival, compared to manual compression. Due to the limited sample size, non-randomized design with time-based allocation, single-center setting, potential residual confounding, and absence of neurologic outcomes, these results should be interpreted with caution.</p>","PeriodicalId":8146,"journal":{"name":"Archives of Academic Emergency Medicine","volume":"14 1","pages":"e3"},"PeriodicalIF":2.0,"publicationDate":"2025-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12883177/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146148961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}