Objective This study aimed to clarify the relative prognostic value of each History, Electrocardiography, Age, Risk Factors, and Troponin (HEART) score component for major adverse cardiac events (MACE) within 3 months and validate the modified HEART (mHEART) score.
Methods This study evaluated the HEART score components for patients with chest symptoms visiting the emergency department from November 19, 2018 to November 19, 2019. All components were evaluated using logistic regression analysis and the scores for HEART, mHEART, and Thrombolysis in Myocardial Infarction (TIMI) were determined using the receiver operating characteristics curve.
Results The patients were divided into a derivation (809 patients) and a validation group (298 patients). In multivariate analysis, age did not show statistical significance in the detection of MACE within 3 months and the mHEART score was calculated after omitting the age component. The areas under the receiver operating characteristics curves for HEART, mHEART and TIMI scores in the prediction of MACE within 3 months were 0.88, 0.91, and 0.83, respectively, in the derivation group; and 0.88, 0.91, and 0.81, respectively, in the validation group. When the cutoff value for each scoring system was determined for the maintenance of a negative predictive value for a MACE rate >99%, the mHEART score showed the highest sensitivity, specificity, positive predictive value, and negative predictive value (97.4%, 54.2%, 23.7%, and 99.3%, respectively).
Conclusion Our study showed that the mHEART score better detects short-term MACE in high-risk patients and ensures the safe disposition of low-risk patients than the HEART and TIMI scores.
Citations
Citations to this article as recorded by
Reassessing risk stratification in the ED: HEART, HET, SVEAT, and the emerging role of HASI Hsih-Hao Huang, Chien-Chieh Hsieh, Fu-Shan Jaw, Che-Ming Yeh The American Journal of Emergency Medicine.2025; 96: 278. CrossRef
Chest Pain Risk Stratification in the Emergency Department: Current Perspectives Zeynep Yukselen, Vidit Majmundar, Mahati Dasari, Pramukh Arun Kumar, Yuvaraj Singh Open Access Emergency Medicine.2024; Volume 16: 29. CrossRef
Performance of the EDACS-ADP incorporating high-sensitivity troponin assay: Do components of major adverse cardiac events matter? Yedalm Yoo, Shin Ahn, Bora Chae, Won Young Kim World Journal of Emergency Medicine.2024; 15(3): 175. CrossRef
Adapting the HEART Pathway for Korean Patients: The Potential Impact on Chest Pain Management at Emergency Department Hack-Lyoung Kim Korean Circulation Journal.2023; 53(9): 645. CrossRef
Computed tomography coronary angiography after excluding myocardial infarction: high-sensitivity troponin versus risk score-guided approach Won Jae Yoo, Shin Ahn, Bora Chae, Won Young Kim World Journal of Emergency Medicine.2023; 14(6): 428. CrossRef
Erratum to “Validation and modification of HEART score components for patients with chest pain in the emergency department” Min Jae Kim, Sang Ook Ha, Young Sun Park, Jeong Hyeon Yi, Won Seok Yang, Jin Hyuck Kim Clinical and Experimental Emergency Medicine.2022; 9(4): 386. CrossRef
Objective Recent studies have suggested that deep-learning models can satisfactorily assist in fracture diagnosis. We aimed to evaluate the performance of two of such models in wrist fracture detection.
Methods We collected image data of patients who visited with wrist trauma at the emergency department. A dataset extracted from January 2018 to May 2020 was split into training (90%) and test (10%) datasets, and two types of convolutional neural networks (i.e., DenseNet-161 and ResNet-152) were trained to detect wrist fractures. Gradient-weighted class activation mapping was used to highlight the regions of radiograph scans that contributed to the decision of the model. Performance of the convolutional neural network models was evaluated using the area under the receiver operating characteristic curve.
Results For model training, we used 4,551 radiographs from 798 patients and 4,443 radiographs from 1,481 patients with and without fractures, respectively. The remaining 10% (300 radiographs from 100 patients with fractures and 690 radiographs from 230 patients without fractures) was used as a test dataset. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of DenseNet-161 and ResNet-152 in the test dataset were 90.3%, 90.3%, 80.3%, 95.6%, and 90.3% and 88.6%, 88.4%, 76.9%, 94.7%, and 88.5%, respectively. The area under the receiver operating characteristic curves of DenseNet-161 and ResNet-152 for wrist fracture detection were 0.962 and 0.947, respectively.
Conclusion We demonstrated that DenseNet-161 and ResNet-152 models could help detect wrist fractures in the emergency room with satisfactory performance.
Citations
Citations to this article as recorded by
Diagnostic performance of artificial intelligence for facial fracture detection: a systematic review Nozimjon Tuygunov, Shukhrat A. Boymuradov, Zohaib Khurshid, Siriporn Songsiripradubboon, Jamshid Abdulahtov, Ulugbek Khatamov Oral Radiology.2026; 42(2): 262. CrossRef
The Application of Agentic Artificial Intelligence in Orthopaedics Fabrizio Billi, Stefano A. Bini Journal of Bone and Joint Surgery.2026; 108(4): 278. CrossRef
Artificial intelligence in virtual fracture clinics: a systematic review of imaging and clinical-text tools Tenghis Sukhbaatar, Andrew Davies, Aran Koye, Mohamed Hashem, Sivan Sivaloganathan Journal of Orthopaedic Surgery and Research.2026;[Epub] CrossRef
Advancements in smart healthcare in emergency trauma care: from intelligent triage to prognostic prediction Fanyi Cheng, Tao Xu, Junwei Mao, Zhiping Li, Yajun Wang Frontiers in Public Health.2026;[Epub] CrossRef
Meta-analysis and Systematic Review of Diagnostic Performance of Machine Learning Algorithms on Skeletally Mature Wrist Fractures Reem Sarsour, Sultan Baz, Christopher E. Collins, Angelene Won, Peter Aldo Giammanco, James Hagerty, Jose Jesurajan, Brian A. Schneiderman, Evelyn Ouro-Rodrigues, Joseph G. Elsissy HAND.2026;[Epub] CrossRef
Artificial intelligence-guided distal radius fracture detection on plain radiographs in comparison with human raters Nikolai Ramadanov, Patric John, Robert Hable, Andreas Georg Schreyer, Simon Shabo, Robert Prill, Mikhail Salzmann Journal of Orthopaedic Surgery and Research.2025;[Epub] CrossRef
Integrating Artificial Intelligence and Virtual Reality in Orthopedic Surgery: A Comprehensive Review Robert Koucheki, Johnathan R. Lex, Michael Brock, Danny P. Goel HSS Journal®: The Musculoskeletal Journal of Hospital for Special Surgery.2025; 21(3): 289. CrossRef
AI-driven Technologies for Wrist Fracture Prediction: A Narrative Review of Emerging Approaches Stefania Briano, Maria Cesarina May, Giacomo Demontis, Giulia Pachera, Vittoria Mazzola, Federico Vitali, Alessandra Galuppi, Emanuela Dapelo, Andrea Zanirato, Matteo Formica Journal of Wrist Surgery.2025; 14(06): 500. CrossRef
Artificial Intelligence in Emergency Trauma Care: A Preliminary Scoping Review Christian Angelo Ventura, Edward Denton, Jessica David Medical Devices: Evidence and Research.2024; Volume 17: 191. CrossRef
Deep learning performance compared to healthcare experts in detecting wrist fractures from radiographs: A systematic review and meta-analysis V. Hansen, J. Jensen, M.W. Kusk, O. Gerke, H.B. Tromborg, S. Lysdahlgaard European Journal of Radiology.2024; 174: 111399. CrossRef
Artificial intelligence diagnostic accuracy in fracture detection from plain radiographs and comparing it with clinicians: a systematic review and meta-analysis A. Nowroozi, M.A. Salehi, P. Shobeiri, S. Agahi, S. Momtazmanesh, P. Kaviani, M.K. Kalra Clinical Radiology.2024; 79(8): 579. CrossRef
Learning from the few: Fine-grained approach to pediatric wrist pathology recognition on a limited dataset Ammar Ahmed, Ali Shariq Imran, Zenun Kastrati, Sher Muhammad Daudpota, Mohib Ullah, Waheed Noor Computers in Biology and Medicine.2024; 181: 109044. CrossRef
Mapping the Impact of Artificial Intelligence on Trauma Research via Scientometric Analysis Chun Wang, Mengzhou Zhang, Dong Zhao Journal of Forensic Science and Medicine.2024; 10(2): 133. CrossRef
Artificial intelligence in musculoskeletal imaging: realistic clinical applications in the next decade Huibert C. Ruitenbeek, Edwin H. G. Oei, Jacob J. Visser, Richard Kijowski Skeletal Radiology.2024; 53(9): 1849. CrossRef
Accuracy of wrist fracture detection on radiographs by artificial intelligence compared to human clinicians. A systematic review and meta-analysis Kary Suen, Richard Zhang, Numan Kutaiba European Journal of Radiology.2024; 178: 111593. CrossRef
AI for detection, classification and prediction of loss of alignment of distal radius fractures; a systematic review Koen D. Oude Nijhuis, Lente H. M. Dankelman, Jort P. Wiersma, Britt Barvelink, Frank F.A. IJpma, Michael H. J. Verhofstad, Job N. Doornberg, Joost W. Colaris, Mathieu M.E. Wijffels European Journal of Trauma and Emergency Surgery.2024; 50(6): 2819. CrossRef
The Accuracy of Artificial Intelligence Models in Hand/Wrist Fracture and Dislocation Diagnosis Chloe R. Wong, Alice Zhu, Heather L. Baltzer JBJS Reviews.2024;[Epub] CrossRef
Artificial intelligence in fracture detection on radiographs: a literature review Antonio Lo Mastro, Enrico Grassi, Daniela Berritto, Anna Russo, Alfonso Reginelli, Egidio Guerra, Francesca Grassi, Francesco Boccia Japanese Journal of Radiology.2024;[Epub] CrossRef
Application and Prospects of Deep Learning Technology in Fracture Diagnosis Jia-yao Zhang, Jia-ming Yang, Xin-meng Wang, Hong-lin Wang, Hong Zhou, Zi-neng Yan, Yi Xie, Peng-ran Liu, Zhi-wei Hao, Zhe-wei Ye Current Medical Science.2024; 44(6): 1132. CrossRef
MPFracNet: A Deep Learning Algorithm for Metacarpophalangeal Fracture Detection with Varied Difficulties Geng Qin, Ping Luo, Kaiyuan Li, Yufeng Sun, Shiwei Wang, Xiaoting Li, Shuang Liu, Linyan Xue Computers, Materials & Continua.2023; 75(1): 999. CrossRef
Development and validation of a deep learning-based model to distinguish acetabular fractures on pelvic anteroposterior radiographs Pengyu Ye, Sihe Li, Zhongzheng Wang, Siyu Tian, Yi Luo, Zhanyong Wu, Yan Zhuang, Yingze Zhang, Marcin Grzegorzek, Zhiyong Hou Frontiers in Physiology.2023;[Epub] CrossRef
Utilizing heat maps as explainable artificial intelligence for detecting abnormalities on wrist and elbow radiographs S. Lysdahlgaard Radiography.2023; 29(6): 1132. CrossRef
Automatic Segmentation for Favourable Delineation of Ten Wrist Bones on Wrist Radiographs Using Convolutional Neural Network Bo-kyeong Kang, Yelin Han, Jaehoon Oh, Jongwoo Lim, Jongbin Ryu, Myeong Seong Yoon, Juncheol Lee, Soorack Ryu Journal of Personalized Medicine.2022; 12(5): 776. CrossRef
Diagnostic accuracy and potential covariates of artificial intelligence for diagnosing orthopedic fractures: a systematic literature review and meta-analysis Xiang Zhang, Yi Yang, Yi-Wei Shen, Ke-Rui Zhang, Ze-kun Jiang, Li-Tai Ma, Chen Ding, Bei-Yu Wang, Yang Meng, Hao Liu European Radiology.2022; 32(10): 7196. CrossRef
Joonghee Kim, Joon-Won Kang, Kyuseok Kim, Sang Il Choi, Eun Ju Chun, Yeo Goon Kim, Won Young Kim, Dong Woo Seo, Jonghwan Shin, Huijai Lee, Kwang-Nam Jin, Soyeon Ahn, Seung Sik Hwang, Kwang Pyo Kim, Ru-Bi Jeong, Sang Ook Ha, Byungho Choi, Chang-Hwan Yoon, Jung-Won Suh, Hack-Lyoung Kim, Ju Kyoung Kim, Sujin Jang, Ji Seon Seo
Clin Exp Emerg Med 2017;4(4):208-213. Published online December 30, 2017
Objective Chest pain is one of the most common complaints in the emergency department (ED). Cardiac computed tomography angiography (CCTA) is a frequently used tool for the early triage of patients with low- to intermediate-risk acute chest pain. We present a study protocol for a multicenter prospective randomized controlled clinical trial testing the hypothesis that a low-dose CCTA protocol using prospective electrocardiogram (ECG)-triggering and limited-scan range can provide sufficient diagnostic safety for early triage of patients with acute chest pain.
Methods The trial will include 681 younger adult (aged 20 to 55) patients visiting EDs of three academic hospitals for acute chest pain or equivalent symptoms who require further evaluation to rule out acute coronary syndrome. Participants will be randomly allocated to either low-dose or conventional CCTA protocol at a 2:1 ratio. The low-dose group will undergo CCTA with prospective ECG-triggering and restricted scan range from sub-carina to heart base. The conventional protocol group will undergo CCTA with retrospective ECG-gating covering the entire chest. Patient disposition is determined based on computed tomography findings and clinical progression and all patients are followed for a month. The primary objective is to prove that the chance of experiencing any hard event within 30 days after a negative low-dose CCTA is less than 1%. The secondary objectives are comparisons of the amount of radiation exposure, ED length of stay and overall cost.
Results and Conclusion Our low-dose protocol is readily applicable to current multi-detector computed tomography devices. If this study proves its safety and efficacy, dose-reduction without purchasing of expensive newer devices would be possible.
The typical presentation of intussusception includes intermittent severe abdominal pain, vomiting, rectal bleeding, and the presence of an abdominal mass. We present a case of intussusception after abdominal blunt trauma along with a literature review. A 4-year-old girl was admitted to the emergency department after a bicycle accident. She complained of progressively worsening abdominal pain, but there was no vomiting, fever, bloody stool, or abdominal mass. She was finally diagnosed with traumatic intussusception by ultrasonography and treated with air reduction. Because the typical symptoms are unusual in traumatic intussusception, close attention must be paid to avoid a delayed diagnosis.
Citations
Citations to this article as recorded by
Expectant management of a pediatric patient with traumatic intussusception: Case report with literature review Nouf Albalawi, Mohammed Wasili, Ahmed Alageel, Dina Sami, Khaled Aldraihem, Ethar Shabana Radiology Case Reports.2026; 21(2): 733. CrossRef
Multiple intussusceptions after blunt abdominal trauma in a 9-year-old boy: A case report and literature review Shin Ae Lee, Joong Kee Youn, Ye Rim Chang Trauma Case Reports.2022; 38: 100630. CrossRef
Objective Airway management in patients with suspected cervical spine injury is classified as a “difficult airway.” The best device for managing difficult airways is not known. Therefore, we conducted an intubation study simulating patients with cervical spine injury using three devices: a conventional Macintosh laryngoscope, a video laryngoscope (GlideScope), and a fiberoptic bronchoscope (MAF-TM). Success rates, intubation time, and complication rates were compared.
Methods Nine physician experts in airway management participated in this study. Cervical immobilization was used to simulate a difficult airway. Each participant performed intubation using airway devices in a randomly chosen order. We measured the time to vocal cord visualization, time to endotracheal tube insertion, and total tracheal intubation time. Success rates and dental injury rates were compared between devices.
Results Total tracheal intubation time using the Macintosh laryngoscope, GlideScope, and fiberoptic bronchoscope was 13.3 (range, 11.1 to 20.1), 14.9 (range, 12.7 to 22.3), and 19.4 seconds (range, 14.1 to 32.5), respectively. Total tracheal intubation time differed significantly among the devices (P=0.009). Success rates for the Macintosh laryngoscope, GlideScope, and fiberoptic bronchoscope were 98%, 96%, and 100%, respectively, and dental injury rates were 5%, 19%, and 0%, respectively.
Conclusion The fiberoptic bronchoscope required longer intubation times than the other devices. However, this device had the best success rate with the least incidence of dental injury.
Citations
Citations to this article as recorded by
Laryngoscopes for difficult airway scenarios: a comparison of the available devices Lukasz Szarpak Expert Review of Medical Devices.2018; 15(9): 631. CrossRef
C-MAC compared with direct laryngoscopy for intubation in patients with cervical spine immobilization: A manikin trial Jacek Smereka, Jerzy R. Ladny, Amanda Naylor, Kurt Ruetzler, Lukasz Szarpak The American Journal of Emergency Medicine.2017; 35(8): 1142. CrossRef
Comparison of the ETView Single Lumen and Macintosh laryngoscopes for endotracheal intubation in an airway manikin with immobilized cervical spine by novice paramedics Pawel Gawlowski, Jacek Smereka, Marcin Madziala, Barak Cohen, Kurt Ruetzler, Lukasz Szarpak Medicine.2017; 96(16): e5873. CrossRef
Porównanie laryngoskopii bezpośredniej i wideolaryngoskopii podczas symulowanego unieruchomienia odcinka szyjnego kręgosłupa u dziecka Marcin Madziala, Marek Dabrowski, Agata Dabrowska, Wojciech Wieczorek, Zenon Truszewski, Lukasz Szarpak Pediatria Polska.2017; 92(4): 406. CrossRef
First
Prev
