Comparative Evaluation of Emergency Medical Service Trauma Patient Transportation Patterns Before and After Level 1 Regional Trauma Center Establishment: A Retrospective Single-Center Study

Lee, Hyeong Seok; Sung, Won Young; Lee, Jang Young; Lee, Won Suk; Seo, Sang Won

doi:10.20408/jti.2020.0021

Cited by 3 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning is generally considered a “black box,” hence the feature importance analysis based on a machine learning algorithm provides meaningful insight to clinicians and researchers. Finally, we aspire for the global application of our model and have produced a publicly available web application for hospitals to utilize for the benefit of the entire trauma system [ 28 , 29 ].…”

Section: Discussionmentioning

confidence: 99%

Model for Predicting In-Hospital Mortality of Physical Trauma Patients Using Artificial Intelligence Techniques: Nationwide Population-Based Study in Korea

Lee¹,

Kang²,

Seo³

et al. 2022

J Med Internet Res

View full text Add to dashboard Cite

Background Physical trauma–related mortality places a heavy burden on society. Estimating the mortality risk in physical trauma patients is crucial to enhance treatment efficiency and reduce this burden. The most popular and accurate model is the Injury Severity Score (ISS), which is based on the Abbreviated Injury Scale (AIS), an anatomical injury severity scoring system. However, the AIS requires specialists to code the injury scale by reviewing a patient's medical record; therefore, applying the model to every hospital is impossible. Objective We aimed to develop an artificial intelligence (AI) model to predict in-hospital mortality in physical trauma patients using the International Classification of Disease 10th Revision (ICD-10), triage scale, procedure codes, and other clinical features. Methods We used the Korean National Emergency Department Information System (NEDIS) data set (N=778,111) compiled from over 400 hospitals between 2016 and 2019. To predict in-hospital mortality, we used the following as input features: ICD-10, patient age, gender, intentionality, injury mechanism, and emergent symptom, Alert/Verbal/Painful/Unresponsive (AVPU) scale, Korean Triage and Acuity Scale (KTAS), and procedure codes. We proposed the ensemble of deep neural networks (EDNN) via 5-fold cross-validation and compared them with other state-of-the-art machine learning models, including traditional prediction models. We further investigated the effect of the features. Results Our proposed EDNN with all features provided the highest area under the receiver operating characteristic (AUROC) curve of 0.9507, outperforming other state-of-the-art models, including the following traditional prediction models: Adaptive Boosting (AdaBoost; AUROC of 0.9433), Extreme Gradient Boosting (XGBoost; AUROC of 0.9331), ICD-based ISS (AUROC of 0.8699 for an inclusive model and AUROC of 0.8224 for an exclusive model), and KTAS (AUROC of 0.1841). In addition, using all features yielded a higher AUROC than any other partial features, namely, EDNN with the features of ICD-10 only (AUROC of 0.8964) and EDNN with the features excluding ICD-10 (AUROC of 0.9383). Conclusions Our proposed EDNN with all features outperforms other state-of-the-art models, including the traditional diagnostic code-based prediction model and triage scale.

show abstract

Section: Discussionmentioning

confidence: 99%

Model for Predicting In-Hospital Mortality of Physical Trauma Patients Using Artificial Intelligence Techniques: Nationwide Population-Based Study in Korea

Lee¹,

Kang²,

Seo³

et al. 2022

J Med Internet Res

View full text Add to dashboard Cite

show abstract

Establishment of Emergency Teaching Model and Optimization of Discrete Dynamic Calculation in Complex Virtual Simulation Environment

Sun

Song

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Virtual surgery is a typical application of virtual reality technology in the medical field, which can help improve the success rate of surgery and reduce medical costs in various aspects such as medical training, surgery planning, and intraoperative navigation, and is becoming a hot research topic and a frontier subject in the medical field. The establishment of virtual surgery simulation system involves the intersection and penetration of various disciplines, and the research is difficult, and many functional modules are still not perfect. This study focuses on the key technologies in the virtual surgery simulation system, focusing on two core modules, the soft tissue modeling method and the collision detection algorithm, to improve the accuracy of the soft tissue model deformation under the condition of meeting the real-time system. The biomechanical properties of soft tissues are studied, the viscoelastic properties are analyzed, and the viscoelastic theory is used as the basis for soft tissue modeling; the geometric model is established by using a complementary method of surface model and tetrahedral mesh cells, with the surface model covering the outer surface for visual rendering and the tetrahedral mesh cells for skeleton support of the physical model, so that the model has a better visual effect and deformation effect, which enhances the model fidelity that is enhanced by the better visual effect and deformation effect; the soft tissue physical modeling method is summarized and summarized to lay the foundation for soft tissue model optimization. The experimental results show that the bilateral teleoperation system under analog control can give the operator a better haptic sensation (smaller value of input impedance felt by the operator when doing free motion from the robot) while ensuring good positional tracking and force tracking effects. This method solves the problems of collapse distortion and lack of viscoelastic properties of the traditional mass-spring model, and improves the accuracy of model deformation. Based on the improved algorithm, the viscoelastic hybrid filled sphere model of the liver organ is successfully established, which proves that the modeling method is feasible and effective.

show abstract

Development of artificial intelligence model for predicting in-hospital mortality derived from international classification of diseases, triage scales, procedure codes, and other clinical features in trauma patients: A nationwide population-based study (Preprint)

Lee¹,

Kang²,

Seo³

et al. 2022

Preprint

View full text Add to dashboard Cite

BACKGROUND Trauma-related mortality is a heavy burden. Estimating the mortality risk in trauma patients is crucial to enhance treatment efficiency and reduce the burden. The most popular and accurate model is the injury severity score based on the abbreviated injury scale (AIS), which is an anatomical injury severity scoring system. However, the AIS requires specialists to code the injury scale by reviewing a patient's medical record; therefore, applying the model to every hospital is impossible. OBJECTIVE We aimed to develop an artificial intelligence (AI) model to predict in-hospital mortality in trauma patients using the international classification of disease (ICD)-10, triage scale, procedure codes, and other clinical features. METHODS We used the Korean National Emergency Department Information System (NEDIS) dataset (n=778,111) from over 400 hospitals from 2016 to 2019. To predict in-hospital mortality, we used ICD-10; patient’s age; gender; intentionality; injury mechanism; emergent symptom; AVPU scale; Korean triage and acuity scale (KTAS); and procedure codes as input features. We proposed the ensemble of deep neural networks (EDNN) via five-fold cross-validation, and compared with other state-of-the-art machine learning models, including traditional prediction models. We further investigated the effect of features. RESULTS Our proposed EDNN with all features provided the highest AUROC of 0.9507, which outperformed other state-of-the-art models, including traditional prediction models: AdaBoost (AUROC of 0.9433), XGBoost (AUROC of 0.9331), ICD-based injury severity score (AUROC of 0.8699 an inclusive model and AUROC of 0.8224 an exclusive model), and KTAS (AUROC of 0.1841). In addition, using all features provided higher AUROC than any other partial features: EDNN with the features of ICD-10 only (AUROC of 0.8964) and EDNN with the features excluding ICD-10 (AUROC of 0.9383). CONCLUSIONS Our proposed EDNN with all features outperforms other state-of-the-art models, including the traditional diagnostic code-based prediction model and triage scale.

show abstract

Comparative Evaluation of Emergency Medical Service Trauma Patient Transportation Patterns Before and After Level 1 Regional Trauma Center Establishment: A Retrospective Single-Center Study

Cited by 3 publications

References 4 publications

Model for Predicting In-Hospital Mortality of Physical Trauma Patients Using Artificial Intelligence Techniques: Nationwide Population-Based Study in Korea

Model for Predicting In-Hospital Mortality of Physical Trauma Patients Using Artificial Intelligence Techniques: Nationwide Population-Based Study in Korea

Establishment of Emergency Teaching Model and Optimization of Discrete Dynamic Calculation in Complex Virtual Simulation Environment

Development of artificial intelligence model for predicting in-hospital mortality derived from international classification of diseases, triage scales, procedure codes, and other clinical features in trauma patients: A nationwide population-based study (Preprint)

Contact Info

Product

Resources

About