Sang Hyun Seo

Sang Hyun Seo

Auto-generated profile, based on publicly available information

Sang Hyun Seo

Department of Radiology, Wonkwang University Hospital, Iksan, Korea

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 June 2021 in Gut and Liver
Verified
Journal Article
Open access
PDF file
HCHyung Ku Chon
Hyung Ku Chon
KCKeum Ha Choi
Keum Ha Choi
SSSang Hyun Seo
Sang Hyun Seo
TKTae Hyeon Kim
Tae Hyeon Kim
Hyung Ku Chon, Keum Ha Choi, Sang Hyun Seo, and Tae Hyeon Kim. Gut and Liver 2022;16:111-7. https://doi.org/10.5009/gnl210028

29 August 2023 in Journal of Medical Internet Research
Verified
Journal Article
Open access
SLSeungseok Lee
Seungseok Lee
WKWu Seong Kang
Wu Seong Kang
DKDO WAN KIM
DO WAN KIM
SSSang Hyun Seo
Sang Hyun Seo
JKJoongsuck Kim
Joongsuck Kim
Jinseok LeeJinseok Lee
Jinseok Lee
Background: Within the trauma system, the emergency department (ED) is the hospital’s first contact and is vital for allocating medical resources. However, there is generally limited information about patients that die in the ED. Objective: The aim of this study was to develop an artificial intelligence (AI) model to predict trauma mortality and analyze pertinent mortality factors for all patients visiting the ED. Methods: We used the Korean National Emergency Department Information System (NEDIS) data set (N=6,536,306), incorporating over 400 hospitals between 2016 and 2019. We included the International Classification of Disease 10th Revision (ICD-10) codes and chose the following input features to predict ED patient mortality: age, sex, intentionality, injury, emergent symptom, Alert/Verbal/Painful/Unresponsive (AVPU) scale, Korean Triage and Acuity Scale (KTAS), and vital signs. We compared three different feature set performances for AI input: all features (n=921), ICD-10 features (n=878), and features excluding ICD-10 codes (n=43). We devised various machine learning models with an ensemble approach via 5-fold cross-validation and compared the performance of each model with that of traditional prediction models. Lastly, we investigated explainable AI feature effects and deployed our final AI model on a public website, providing access to our mortality prediction results among patients visiting the ED. Results: Our proposed AI model with the all-feature set achieved the highest area under the receiver operating characteristic curve (AUROC) of 0.9974 (adaptive boosting [AdaBoost], AdaBoost + light gradient boosting machine [LightGBM]: Ensemble), outperforming other state-of-the-art machine learning and traditional prediction models, including extreme gradient boosting (AUROC=0.9972), LightGBM (AUROC=0.9973), ICD-based injury severity scores (AUC=0.9328 for the inclusive model and AUROC=0.9567 for the exclusive model), and KTAS (AUROC=0.9405). In addition, our proposed AI model outperformed a cutting-edge AI model designed for in-hospital mortality prediction (AUROC=0.7675) for all ED visitors. From the AI model, we also discovered that age and unresponsiveness (coma) were the top two mortality predictors among patients visiting the ED, followed by oxygen saturation, multiple rib fractures (ICD-10 code S224), painful response (stupor, semicoma), and lumbar vertebra fracture (ICD-10 code S320). Conclusions: Our proposed AI model exhibits remarkable accuracy in predicting ED mortality. Including the necessity for external validation, a large nationwide data set would provide a more accurate model and minimize overfitting. We anticipate that our AI-based risk calculator tool will substantially aid health care providers, particularly regarding triage and early diagnosis for trauma patients.

13 December 2022 in Journal of Medical Internet Research
Verified
Journal Article
Open access
SLSeungseok Lee
Seungseok Lee
WKWu Seong Kang
Wu Seong Kang
SSSanghyun Seo
Sanghyun Seo
DKDO WAN KIM
DO WAN KIM
HKHoon Ko
Hoon Ko
Jinseok LeeJinseok Lee
Jinseok Lee
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.

31 December 2023 in Journal of Trauma and Injury
Verified
Journal Article
Open access
CPChan Yong PARK
Chan Yong PARK
JLJoo Hyun Lee
Joo Hyun Lee
SSSang Hyun Seo
Sang Hyun Seo
CPChan Yong Park
Chan Yong Park
Mesenteric injury occurs rarely in cases associated with blunt abdominal trauma. Despite its low incidence, mesenteric injury can lead to fatal outcomes such as hypovolemic shock due to hemoperitoneum or sepsis due to intestinal ischemia, or perforation-related peritonitis. For mesenteric injuries, especially those involving massive bleeding, intestinal ischemia, and perforation, the standard treatment is surgery. However, in the case of operative management, it should be borne in mind that there is a possibility of complications and mortality during and after surgery. The usefulness of transcatheter arterial embolization (TAE) is well known in solid organs but is controversial for mesenteric injury. We present a 75-year-old man with mesenteric injury due to blunt abdominal trauma. Initial abdominal computed tomography showed no hemoperitoneum, but a mesenteric contusion and pseudoaneurysm with a diameter of 17 mm were observed near the origin of the superior mesenteric artery. Since there were no findings requiring emergency surgery such as free air or intestinal ischemia, it was decided to perform nonoperative management with TAE using microcoils in hybrid emergency room system. TAE was performed successfully, and there were no complications such as bleeding, bowel ischemia, or delayed bowel perforation. He was discharged on the 23rd day after admission with percutaneous catheter drainage for drainage of mesenteric hematoma. The authors believe that treatment with TAE for highly selected elderly patients with mesenteric injuries has the positive aspect of minimally invasive management, considering the burden of general anesthesia and the various avoidable intraoperative and postoperative complications.

1 January 2025 in Journal of the Korean Society of Radiology
Verified
Journal Article
Open access
PDF file
JIJee Yea Im
Jee Yea Im
SSSang Hyun Seo
Sang Hyun Seo
임지예, et al. J Korean Soc Radiol. 2025 Jan;86:e1. https://doi.org/10.3348/jksr.2024.0071

1 January 2023 in Journal of the Korean Society of Radiology
Verified
Journal Article
Open access
PDF file
HJHyun Seok Jung
Hyun Seok Jung
CJChang Ho Jeon
Chang Ho Jeon
SSSang Hyun Seo
Sang Hyun Seo
정현석, et al. J Korean Soc Radiol. 2023 Jul;84(4):824-834. https://doi.org/10.3348/jksr.2023.0046