Jihoon Seo

Jihoon Seo

Auto-generated profile, based on publicly available information

Jihoon Seo

Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Yongin, Korea

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
13 February 2025 in Clinical Psychopharmacology and Neuroscience
Verified
Journal Article
Open access
PDF file
HKHeeyeon Kim
Heeyeon Kim
KJKyungun Jhung
Kyungun Jhung
DYDukyong Yoon
Dukyong Yoon
JSJihoon Seo
Jihoon Seo
HCHee Young Cho
Hee Young Cho
JPJin Young Park
Jin Young Park
Heeyeon Kim, Kyungun Jhung, Dukyong Yoon, Jihoon Seo, Hee Young Cho, Jin Young Park. Clin Psychopharmacol Neurosci 2025;23:368-78. https://doi.org/10.9758/cpn.24.1256

1 October 2019 in International Journal of Machine Learning and Computing
Verified
Journal Article
Open access
JSJihoon Seo
Jihoon Seo
KJKilhong Joo
Kilhong Joo

15 March 2024 in medRxiv
Verified
Preprint
Open access
PDF file
DKDong Won Kim
Dong Won Kim
JSJihoon Seo
Jihoon Seo
SKSujin Kwon
Sujin Kwon
CPChan Min Park
Chan Min Park
CHChangho Han
Changho Han
Kyoung Min KimKyoung Min Kim
Kyoung Min Kim
Hospital falls are the most prevalent adverse event in healthcare, posing significant risks to patient health outcomes and institutional care quality. The effectiveness of several fall prediction models currently in use is limited by various clinical factors. This study explored the efficacy of merging real-time location system (RTLS) data with clinical information to enhance the accuracy of in-hospital fall predictions. The model performances were compared based on the clinical data, RTLS data, and a hybrid approach using various evaluation metrics. The RTLS and integrated clinical data were obtained from 22,201 patients between March 2020 and June 2022. From the initial cohort, 118 patients with falls and 443 patients without falls were included. Predictive models were developed using the XGBoost algorithm across three distinct frameworks: clinical model, RTLS model, and clinical + RTLS model. The model performance was evaluated using metrics, such as AUROC, AUPRC, accuracy, PPV, sensitivity, specificity, and F1 score. Shapley additive explanation values were used to enhance the model interpretability. The clinical model yielded an AUROC of 0.813 and AUPRC of 0.407. The RTLS model demonstrated superior fall prediction capabilities, with an AUROC of 0.842 and AUPRC of 0.480. The clinical + RTLS model excelled further, achieving an AUROC of 0.853 and AUPRC of 0.497. Feature importance analysis revealed that movement patterns of patients on the last day of their stay were significantly associated with falls, together with elevated RDW levels, sedative administration, age. This study underscored the advantages of combining RTLS data with clinical information to predict in-hospital falls more accurately. This innovative technology-driven approach may enhance early fall risk detection during hospitalization, potentially preventing falls, improving patient safety, and contributing to more efficient healthcare delivery.

21 October 2018 in International Journal of Engineering & Technology
Verified
Journal Article
Open access
PDF file
JSJi-Hoon Seo
Ji-Hoon Seo
NPNam-Hun Park
Nam-Hun Park
KJKil-Hong Joo
Kil-Hong Joo
The Currently, along with the advent of the web 2.0 era, due to the continuous expansion of social media service infrastructures, the shares of conventional public opinion evaluation functions have been gradually shifting from the existing mass media to social media. This phe-nomenon is attributable to the two-way communication and convenience unique to social media and social media are now in charge of an axis of public opinion evaluation standards. In particular, since diverse interests conflict in education policies and countless conflicts of opinions occur in the process of setting up policy agendas, in establishing education policies, accurately analyzing reputations among the public, who are the targets of education policies, in order to set up effective policy agendas, is the most important issue. Therefore, in this study, the resultant values of huge unstructured data on the positive and negative reputations of past policy agendas related to the mandatory software education that has been organized as a regular curriculum of middle/high schools from 2018 in Korea, which have been addressed by the Ministry of Education, the Ministry of Science, ICT and Future Planning, and the Korea Foundation for the Advancement of Science and Creativity, felt and judged by the general public on social media such as blogs and Twitter and on online media including portal news were visualized through opinion mining analysis techniques to derive more effective software education related policy agendas. In addition, based on the foregoing, a Korean style software education system that fits circumstances was constructed and the system is expected to become an important measure that provides guidelines for setting mid/long-term road maps for the fostering of creative and convergent talented persons equipped with international competitiveness and software education in Korea.