JiHoon Park
Research Subjects
JiHoon Park has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Dong-Suk Lee
College of Nursing, Kangwon National University, Chuncheon 24341, Korea
1 shared publication - Gyeong-Nam Lee
Department of Nursing Science, Hallym Polytechnic University, Chuncheon 24210, Republic of Korea
1 shared publication - Hee-Won Park
Department of Rehabilitation Medicine, Kangwon National University, Chuncheon 24341, Republic of Korea
1 shared publication - MoonKi Choi
College of Nursing, Kangwon National University, Chuncheon 24341, Republic of Korea
1 shared publication - Seung-Ok Choi
Department of Medical Innovation, Kangwon National University Hospital, Chuncheon 24289, Republic of Korea
1 shared publication - Young-Ju Kim
Department of Statistics, Kangwon National University, Chuncheon, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 14 September 2026
- Published by MDPI AG in Healthcare
- Vol. 14 (18) , 2999
Evaluation of Artificial Intelligence-Assisted Video Monitoring for Inpatient Fall Prevention: A Retrospective Matched Cohort Study
Background/Objectives: Effective strategies to prevent inpatient falls are essential for reducing fall-related injuries, mortality, length of hospital stay, and healthcare costs. Although advanced technologies have increasingly been adopted for fall prevention, evidence regarding effectiveness in real-world clinical settings remains limited. This study evaluated the effect of implementing an artificial intelligence-assisted video monitoring system on the incidence of inpatient falls and fall-related injuries. Methods: This retrospective matched cohort study used electronic medical record data from a tertiary hospital in C city, South Korea. The system was implemented in January 2022. Patients admitted between 2020 and 2021 comprised the non-exposed group, whereas those admitted between 2023 and 2024 comprised the exposed group. Nearest neighbor propensity score matching based on age, sex, the number of diagnoses, and the number of ward days was performed to create comparable groups. Fall incidence rates per 1000 patient-days were calculated, and Firth’s penalized likelihood logistic regression and Cox proportional hazards regression with robust errors were conducted. Results: Propensity score matching yielded a 1:1 matched sample of 3002 cases per group. The fall incidence rate was 1.017 per 1000 patient-days in the exposed group, lower than 1.286 in the non-exposed group. However, penalized likelihood logistic regression and Cox proportional hazards regression revealed no statistically significant effect of artificial intelligence-assisted video monitoring on fall reduction. Conclusions: Artificial intelligence-assisted video monitoring was associated with a lower fall incidence, but no statistically significant effect was identified. These findings highlight the potential and limitations of artificial intelligence-assisted video monitoring for inpatient fall prevention and underscore the need for further research to enhance its clinical utility.
- 14 September 2026
- Published by MDPI AG in Healthcare
- Vol. 14 (18) , 2999
Open AccessEvaluation of Artificial Intelligence-Assisted Video Monitoring for Inpatient Fall Prevention: A Retrospective Matched Cohort Study
Background/Objectives: Effective strategies to prevent inpatient falls are essential for reducing fall-related injuries, mortality, length of hospital stay, and healthcare costs. Although advanced technologies have increasingly been adopted for fall prevention, evidence regarding effectiveness in real-world clinical settings remains limited. This study evaluated the effect of implementing an artificial intelligence-assisted video monitoring system on the incidence of inpatient falls and fall-related injuries. Methods: This retrospective matched cohort study used electronic medical record data from a tertiary hospital in C city, South Korea. The system was implemented in January 2022. Patients admitted between 2020 and 2021 comprised the non-exposed group, whereas those admitted between 2023 and 2024 comprised the exposed group. Nearest neighbor propensity score matching based on age, sex, the number of diagnoses, and the number of ward days was performed to create comparable groups. Fall incidence rates per 1000 patient-days were calculated, and Firth’s penalized likelihood logistic regression and Cox proportional hazards regression with robust errors were conducted. Results: Propensity score matching yielded a 1:1 matched sample of 3002 cases per group. The fall incidence rate was 1.017 per 1000 patient-days in the exposed group, lower than 1.286 in the non-exposed group. However, penalized likelihood logistic regression and Cox proportional hazards regression revealed no statistically significant effect of artificial intelligence-assisted video monitoring on fall reduction. Conclusions: Artificial intelligence-assisted video monitoring was associated with a lower fall incidence, but no statistically significant effect was identified. These findings highlight the potential and limitations of artificial intelligence-assisted video monitoring for inpatient fall prevention and underscore the need for further research to enhance its clinical utility.