Objective Fall from height (FFH) is a major public health problem that can result in severe injury, disability, and death. This study investigated how the characteristics of jumpers and fallers differ.
Methods This was a retrospective study of FFH patients enrolled in an Emergency Department-based Injury In-depth Surveillance (EDIIS) registry between 2011 and 2018. Depending on whether the injury was intentional, FFH patients who had fallen from a height of at least 1 m were divided into two groups: jumpers and fallers. Patient characteristics, organ damage, and death were compared between the two groups, and factors that significantly affected death were identified using multivariable logistic analysis.
Results Among 39,419 patients, 1,982 (5.0%) were jumpers. Of the jumpers, 977 (49.3%) were male, while 30,643 (81.9%) of fallers were male. The jumper group had the highest number of individuals in their 20s, with the number decreasing as age increased. In contrast, the number of individuals in the faller group rose until reaching their 50s, after which it declined. More thoracoabdominal, spinal, and brain injuries were found in jumpers. The in-hospital mortality of jumpers and fallers was 832 (42.0%) and 1,268 (3.4%), respectively. Intentionality was a predictor of in-hospital mortality, along with sex, age, and fall height, with an odds ratio of 7.895 (95% confidence interval, 6.746–9.240).
Conclusion Jumpers and fallers have different epidemiological characteristics, and jumpers experienced a higher degree of injury and mortality than fallers. Differentiated prevention and treatment strategies are needed for jumpers and fallers to reduce mortality in FFH patients.
Citations
Citations to this article as recorded by
Criteria for Methods of Radio Frequency Scanning at Telecommunication Towers in Malaysia Based on Delphi-AHP Analysis Rosdin Abdul Kahar, Mohd Nizam Ab Rahman, Nizaroyani Saibani, Mohd Fais Mansor, Mirza Basyir Rodhuan Eng.2026; 7(1): 35. CrossRef
Soyun Shim, Jae Yong Yu, Seyong Jekal, Yee Jun Song, Ki Tae Moon, Ju Hee Lee, Kyung Mi Yeom, Sook Hyun Park, In Sook Cho, Mi Ra Song, Sejin Heo, Jeong Hee Hong
Clin Exp Emerg Med 2022;9(4):345-353. Published online September 21, 2022
Objective Falls are one of the most frequently occurring adverse events among hospitalized patients. The Morse Fall Scale, which has been widely used for fall risk assessment, has the two limitations of low specificity and difficulty in practical implementation. The aim of this study was to develop and validate an interpretable machine learning model for prediction of falls to be integrated in an electronic medical record (EMR) system.
Methods This was a retrospective study involving a tertiary teaching hospital in Seoul, Korea. Based on the literature, 83 known predictors were grouped into seven categories. Interpretable fall event prediction models were developed using multiple machine learning models including gradient boosting and Shapley values.
Results Overall, 191,778 cases with 272 fall events (0.1%) were included in the analysis. With the validation cohort of 2020, the area under the receiver operating curve (AUROC) of the gradient boosting model was 0.817 (95% confidence interval [CI], 0.720–0.904), better performance than random forest (AUROC, 0.801; 95% CI, 0.708–0.890), logistic regression (AUROC, 0.802; 95% CI, 0.721–0.878), artificial neural net (AUROC, 0.736; 95% CI, 0.650–0.821), and conventional Morse fall score (AUROC, 0.652; 95% CI, 0.570–0.715). The model’s interpretability was enhanced at both the population and patient levels. The algorithm was later integrated into the current EMR system.
Conclusion We developed an interpretable machine learning prediction model for inpatient fall events using EMR integration formats.
Citations
Citations to this article as recorded by
Development and Validation of Machine Learning Models for Predicting Falls Among Hospitalized Older Adults: Retrospective Cross-Sectional Study Xiyao Yang, Juan Ren, Dan Su, Manzhen Bao, Miao Zhang, Xiaoming Chen, Yanhua Li, Zonggui Wang, Xiujing Dai, Zengzeng Wei, Shuiyu Zhang, Yuxin Zhang, Juan Li, Xiaolin Li, Junjin Xu, Nan Mo JMIR Aging.2026; 9: e80602. CrossRef
Cognitive readiness of nurses regarding artificial intelligence predictions: understanding through the dual lens of verbatim and gist knowledge Insook Cho, Soyun Shim, Hyunchul Park JAMIA Open.2026;[Epub] CrossRef
Prediction of inpatient falls and key predictors using machine learning applied to electronic health records: a retrospective cohort study in a tertiary hospital in Türkiye Veysel Karani Baris, Burcu Hudaverdi BMJ Open.2026; 16(5): e113384. CrossRef
Relative contributions of modifiable risk factors to injurious fall prediction in older adults: A predictive modelling study Tewodros Yosef, Julie A Pasco, Monica C Tembo, Kara B Anderson, Kara L Holloway-Kew Archives of Gerontology and Geriatrics.2026; 150: 106333. CrossRef
Pressure Injury Risk Assessment in Nursing Practice: A Head-to-Head Comparison of the Braden Scale and Machine Learning Models Fredy Barriga-Gallegos, Gonzalo Ríos-Vásquez, Paulo Figueroa-Torrez, Hanns de la Fuente-Mella, Catherine Almarza Garrido, Naldy Febré Vergara Journal of Clinical Medicine.2026; 15(12): 4683. CrossRef
Machine-learning-based Fall-prediction Model for Inpatients in Military Hospitals YunJung Choi, WooJin Lee, Juyeon Baek CIN: Computers, Informatics, Nursing.2026;[Epub] CrossRef
Artificial intelligence in healthcare: transforming patient safety with intelligent systems—A systematic review Francesco De Micco, Gianmarco Di Palma, Davide Ferorelli, Anna De Benedictis, Luca Tomassini, Vittoradolfo Tambone, Mariano Cingolani, Roberto Scendoni Frontiers in Medicine.2025;[Epub] CrossRef
Machine learning-based prediction models for falls in hospitalized patients: A systematic review and meta-analysis Ronggui Xie, Le Shao, Jingru Pei, Yuyan Shi, Mingming Tang, Xueqin Sun, Guiyu Deng, Hong Zhao Geriatric Nursing.2025; 63: 487. CrossRef
Digital Healthcare Approaches for Fall Detection and Prediction in Older Adults: A Systematic Review of Evidence from Hospital and Long-Term Care Settings Aijin Lee, Haneul Lee, Seon-Heui Lee Medicina.2025; 61(11): 1926. CrossRef
An inpatient fall risk assessment tool: Application of machine learning models on intrinsic and extrinsic risk factors Sonia Jahangiri, Masoud Abdollahi, Rasika Patil, Ehsan Rashedi, Nasibeh Azadeh-Fard Machine Learning with Applications.2024; 15: 100519. CrossRef
The application of explainable artificial intelligence (XAI) in electronic health record research: A scoping review Jessica Caterson, Alexandra Lewin, Elizabeth Williamson DIGITAL HEALTH.2024;[Epub] CrossRef
Objective Suicide is a major issue in South Korea, and falling is a common method of suicide. Further, accidental falls are a common cause of death. However, whether suicidal falls differ from accidental falls is inconclusive. This study aimed to compare suicidal and accidental falls to identify risk factors for mortality.
Methods From March 2010 to December 2016, patients admitted to our hospital because of falls were reviewed retrospectively. Characteristics and outcomes were compared between suicide and accident groups. Injury distribution was compared using the Injury Severity Score and Abbreviated Injury Scales. Multivariate analysis was performed to identify risk factors, including suicide intent, for mortality.
Results Of 242 patients, 42 were included in the suicide group and 200 were included in the accident group. The suicide group showed higher fall heights and injuries of greater severity. The accident group was younger and included a higher number of men. The suicide group showed a higher mortality (23.8% vs. 6.5%, P=0.001) and a higher proportion of injuries in the lower extremities or abdomen. In the multivariate analysis, Glasgow Coma Scale score (0.575 [0.433–0.764], P<0.001), body mass index (1.638 [1.194–2.247], P=0.002), suicide intent (9.789 [1.026–93.404], P=0.047) and Injury Severity Score (1.091 [1.000–1.190], P=0.049) were identified as risk factors for mortality.
Conclusion Suicidal falls were associated with poorer outcomes and a greater tendency to land feet first relative to accidental falls. Suicide intent was a risk factor for mortality.
Citations
Citations to this article as recorded by
Differentiating injury patterns and outcomes in accidental, suicidal and occupational falls from heights Christoph Beyersdorf, Bjoern Hussmann, Niklas Wergen, Rolf Lefering, Erik Schiffner, Uwe Maus, Carina Jaekel, TraumaRegister DGU European Journal of Trauma and Emergency Surgery.2026;[Epub] CrossRef
Vertebral injury patterns in suicidal vs homicidal falls: A forensic and physical therapy collaborative framework Asma Sattar, Mamona Ansari, Maryam Rafique, Hafiz Muhammad Abbas Malik, Akbar Ali Forensic Insights and Health Sciences Bulletin.2026; : 21. CrossRef
Fracture Patterns in Fatal Free Falls: A Systematic Review of Intrinsic and Extrinsic Risk Factors and the Role of Postmortem CT Filip Woliński, Kacper Kraśnik, Łukasz Bryliński, Jolanta Sado, Justyna Sagan, Katarzyna Brylińska, Grzegorz Teresiński, Tomasz Cywka, Robert Karpiński, Jacek Baj Journal of Clinical Medicine.2025; 14(17): 6305. CrossRef
Forensic Differentiation of Accidental and Intentional Falls from Height: A Systematic Review of Injury Patterns, Severity Scores, and Classification Indicators Abdulkreem Abdullah Al-Juhani, Naif Abdulaziz Aljohani, Abdulaziz A. Binshalhoub, Rodan Mahmoud Desoky, Rimaz M. Alotaibe The Saudi Journal of Forensic Medicine and Sciences.2025; 5(1): 6. CrossRef
Do the management and functional outcomes of the surgically treated spinal fractures change in suicidal jumpers? Başar Burak Çakmur, Altuğ Duramaz, Kadriye Nur Çakmur, Altan Duramaz European Spine Journal.2024; 33(10): 3695. CrossRef
Assessing Fall Mortality by Field-Relevant Categories at an Urban Level I Trauma Center Christopher Gross, Josué Menard, Jennifer Mull, Yohan Diaz-Zuniga, David Skarupa, Marie Crandall Journal of Surgical Research.2024; 300: 279. CrossRef
Factors associated with the injury severity of falls from a similar height and features of the injury site: a retrospective study Dae Hyun Kim, Jae-Hyug Woo, Yang Bin Jeon, Jin-Seong Cho, Jae Ho Jang, Jea Yeon Choi, Woo Sung Choi Journal of Trauma and Injury.2023; 36(3): 187. CrossRef
Characteristics of fall-from-height patients: a retrospective comparison of jumpers and fallers using a multi-institutional registry Jinhae Jun, Ji Hwan Lee, Juhee Han, Sun Hyu Kim, Sunpyo Kim, Gyu Chong Cho, Eun Jung Park, Duk Hee Lee, Ju Young Hong, Min Joung Kim Clinical and Experimental Emergency Medicine.2023; 11(1): 79. CrossRef
Suicidological analysis of Moscow and Saint Petersburg in the context of the pandemic Vsevolod A. Rozanov, Natalia V. Semenova, Alexandr Ja. Vuks, Victoria V. Freize, Larisa V. Malyshko, Georgy P. Kostyuk, Vladimir D. Isakov, Orazmurad D. Yagmurov, Alexandr G. Sofronov, Nikolay G. Neznanov Ekologiya cheloveka (Human Ecology).2022; 29(4): 241. CrossRef
Objective Alcohol consumption is associated with an increased risk of injuries. However, its effects on injury severity and mortality remain unclear. Specifically, the effects of alcohol intake on the severity of slip injuries have not been thoroughly investigated. Therefore, our study aimed to investigate the effects of alcohol intake on injury patterns and severity in patients experiencing slip injuries.
Methods Emergency department surveillance data collected from 2011 to 2016 were analyzed for this study. Among patients aged 15 and older who were admitted for slip injuries, we compared the type and severity of injuries between the alcohol-intake group and the no-alcohol-intake group. Injury severity was classified as non-severe and severe based on the excess mortality ratio-adjusted injury severity score.
Results In total, 227,548 (alcohol-intake, n=48,581; no-alcohol-intake, n=178,967) patients were included. After adjusting for age, time of injury, use of public ambulance, and season, multivariate logistic regression analysis showed that injuries were more likely to be severe in the alcohol-intake group than in the no-alcohol-intake group (odds ratio, 1.60; 95% confidence interval, 1.47–1.75). In addition, male gender and alcohol consumption had a greater synergistic effect on injury severity than the mere sum of each effect of these factors (odds ratio, 2.65; 95% confidence interval, 2.53–2.78).
Conclusion Assessment of the patients influenced by alcohol was a challenge in the emergency department due to altered mental status. We suggest a considerate approach in testing and assessing male patients who slipped after alcohol-intake in the emergency department.
Citations
Citations to this article as recorded by
Repeated Blunt-Force Trauma in an Elderly Male: An Atypical Intimate Partner Homicide Case Involving a Female Partner Gebremariam Tewelemedhin Gebremariam, Charles Karangwa, Innocent Nkurunziza, David Ishimwe Forensic Sciences.2026; 6(2): 46. CrossRef
First
Prev
