Su Jiang,1,* Feng Zhao,2,* Yan Liang,2 Sulei Wang,2 Qiuyue Xu,3 Ruilin Wang,4 Tianchen Wu,2 Hui Yang3 

1Department of Rehabilitation Medicine, The Affiliated Taizhou People’s Hospital of Nanjing Medical University, Taizhou, 225300, People’s Republic of China; 2Department of Neurology, Nanjing Hospital of Chinese Medicine Affiliated to Nanjing University of Chinese Medicine, Nanjing, 210012, People’s Republic of China; 3School of Nursing, Nanjing University of Chinese Medicine, Nanjing, 210023, People’s Republic of China; 4College of Acupuncture, Moxibustion and Orthopedics, Hubei University of Chinese Medicine, Wuhan, 430000, People’s Republic of China

*These authors contributed equally to this work

Correspondence: Hui Yang, School of Nursing, Nanjing University of Chinese Medicine, No. 138 of Xianlin Road, Qixia District, Nanjing, 210023, People’s Republic of China, Tel +86 25 85811993, Email yanghuiyhcc@163.com Tianchen Wu, Department of Neurology, Nanjing Hospital of Chinese Medicine Affiliated to Nanjing University of Chinese Medicine, No. 157 Daming Road, Qinhuai District, Nanjing, 210012, People’s Republic of China, Tel +86 25 5227 6666, Email wutianchenwtc@126.com

Objective: This study aimed to develop and validate a dynamic online nomogram for predicting inpatient fall risk using data from a Dryad database cohort to strengthen fall prevention strategies and enhance patient safety in hospital settings.
Methods: We analyzed data from a cohort study conducted at Fukushima Medical University Hospital, with external validation using an independent dataset from Taizhou People’s Hospital (2019– 2023, n=2000). Following multiple imputation, 9470 cases were included and divided into training (n=6631) and validation (n=2839) sets. LASSO regression identified fall-associated factors, leading to development of two predictive models using binomial logistic regression. Model 1 incorporated all selected variables, while Model 2 emphasized clinically relevant factors. Discriminatory power, calibration, and clinical decision curve analysis were conducted for both models.
Results: LASSO regression identified 14 key variables, reduced to 11 in Model 1 and 6 clinically relevant variables in Model 2. Both models demonstrated comparable performance (Z=1.152, p=0.249), with Model 2 selected for clinical applicability. Bootstrap validation showed strong performance with AUC of 0.801 (training set) and 0.796 (validation set). Calibration was adequate (Hosmer-Lemeshow test p> 0.05). Decision curve analysis indicated potential intervention benefit for predicted probabilities of 1– 95.1% (training) and 1– 89.2% (validation). External validation in 2000 patients demonstrated robust generalizability (AUC=0.87, 95% CI: 0.80– 0.93).
Conclusion: We developed a predictive model for assessing fall risk among hospitalized patients. This model supports individualized patient evaluations, assists in identifying high-risk patients, and may contribute to reducing fall incidence in hospital settings.

Keywords: dynamic nomogram, fall risk assessment, hospital fall prevention, inpatient falls, patient safety, prediction model