Constructing a fall risk prediction model for hospitalized patients using machine learning
Abstract Study objectives This study aimed to identify the risk factors associated with falls in hospitalized patients, develop a predictive risk model using machine learning algorithms, and evaluate the validity of the model’s predictions. Study design A cross-sectional design was employed using da...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Public Health |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12889-025-21284-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585373965877248 |
|---|---|
| author | Cheng-Wei Kang Zhao-Kui Yan Jia-Liang Tian Xiao-Bing Pu Li-Xue Wu |
| author_facet | Cheng-Wei Kang Zhao-Kui Yan Jia-Liang Tian Xiao-Bing Pu Li-Xue Wu |
| author_sort | Cheng-Wei Kang |
| collection | DOAJ |
| description | Abstract Study objectives This study aimed to identify the risk factors associated with falls in hospitalized patients, develop a predictive risk model using machine learning algorithms, and evaluate the validity of the model’s predictions. Study design A cross-sectional design was employed using data from the DRYAD public database. Research methods The study utilized data from the Fukushima Medical University Hospital Cohort Study, obtained from the DRYAD public database. 20% of the dataset was allocated as an independent test set, while the remaining 80% was utilized for training and validation. To address data imbalance in binary variables, the Synthetic Minority Oversampling Technique combined with Edited Nearest Neighbors (SMOTE-ENN) was applied. Univariate analysis and least absolute shrinkage and selection operator (LASSO) regression were used to analyze and screen variables. Predictive models were constructed by integrating key clinical features, and eight machine learning algorithms were evaluated to identify the most effective model. Additionally, SHAP (Shapley Additive Explanations) was used to interpret the predictive models and rank the importance of risk factors. Results The final model included the following variables: Adl_standing, Adl_evacuation, Age_group, Planned_surgery, Wheelchair, History_of_falls, Hypnotic_drugs, Psychotropic_drugs, and Remote_caring_system. Among the evaluated models, the Random Forest algorithm demonstrated superior performance, achieving an AUC of 0.814 (95% CI: 0.802–0.827) in the training set, 0.781 (95% CI: 0.740–0.821) in the validation set, and 0.795 (95% CI: 0.770–0.820) in the test set. Conclusion Machine learning algorithms, particularly Random Forest, are effective in predicting fall risk among hospitalized patients. These findings can significantly enhance fall prevention strategies within healthcare settings. |
| format | Article |
| id | doaj-art-a3e60d5efec347edbda300b08addaafe |
| institution | Kabale University |
| issn | 1471-2458 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Public Health |
| spelling | doaj-art-a3e60d5efec347edbda300b08addaafe2025-01-26T12:55:32ZengBMCBMC Public Health1471-24582025-01-0125111410.1186/s12889-025-21284-8Constructing a fall risk prediction model for hospitalized patients using machine learningCheng-Wei Kang0Zhao-Kui Yan1Jia-Liang Tian2Xiao-Bing Pu3Li-Xue Wu4Department of Orthopaedics, West China School of Public Health and West China Fourth Hospital, Sichuan UniversityDepartment of Orthopaedics, West China School of Public Health and West China Fourth Hospital, Sichuan UniversityDepartment of Orthopaedics, West China School of Public Health and West China Fourth Hospital, Sichuan UniversityDepartment of Orthopaedics, West China School of Public Health and West China Fourth Hospital, Sichuan UniversityDepartment of Pathology, West China School of Public Health and West China Fourth Hospital, Sichuan UniversityAbstract Study objectives This study aimed to identify the risk factors associated with falls in hospitalized patients, develop a predictive risk model using machine learning algorithms, and evaluate the validity of the model’s predictions. Study design A cross-sectional design was employed using data from the DRYAD public database. Research methods The study utilized data from the Fukushima Medical University Hospital Cohort Study, obtained from the DRYAD public database. 20% of the dataset was allocated as an independent test set, while the remaining 80% was utilized for training and validation. To address data imbalance in binary variables, the Synthetic Minority Oversampling Technique combined with Edited Nearest Neighbors (SMOTE-ENN) was applied. Univariate analysis and least absolute shrinkage and selection operator (LASSO) regression were used to analyze and screen variables. Predictive models were constructed by integrating key clinical features, and eight machine learning algorithms were evaluated to identify the most effective model. Additionally, SHAP (Shapley Additive Explanations) was used to interpret the predictive models and rank the importance of risk factors. Results The final model included the following variables: Adl_standing, Adl_evacuation, Age_group, Planned_surgery, Wheelchair, History_of_falls, Hypnotic_drugs, Psychotropic_drugs, and Remote_caring_system. Among the evaluated models, the Random Forest algorithm demonstrated superior performance, achieving an AUC of 0.814 (95% CI: 0.802–0.827) in the training set, 0.781 (95% CI: 0.740–0.821) in the validation set, and 0.795 (95% CI: 0.770–0.820) in the test set. Conclusion Machine learning algorithms, particularly Random Forest, are effective in predicting fall risk among hospitalized patients. These findings can significantly enhance fall prevention strategies within healthcare settings.https://doi.org/10.1186/s12889-025-21284-8Accidental fallsHospitalized patientsRisk factorsMachine learningPredictive modelingModel interpretation |
| spellingShingle | Cheng-Wei Kang Zhao-Kui Yan Jia-Liang Tian Xiao-Bing Pu Li-Xue Wu Constructing a fall risk prediction model for hospitalized patients using machine learning BMC Public Health Accidental falls Hospitalized patients Risk factors Machine learning Predictive modeling Model interpretation |
| title | Constructing a fall risk prediction model for hospitalized patients using machine learning |
| title_full | Constructing a fall risk prediction model for hospitalized patients using machine learning |
| title_fullStr | Constructing a fall risk prediction model for hospitalized patients using machine learning |
| title_full_unstemmed | Constructing a fall risk prediction model for hospitalized patients using machine learning |
| title_short | Constructing a fall risk prediction model for hospitalized patients using machine learning |
| title_sort | constructing a fall risk prediction model for hospitalized patients using machine learning |
| topic | Accidental falls Hospitalized patients Risk factors Machine learning Predictive modeling Model interpretation |
| url | https://doi.org/10.1186/s12889-025-21284-8 |
| work_keys_str_mv | AT chengweikang constructingafallriskpredictionmodelforhospitalizedpatientsusingmachinelearning AT zhaokuiyan constructingafallriskpredictionmodelforhospitalizedpatientsusingmachinelearning AT jialiangtian constructingafallriskpredictionmodelforhospitalizedpatientsusingmachinelearning AT xiaobingpu constructingafallriskpredictionmodelforhospitalizedpatientsusingmachinelearning AT lixuewu constructingafallriskpredictionmodelforhospitalizedpatientsusingmachinelearning |