AI-driven fall risk prediction in inpatients: Development, validation, and comparative evaluation
Background & Aim: Falls among hospitalized patients pose severe consequences, necessitating accurate risk prediction. Traditional assessment tools rely on cross-sectional data and lack dynamic analysis, limiting clinical applicability. This study developed an AI-based fall risk prediction model...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tehran University of Medical Sciences
2025-03-01
|
| Series: | Nursing Practice Today |
| Subjects: | |
| Online Access: | https://npt.tums.ac.ir/index.php/npt/article/view/3374 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850202876024979456 |
|---|---|
| author | Chia-Lun Lo Chia-En Liu Hsiao Yun Chang Chiu-Hsiang Wu |
| author_facet | Chia-Lun Lo Chia-En Liu Hsiao Yun Chang Chiu-Hsiang Wu |
| author_sort | Chia-Lun Lo |
| collection | DOAJ |
| description |
Background & Aim: Falls among hospitalized patients pose severe consequences, necessitating accurate risk prediction. Traditional assessment tools rely on cross-sectional data and lack dynamic analysis, limiting clinical applicability. This study developed an AI-based fall risk prediction model using supervised learning techniques to enhance predictive accuracy and clinical integration.
Methods & Materials: This study was conducted at a medical center in Taiwan, excluding pediatric patients due to non-disease-related fall factors. Fall cases were obtained from hospital records, and non-fall cases were stratified based on age and gender to create a balanced 1:1 dataset.
A total of 52 predictive variables were identified and refined to 39 through expert review. The AI model was compared with MORSE, STRATIFY, and HII-FRM using supervised learning with 10-fold cross-validation. Performance was evaluated based on accuracy, sensitivity, and specificity.
Results: The results demonstrated that the AI-based model significantly outperformed traditional fall risk assessment tools in accuracy, sensitivity, and specificity. More importantly, the model’s superior predictive power allows for real-time risk assessment and seamless integration into clinical decision support systems. This integration can enable timely interventions, optimize patient safety protocols, and ultimately reduce fall-related incidents in hospitalized settings.
Conclusion: By automating risk assessment, the AI model can alleviate the workload of healthcare professionals, reducing the time required for manual evaluations and minimizing subjective biases in clinical decision-making. This not only enhances operational efficiency but also allows nursing staff to allocate more time to direct patient care. These findings underscore the transformative potential of AI-driven approaches in healthcare, improving patient safety through data-driven.
|
| format | Article |
| id | doaj-art-2ca3e331cb7a4dc688fb51a928acebf7 |
| institution | OA Journals |
| issn | 2383-1154 2383-1162 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Tehran University of Medical Sciences |
| record_format | Article |
| series | Nursing Practice Today |
| spelling | doaj-art-2ca3e331cb7a4dc688fb51a928acebf72025-08-20T02:11:38ZengTehran University of Medical SciencesNursing Practice Today2383-11542383-11622025-03-0112210.18502/npt.v12i2.18337AI-driven fall risk prediction in inpatients: Development, validation, and comparative evaluationChia-Lun Lo0Chia-En Liu1Hsiao Yun Chang2Chiu-Hsiang Wu3Department of Health-Business Administration, Fooyin University, Kaohsiung, TaiwanDepartment of Nursing, St Joseph’s Hospital, Yunlin, TaiwanDepartment of Nursing, Chang Gung University of Science and Technology, Taoyuan, Taiwan AND Division of Endocrinology and Metabolism, Department of Internal Medicine, Chang Gung Memorial Hospital, Taoyuan, TaiwanDepartment of Nursing, Kaohsiung Municipal Kai-Syuan Psychiatric Hospital, Kaohsiung, Taiwan Background & Aim: Falls among hospitalized patients pose severe consequences, necessitating accurate risk prediction. Traditional assessment tools rely on cross-sectional data and lack dynamic analysis, limiting clinical applicability. This study developed an AI-based fall risk prediction model using supervised learning techniques to enhance predictive accuracy and clinical integration. Methods & Materials: This study was conducted at a medical center in Taiwan, excluding pediatric patients due to non-disease-related fall factors. Fall cases were obtained from hospital records, and non-fall cases were stratified based on age and gender to create a balanced 1:1 dataset. A total of 52 predictive variables were identified and refined to 39 through expert review. The AI model was compared with MORSE, STRATIFY, and HII-FRM using supervised learning with 10-fold cross-validation. Performance was evaluated based on accuracy, sensitivity, and specificity. Results: The results demonstrated that the AI-based model significantly outperformed traditional fall risk assessment tools in accuracy, sensitivity, and specificity. More importantly, the model’s superior predictive power allows for real-time risk assessment and seamless integration into clinical decision support systems. This integration can enable timely interventions, optimize patient safety protocols, and ultimately reduce fall-related incidents in hospitalized settings. Conclusion: By automating risk assessment, the AI model can alleviate the workload of healthcare professionals, reducing the time required for manual evaluations and minimizing subjective biases in clinical decision-making. This not only enhances operational efficiency but also allows nursing staff to allocate more time to direct patient care. These findings underscore the transformative potential of AI-driven approaches in healthcare, improving patient safety through data-driven. https://npt.tums.ac.ir/index.php/npt/article/view/3374falls; fall risk assessment comparison; hospitalized patients; supervised learning technology; nursing assessment; decision support system |
| spellingShingle | Chia-Lun Lo Chia-En Liu Hsiao Yun Chang Chiu-Hsiang Wu AI-driven fall risk prediction in inpatients: Development, validation, and comparative evaluation Nursing Practice Today falls; fall risk assessment comparison; hospitalized patients; supervised learning technology; nursing assessment; decision support system |
| title | AI-driven fall risk prediction in inpatients: Development, validation, and comparative evaluation |
| title_full | AI-driven fall risk prediction in inpatients: Development, validation, and comparative evaluation |
| title_fullStr | AI-driven fall risk prediction in inpatients: Development, validation, and comparative evaluation |
| title_full_unstemmed | AI-driven fall risk prediction in inpatients: Development, validation, and comparative evaluation |
| title_short | AI-driven fall risk prediction in inpatients: Development, validation, and comparative evaluation |
| title_sort | ai driven fall risk prediction in inpatients development validation and comparative evaluation |
| topic | falls; fall risk assessment comparison; hospitalized patients; supervised learning technology; nursing assessment; decision support system |
| url | https://npt.tums.ac.ir/index.php/npt/article/view/3374 |
| work_keys_str_mv | AT chialunlo aidrivenfallriskpredictionininpatientsdevelopmentvalidationandcomparativeevaluation AT chiaenliu aidrivenfallriskpredictionininpatientsdevelopmentvalidationandcomparativeevaluation AT hsiaoyunchang aidrivenfallriskpredictionininpatientsdevelopmentvalidationandcomparativeevaluation AT chiuhsiangwu aidrivenfallriskpredictionininpatientsdevelopmentvalidationandcomparativeevaluation |