An inpatient fall risk assessment tool: Application of machine learning models on intrinsic and extrinsic risk factors
Background: This study aimed to identify the most impactful set of intrinsic and extrinsic fall risk factors and develop a data-driven inpatient fall risk assessment tool (FRAT). Methods: The dataset used for the study comprised in-hospital fall records from 2012 to 2017. Four machine learning (ML) ...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-03-01
|
| Series: | Machine Learning with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666827023000725 |
| _version_ | 1797391733711962112 |
|---|---|
| author | Sonia Jahangiri Masoud Abdollahi Rasika Patil Ehsan Rashedi Nasibeh Azadeh-Fard |
| author_facet | Sonia Jahangiri Masoud Abdollahi Rasika Patil Ehsan Rashedi Nasibeh Azadeh-Fard |
| author_sort | Sonia Jahangiri |
| collection | DOAJ |
| description | Background: This study aimed to identify the most impactful set of intrinsic and extrinsic fall risk factors and develop a data-driven inpatient fall risk assessment tool (FRAT). Methods: The dataset used for the study comprised in-hospital fall records from 2012 to 2017. Four machine learning (ML) algorithms, Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting (Gboost), and Deep Neural Network (DNN) were utilized to predict the inpatient fall risk level. To enhance the performance of the prediction models, two approaches were implemented, including (1) feature selection to identify the optimal feature set and (2) the development of three distinct shift-wise models. Furthermore, the optimal feature sets in the shift-wise models were extracted. Results: According to the results, DNN outperformed other methods by reaching an accuracy, sensitivity, specificity, and AUC of 0.71, 0.8, 0.6, and 0.7, respectively, considering the full set of features. The performance of the models was further improved (by 3-5 %) by conducting a feature selection process for all models. Specifically, the DNN model achieved an accuracy of 0.74 while considering the optimal set of predictors. Moreover, the shift-wise RF models demonstrated higher accuracies (by 4-10 %) compared to the same model using a full feature set. Conclusions: This study's outcome confirms ML models' compelling capability in developing an inpatient FRAT while considering intrinsic and extrinsic factors. The insight from such models could form a foundation to (1) monitor the inpatients’ fall risk, (2) identify the major factors involved in inpatient falls, and (3) create subject-specific self-care plans. |
| first_indexed | 2024-03-08T23:37:55Z |
| format | Article |
| id | doaj.art-96edfc89321d4a5f88e0ff8e5ac5d54b |
| institution | Directory Open Access Journal |
| issn | 2666-8270 |
| language | English |
| last_indexed | 2024-03-08T23:37:55Z |
| publishDate | 2024-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Machine Learning with Applications |
| spelling | doaj.art-96edfc89321d4a5f88e0ff8e5ac5d54b2023-12-14T05:24:05ZengElsevierMachine Learning with Applications2666-82702024-03-0115100519An inpatient fall risk assessment tool: Application of machine learning models on intrinsic and extrinsic risk factorsSonia Jahangiri0Masoud Abdollahi1Rasika Patil2Ehsan Rashedi3Nasibeh Azadeh-Fard4Corresponding author.; Industrial and Systems Engineering Department, Rochester Institute of Technology, 81 Lomb Memorial Dr. Rochester, NY 14623, United StatesIndustrial and Systems Engineering Department, Rochester Institute of Technology, 81 Lomb Memorial Dr. Rochester, NY 14623, United StatesIndustrial and Systems Engineering Department, Rochester Institute of Technology, 81 Lomb Memorial Dr. Rochester, NY 14623, United StatesIndustrial and Systems Engineering Department, Rochester Institute of Technology, 81 Lomb Memorial Dr. Rochester, NY 14623, United StatesIndustrial and Systems Engineering Department, Rochester Institute of Technology, 81 Lomb Memorial Dr. Rochester, NY 14623, United StatesBackground: This study aimed to identify the most impactful set of intrinsic and extrinsic fall risk factors and develop a data-driven inpatient fall risk assessment tool (FRAT). Methods: The dataset used for the study comprised in-hospital fall records from 2012 to 2017. Four machine learning (ML) algorithms, Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting (Gboost), and Deep Neural Network (DNN) were utilized to predict the inpatient fall risk level. To enhance the performance of the prediction models, two approaches were implemented, including (1) feature selection to identify the optimal feature set and (2) the development of three distinct shift-wise models. Furthermore, the optimal feature sets in the shift-wise models were extracted. Results: According to the results, DNN outperformed other methods by reaching an accuracy, sensitivity, specificity, and AUC of 0.71, 0.8, 0.6, and 0.7, respectively, considering the full set of features. The performance of the models was further improved (by 3-5 %) by conducting a feature selection process for all models. Specifically, the DNN model achieved an accuracy of 0.74 while considering the optimal set of predictors. Moreover, the shift-wise RF models demonstrated higher accuracies (by 4-10 %) compared to the same model using a full feature set. Conclusions: This study's outcome confirms ML models' compelling capability in developing an inpatient FRAT while considering intrinsic and extrinsic factors. The insight from such models could form a foundation to (1) monitor the inpatients’ fall risk, (2) identify the major factors involved in inpatient falls, and (3) create subject-specific self-care plans.http://www.sciencedirect.com/science/article/pii/S2666827023000725Inpatient fallRisk assessmentMachine learningIntrinsic risk factorsExtrinsic risk factors |
| spellingShingle | Sonia Jahangiri Masoud Abdollahi Rasika Patil Ehsan Rashedi Nasibeh Azadeh-Fard An inpatient fall risk assessment tool: Application of machine learning models on intrinsic and extrinsic risk factors Machine Learning with Applications Inpatient fall Risk assessment Machine learning Intrinsic risk factors Extrinsic risk factors |
| title | An inpatient fall risk assessment tool: Application of machine learning models on intrinsic and extrinsic risk factors |
| title_full | An inpatient fall risk assessment tool: Application of machine learning models on intrinsic and extrinsic risk factors |
| title_fullStr | An inpatient fall risk assessment tool: Application of machine learning models on intrinsic and extrinsic risk factors |
| title_full_unstemmed | An inpatient fall risk assessment tool: Application of machine learning models on intrinsic and extrinsic risk factors |
| title_short | An inpatient fall risk assessment tool: Application of machine learning models on intrinsic and extrinsic risk factors |
| title_sort | inpatient fall risk assessment tool application of machine learning models on intrinsic and extrinsic risk factors |
| topic | Inpatient fall Risk assessment Machine learning Intrinsic risk factors Extrinsic risk factors |
| url | http://www.sciencedirect.com/science/article/pii/S2666827023000725 |
| work_keys_str_mv | AT soniajahangiri aninpatientfallriskassessmenttoolapplicationofmachinelearningmodelsonintrinsicandextrinsicriskfactors AT masoudabdollahi aninpatientfallriskassessmenttoolapplicationofmachinelearningmodelsonintrinsicandextrinsicriskfactors AT rasikapatil aninpatientfallriskassessmenttoolapplicationofmachinelearningmodelsonintrinsicandextrinsicriskfactors AT ehsanrashedi aninpatientfallriskassessmenttoolapplicationofmachinelearningmodelsonintrinsicandextrinsicriskfactors AT nasibehazadehfard aninpatientfallriskassessmenttoolapplicationofmachinelearningmodelsonintrinsicandextrinsicriskfactors AT soniajahangiri inpatientfallriskassessmenttoolapplicationofmachinelearningmodelsonintrinsicandextrinsicriskfactors AT masoudabdollahi inpatientfallriskassessmenttoolapplicationofmachinelearningmodelsonintrinsicandextrinsicriskfactors AT rasikapatil inpatientfallriskassessmenttoolapplicationofmachinelearningmodelsonintrinsicandextrinsicriskfactors AT ehsanrashedi inpatientfallriskassessmenttoolapplicationofmachinelearningmodelsonintrinsicandextrinsicriskfactors AT nasibehazadehfard inpatientfallriskassessmenttoolapplicationofmachinelearningmodelsonintrinsicandextrinsicriskfactors |