Development of an explainable machine learning model for predicting device-related pressure injuries in clinical settings

Abstract Background Device-related pressure injury (DRPI) is a prevalent and severe problem for patients using medical devices. Timely identification of patients at high risk of DRPI is crucial for healthcare providers to make informed decisions and prevent DRPI quickly. Given the rapid advancements...

Full description

Saved in:
Bibliographic Details
Main Authors: Yijie Qian, Hongying Pan, Jun Chen, Hongyang Hu, Mei Fang, Chen Huang, Yihong Xu, Yang Gao
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BMC Medical Informatics and Decision Making
Subjects:
Online Access:https://doi.org/10.1186/s12911-025-03090-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849234943167692800
author Yijie Qian
Hongying Pan
Jun Chen
Hongyang Hu
Mei Fang
Chen Huang
Yihong Xu
Yang Gao
author_facet Yijie Qian
Hongying Pan
Jun Chen
Hongyang Hu
Mei Fang
Chen Huang
Yihong Xu
Yang Gao
author_sort Yijie Qian
collection DOAJ
description Abstract Background Device-related pressure injury (DRPI) is a prevalent and severe problem for patients using medical devices. Timely identification of patients at high risk of DRPI is crucial for healthcare providers to make informed decisions and prevent DRPI quickly. Given the rapid advancements in computer technology, we aimed to develop an interpretable artificial intelligence (AI) model for predicting DRPI, utilizing SHAP (SHapley Additive exPlanations) to enhance the model’s transparency and provide insights into feature importance. Methods We enrolled 675 study subjects (225 in the DRPI group and 450 in the non-DRPI group) from a single medical center between January 2019 and December 2020. Python was used to perform classification models, including extreme gradient boosting (XGBoost), random forest (RF), decision tree (DT), Logistic Regression (LR), support vector machine (SVM), and K-Nearest neighbors (KNN). We evaluated the performance of the six models using area under the ROC curve (AUC), specificity, accuracy, and sensitivity, with the dataset split into a 80% training set and a 20% testing set. We utilized several analyses, such as SHAP and Uniform Manifold Approximation and Projection (UMAP), to explore the potential contribution of different characteristics in our risk prediction models. Results In the test set, XGBoost model outperformed the other models (AUC = 0.964). The interpretation of the model using SHAPscores revealed that the length of stay, instrument type, emergency admissions, instrument material, and instrument duration of use are the top five most important features in predicting DRPI. Conclusion Our study demonstrated that the development of DRPI in patients can be accurately predicted using the machine learning (ML) model. The findings not only provide clinical caregivers with a valuable framework to identify patients at high risk of DRPI, but also lay the groundwork for developing targeted preventive strategies and personalized interventions.
format Article
id doaj-art-c898a6df44434dd18ec70f3cdeefaad0
institution Kabale University
issn 1472-6947
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BMC Medical Informatics and Decision Making
spelling doaj-art-c898a6df44434dd18ec70f3cdeefaad02025-08-20T04:02:56ZengBMCBMC Medical Informatics and Decision Making1472-69472025-07-0125111210.1186/s12911-025-03090-9Development of an explainable machine learning model for predicting device-related pressure injuries in clinical settingsYijie Qian0Hongying Pan1Jun Chen2Hongyang Hu3Mei Fang4Chen Huang5Yihong Xu6Yang Gao7Nursing Department, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineNursing Department, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineNursing Department, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineNursing Department, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineNursing Department, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineNursing Department, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineNursing Department, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineNursing Department, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineAbstract Background Device-related pressure injury (DRPI) is a prevalent and severe problem for patients using medical devices. Timely identification of patients at high risk of DRPI is crucial for healthcare providers to make informed decisions and prevent DRPI quickly. Given the rapid advancements in computer technology, we aimed to develop an interpretable artificial intelligence (AI) model for predicting DRPI, utilizing SHAP (SHapley Additive exPlanations) to enhance the model’s transparency and provide insights into feature importance. Methods We enrolled 675 study subjects (225 in the DRPI group and 450 in the non-DRPI group) from a single medical center between January 2019 and December 2020. Python was used to perform classification models, including extreme gradient boosting (XGBoost), random forest (RF), decision tree (DT), Logistic Regression (LR), support vector machine (SVM), and K-Nearest neighbors (KNN). We evaluated the performance of the six models using area under the ROC curve (AUC), specificity, accuracy, and sensitivity, with the dataset split into a 80% training set and a 20% testing set. We utilized several analyses, such as SHAP and Uniform Manifold Approximation and Projection (UMAP), to explore the potential contribution of different characteristics in our risk prediction models. Results In the test set, XGBoost model outperformed the other models (AUC = 0.964). The interpretation of the model using SHAPscores revealed that the length of stay, instrument type, emergency admissions, instrument material, and instrument duration of use are the top five most important features in predicting DRPI. Conclusion Our study demonstrated that the development of DRPI in patients can be accurately predicted using the machine learning (ML) model. The findings not only provide clinical caregivers with a valuable framework to identify patients at high risk of DRPI, but also lay the groundwork for developing targeted preventive strategies and personalized interventions.https://doi.org/10.1186/s12911-025-03090-9Device-Related Pressure InjuryPressure UlcerMachine learningExplainable artificial intelligenceForecasting
spellingShingle Yijie Qian
Hongying Pan
Jun Chen
Hongyang Hu
Mei Fang
Chen Huang
Yihong Xu
Yang Gao
Development of an explainable machine learning model for predicting device-related pressure injuries in clinical settings
BMC Medical Informatics and Decision Making
Device-Related Pressure Injury
Pressure Ulcer
Machine learning
Explainable artificial intelligence
Forecasting
title Development of an explainable machine learning model for predicting device-related pressure injuries in clinical settings
title_full Development of an explainable machine learning model for predicting device-related pressure injuries in clinical settings
title_fullStr Development of an explainable machine learning model for predicting device-related pressure injuries in clinical settings
title_full_unstemmed Development of an explainable machine learning model for predicting device-related pressure injuries in clinical settings
title_short Development of an explainable machine learning model for predicting device-related pressure injuries in clinical settings
title_sort development of an explainable machine learning model for predicting device related pressure injuries in clinical settings
topic Device-Related Pressure Injury
Pressure Ulcer
Machine learning
Explainable artificial intelligence
Forecasting
url https://doi.org/10.1186/s12911-025-03090-9
work_keys_str_mv AT yijieqian developmentofanexplainablemachinelearningmodelforpredictingdevicerelatedpressureinjuriesinclinicalsettings
AT hongyingpan developmentofanexplainablemachinelearningmodelforpredictingdevicerelatedpressureinjuriesinclinicalsettings
AT junchen developmentofanexplainablemachinelearningmodelforpredictingdevicerelatedpressureinjuriesinclinicalsettings
AT hongyanghu developmentofanexplainablemachinelearningmodelforpredictingdevicerelatedpressureinjuriesinclinicalsettings
AT meifang developmentofanexplainablemachinelearningmodelforpredictingdevicerelatedpressureinjuriesinclinicalsettings
AT chenhuang developmentofanexplainablemachinelearningmodelforpredictingdevicerelatedpressureinjuriesinclinicalsettings
AT yihongxu developmentofanexplainablemachinelearningmodelforpredictingdevicerelatedpressureinjuriesinclinicalsettings
AT yanggao developmentofanexplainablemachinelearningmodelforpredictingdevicerelatedpressureinjuriesinclinicalsettings