Opioid Nonadherence Risk Prediction of Patients with Cancer-Related Pain Based on Five Machine Learning Algorithms
Objectives. Opioid nonadherence represents a significant barrier to cancer pain treatment efficacy. However, there is currently no effective prediction method for opioid adherence in patients with cancer pain. We aimed to develop and validate a machine learning (ML) model and evaluate its feasibilit...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | Pain Research and Management |
| Online Access: | http://dx.doi.org/10.1155/2024/7347876 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832546163197214720 |
|---|---|
| author | Jinmei Liu Juan Luo Xu Chen Jiyi Xie Cong Wang Hanxiang Wang Qi Yuan Shijun Li Yu Zhang Jianli Hu Chen Shi |
| author_facet | Jinmei Liu Juan Luo Xu Chen Jiyi Xie Cong Wang Hanxiang Wang Qi Yuan Shijun Li Yu Zhang Jianli Hu Chen Shi |
| author_sort | Jinmei Liu |
| collection | DOAJ |
| description | Objectives. Opioid nonadherence represents a significant barrier to cancer pain treatment efficacy. However, there is currently no effective prediction method for opioid adherence in patients with cancer pain. We aimed to develop and validate a machine learning (ML) model and evaluate its feasibility to predict opioid nonadherence in patients with cancer pain. Methods. This was a secondary analysis from a cross-sectional study that included 1195 patients from March 1, 2018, to October 31, 2019. Five ML algorithms, such as logistic regression (LR), random forest, eXtreme Gradient Boosting, multilayer perceptron, and support vector machine, were used to predict opioid nonadherence in patients with cancer pain using 43 demographic and clinical factors as predictors. The predictive effects of the models were compared by the area under the receiver operating characteristic curve (AUC_ROC), accuracy, precision, sensitivity, specificity, and F1 scores. The value of the best model for clinical application was assessed using decision curve analysis (DCA). Results. The best model obtained in this study, the LR model, had an AUC_ROC of 0.82, accuracy of 0.82, and specificity of 0.71. The DCA showed that clinical interventions for patients at high risk of opioid nonadherence based on the LR model can benefit patients. The strongest predictors for adherence were, in order of importance, beliefs about medicines questionnaire (BMQ)-harm, time since the start of opioid, and BMQ-necessity. Discussion. ML algorithms can be used as an effective means of predicting adherence to opioids in patients with cancer pain, which allows for proactive clinical intervention to optimize cancer pain management. This trial is registered with ChiCTR2000033576. |
| format | Article |
| id | doaj-art-d1c525fdcc4f4fa6bfd6013224d4ac8f |
| institution | Kabale University |
| issn | 1918-1523 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Pain Research and Management |
| spelling | doaj-art-d1c525fdcc4f4fa6bfd6013224d4ac8f2025-02-03T07:23:45ZengWileyPain Research and Management1918-15232024-01-01202410.1155/2024/7347876Opioid Nonadherence Risk Prediction of Patients with Cancer-Related Pain Based on Five Machine Learning AlgorithmsJinmei Liu0Juan Luo1Xu Chen2Jiyi Xie3Cong Wang4Hanxiang Wang5Qi Yuan6Shijun Li7Yu Zhang8Jianli Hu9Chen Shi10Department of PharmacyDepartment of PharmacyDepartment of PharmacyDepartment of PharmacyDepartment of PharmacyDepartment of PharmacyDepartment of PharmacyDepartment of PharmacyDepartment of PharmacyCancer CenterDepartment of PharmacyObjectives. Opioid nonadherence represents a significant barrier to cancer pain treatment efficacy. However, there is currently no effective prediction method for opioid adherence in patients with cancer pain. We aimed to develop and validate a machine learning (ML) model and evaluate its feasibility to predict opioid nonadherence in patients with cancer pain. Methods. This was a secondary analysis from a cross-sectional study that included 1195 patients from March 1, 2018, to October 31, 2019. Five ML algorithms, such as logistic regression (LR), random forest, eXtreme Gradient Boosting, multilayer perceptron, and support vector machine, were used to predict opioid nonadherence in patients with cancer pain using 43 demographic and clinical factors as predictors. The predictive effects of the models were compared by the area under the receiver operating characteristic curve (AUC_ROC), accuracy, precision, sensitivity, specificity, and F1 scores. The value of the best model for clinical application was assessed using decision curve analysis (DCA). Results. The best model obtained in this study, the LR model, had an AUC_ROC of 0.82, accuracy of 0.82, and specificity of 0.71. The DCA showed that clinical interventions for patients at high risk of opioid nonadherence based on the LR model can benefit patients. The strongest predictors for adherence were, in order of importance, beliefs about medicines questionnaire (BMQ)-harm, time since the start of opioid, and BMQ-necessity. Discussion. ML algorithms can be used as an effective means of predicting adherence to opioids in patients with cancer pain, which allows for proactive clinical intervention to optimize cancer pain management. This trial is registered with ChiCTR2000033576.http://dx.doi.org/10.1155/2024/7347876 |
| spellingShingle | Jinmei Liu Juan Luo Xu Chen Jiyi Xie Cong Wang Hanxiang Wang Qi Yuan Shijun Li Yu Zhang Jianli Hu Chen Shi Opioid Nonadherence Risk Prediction of Patients with Cancer-Related Pain Based on Five Machine Learning Algorithms Pain Research and Management |
| title | Opioid Nonadherence Risk Prediction of Patients with Cancer-Related Pain Based on Five Machine Learning Algorithms |
| title_full | Opioid Nonadherence Risk Prediction of Patients with Cancer-Related Pain Based on Five Machine Learning Algorithms |
| title_fullStr | Opioid Nonadherence Risk Prediction of Patients with Cancer-Related Pain Based on Five Machine Learning Algorithms |
| title_full_unstemmed | Opioid Nonadherence Risk Prediction of Patients with Cancer-Related Pain Based on Five Machine Learning Algorithms |
| title_short | Opioid Nonadherence Risk Prediction of Patients with Cancer-Related Pain Based on Five Machine Learning Algorithms |
| title_sort | opioid nonadherence risk prediction of patients with cancer related pain based on five machine learning algorithms |
| url | http://dx.doi.org/10.1155/2024/7347876 |
| work_keys_str_mv | AT jinmeiliu opioidnonadherenceriskpredictionofpatientswithcancerrelatedpainbasedonfivemachinelearningalgorithms AT juanluo opioidnonadherenceriskpredictionofpatientswithcancerrelatedpainbasedonfivemachinelearningalgorithms AT xuchen opioidnonadherenceriskpredictionofpatientswithcancerrelatedpainbasedonfivemachinelearningalgorithms AT jiyixie opioidnonadherenceriskpredictionofpatientswithcancerrelatedpainbasedonfivemachinelearningalgorithms AT congwang opioidnonadherenceriskpredictionofpatientswithcancerrelatedpainbasedonfivemachinelearningalgorithms AT hanxiangwang opioidnonadherenceriskpredictionofpatientswithcancerrelatedpainbasedonfivemachinelearningalgorithms AT qiyuan opioidnonadherenceriskpredictionofpatientswithcancerrelatedpainbasedonfivemachinelearningalgorithms AT shijunli opioidnonadherenceriskpredictionofpatientswithcancerrelatedpainbasedonfivemachinelearningalgorithms AT yuzhang opioidnonadherenceriskpredictionofpatientswithcancerrelatedpainbasedonfivemachinelearningalgorithms AT jianlihu opioidnonadherenceriskpredictionofpatientswithcancerrelatedpainbasedonfivemachinelearningalgorithms AT chenshi opioidnonadherenceriskpredictionofpatientswithcancerrelatedpainbasedonfivemachinelearningalgorithms |