An interpretable boosting model to predict side effects of analgesics for osteoarthritis

Abstract

BackgroundOsteoarthritis (OA) is the most common disease of arthritis. Analgesics are widely used in the treat of arthritis, which may increase the risk of cardiovascular diseases by 20% to 50% overall.There are few studies on the side effects of OA medication, especially the risk prediction models on side effects of analgesics. In addition, most prediction models do not provide clinically useful interpretable rules to explain the reasoning process behind their predictions. In order to assist OA patients, we use the eXtreme Gradient Boosting (XGBoost) method to balance the accuracy and interpretability of the prediction model.ResultsIn this study we used the XGBoost model as a classifier, which is a supervised machine learning method and can predict side effects of analgesics for OA patients and identify high-risk features (RFs) of cardiovascular diseases caused by analgesics. The Electronic Medical Records (EMRs), which were derived from public knee OA studies, were used to train the model. The performance of the XGBoost model is superior to four well-known machine learning algorithms and identifies the risk features from the biomedical literature. In addition the model can provide decision support for using analgesics in OA patients.ConclusionCompared with other machine learning methods, we used XGBoost method to predict side effects of analgesics for OA patients from EMRs, and selected the individual informative RFs. The model has good predictability and interpretability, this is valuable for both medical researchers and patients.

Machine learning and deep learning to predict mortality in patients with spontaneous coronary artery dissection

“…Even the relatively rudimentary decision tree ML approach, which had limited predictive power, had better predictive capacity. These observations are consistent with previous studies establishing that ML algorithms typically outperform regression models 18 – 20 . Deep neural network models also generally perform better than regression, reflecting the mathematical complexity and non-linearity of medical diagnosis and prognosis that defy simple parametric methodologies.…”

Machine learning and deep learning to predict mortality in patients with spontaneous coronary artery dissection

“…Even the relatively rudimentary decision tree ML approach, which had limited predictive power, had better predictive capacity. These observations are consistent with previous studies establishing that ML algorithms typically outperform regression models 18 – 20 . Deep neural network models also generally perform better than regression, reflecting the mathematical complexity and non-linearity of medical diagnosis and prognosis that defy simple parametric methodologies.…”

Explainable Machine Learning Techniques To Predict Amiodarone-Induced Thyroid Dysfunction Risk: Multicenter, Retrospective Study With External Validation

“…Their contributions might be masked by factorial interactions in statistical approaches. Similar phenomena were reported for thyroid disease, chronic kidney disease, and analgesic adverse-effect prediction [ 54 , 62 , 63 ]. The machine learning models identified relevant features with nonlinear relationships and complex interactions between factors and outcomes, such as HDL and LDL, in the present study; Promising to help doctors and pharmacists to pay special attention when checking amiodarone users’ lipid panels to prevent adverse thyroid events.…”

XGBoost, a Machine Learning Method, Predicts Neurological Recovery in Patients with Cervical Spinal Cord Injury

“…22,[36][37][38] In addition, although overfitting is a common limitation in refined non-linear machine learning algorithms, XGBoost supervises machine learning problems by parallel computing, regularization, cross validation, flexibility, or availability. 16,39,40 Comparison with previous research DeVries and associates previously reported that no clinically significant differences were observed between the use of unsupervised machine learning with complete admission neurological information and established standards. 10 They showed the inherent weakness of applying AUC to imbalanced data sets and outlined a new strategy to evaluate performance.…”

Machine learning and deep learning to predict mortality in patients with spontaneous coronary artery dissection

“…Even the relatively rudimentary decision tree ML approach, which had limited predictive power, had better predictive capacity. These observations are consistent with previous studies establishing that ML algorithms typically outperform regression models 18 – 20 . Deep neural network models also generally perform better than regression, reflecting the mathematical complexity and non-linearity of medical diagnosis and prognosis that defy simple parametric methodologies.…”

Explainable Machine Learning Techniques To Predict Amiodarone-Induced Thyroid Dysfunction Risk: Multicenter, Retrospective Study With External Validation

“…Their contributions might be masked by factorial interactions in statistical approaches. Similar phenomena were reported for thyroid disease, chronic kidney disease, and analgesic adverse-effect prediction [ 54 , 62 , 63 ]. The machine learning models identified relevant features with nonlinear relationships and complex interactions between factors and outcomes, such as HDL and LDL, in the present study; Promising to help doctors and pharmacists to pay special attention when checking amiodarone users’ lipid panels to prevent adverse thyroid events.…”

XGBoost, a Machine Learning Method, Predicts Neurological Recovery in Patients with Cervical Spinal Cord Injury

“…22,[36][37][38] In addition, although overfitting is a common limitation in refined non-linear machine learning algorithms, XGBoost supervises machine learning problems by parallel computing, regularization, cross validation, flexibility, or availability. 16,39,40 Comparison with previous research DeVries and associates previously reported that no clinically significant differences were observed between the use of unsupervised machine learning with complete admission neurological information and established standards. 10 They showed the inherent weakness of applying AUC to imbalanced data sets and outlined a new strategy to evaluate performance.…”

Machine learning and deep learning to predict mortality in patients with spontaneous coronary artery dissection

“…Even the relatively rudimentary decision tree ML approach, which had limited predictive power, had better predictive capacity. These observations are consistent with previous studies establishing that ML algorithms typically outperform regression models 18 – 20 . Deep neural network models also generally perform better than regression, reflecting the mathematical complexity and non-linearity of medical diagnosis and prognosis that defy simple parametric methodologies.…”

Explainable Machine Learning Techniques To Predict Amiodarone-Induced Thyroid Dysfunction Risk: Multicenter, Retrospective Study With External Validation

“…Their contributions might be masked by factorial interactions in statistical approaches. Similar phenomena were reported for thyroid disease, chronic kidney disease, and analgesic adverse-effect prediction [ 54 , 62 , 63 ]. The machine learning models identified relevant features with nonlinear relationships and complex interactions between factors and outcomes, such as HDL and LDL, in the present study; Promising to help doctors and pharmacists to pay special attention when checking amiodarone users’ lipid panels to prevent adverse thyroid events.…”

XGBoost, a Machine Learning Method, Predicts Neurological Recovery in Patients with Cervical Spinal Cord Injury

“…22,[36][37][38] In addition, although overfitting is a common limitation in refined non-linear machine learning algorithms, XGBoost supervises machine learning problems by parallel computing, regularization, cross validation, flexibility, or availability. 16,39,40 Comparison with previous research DeVries and associates previously reported that no clinically significant differences were observed between the use of unsupervised machine learning with complete admission neurological information and established standards. 10 They showed the inherent weakness of applying AUC to imbalanced data sets and outlined a new strategy to evaluate performance.…”