Improvement of Adequate Digoxin Dosage: An Application of Machine Learning Approach.

Digoxin is a high-alert medication because of its narrow therapeutic range and high drug-to-drug interactions (DDIs). Approximately 50% of digoxin toxicity cases are preventable, which motivated us to improve the treatment outcomes of digoxin. The objective of this study is to apply machine learning techniques to predict the appropriateness of initial digoxin dosage. A total of 307 inpatients who had their conditions treated with digoxin between 2004 and 2013 at a medical center in Taiwan were collected in the study. Ten independent variables, including demographic information, laboratory data, and whether the patients had CHF were also noted. A patient with serum digoxin concentration being controlled at 0.5-0.9 ng/mL after his/her initial digoxin dosage was defined as having an appropriate use of digoxin; otherwise, a patient was defined as having an inappropriate use of digoxin. Weka 3.7.3, an open source machine learning software, was adopted to develop prediction models. Six machine learning techniques were considered, including decision tree (C4.5), k-nearest neighbors (kNN), classification and regression tree (CART), randomForest (RF), multilayer perceptron (MLP), and logistic regression (LGR). In the non-DDI group, the area under ROC curve (AUC) of RF (0.912) was excellent, followed by that of MLP (0.813), CART (0.791), and C4.5 (0.784); the remaining classifiers performed poorly. For the DDI group, the AUC of RF (0.892) was the best, followed by CART (0.795), MLP (0.777), and C4.5 (0.774); the other classifiers' performances were less than ideal. The decision tree-based approaches and MLP exhibited markedly superior accuracy performance, regardless of DDI status. Although digoxin is a high-alert medication, its initial dose can be accurately determined by using data mining techniques such as decision tree-based and MLP approaches. Developing a dosage decision support system may serve as a supplementary tool for clinicians and also increase drug safety in clinical practice.

Predicting return visits to the emergency department for pediatric patients: Applying supervised learning techniques to the Taiwan National Health Insurance Research Database.

BACKGROUND AND OBJECTIVE: Return visits (RVs) to the emergency department (ED) consume medical resources and may represent a patient safety issue. The occurrence of unexpected RVs is considered a performance indicator for ED care quality. Because children are susceptible to medical errors and utilize considerable ED resources, knowing the factors that affect RVs in pediatric patients helps improve the quality of pediatric emergency care. METHODS: We collected data on visits made by patients aged ≤18years to EDs from the National Health Insurance Research Database. The outcome of interest was a RV within 3days of the initial visit. Potential factors were categorized into demographics, medical history, features of ED visits, physician characteristics, hospital characteristics, and treatment-seeking behavior. A multivariate logistic regression was used to identify independent predictors of RVs. We compared the performance of various data mining techniques, including Naïve Bayes, classification and regression tree (CART), random forest, and logistic regression, in predicting RVs. Finally, we developed a decision tree to stratify the risk of RVs. RESULTS: Of 125,940 visits, 6,282 (5.0%) were followed by a RV within 3 days. Predictors of RVs included younger age, higher acuity, intravenous fluid, more examination types, complete blood count, consultation, lower hospital level, hospitalization within one week before the initial visit, frequent ED visits in the past one year, and visits made in Spring or on Saturdays. Patients with allergic diseases and those underwent ultrasound examination were less likely to return. Decision tree models performed better in predicting RVs in terms of area under curve. The decision tree constructed using the CART technique showed that the number of ED visits in the past one year, diagnosis category, testing of complete blood count, and age were important discriminators of risk of RVs. CONCLUSIONS: We identified several factors which are associated with RVs to the ED in pediatric patients. The knowledge of these factors may help assess risk of RVs in the ED and guide physicians to reevaluate and provide interventions to children belonging to the high risk groups before ED discharge.

Predicting warfarin dosage from clinical data: a supervised learning approach.

OBJECTIVE: Safety of anticoagulant administration has been a primary concern of the Joint Commission on Accreditation of Healthcare Organizations. Among all anticoagulants, warfarin has long been listed among the top ten drugs causing adverse drug events. Due to narrow therapeutic range and significant side effects, warfarin dosage determination becomes a challenging task in clinical practice. For superior clinical decision making, this study attempts to build a warfarin dosage prediction model utilizing a number of supervised learning techniques. METHODS AND MATERIALS: The data consists of complete historical records of 587 Taiwan clinical cases who received warfarin treatment as well as warfarin dose adjustment. A number of supervised learning techniques were investigated, including multilayer perceptron, model tree, k nearest neighbors, and support vector regression (SVR). To achieve higher prediction accuracy, we further consider both homogeneous and heterogeneous ensembles (i.e., bagging and voting). For performance evaluation, the initial dose of warfarin prescribed by clinicians is established as the baseline. The mean absolute error (MAE) and standard deviation of errors (σ(E)) are considered as evaluation indicators. RESULTS: The overall evaluation results show that all of the learning based systems are significantly more accurate than the baseline (MAE=0.394, σ(E)=0.558). Among all prediction models, both Bagged Voting (MAE=0.210, σ(E)=0.357) with four classifiers and Bagged SVR (MAE=0.210, σ(E)=0.366) are suggested as the two most effective prediction models due to their lower MAE and σ(E). CONCLUSION: The investigated models can not only facilitate clinicians in dosage decision-making, but also help reduce patient risk from adverse drug events.