Can available mathematical models predict serum digoxin levels in Thai patients?

Prediction Of Serum Digoxin Concentration Using Estimated Glomerular Filtration Rate In Thai Population

PURPOSE

Serum digoxin concentration (SDC) monitoring may be unavailable in some healthcare settings. Predicted SDC comes into play in the efficacy and toxicity monitoring of digoxin. Renal function is the important parameter for predicting SDC. This study was conducted to compare measured and predicted SDC when using creatinine clearance (CrCl) from Cockcroft-Gault (CG) equation and estimated glomerular filtration rate (eGFR) calculated from CKD-Epidemiology Collaboration (CKD-EPI), re-expressed Modification of Diet in Renal Disease (Re-MDRD4), Thai-MDRD4, and Thai-eGFR equations in Sheiner's and Konishi's pharmacokinetic models.

PATIENTS AND METHODS

In this retrospective study, patients with cardiovascular disease with a steady-state of SDC within 0.5-2.0 mcg/L were enrolled. CrCl and studied eGFR adjusted for body surface area (BSA) were used in the models to determine the predicted SDC. The discrepancies of the measured and the predicted SDC were analyzed and compared.

RESULTS

One hundred and twenty-four patients ranging in age from 22 to 88 years (median 60 years, IQR 50.2, 69.2) were studied. Their serum creatinine ranged from 0.40 to 1.80 mg/dL (median 0.90 mg/dL, IQR 0.79, 1.10). The mean±SD of measured SDC was 1.12±0.34 mcg/L. In the Sheiner's model, the mean predicted SDC was calculated by using the CG and the BSA adjusted CKD-EPI equations and was not different when compared with the measured levels (1.10±0.36 mcg/L (p=0.669) and 1.08±0.42 mcg/L (p=0.374), respectively). The CG, CKD-EPI, and Re-MDRD4 equations were a better fit for patients with creatinine ≥0.9 mg/dL for prediction with minimal errors. In the Konishi's model, the predicted SDC using the CG and the studied eGFR equation was lower than the measured SDC (p<0.05).

CONCLUSION

In Sheiner's model, the CG and the BSA adjusted CKD-EPI equations should be used for predicting SDC, especially in patients with serum creatinine ≥0.9 mg/dL. The other studied eGFRs underestimated SDC in both Sheiner's and Konishi's model.

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.