Predicting the serum digoxin concentrations of infants in the neonatal intensive care unit through an artificial neural network.

BACKGROUND: Given its narrow therapeutic range, digoxin's pharmacokinetic parameters in infants are difficult to predict due to variation in birth weight and gestational age, especially for critically ill newborns. There is limited evidence to support the safety and dosage requirements of digoxin, let alone to predict its concentrations in infants. This study aimed to compare the concentrations of digoxin predicted by traditional regression modeling and artificial neural network (ANN) modeling for newborn infants given digoxin for clinically significant patent ductus arteriosus (PDA). METHODS: A retrospective chart review was conducted to obtain data on digoxin use for clinically significant PDA in a neonatal intensive care unit. Newborn infants who were given digoxin and had digoxin concentration(s) within the acceptable range were identified as subjects in the training model and validation datasets, accordingly. Their demographics, disease, and medication information, which were potentially associated with heart failure, were used for model training and analysis of digoxin concentration prediction. The models were generated using backward standard multivariable linear regressions (MLRs) and a standard backpropagation algorithm of ANN, respectively. The common goodness-of-fit estimates, receiver operating characteristic curves, and classification of sensitivity and specificity of the toxic concentrations in the validation dataset obtained from MLR or ANN models were compared to identify the final better predictive model. RESULTS: Given the weakness of correlations between actual observed digoxin concentrations and pre-specified variables in newborn infants, the performance of all ANN models was better than that of MLR models for digoxin concentration prediction. In particular, the nine-parameter ANN model has better forecasting accuracy and differentiation ability for toxic concentrations. CONCLUSION: The nine-parameter ANN model is the best alternative than the other models to predict serum digoxin concentrations whenever therapeutic drug monitoring is not available. Further cross-validations using diverse samples from different hospitals for newborn infants are needed.

Regression of Neonatal Cardiac Rhabdomyoma in Two Months Through Low-Dose Everolimus Therapy: A Report of Three Cases.

Cardiac rhabdomyoma (CR) is the most common cardiac tumor in newborns. Approximately 75% of cases are associated with tuberous sclerosis complex. Although these tumors usually spontaneously regress after 2 years of age, they can be life-threatening when they obstruct major cardiac inflow or outflow pathways. Everolimus is an inhibitor of the mammalian target of rapamycin, reducing its production of the proteins harmartin and tuberin. Everolimus has demonstrated a remarkable suppression effect in children with tuberous sclerosis complex at doses of 4.7-5.6 mg/M2/day and serum trough levels of 5-15 ng/mL. Since 2012, five case reports of neonates with CR have also reported the tumor-regressing effect of everolimus. However, the optimal dosage for neonates is still unknown. Over the past 2 years, we have deliberately used a low dose everolimus regimen (0.3-0.67 mg/M2/day) in three neonates with large CRs, in an effort to maintain serum trough levels at 3-7 ng/mL. In all three cases, the tumors regressed smoothly within 2 months. Regarding the drug's side effect of predisposing patients to infection, we observed that adenovirus pneumonia occurred in one case at 3 months of age, and chicken pox occurred in another case at 9 months of age; both recovered smoothly. Our three cases of neonatal CR demonstrate that a low-dose everolimus regimen is an effective treatment for tumor regression.