Predicting the serum digoxin concentrations of infants in the neonatal intensive care unit through an artificial
Shu-Hui Yao1,2, Hsiang-Te Tsai1,3,4, Wen-Lin Lin1,5
1College of Pharmacy, China Medical University, Taichung, Taiwan.
Insights
Artificial neural network (ANN) models better predict digoxin concentrations in newborns than traditional regression. A nine-parameter ANN model offers superior accuracy for forecasting and identifying toxic levels, especially when therapeutic drug monitoring is unavailable.
Area of Science:
- Neonatal pharmacology
- Computational modeling
- Pediatric critical care
Background:
- Digoxin dosing in infants is challenging due to narrow therapeutic range and variability in neonates.
- Limited data exists on digoxin safety, dosage, and concentration prediction in infants, particularly critically ill newborns.
- Patent ductus arteriosus (PDA) is a common condition in neonates requiring treatment, sometimes with digoxin.
Purpose of the Study:
- To compare the predictive performance of artificial neural network (ANN) modeling against traditional regression modeling for digoxin concentrations in newborn infants.
- To evaluate the accuracy of different models in predicting serum digoxin levels for infants with clinically significant PDA.
Main Methods:
- A retrospective chart review identified neonates treated with digoxin for PDA.
- Data including demographics, disease, and medication information were used to train and validate multivariable linear regression (MLR) and ANN models.
- Model performance was assessed using goodness-of-fit estimates, receiver operating characteristic curves, and classification of toxic concentrations.
Main Results:
- Artificial neural network (ANN) models demonstrated superior performance compared to MLR models in predicting digoxin concentrations.
- The nine-parameter ANN model exhibited enhanced forecasting accuracy and better ability to differentiate toxic concentrations.
- Weak correlations were observed between actual digoxin concentrations and pre-specified variables in the regression models.
Conclusions:
- The nine-parameter ANN model is a valuable tool for predicting serum digoxin concentrations in newborns when therapeutic drug monitoring is not feasible.
- Further validation of ANN models with diverse infant populations across multiple institutions is recommended.
- Accurate digoxin concentration prediction is crucial for optimizing treatment and ensuring patient safety in neonatal care.
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.
More Related Videos
Related Concept Videos
01:15Determination of Multiple Dosing Parameters: Steady-State, Minimum and Maximum Concentrations
01:29Drug Dosing: Infants and Children
01:17Pharmacokinetics in Pediatric Patients: Drug Distribution
01:20Estimation of k and VD of Aminoglycosides
01:24Drug Accumulation During Multiple Dosing: Intermittent IV Infusions
01:26Pharmacokinetics in Pediatric Patients: Drug Excretion