Why the study?
Do machine learning imputation methods improve the performance of predictive models in pediatric patients undergoing evaluation for cardiomyopathy?
Do machine learning imputation methods improve the performance of predictive models in pediatric patients undergoing evaluation for cardiomyopathy?
Machine learning imputation methods did not improve the performance of predictive models for ordering cardiac MRI in pediatric cardiomyopathy evaluation, but demonstrated the robustness of the unaugmented models.
Answers are grounded in this paper and cite their sources.
Imputation adds no performance gain for pediatric cardiomyopathy MRI prediction models; leaves open whether robustness generalizes to prospective cohorts.
Many clinical research datasets have a large percentage of missing values that directly impacts their usefulness in yielding high accuracy classifiers when used for training in supervised machine learning. While missing value imputation methods have been shown to work well with smaller percentages of missing values, their ability to impute sparse clinical research data can be problem specific. We previously attempted to learn quantitative guidelines for ordering cardiac magnetic resonance imaging during the evaluation for pediatric cardiomyopathy, but missing data significantly reduced our usable sample size. In this work, we sought to determine if increasing the usable sample size through imputation would allow us to learn better guidelines. We first review several machine learning methods for estimating missing data. Then, we apply four popular methods (mean imputation, decision tree, k-nearest neighbors, and self-organizing maps) to a clinical research dataset of pediatric patients undergoing evaluation for cardiomyopathy. Using Bayesian Rule Learning (BRL) to learn ruleset models, we compared the performance of imputation-augmented models versus unaugmented models. We found that all four imputation-augmented models performed similarly to unaugmented models. While imputation did not improve performance, it did provide evidence for the robustness of our learned models.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2016) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: