Feature Ranking in Predictive Models for Hospital-Acquired Acute Kidney Injury

Abstract

Acute Kidney Injury (AKI) is a common complication encountered among hospitalized patients, imposing significantly increased cost, morbidity, and mortality. Early prediction of AKI has profound clinical implications because currently no treatment exists for AKI once it develops. Feature selection (FS) is an essential process for building accurate and interpretable prediction models, but to our best knowledge no study has investigated the robustness and applicability of such selection process for AKI. In this study, we compared eight widely-applied FS methods for AKI prediction using nine-years of electronic medical records (EMR) and examined heterogeneity in feature rankings produced by the methods. FS methods were compared in terms of stability with respect to data sampling variation, similarity between selection results, and AKI prediction performance. Prediction accuracy did not intrinsically guarantee the feature ranking stability. Across different FS methods, the prediction performance did not change significantly, while the importance rankings of features were quite different. A positive correlation was observed between the complexity of suitable FS method and sample size. This study provides several practical implications, including recognizing the importance of feature stability as it is desirable for model reproducibility, identifying important AKI risk factors for further investigation, and facilitating early prediction of AKI.

Keratoconus Detection Using the Fusion Features of Anterior and Lateral Segment Photographed Images

“…The ILFS technique presents the best classification performance for all three sets of features, ASPI, LSPI and A&LSPI, as shown in Table IX. This could be because ReliefF is more stable with more sample counts (> 200), which would affect the performance of the ReliefF technique in our experiments; this finding is similar to that from L. Wu et al [51]. Additionally, ILFS is found to have the best and most stable performance suitable for the size of the data and the numbers of features.…”

“…The FS method is also selected based on the suitability of the data size. L. Wu et al [51] reported that the embedded random forest (RF) method appeared to be more suitable with a large number of samples, whereas ReliefF was better for medium-sized data, and the chi-square method outperformed the other methods when the number of samples was small. The ILFS method returns the best results in terms of AUC.…”

A Proxy for Detecting IUGR Based on Gestational Age Estimation in a Guatemalan Rural Population

“…To that end, the features were ranked at each feature vectors, and the mean rank was determined by averaging the ranking of each feature over the 250 feature vectors. This simple aggregation technique was used as it has shown to be effective to combine different features sets in the medical application field (Saeys et al, 2007;Wu et al, 2018).…”

Changing relative risk of clinical factors for hospital-acquired acute kidney injury across age groups: a retrospective cohort study

“…To examine the change in relative risk of AKI predictors in the general inpatient population, we applied a machine learning-based feature selection algorithm over a large EMR dataset with close to two thousand variables to derive the relative ranking profiles and compared profiles across different age groups. Based on our previous research [ 31 ], we acknowledge that relative importance rankings of variables are affected by data samplings and feature selection methods. This study is not in any way to provide an absolute ranking of important predictors.…”