Dealing with the Missing, Imbalanced and Sparse Features Problems in Emergency Data Using Random Forest, K-means and PCA Respectively (Preprint)

Abstract

BACKGROUND In emergency departments (ED), timely rescue is very important as patients’ conditions usually deteriorate rapidly. Early diagnosis can increase patients’ chances of survival. Early diagnosis can be improved by predictive models based on machine learning using Electronic Medical Record (EMR) data. However, ED data are usually imbalanced, having missing values and sparse features. These quality issues make it challenging to build early identification models for diseases in ED. OBJECTIVE The objective of this study is to propose a systematic approach to deal with missing, imbalanced and sparse feature problems of ED data. METHODS We used random forest and K-means algorithms to interpolate missing values and under-sample data. Regarding sparse features, we used principal component analysis to reduce dimensions. For continuous and discrete variables, the decision coefficient R2 and Kappa coefficient are used to evaluate the performance respectively. The area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUPRC) are used to estimate the model performance. To further evaluate the proposed approach, we carried out a case study using an ED dataset extracted from Hainan Hospital of Chinese PLA General Hospital. A logistic regression model for patient condition worsening prediction was built out of the data processed by the proposed approach. RESULTS A total of 1085 patients with rescue record and 17959 patients without rescue record were collected, which were significantly imbalanced. 275, 402 and 891 variables are extracted from laboratory tests, medications and diagnosis, respectively. After data preprocessing, the median R2 of random forest interpolation for continuous variables is 0.623 (IQR: 0.647), and the median of Kappa coefficient for discrete variable interpolation is 0.444 (IQR: 0.285). The logistic regression model constructed using the initial diagnostic data has poor performance and variable separation, which is reflected in the abnormally high OR values of the two variables of cardiac arrest and respiratory arrest (27857.4 and 9341.6) and an abnormal confidence interval. Using the processed data, the recall of the model reaches 0.77, F1-SCORE is 0.74, and AUC is 0.64. CONCLUSIONS We proposed a machine learning method to deal with data quality issues such as missing data, data imbalance, and sparse features in emergency data, so as to improve data availability. A preliminary case study indicate the results produced by the proposed method can be used for building prediction model for emergency patients.

Assessing Predictability of Marine Heatwaves With Random Forests

“…In other words, the majority class (i.e., no MHW) has been down-sampled to balance out the categories. Similar techniques have been previously reported to yield higher efficiency in classifying imbalanced datasets by tree classifiers (Drummond & Holte, 2003;Kubat & Matwin, 1997) as well as random forest algorithms (Chen et al, 2004). Preliminary analyses with no balancing showed spurious extreme high accuracies due to model overfitting, that mainly identifies MHW absence throughout the whole northeast Pacific.…”

Development and validation of a simplified risk score for the prediction of critical COVID‐19 illness in newly diagnosed patients

“…For the classification RFs, we used the presence of an event (critical phase or COVID‐19‐related death) within 7 days of diagnosis as the outcome of interest during Boruta selection. We used the balanced method by Chen et al 11 both during Boruta selection and modeling with the selected variables. We used survival random forest (RSF) as described by Ishwaran et al, 12 during Boruta selection, and during the final modeling of time‐to‐event data.…”

A novel lower extremity non-contact injury risk prediction model based on multimodal fusion and interpretable machine learning

“…7 , is the decision tree model, is the classification result of the decision tree, and is the index function. Since there was a class imbalance problem in the dataset, this study improved the impact of the class imbalance problem on model construction by introducing a sample weight parameter in the RF ( Chen, 2004 ), as shown in Eq. 8 .…”