Forecasting Hospital Readmissions with Machine Learning

Abstract

Hospital readmissions are regarded as a compounding economic factor for healthcare systems. In fact, the readmission rate is used in many countries as an indicator of the quality of services provided by a health institution. The ability to forecast patients' readmissions allows for timely intervention and better post-discharge strategies, preventing future life-threatening events, and reducing medical costs to either the patient or the healthcare system. In this paper, four machine learning models are used to forecast readmissions: support vector machines with a linear kernel, support vector machines with an RBF kernel, balanced random forests, and weighted random forests. The dataset consists of 11,172 actual records of hospitalizations obtained from the General Hospital of Komotini "Sismanogleio" with a total of 24 independent variables. Each record is composed of administrative, medical-clinical, and operational variables. The experimental results indicate that the balanced random forest model outperforms the competition, reaching a sensitivity of 0.70 and an AUC value of 0.78.

Keywords: forecasting; machine learning; readmissions.

Figure 1

Hyperplane selection and support vectors. The pronounced black contour represents the SVs thus defining the margins with the dashed lines. The plain single line describes the separating hyperplane.

Figure 2

The non-separable two-class scenario in the input space(left) and the two-dimensional data space in a three-feature space after the projection (right). The two classes are represented by the different colors: blue and red.

Figure 3

Overview of a 3-fold Cross Validation training scheme. It shows that each fold is used as a testing sample, while the remaining folds are used for training the model for each parameters’ value combination.

Figure 4

Aggregated results and comparison of proposed methodologies.

Figure 5

Classification performance measurement (AUC).