Unscheduled 30-day readmissions are a hallmark of Congestive Heart Failure (CHF) patients that pose significant health risks and escalate care cost. In order to reduce readmissions and curb the cost of care, it is important to initiate targeted intervention programs for patients at risk of readmission. This requires identifying high-risk patients at the time of discharge from hospital. Here, using real data from over 7500 CHF patients hospitalized between 2012 and 2016 in Sweden, we built and tested a deep learning framework to predict 30-day unscheduled readmission. We present a cost-sensitive formulation of Long Short-Term Memory (LSTM) neural network using expert features and contextual embedding of clinical concepts. This study targets key elements of an Electronic Health Record (EHR) driven prediction model in a single framework: using both expert and machine derived features, incorporating sequential patterns and addressing the class imbalance problem. We evaluate the contribution of each element towards prediction performance (ROC-AUC, F1-measure) and cost-savings. We show that the model with all key elements achieves higher discrimination ability (AUC: 0.77; F1: 0.51; Cost: 22% of maximum possible savings) outperforming the reduced models in at least two evaluation metrics. Additionally, we present a simple financial analysis to estimate annual savings if targeted interventions are offered to high risk patients.

In classification problems, as the number of classes increases, correctly classifying a new instance into one of them is assumed to be more challenging than making the same decision in the presence of fewer classes. The essence of the problem is that using the learning algorithm on each decision boundary individually is better than using the same learning algorithm on several of them simultaneously. However, why and when it happens is still not well-understood today. This work’s main contribution is to introduce the concept of heterogeneity of decision boundaries as an explanation of this phenomenon. Based on the definition of heterogeneity of decision boundaries, we analyze and explain the differences in the performance of state of the art approaches to solve multi-class classification. We demonstrate that as the heterogeneity increases, the performances of all approaches, except one-vs-one, decrease. We show that by correctly encoding the knowledge of the heterogeneity of decision boundaries in a decomposition of the multi-class problem, we can obtain better results than state of the art decompositions. The benefits can be an increase in classification performance or a decrease in the time it takes to train and evaluate the models. We first provide intuitions and illustrate the effects of the heterogeneity of decision boundaries using synthetic datasets and a simplistic classifier. Then, we demonstrate how a real dataset exhibits these same principles, also under realistic learning algorithms. In this setting, we devise a method to quantify the heterogeneity of different decision boundaries, and use it to decompose the multi-class problem. The results show significant improvements over state-of-the-art decompositions that do not take the heterogeneity of decision boundaries into account.