Dynamic Predictive Models for Hospital Readmission Risk

Healthcare readmission rates in hospitals are sensitive indicators of quality and clients’ outcomes. Proper models for prediction are crucial in helping avoid cases of unnecessary readmission and the correct allocation of re-sources. In this paper, dynamic predictive models for risk evaluation of hospital readmission are developed, and machine learning strategies are applied to enhance the model's accuracy. In this paper, two types of models are considered and built using logistic regression and a neural network model. Incident data sources include clinical and demographic measures from a hospital database and accuracy, precision, recall, and F1- score are used to assess the performance of the models. Comparing the predictive accuracy of the results, the neural network model performs better than the selected logistic regression model when identifying high-risk patients for readmission. This paper also presents a comparative analysis depending on the model parameters and data divisions, which shows that the neural network can more flexibly approximate nonlinear trends in the data distribution. This paper ends with a discourse on applying high-dependent predictive models to decreasing hospital readmission rates in clinical practice. The results of the research are directed to the need for proper risk assessment to enhance the results of the treatments and the quality of the healthcare services.