Approaches for Dealing with Seasonality in Clinical Prediction Models for Infections

The quantitative effect of seasonality on the prevalence of infectious diseases has been widely studied in epidemiological models. However, its influence in clinical prediction models has not been analyzed in great depth. In this work, we study the different approaches that can be employed to deal with seasonality when using white-box models related to infections, including two new proposals based on sliding windows and ensembles. We additionally consider the effects of class imbalance and high dimensionality, as they are common problems that must be confronted when building clinical prediction models. These approaches were tested with four datasets: two created synthetically and two extracted from the MIMIC-III database. Our proposed methods obtained the best results in the majority of the experiments, although traditional approaches attained good results in certain cases. On the whole, our results corroborate the theory that clinical prediction models for infections can be improved by considering the effect of seasonality, although the techniques employed to obtain the best results are highly dependent on both the dataset and the modeling technique considered.