Dynamic Prediction of Alternating Recurrent Events via Neural Network
It provides a novel method for predicting alternating recurrent events in behavioral science and biostatistics, addressing correlated observations and censoring, but the application is domain-specific.
The paper develops a neural network-based dynamic prediction framework for alternating recurrent events, demonstrating good simulation performance and outstanding capability in predicting low-mood periods for first-year medical residents.
Alternating recurrent events -- event-times of a specific nature that trigger a secondary refractory period -- occur in a wide-range of fields, including behavioral science, criminal justice, and biostatistics. Analysis of these events requires careful attention to the statistical nuance, including correlated observations and repeated outcomes subject to potential censoring. We develop an online dynamic prediction framework appropriate for predicting subsequent alternating recurrent events, by developing neural network theory for a statistical audiences and applying inverse probability weighted pseudo-observations. The proposed model is applied to dynamically predict alternating recurrent event-free time, showing good performance in simulation, and outstanding capability in application to predicting periods of low mood for first-year medical residents. We close with a discussion.