Interpretable Predictive Models for Healthcare via Rational Logistic Regression
This addresses the need for interpretable and effective predictive models in healthcare, particularly for clinical applications like morbidity prediction, but it is incremental as it builds on logistic regression.
The paper tackles the problem of predictive modeling in healthcare using electronic health records (EHRs), where deep learning often underperforms compared to simple models like logistic regression, by developing rational logistic regression (RLR), which shows efficacy in empirical comparisons on real-world clinical tasks.
The healthcare sector has experienced a rapid accumulation of digital data recently, especially in the form of electronic health records (EHRs). EHRs constitute a precious resource that IS researchers could utilize for clinical applications (e.g., morbidity prediction). Deep learning seems like the obvious choice to exploit this surfeit of data. However, numerous studies have shown that deep learning does not enjoy the same kind of success on EHR data as it has in other domains; simple models like logistic regression are frequently as good as sophisticated deep learning ones. Inspired by this observation, we develop a novel model called rational logistic regression (RLR) that has standard logistic regression (LR) as its special case (and thus inherits LR's inductive bias that aligns with EHR data). RLR has rational series as its theoretical underpinnings, works on longitudinal time-series data, and learns interpretable patterns. Empirical comparisons on real-world clinical tasks demonstrate RLR's efficacy.