Deeply-Learned Generalized Linear Models with Missing Data
This addresses a critical problem for biomedical researchers using deep learning, as missing data is common and complex in such datasets, though the approach appears incremental by extending existing generalized linear models to handle missingness.
The paper tackles the challenge of missing data in biomedical datasets for deep learning by introducing a new architecture, dlglm, that handles both ignorable and non-ignorable missingness in features and responses during training. It demonstrates through simulation that dlglm outperforms existing methods in the presence of missing not at random (MNAR) missingness.
Deep Learning (DL) methods have dramatically increased in popularity in recent years, with significant growth in their application to supervised learning problems in the biomedical sciences. However, the greater prevalence and complexity of missing data in modern biomedical datasets present significant challenges for DL methods. Here, we provide a formal treatment of missing data in the context of deeply learned generalized linear models, a supervised DL architecture for regression and classification problems. We propose a new architecture, \textit{dlglm}, that is one of the first to be able to flexibly account for both ignorable and non-ignorable patterns of missingness in input features and response at training time. We demonstrate through statistical simulation that our method outperforms existing approaches for supervised learning tasks in the presence of missing not at random (MNAR) missingness. We conclude with a case study of a Bank Marketing dataset from the UCI Machine Learning Repository, in which we predict whether clients subscribed to a product based on phone survey data. Supplementary materials for this article are available online.