A DEEP NEURAL NETWORK TWO-PART MODEL AND FEATURE IMPORTANCE TEST FOR SEMI-CONTINUOUS DATA.

Semi-continuous data frequently arise in clinical practice. For example, while many surgical patients still suffer from varying degrees of acute postoperative pain (POP) sometime after surgery (i.e., POP score > 0), others experience none (i.e., POP score = 0), indicating the existence of two distinct data processes at play. Existing parametric or semi-parametric two-part modeling methods for this type of semi-continuous data can fail to appropriately model the two underlying data processes as such methods rely heavily on (generalized) linear additive assumptions. However, many factors may interact to jointly influence the experience of POP non-additively and non-linearly. Motivated by this challenge and inspired by the flexibility of deep neural networks (DNN) to accurately approximate complex functions universally, we derive a DNN-based two-part model by adapting the conventional DNN methods with two additional components: a bootstrapping procedure along with a filtering algorithm to boost the stability of the conventional DNN, an approach we denote as sDNN. To improve the interpretability and transparency of sDNN, we further derive a feature importance testing procedure to identify important features associated with the outcome measurements of the two data processes, denoting this approach fsDNN. We show that fsDNN not only offers a statistical inference procedure for each feature under complex association but also that using the identified features can further improve the predictive performance of sDNN. The proposed sDNN- and fsDNN-based two-part models are applied to the analysis of real data from a POP study, in which application they clearly demonstrate advantages over the existing parametric and semi-parametric two-part models. Further, we conduct extensive numerical studies and draw comparisons with other machine learning methods to demonstrate that sDNN and fsDNN consistently outperform the existing two-part models and frequently used machine learning methods regardless of the data complexity. An R package implementing the proposed methods has been developed and is available in the Supplementary Material (Zou et al, 2025) and is also deposited on GitHub (https://github.com/BZou-lab/fsDNN).