Distilling Knowledge from Deep Networks with Applications to Healthcare Domain
This addresses the need for interpretable AI in healthcare to aid clinicians in decision-making, though it is incremental as it builds on existing knowledge-distillation and interpretability methods.
The paper tackles the problem of model interpretability in deep learning for computational phenotyping in healthcare by introducing Interpretable Mimic Learning, a knowledge-distillation approach that uses Gradient Boosting Trees to learn interpretable features from deep models, achieving similar or better performance on a real-world clinical dataset.
Exponential growth in Electronic Healthcare Records (EHR) has resulted in new opportunities and urgent needs for discovery of meaningful data-driven representations and patterns of diseases in Computational Phenotyping research. Deep Learning models have shown superior performance for robust prediction in computational phenotyping tasks, but suffer from the issue of model interpretability which is crucial for clinicians involved in decision-making. In this paper, we introduce a novel knowledge-distillation approach called Interpretable Mimic Learning, to learn interpretable phenotype features for making robust prediction while mimicking the performance of deep learning models. Our framework uses Gradient Boosting Trees to learn interpretable features from deep learning models such as Stacked Denoising Autoencoder and Long Short-Term Memory. Exhaustive experiments on a real-world clinical time-series dataset show that our method obtains similar or better performance than the deep learning models, and it provides interpretable phenotypes for clinical decision making.