Barttender: An approachable & interpretable way to compare medical imaging and non-imaging data
This addresses the problem of limited clinical adoption of imaging-based deep learning by providing an interpretable way for researchers to compare data modalities, though it appears incremental as it builds on existing deep learning approaches.
The paper tackles the challenge of comparing imaging and non-imaging data in healthcare by introducing Barttender, an interpretable framework that converts tabular features into grayscale bars for deep learning-based modeling, achieving performance comparable to traditional methods on CheXpert and MIMIC datasets.
Imaging-based deep learning has transformed healthcare research, yet its clinical adoption remains limited due to challenges in comparing imaging models with traditional non-imaging and tabular data. To bridge this gap, we introduce Barttender, an interpretable framework that uses deep learning for the direct comparison of the utility of imaging versus non-imaging tabular data for tasks like disease prediction. Barttender converts non-imaging tabular features, such as scalar data from electronic health records, into grayscale bars, facilitating an interpretable and scalable deep learning based modeling of both data modalities. Our framework allows researchers to evaluate differences in utility through performance measures, as well as local (sample-level) and global (population-level) explanations. We introduce a novel measure to define global feature importances for image-based deep learning models, which we call gIoU. Experiments on the CheXpert and MIMIC datasets with chest X-rays and scalar data from electronic health records show that Barttender performs comparably to traditional methods and offers enhanced explainability using deep learning models.