Feature importance to explain multimodal prediction models. A clinical use case
This work addresses the need for explainable AI in clinical settings to improve early warning systems for complications in elderly hip fracture patients, but it is incremental as it applies existing explainability techniques to a specific domain.
The researchers tackled the problem of predicting post-operative mortality in elderly hip fracture patients by developing a multimodal deep-learning model using pre-operative and per-operative data, and they found that Shapley values could explain the model's predictions by estimating modality contributions and enabling interpretable local explanations.
Surgery to treat elderly hip fracture patients may cause complications that can lead to early mortality. An early warning system for complications could provoke clinicians to monitor high-risk patients more carefully and address potential complications early, or inform the patient. In this work, we develop a multimodal deep-learning model for post-operative mortality prediction using pre-operative and per-operative data from elderly hip fracture patients. Specifically, we include static patient data, hip and chest images before surgery in pre-operative data, vital signals, and medications administered during surgery in per-operative data. We extract features from image modalities using ResNet and from vital signals using LSTM. Explainable model outcomes are essential for clinical applicability, therefore we compute Shapley values to explain the predictions of our multimodal black box model. We find that i) Shapley values can be used to estimate the relative contribution of each modality both locally and globally, and ii) a modified version of the chain rule can be used to propagate Shapley values through a sequence of models supporting interpretable local explanations. Our findings imply that a multimodal combination of black box models can be explained by propagating Shapley values through the model sequence.