Summary of Feature Importance to Explain Multimodal Prediction Models. a Clinical Use Case, by Jorn-jan Van De Beld et al.
Feature importance to explain multimodal prediction models. A clinical use case
by Jorn-Jan van de Beld, Shreyasi Pathak, Jeroen Geerdink, Johannes H. Hegeman, Christin Seifert
First submitted to arxiv on: 29 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a deep-learning-based early warning system for predicting post-operative mortality in elderly hip fracture patients. The model combines pre-operative and per-operative data, including patient demographics, images, vital signs, and medications. The authors use ResNet to extract features from images and LSTM to analyze vital signals. To ensure explainability, the team employs Shapley values to quantify the relative contribution of each modality to the predictions. This approach enables interpretable local explanations for clinicians. Experimental results show that the multimodal model outperforms unimodal models in predicting post-operative mortality. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research aims to create a warning system to help doctors predict when elderly hip fracture patients might have complications after surgery, which can be life-threatening. The team uses special AI models and combines different types of data before and during the surgery to make predictions. They also developed a way to explain why the model made certain predictions, making it more useful for doctors. This could help save lives by alerting doctors to take extra care with high-risk patients or even inform patients about potential complications. |
Keywords
» Artificial intelligence » Deep learning » Lstm » Resnet
