Summary of Graph Neural Networks For Heart Failure Prediction on An Ehr-based Patient Similarity Graph, by Heloisa Oss Boll et al.
Graph Neural Networks for Heart Failure Prediction on an EHR-Based Patient Similarity Graph
by Heloisa Oss Boll, Ali Amirahmadi, Amira Soliman, Stefan Byttner, Mariana Recamonde-Mendoza
First submitted to arxiv on: 29 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 The study introduces a novel approach using graph neural networks (GNNs) and a Graph Transformer (GT) to predict the incidence of heart failure (HF) on a patient similarity graph at the next hospital visit. The approach utilizes electronic health records (EHR) from the MIMIC-III dataset, K-Nearest Neighbors (KNN) algorithm, and three models – GraphSAGE, Graph Attention Network (GAT), and Graph Transformer (GT). The study evaluates model performance using F1 score, AUROC, and AUPRC metrics and compares results against baseline algorithms. The GT model demonstrates the best performance with a high F1 score of 0.5361, AUROC of 0.7925, and AUPRC of 0.5168. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study uses special computers called graph neural networks (GNNs) to help doctors predict when someone will have heart failure again in the future. It looks at a patient’s medical history and tries to find patterns that can help make this prediction. The computer program uses something called a “graph” which is like a map of all the different things that are connected to a person, like their medications or diagnoses. This helps the computer understand how all these things relate to each other. |
Keywords
» Artificial intelligence » F1 score » Graph attention network » Transformer
