Summary of Integrating Social Determinants Of Health Into Knowledge Graphs: Evaluating Prediction Bias and Fairness in Healthcare, by Tianqi Shang et al.
Integrating Social Determinants of Health into Knowledge Graphs: Evaluating Prediction Bias and Fairness in Healthcare
by Tianqi Shang, Weiqing He, Tianlong Chen, Ying Ding, Huanmei Wu, Kaixiong Zhou, Li Shen
First submitted to arxiv on: 29 Nov 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computers and Society (cs.CY); Machine Learning (cs.LG)
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 proposed study constructs a social determinants of health (SDoH)-enriched knowledge graph using the MIMIC-III dataset and PrimeKG, addressing the underexplored integration of SDoH into biomedical knowledge graphs. The research introduces a novel fairness formulation for graph embeddings focusing on invariance with respect to sensitive SDoH information. A heterogeneous-GCN model is employed for drug-disease link prediction, detecting biases related to various SDoH factors. To mitigate these biases, the study proposes a post-processing method that strategically reweights edges connected to SDoHs, balancing their influence on graph representations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary SdoH play an important role in patient health outcomes, but are often overlooked in biomedical research. This study creates a special type of computer database called a knowledge graph that includes information about SdoH. The researchers use a new way to make sure the database is fair by ignoring sensitive information like where people live or how much money they have. They then use this database to predict which medicines are good for certain diseases and find out that some biases are present in the predictions. To fix these biases, the study proposes a new method that adjusts the importance of different factors in the database. |
Keywords
» Artificial intelligence » Gcn » Knowledge graph
