Summary of Learning Disease Progression Models That Capture Health Disparities, by Erica Chiang et al.
Learning Disease Progression Models That Capture Health Disparities
by Erica Chiang, Divya Shanmugam, Ashley N. Beecy, Gabriel Sayer, Nir Uriel, Deborah Estrin, Nikhil Garg, Emma Pierson
First submitted to arxiv on: 20 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Applications (stat.AP); Machine Learning (stat.ML)
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 A new Bayesian disease progression model is introduced to account for health disparities in progressive diseases. The model captures three key disparities: delayed or reduced care, faster disease progression, and reduced follow-up care. Existing models neglect these disparities, leading to biased estimates of severity, particularly underestimating severity in disadvantaged groups. The proposed approach is theoretically and empirically validated on a heart failure patient dataset, demonstrating its ability to identify high-risk patients. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Disease progression models are important tools for diagnosing and treating many diseases that get worse over time. However, these models often don’t take into account the fact that some people may not receive proper care until their disease is quite advanced. This can lead to biased estimates of how severe someone’s disease is, especially for people who are already disadvantaged. To fix this problem, a new model was developed that considers three key disparities: when people start getting treatment, how fast their disease progresses while they’re being treated, and how often they get follow-up care based on the severity of their condition. This new model was tested on data from heart failure patients and showed that it can identify which groups are most at risk. |
