A new research paper explores how to improve the perception of patients' experiences in medical records by addressing testimonial injustice. The study uses causal discovery to build a structural causal model that links demographic features like age, gender, and race to specific types of testimonial injustice. Researchers then selectively edited physician notes based on this model, comparing the results to blanket LLM modifications. Human experts and an LLM found that these targeted edits enhanced clarity regarding patient conditions and, for human experts, shifted blame from patients to objective external factors. AI
IMPACT This research could lead to more equitable patient representation in medical records, potentially improving health outcomes.
RANK_REASON The cluster contains a single academic paper published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX
- DagsHub
- Gotit.pub
- Hugging Face
- Kenya Andrews
- ScienceCast
- structural causal model
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
