A new review paper published on arXiv synthesizes recent advancements in trustworthy artificial intelligence, focusing specifically on robustness and explainability within the digital health domain. The paper outlines key dimensions such as fairness, accountability, and privacy, which are critical for the ethical integration of machine learning in healthcare. It explores application-specific trust considerations in areas like intensive care and metabolic health, and details methods for improving model robustness and explainability, including techniques for data scarcity and distributional shifts. AI
IMPACT Provides a framework for developing more reliable and explainable AI solutions in critical healthcare applications.
RANK_REASON The item is a comprehensive review paper published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]
- accountability
- arXiv
- Digital Health
- explainability
- intensive care unit
- machine learning
- metabolic health
- Neonatal health care costs related to smoking during pregnancy
- privacy
- robustness
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
