An interpretable and trustworthy AI framework for large-scale longitudinal structure-pain association studies using data from the Osteoarthritis Initiative (OAI)
Quick Answer
This paper shows that An AI framework combining deep learning and interpretable modeling was developed to analyze structure-pain associations in osteoarthritis using OAI data.
Quick Take
It achieved significant improvements in predicting MRI-defined abnormalities, with Matthews correlation coefficients rising from 0.69 to 0.91 for bone marrow lesions. The study identified two pain trajectories, highlighting structural abnormalities as critical risk factors for pain progression.
Key Points
- Developed a deep learning framework for predicting MOAKS from knee MRIs.
- Incorporated conformal prediction for uncertainty quantification in model outputs.
- Matthews correlation coefficients improved: BML from 0.69 to 0.91, CART from 0.45 to 0.80.
- Identified two pain trajectories: rapid and stable progression.
- Structural abnormalities are critical risk factors for osteoarthritis pain.
Paper Resources
Source Excerpt
arXiv:2606. 05357v1 Announce Type: new Abstract: Purpose: To develop an interpretable and trustworthy AI framework that combines deep learning based MRI Osteoarthritis Knee Score (MOAKS) prediction with interpretable statistical modeling to study structure-pain relationships at scale using data from the Osteoarthritis Initiative (OAI).
Materials and Methods: We first developed a deep learning framework to predict MOAKS features directly from knee MRIs and incorporated conformal prediction to provide prediction uncertainty quantification. This uncertainty-aware strategy enables explicit filtering of model outputs, retaining only high-confidence MOAKS predictions at the knee level. …
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →RAIL Guard: Closing the Evaluation-to-Remediation Gap in Responsible AI for Agents
RAIL Guard introduces a closed-loop AI pipeline for large language models (LLMs) that evaluates outputs across eight dimensions and iteratively remediates failures, achieving 96.9% convergence compared to 49.1% for traditional block-and-retry methods. The system reduces unsafe agent executions by 33% without impacting task completion and is available as open-source SDKs.