A physician-facing system that uses Grad-CAM heatmaps plus pixel-level annotations to fine-tune multi-label medical classifiers reduces measured bias on one rare chest X-ray label and earns positive usability ratings from 12 participants.
A Two-Phase Visualization System for Continuous Human-AI Collaboration in Sequelae Analysis and Modeling
1 Pith paper cite this work, alongside 1 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1
external citations · Pith
abstract
In healthcare, AI techniques are widely used for tasks like risk assessment and anomaly detection. Despite AI's potential as a valuable assistant, its role in complex medical data analysis often oversimplifies human-AI collaboration dynamics. To address this, we collaborated with a local hospital, engaging six physicians and one data scientist in a formative study. From this collaboration, we propose a framework integrating two-phase interactive visualization systems: one for Human-Led, AI-Assisted Retrospective Analysis and another for AI-Mediated, Human-Reviewed Iterative Modeling. This framework aims to enhance understanding and discussion around effective human-AI collaboration in healthcare.
citation-role summary
background 1
citation-polarity summary
fields
cs.HC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
MEDebiaser: A Human-AI Feedback System for Mitigating Bias in Multi-label Medical Image Classification
A physician-facing system that uses Grad-CAM heatmaps plus pixel-level annotations to fine-tune multi-label medical classifiers reduces measured bias on one rare chest X-ray label and earns positive usability ratings from 12 participants.