Bidirectional human-AI collaboration in brain tumour assessments improves both expert human and AI agent performance

2025-12-13

AI Summary

Current human–AI collaboration in brain tumor MRI diagnosis remains unidirectional—primarily AI-assisted interpretation—neglecting the potential for human expertise to actively refine AI models. Method: We propose and empirically validate a bidirectional empowerment framework: (1) radiologists provide real-time, task-specific feedback to drive iterative AI model refinement, and (2) AI outputs augment clinicians’ metacognitive awareness and diagnostic decision quality. Our collaborative decision-support system integrates human–AI interaction, feedback-driven model updating, and multidimensional metacognitive assessment, evaluated on real-world clinical MRI data. Contribution/Results: Radiologists’ diagnostic accuracy improved by 12%; the AI model’s AUC increased by 0.08; inter-rater agreement between human and AI reached Cohen’s κ = 0.91. Critically, this is the first empirical demonstration that expert human feedback significantly enhances AI’s accuracy, confidence calibration, and output consistency—establishing bidirectional collaboration as superior to unidirectional assistance and challenging the “AI-as-replacement” paradigm. Our work advances trustworthy, human-centered medical AI.

Technology Category

• Humans and AI: Human-in-the-loop Machine Learning
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The benefits of artificial intelligence (AI) human partnerships-evaluating how AI agents enhance expert human performance-are increasingly studied. Though rarely evaluated in healthcare, an inverse approach is possible: AI benefiting from the support of an expert human agent. Here, we investigate both human-AI clinical partnership paradigms in the magnetic resonance imaging-guided characterisation of patients with brain tumours. We reveal that human-AI partnerships improve accuracy and metacognitive ability not only for radiologists supported by AI, but also for AI agents supported by radiologists. Moreover, the greatest patient benefit was evident with an AI agent supported by a human one. Synergistic improvements in agent accuracy, metacognitive performance, and inter-rater agreement suggest that AI can create more capable, confident, and consistent clinical agents, whether human or model-based. Our work suggests that the maximal value of AI in healthcare could emerge not from replacing human intelligence, but from AI agents that routinely leverage and amplify it.

Problem

• Enhancing brain tumor assessment accuracy through human-AI collaboration.
• Improving metacognitive ability and consistency in clinical decision-making.
• Maximizing patient benefit by leveraging synergistic human-AI partnerships.

Innovation

• Bidirectional human-AI collaboration enhances brain tumor assessment accuracy
• AI agents improve with expert human support in clinical partnerships
• Synergistic partnership boosts accuracy, metacognition, and inter-rater agreement