Explainable artificial intelligence with anchors method for breast cancer treatment recommendation

Abstract

In the search of precision medicine for breast cancer, the integration of artificial intelligence (AI) offers unprecedented opportunities to improve diagnosis, prognosis, and treatment strategies. This paper discovers the prospective of explainable artificial intelligence (XAI) to demystify the black-box landscape of AI, fostering both transparency and trust. We introduce an XAI-based approach, anchored by the anchors explanation method, to provide interpretable predictions for breast cancer treatment. Our results demonstrate that while anchors improve the interpretability of model predictions, the precision and coverage of these explanations vary, highlighting the challenges of achieving high-fidelity explanations in complex clinical scenarios. Our findings underscore the importance of balancing the trade-off between model complexity and explainability. They advocate for the iterative development of AI systems with iterative feedback loops from clinicians to align the model's logic with clinical reasoning. We propose a framework for the clinical deployment of XAI in breast cancer. Ultimately, XAI, equipped with techniques like Anchors, holds the promise of enhancing precision medicine by making AI-assisted decisions more transparent and trustworthy, empowering clinicians and enabling patients to engage in informed discussions about their treatment options. However, anchors lag in the accuracy of rules and remains a challenge to the AI developers.