Open Access Open Access  Restricted Access Subscription Access

The Development of Prompt-Guided, Explainable Artificial Intelligence for Transparent Healthcare Decision Support

Shwetha D S, Madhu M C, Nayana MR, Pawan Kumar NS, Swathi A, Rakshitha GB, Dr Prakash Kuppuswamy

Abstract


Using artificial intelligence (AI) to predict diseases, diagnose patients, analyze medical imaging, and make clinical decisions is revolutionizing the healthcare sector. Nevertheless, numerous sophisticated artificial intelligence models operate as “black-box” systems, wherein the rationale underlying their prognostications remains opaque to medical practitioners and patients alike. In high-stakes medical situations, the absence of interpretability may undermine trust, provoke ethical dilemmas, and engender risks pertaining to clinical implementation. To mitigate this predicament, Explainable AI (XAI) has emerged as a viable solution that guarantees transparency and accountability within AI-driven healthcare frameworks. This manuscript investigates the amalgamation of Explainable AI with prompt-guided reasoning methodologies to bolster clarity within medical decision support systems. The suggested methodology underscores applications in clinical diagnostic assistance, summarization of medical reports, and systems for risk evaluation. Furthermore, the manuscript addresses challenges including data privacy, model bias, and adherence to regulatory standards in the deployment of healthcare AI. By merging explainability with structured prompt-based reasoning, this research aspires to foster transparent, ethical, and dependable AI systems for forthcoming healthcare environments.

 


Full Text:

PDF

References


R. Guidotti et al., “A Survey of Methods for Explaining Black Box Models,” ACM Computing Surveys, vol. 51, no. 5, pp. 1–42, 2018.

M. T. Ribeiro, S. Singh, and C. Guestrin, “Why Should I Trust You? Explaining the Predictions of Any Classifier,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016.

S. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” in Advances in Neural Information Processing Systems (NeurIPS), 2017.

T. Brown et al., “Language Models are Few-Shot Learners,” in Advances in Neural Information Processing Systems (NeurIPS), 2020.

E. Topol, “High-performance medicine: the convergence of human and artificial intelligence,” Nature Medicine, vol. 25, pp. 44–56, 2019.

Yang H, Liang X, Li Z, Sun Y, Hu Z, Xie X, Dashtbozorg B, Huang J, Zhu S, Han L, Zhang J. Prompt mechanisms in medical imaging: a comprehensive survey. The Innovation. 2025 Jun 28.

Wang MH, Jiang X, Zeng P, Li X, Chong KK, Hou G, Fang X, Yu Y, Yu X, Fang J, Pan Y. Balancing accuracy and user satisfaction: the role of prompt engineering in AI-driven healthcare solutions. Frontiers in Artificial Intelligence. 2025 Feb 13; 8:1517918.

Nejadgholi I, Omidyeganeh M, Drouin MA, Boisvert J. Taxonomy for Design and Evaluation of Prompt-Based Natural Language Explanations. arXiv preprint arXiv:2507.10585. 2025 Jul 11.

Wang MH. An Explainable AI Framework for Corneal Imaging Interpretation and Refractive Surgery Decision Support. Bioengineering. 2025 Oct 28; 12(11):1174.


Refbacks

  • There are currently no refbacks.