Leveraging explainable AI models to improve predictive accuracy and ethical accountability in healthcare diagnostic decision support systems
Department of Computer Science, Franklin University, USA.
Review Article
World Journal of Advanced Research and Reviews, 2020, 08(02), 415-434
Publication history:
Received on 11 Sepetmber 2020; revised on 25 November 2020; accepted on 28 November 2020
Abstract:
Artificial intelligence (AI) has emerged as a transformative force in healthcare, particularly within diagnostic decision support systems (DDSS). However, the integration of black-box predictive models into clinical workflows has raised critical concerns about trust, transparency, and ethical accountability. This study presents a framework for leveraging explainable AI (XAI) models to enhance both predictive accuracy and interpretability in healthcare diagnostics, ensuring that algorithmic outputs are clinically meaningful, ethically sound, and aligned with evidence-based practices. The paper investigates the application of various XAI techniques—including SHAP (Shapley Additive Explanations), LIME (Local Interpretable Model-agnostic Explanations), and attention mechanisms—in improving transparency and clinician trust during disease risk stratification and diagnostic recommendation processes. Through comparative modeling experiments across multimodal datasets (EHRs, imaging, lab reports), the study demonstrates that XAI-enhanced models maintain competitive predictive performance while offering interpretable insights into feature contributions and decision logic. To address ethical accountability, the framework includes a real-time auditing layer for bias detection and sensitivity analysis across subpopulations, ensuring fair outcomes for marginalized or underrepresented groups. Integration with clinical feedback loops allows models to evolve iteratively, aligning predictions with practitioner expertise and patient-centered goals. The system is also designed to support regulatory compliance by generating traceable, explainable decision pathways essential for validation and accountability in healthcare governance. By embedding explainability into model design and deployment, this research bridges the gap between AI-driven prediction and ethical, informed clinical judgment. It provides a roadmap for the responsible adoption of AI in healthcare, where transparency, fairness, and trust are as critical as technical performance.
Keywords:
Explainable AI; Healthcare Diagnostics; Ethical Accountability; Decision Support Systems; Interpretability; Clinical Trust
Full text article in PDF:
Copyright information:
Copyright © 2020 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0