What question did this study set out to answer?

This review aims to map AI models to explainable AI techniques and assess their impact on healthcare applications.

March 26, 2026Health Science Reports5 citationsOpen Access

Explainable Artificial Intelligence in Healthcare: Current Landscape, Challenges, and Future Directions

Puntos clave

This review aims to map AI models to explainable AI techniques and assess their impact on healthcare applications.
Conducted a systematic search across six databases for peer-reviewed articles from 2017 to 2025.
Evaluated full texts against predefined inclusion/exclusion criteria according to PRISMA guidelines.
Extracted data on AI model types, XAI techniques, healthcare domains, study designs, and ethical considerations.
Included 70 studies across various healthcare domains like oncology and cardiology.
Deep learning models were most commonly used in 76% of studies, with SHAP and LIME as the primary XAI techniques.
Identified challenges in ethical compliance, inconsistent validation, and lack of standardized interpretability measures.

Resumen

ABSTRACT Background and Aims Artificial Intelligence (AI), particularly Machine Learning (ML) and Deep Learning (DL), is transforming healthcare by enabling improved diagnosis, prognosis, and personalized treatments. However, the opacity of many AI models operates as “black boxes,” limiting interperability, clinician trust, and real‐world adoption. Explainable Artificial Intelligence (XAI) has emerged to address these limitations by providing transparent and actionable insights. This systematic review aims to synthesize the current evidence on XAI in healthcare, mapping AI models to XAI techniques, domains, and clinical applications. Methods A systematic search was conducted across six databases (Elsevier, Springer, Taylor 24%). SHAP (54%) and LIME (30%) were the most commonly used XAI techniques, with Grad‐CAM (23%) and attention mechanisms (20%) applied mainly in imaging and sequence‐based tasks. Only 12 studies explicitly addressed ethical or regulatory considerations. Hybrid interpretable models and human‐centered designs are emerging trends, but real‐world validation and standardized interpretability metrics remain limited. Conclusion XAI enhances transparency, clinician trust, and decision‐making in healthcare AI applications, yet challenges persist, including inconsistent validation, underdeveloped ethical/regulatory frameworks, and lack of standardized interpretability measures. Future work should focus on hybrid, clinically validated XAI models, comprehensive ethical compliance, and user‐centered, domain‐specific implementations to ensure safe and effective integration into clinical practice.

Preguntar a la IA

Me gusta

Guardar

Ver artículo completo