Explainable AI in Healthcare: Enhancing Trust through Interpretable Machine Learning Models

As artificial intelligence continues to reshape the healthcare industry, a growing concern among professionals and patients is the "black-box" nature of many machine learning models. While accuracy remains important, trust in AI decisions is equally vital, especially in critical areas like diagnosis and treatment planning. This paper explores the role of Explainable Artificial Intelligence (XAI) in building that trust by making machine learning outputs more transparent and understandable. Using real-world datasets and a case study in cardiovascular disease prediction, we evaluate how interpretable models and explanation techniques like SHAP and LIME improve clinician acceptance and decision-making. A structured questionnaire reveals insights from healthcare professionals on their comfort and reliance on AI tools. This study contributes to the understanding that for AI to be truly effective in healthcare, it must not only be smart—but also explain itself.