Medical imaging is crucial for the early diagnosis and management of diseases, offering detailed insights into patient conditions. With the advent of artificial intelligence (AI) and machine learning (ML), the potential to automate and refine these diagnostic processes has expanded significantly. This book chapter outlines advanced machine learning techniques applied to detect abnormalities in medical images, enhancing healthcare management systems. Key algorithms such as Logistic Regression (LR), Random Forest (RF), and Decision Trees (DT) are explored for their efficacy in differentiating COVID-19 from healthy chest X-ray images. The integration of these AI techniques not only improves clinical workflows by reducing costs but also enhances patient outcomes by providing quick and accurate diagnoses. Evidence from this study indicates that deep learning models can identify COVID-19 cases from images with over 99% accuracy, matching the expertise of radiologists. The application of AI in this context demonstrates its capacity to relieve the heavy burdens on healthcare systems by automating complex diagnostic tasks and optimizing the allocation of critical resources. Furthermore, this chapter discusses the broader implications of AI in healthcare administration, highlighting how intelligent algorithms contribute to strategic decision-making and the resilience of healthcare infrastructures during crises like the COVID-19 pandemic. The insights gained underscore AI's transformative potential in augmenting human capabilities and shaping future healthcare solutions.