Pulmonary embolism and esophagitis are two significant medical conditions that require prompt and accurate detection to ensure proper treatment and management. Machine learning algorithms have shown promise in aiding physicians in the accurate and efficient diagnosis of these conditions. This study aims to explore the use of machine learning algorithms in the detection of pulmonary embolism and esophagitis. The study involved the collection of medical data from various health care, including blood tests and endoscopic procedures, to develop a system that can accurately identify these conditions. Machine learning algorithms are trained and validated on the data collected, and the performance of the algorithms is compared. The results of this study have showed significant improvement in the detection and diagnosis of pulmonary embolism and esophagitis, leading to earlier intervention and improved patient outcomes.