Asthma, a prevalent chronic respiratory condition, poses significant challenges to public health worldwide. Accurate and early prediction of asthma risk can greatly aid healthcare professionals in preventive measures and timely interventions. In this study, we employ a diverse set of machine learning algorithms to predict asthma based on an extensive survey dataset collected through Google Forms. Our methodology encompasses data collection, rigorous preprocessing, and the application of six machine learning algorithms, including Logistic Regression, Decision Trees, K-Nearest Neighbors (KNN), Random Forest, Support Vector Machine, and Naive Bayes. Results reveal varying degrees of accuracy among these models, with KNN emerging as the most accurate, achieving a 92% accuracy rate. The study not only sheds light on the potential of machine learning in asthma prediction but also underscores the importance of algorithm selection in healthcare applications. These findings offer promise in enhancing asthma prediction and management, contributing to improved healthcare outcomes for individuals at risk of this respiratory ailment.