This study evaluates the integration of Microsoft OneNote and ChemDraw in organic chemistry education and utilizes machine learning to predict student performance and enhance personalized learning experiences. Results show that the Random Forest model outperforms XGBoost, achieving high accuracy (97%) and recall (97%), effectively identifying students across performance tiers. These predictions enable targeted interventions, such as support for at-risk students or advanced resources for high achievers. However, correlation analysis reveals weak relationships between engagement metrics, such as tool usage and academic performance, with “OneNote Pages Created” and “ChemDraw Tasks Completed” showing minimal direct influence on quiz and exam scores. This indicates that while these tools enhance engagement and conceptual understanding, their direct impact on outcomes is limited. The findings underscore the need for complementary strategies, including guided instruction, assessment alignment, and scaffolding, alongside broader factors like instructional quality and motivation, to optimize learning outcomes effectively.