This study aims to introduce a novel approach that integrates artificial intelligence (AI) and data mining to personalize treatment protocols for cystic fibrosis achieved using decision trees that generate classification rules based on patient symptomatology, offering a path to the most suitable treatment. This study uses the data mining capabilities of AI to uncover hidden information from extensive medical data repositories. Five distinct treatment pathways, identified using the developed AI program, produced five decision trees with varied results, illustrating the effectiveness of the proposed method. This approach depends on the size of the patient data sample used, highlighting the crucial role of data volume in the decision-making process. The new method increases the precision of treatment determination, as demonstrated through a case study in which three patients with similar symptoms received different treatments, revealing a 66.66% probability of correct treatment application, illustrating the potential to reduce human error and improve healthcare delivery efficiency. The methodology enhances precision, streamlines the decision tree structure, and averts lengthy and costly treatments, thus enhancing patients’ quality of life. It further improved accuracy by generating a set of rules from the data, fostering informed decision-making in various research contexts, not solely medical. This groundbreaking approach can supplement existing medical data analysis techniques and could be used to enhance personalized patient care in cystic fibrosis and potentially other diseases. Its novelty lies in using AI and data mining in clinics to uncover patient-specific treatment paths. Keywords: Artificial Intelligence, Data Mining, Cystic Fibrosis, Personalized Treatment, Decision Trees DOI： https://doi.org/10.35741/issn.0258-2724.58.4.86