Cancer is the second leading cause of death globally and is expected to affect 1 in 2 men and 1 in 3 women by 2030. Despite advances in surgery and pharmacology, the lack of implementation of personalized medicine protocols means that patients with very different genetic profiles are treated the same way. Minimal Residual Disease (MRD) has emerged as a crucial prognostic factor, allowing precision medicine to evaluate treatment responses and predict relapses. MRD tests identify tumor cells that survive therapy and cause relapses. Massive sequencing has provided a useful tool for detecting tumor DNA with high sensitivity. However, challenges remain in detecting real tumor signals amidst noise and artifacts, clinical implementation faces hurdles due to lack of standardization and automation, sensitivity and specificity values are not 100%, and costs are high. This research thesis proposes a methodology and digital framework, based on Model Driven Engineering (MDE), to optimize MRD detection and monitoring using data science and artificial intelligence.