Cardiovascular diseases (CVDs) are prevalent among obstructive sleep apnea (OSA) patients, presenting significant challenges in predictive modeling due to the complex interplay of these comorbidities. Current methodologies predominantly lack the dynamic and longitudinal perspective necessary to accurately predict CVD progression in the presence of OSA. This study addresses these limitations by proposing a novel multi-level phenotypic model that analyzes the progression and interaction of these comorbidities over time. Our study utilizes a longitudinal cohort from the Wisconsin sleep cohort, consisting of 1,123 participants, tracked over several decades. The methodology consists of three advanced steps to capture the relationships between these comorbid conditions: (1) performing feature importance analysis using tree-based models to highlight the predominant role of variables in predicting CVD outcomes. (2) developing a logistic mixed-effects model (LGMM) to identify longitudinal transitions and their significant factors, enabling detailed tracking of individual trajectories; (3) and utilizing t-distributed stochastic neighbor embedding (t-SNE) combined with Gaussian mixture models (GMM) to classify patient data into distinct phenotypic clusters. In the analysis of feature importance, clinical indicators such as total cholesterol, low-density lipoprotein, and diabetes emerged as the top predictors, highlighting their significant roles in CVD onset and progression. The LGMM predictive models exhibited a high diagnostic accuracy with an aggregate accuracy of 0.9556. The phenotypic analysis yielded two distinct clusters, each corresponding to unique risk profiles and disease progression pathways. One cluster notably carried a higher risk for major adverse cardiovascular events (MACEs), attributed to key factors like nocturnal hypoxia and sympathetic activation. Analysis using t-SNE and GMM confirmed these phenotypes, which marked differences in progression rates between the clusters. In conclusion, our study provides a profound understanding of the dynamic OSA-CVD interactions, offering robust tools for predicting CVD onset and informing personalized treatment strategies.