[EMBARGOED UNTIL 6/1/2023] Endured by the growing prevalence of cardiovascular diseases (CVDs), the demand for cardiac care services has increased. On the other hand, the supply of cardiologists is expected to be insufficient to meet this growing demand. Considering this imbalance between demand and capacity, cardiology clinics strive to improve their services. Thus, this dissertation proposes two approaches for improving cardiac care services through the application of predictive and prescriptive analytics. The first approach develops an efficient appointment system (AS) that allocates patients' demand during the clinic session effectively to improve resource utilization and patient satisfaction. The proposed AS also addresses the problem of clinical uncertainties, such as patient no-shows and service-time variability, which adversely impact AS efficiency by developing a predict-then-schedule framework. In the predict step, patient-specific no-show risk and service duration are estimated using machine learning (ML) models. The schedule step determines the appointment time and interval for each patient using a sequential AS that leverages the ML predictions. In addition, four new ML-enabled sequencing rules are proposed. The proposed approach and sequencing rules are validated using real clinical data. Besides, the effectiveness of integrating ML-based uncertainty predictions into the AS design is also evaluated for 32 different clinic environments. Results indicate that an AS design adopting the predict-then-schedule approach always dominates the conventional system and could improve the efficiency by 60 percent. The new sequencing rules can improve the AS performance by up to 40 percent when compared to the existing policies. Finally, several managerial insights on sequencing and overbooking are also provided. On the other hand, the second approach develops an ML-based model to predict the long-term CVD risk that can aid in the early detection of CVD. Unlike the existing tools for CVD risk assessment which are only applicable to adults and use cross-sectional data. This research provides the first long-term ML-based CVD risk prediction model among adolescents based on a longitudinal dataset. Our results indicated the capability of ML models to accurately predict the long-term risk of CVD among adolescents. In addition, the most significant factors for predicting CVD risk among adolescents are identified. Furthermore, the proposed model can be used to identify individuals who are at high risk of developing CVD early in life and provide them with the necessary guidance and preventive treatment, which improves the quality of life, lower healthcare costs, and reduces the demand for cardiac care services later.