Digital transformation is revolutionizing the healthcare industry, and the use of digital technologies is generating large amounts of data that can be used to support the healthcare decision-making process. The use of data leads to several improvements in healthcare, such as treatment selection or diagnosis process. The utilization of healthcare services is one of the prominent topics in healthcare, but it is still in its infancy in the digital transformation literature. This study aims to investigate the use of big data analytics to improve the utilization of healthcare services, specifically the Italian national cancer screening programs, through a two-step methodology. First, we investigate the relationship between patient characteristics and the utilization of the healthcare services under consideration. In the second step, the collected data are used to build a data-driven model to identify patients who are more likely not to use healthcare services based on their characteristics. This study contributes to the existing literature on digital transformation in healthcare by proposing a data-driven model to improve healthcare service utilization. While we contribute to the practitioner perspective by proposing a real-world data-driven methodology that overcomes the disadvantages of the most common methods to identify patients that will not utilise healthcare services (i.e., survey-based methods).