According to the World Health Organization, life expectancy has increased by six years in the last two decades. This has led to an increase in chronic diseases among the population. Consequently, health systems have been forced to look for preventive measures and improvement of care processes to guarantee sustainability. Key factors for this improvement are safety, efficacy, efficiency, patient-centred care, timeliness, and equity, all of which pursue to minimize risks and provide optimal care. Likewise, Emergency Services face significant challenges due to the high demand to which they are subjected, which results in saturated Emergency Departments and errors that can lead to adverse events. Therefore, improving patient safety is crucial to obtain better care in the Emergency Department. Paradigms such as Value-Based Healthcare advocate measuring the Quality of Care, optimizing the allocation of resources, and achieving better results through continuous improvement being the traditional performance indicators, those that have played a crucial role in this process by aligning activities and objectives, providing information on the patient's experiences and their state of health, as well as contributing to the evaluation of performance, clinical efficacy and quality improvement. However, these indicators may present limitations due to their abstract nature and the complexity of the data. Therefore, the key indicators may not fully represent the complexity of these processes. Furthermore, adapting these indicators to continuous changes can be challenging, making it difficult to understand the systems. Techniques such as Artificial Intelligence can offer valuable information when processing large data sets, which are particularly interesting in the health sector. In this way, Process Mining, an emerging paradigm gaining popularity in several domains, including health, offers the opportunity to analyze and improve processes, contributing to alleviating the crisis that health systems face today. This doctoral thesis presents a new way to measure the value of the emergency process with interactive process indicators based on Process Mining techniques as a solution to issues not covered by traditional measurement techniques or new technologies such as Artificial Intelligence. In addition, this thesis proposes a novel method to measure the Quality of Care in addition to understanding the stroke care process in Emergency Services. This approach offers a more dynamic and interactive way of analyzing healthcare processes, which allows for a better understanding and measuring of the value chain, which helps identify specificities in the emergency care process and thus discover the behaviour of the stroke disease process. Finally, this thesis presents an application based on Process Mining to support this method, designed and implemented for this purpose.