Pulmonary Arterial Hypertension (PAH) is a rare and severe condition that can be associated with Systemic Sclerosis (SSc), significantly worsening the prognosis of the latter disease. Screening programs based on clinical, laboratory, pulmonary function test, electrocardiographic, and echocardiographic data have been shown to enable earlier diagnosis and improve the prognosis of PAH associated with SSc. However, the hemodynamic criteria for the diagnosis of PAH have recently changed, and the usefulness of these screening programs in this new context is unknown. The primary objective of this study is to develop a PAH screening program in patients with SSc through the use of different artificial intelligence algorithms, comparing these algorithms with classical screening programs. These algorithms will be externally validated in different hospitals in Spain. As secondary objectives, the study will assess the usefulness of various proteins involved in the metabolic pathways related to the development of PAH, as well as certain parameters of right ventricular function and measures of quality-of-life impact, in the prognostic evaluation of PAH associated with SSc. To this end, simple and reproducible clinical data will be used, such as electrocardiogram, echocardiogram, and different quality-of-life scales obtained from major PAH and SSc registries. Machine learning techniques and Bayesian networks will be applied to generate artificial intelligence models for screening and prognostic assessment.