The growing interest in Low-Code Systems, combined with the evolution of Generative Artificial Intelligence (AI), has driven new ways of creating applications in the field of digital health (eHealth). However, the effective integration of these technologies, particularly in regulated and clinical contexts, has not been widely explored. This systematic review aims to identify the main features assisted by generative AI in low-code systems and to understand what the challenges and limitations of these systems are based on the eHealth context. We analysed 56 scientific articles published between 2020 and 2025, selected from databases such as Scopus, PubMed and IEEE Xplore. Data extraction and analysis were based on a multidimensional model constructed from the research questions. The results reveal a prevalence of empirical studies with limited methodological transparency. These studies often lack clearly defined research designs or validation processes, and there is a general absence of practical implementations. Furthermore, none of the studies demonstrated the simultaneous integration of generative AI and interoperability standards such as FHIR or OpenEHR. It was also found that the majority of studies represent a fragmented form of the dimensions, i.e. they address critical dimensions (AI, privacy, scalability) but in isolation. The conclusion is that, although there is great potential, the maturity of these systems is still limited. Future research should focus on the development of Intelligent Low-Code solutions that fulfil the requirements of the health sector, with greater regulatory alignment, integration of generative AI and validation in real clinical environments.