Supercritical Fluid (SCF) technology has been applied in many areas, such as the pharmaceutical and food sectors due to its outstanding features. It is an efficient technology that performs extraction and leaves none or less organic residues compared to conventional processes. Recently, the simulation and prediction of process output from supercritical fluid extraction (SFE) have been determined using intelligent system predictive tools, such as artificial neural networks. The prediction of the set of results from SFE for designing and scale up purposes is because apart from reducing the usage of extraction solvent, and the energy and time of the process, it can also generate a solution for problems that a complex mathematical model cannot solve. For example, the prediction of solubility is important because this particular fundamental value contributes to the optimizing process. A neural network is considered as one of the artificially intelligent systems, and furthermore a key technology in Industry 4.0. Moreover, the use of hybrid predictive tools is also a developing area in the prediction and simulation of supercritical fluid extraction (SFE), which would be discussed further in this paper. Currently, a limited number of studies related to the analysis of processing technology on extracting Gynura procumbens leaves can be found. Most of the research was focused on pre-clinical studies of Gynura procumbens extracts using conventional methods to prove the effectiveness of the herbal product application. Therefore, this overview will discuss and describe previous studies using Gynura procumbens and several recommendations for subsequent analysis.