The general practitioner (GP) is like a catalyst: a small amount of he or she, when present in a "chemical reaction", can produce significant results. Thus, the GP continually performs small or brief interventions that are, in reality, "maximal" due to their profound effects. The GP is a small enzyme, seemingly insignificant at first glance, but upon which the pace and speed of a chemical reaction depend. The GP's work resembles that of a powerful reagent. Their presence is never dominant, always judicious and adapted to the demands of each situation, and this is reflected in the speed and quality of the results. Their task is humble but very important: to discover what stands between people's interest in health and their attainment of it, and to know what he or she can do to help them achieve it using the least amount of our effort. To empower individuals to be in a better position to progress [1,2].

Algorithms enhance the pictorial information of previously captured images to obtain better and more comprehensive information for diagnosing many scenarios, but of particular interest in diseases. This process, known as computer vision, is a useful tool for improving human interpretation of organic images obtained through microscopy in any of its modalities, including x-rays, ultrasound, positron emission tomography, and magnetic resonance imaging (MRI), among others [1-3]. We believe computer vision to be a precursor to artificial intelligence. It is considered a useful tool in the field of medical diagnosis and treatment, as it facilitates image analysis by specialists, exponentially improving the efficient interpretation of what is observed in samples of bodily substances, organs, and systems. Its application in infectious diseases, particularly parasitic diseases (which affect more than 1.5 billion people worldwide), seems of particular interest due to the difficulty of parasitological diagnosis [3-6]. In this regard, the low parasite load, morphological similarity, the parasite's location within the human host, the limited expertise of diagnostic professionals, and the lack of high-tech diagnostic tests (based on protein or nucleic acid detection) greatly hinders the accurate diagnosis of unicellular and multicellular parasites. These obstacles can be overcome with computer vision, as it allows for the examination of the parasite's composition, structure, and morphological characteristics without artifact interference [7-11]. Specifically, parasite classification in images is based on the determination of parasites and non-parasites using deep neural networks with transfer learning (generalization of experience). Furthermore, data augmentation (transforming images to create new ones) can be used in the training set with classical techniques and generative adversarial networks, all with the aim of deep classification. Therefore, in the diagnostic imaging of parasitic diseases, binary classifiers using convolutional neural networks and pre-trained deep neural networks have been employed, all with performance exceeding 95% [10, 12]. Computer vision for parasites undoubtedly allows for accurate diagnosis and timely treatment of these formidable pathologies. Even without thousands of sample images, as is often the case with parasitic diseases, the increased data allows the network to obtain more information and characteristics for the proper classification of these organisms with a high degree of accuracy [13, 14].

The authors have no conflict of interest to declare. The authors declared that this study has received no financial support.