Clinical texts encompass a wide range of information such as patient’s history, disease diagnosis and prescribed drugs, reflecting details and nuances that are valuable in providing knowledge. In the present study, a Natural Language Processing approach, specifically Named Entity Recognition (NER), is applied to extract important concepts from gastroenterology clinical texts. NER is a task of text analytics to identify, in written documents, named entities ranging from general concepts to information in specific fields. The application is performed through freely available Python packages of the spaCy library adapted to the English language. Although the spaCy’s NER is generic, models trained in the clinical domain are used to identify categories belonging to the medical sector of interest. In particular, the main goal is to find as much entities as possible by paying attention to major bowel diseases, such as Ulcerative Colitis and Crohn’s disease. We performed two experiments, the first one involves the use of the ScispaCy package for scientific text processing. The second one applies Med7 that is a spaCy NER model for labeling drug information trained for identification of seven medication-related concepts, dosage, drug names, duration, form, frequency, route of administration, and strength. The results show that two approaches applied for NER analysis perform well to extract knowledge from gastroenterology clinical texts. The results obtained will allow to evaluate the efficiency of the proposed methodology and to analyze, through the extracted entities, the profile and aspects of the diseases considered and the associated drugs.