In healthcare, documenting patient care activities through medical notes, such as those written by doctors and nurses, is a mandatory practice. These records contain valuable information that, when analyzed using data mining and process mining techniques, can improve the understanding of care processes, identify areas for improvement, address errors, and predict health-related care for the coming period. However, the textual nature of these documents poses a significant challenge, as it prevents the direct application of data and process mining techniques. To overcome this, the extraction of events—and subsequently, event logs—from medical notes is needed. We evaluate and compare two zero-shot approaches to event extraction: a sentence transformer–based approach and a large language model–based approach. The evaluation is carried out on a human-annotated dataset derived from an annotated subset of nurse notes in the MIMICS-III dataset. We highlight the strengths and weaknesses of each approach and discuss further steps necessary to effectively obtain event logs from medical notes.