Current students

In the last decade, Natural Language Processing (NLP) has become a trending topic in research. In particular, new machine and deep learning models have obtained relevant results on different tasks, from text classification to information extraction.

In the medical field, there is a huge amount of textual data which could be leveraged to better understand patients’ conditions and medical prescriptions and so to improve policies and support clinicians in their decisions.

Clinical notes and other related texts (eg: medical prescriptions) have some peculiar characteristics, like the specific lexicon and the huge number of often ambiguous abbreviations, which makes NLP tasks harder.  Moreover, current research is mainly focused on English texts, and it is not straightforward to replicate its results on texts in different languages, because of both the linguistic differences and the different guidelines and formats which are followed by clinicians in different countries for textual reports.

My research will focus on the investigation of models for NLP in the medical domain, applied to different tasks, from information extraction to cohort selection. The collaboration with Regione Lombardia will allow me to access relevant data and apply my research to concrete use-cases, driven by the real needs of the Italian health service.