We do research in clinical NLP, with focus on processing health records and on assessing health from language data.

• NHS hospitals see spike in mental health patients on days when tweets about depression soar, as more celebrities open up about their ordeals - Daily Mail (UK), 2020.02.06

ClinRead

Novo Nordisk Foundation, total 543.794 DKK, 2020-2021

ClinRead applies modern artificial intelligence techniques in the subfield of natural language processing to map the techniques and advances available in privileged languages (e.g. English) to clinical notes written in other languages. This will be done via a technique known as transfer learning. The success of the approach will be validated in the first instance against de-identified Danish clinical notes, an under-privileged language in terms of available technology. If successful, the resulting technology gives a route to significantly reducing the barriers in introducing clinical natural language processing to new languages.

DANGER

Aage og Johann Louis-Hansens Fond, total 2.500.000 DKK, 2021-2024

We intend to explore the idea of using uncalibrated and implicitly calibrated eye tracking for people with disabilities (in particular ALS and elderly). This also includes development of new techniques (e.g. deep learning) to robustly find relevant eye features.

• Mental Health-Related Conversations on Social Media and Crisis Episodes: A Time-Series Regression Analysis. 2020.
• Novel psychoactive substances: An investigation of temporal trends in social media and electronic health records. 2016.
• SemEval-2015 Task 6: Clinical TempEval. 2015.
• Analysis of temporal expressions annotated in clinical notes. 2015.

• Danish Clinical Event Extraction Developing a clinical event extraction system for electronic health records using deep learning and active learning, Frederik Wonsild, Mathias Giovanni Møller, 2020, MSc
• Clinical Information Extraction for Danish, Nichlas Berggrein and Mathias Rasmussen, 2019, MSc (Software Design)