Tuesday 2 November 2021, 12:00—17:00h.
Nijmegen, Radboud University
Huygens building, room HG00.303
Discussion Theme: Towards a Research Community for Sharing Healthcare Records for Natural Language Processing
The meeting discusses recent advances in the usage of Natural Language Processing (NLP) on Clinical data. The first Dutch meeting on Clinical NLP was held in Utrecht in 2019.
12.00 - 13.00 Welcome (with lunch) and introductory round
13.00 - 13.45, 3 talks:
- Pablo Mosteiro (Utrecht University): "Aggression Prediction across Multiple Institutions using Federated Learning"
- Anne Dirkson (Leiden University): "Real-world evidence from online patient forums can complement current medical perspectives: The example of gastrointestinal stromal tumor patients"
- Claudia Libbi (University of Twente): "Generating Artificial Electronic Health Records to Train De-Identification Models"
14.00 - 15.00, 4 talks:
- Koen Dercksen (Radboud University Medical Centre): "Weakly supervised SNOMED labeling for Dutch radiology reports"
- François Remy (University of Ghent): "SnomedTranslate.nl: a high-quality clinical notes translation engine based on Transformers"
- Casper Peeters (Medstone Holding BV): "Evaluation of SURUS: a Named Entity Recognition Model for Unstructured Text of Interventional Trials"
- Sjaak Brinkkemper (Utrecht University): "Care2Report: a neural-symbolic linguistic pipeline architecture for conversation summarization into medical reporting"
15.15 - 16.00, 3 talks:
- Emil Rijcken (Eindhoven University of Technology): "A Comparative Study of Fuzzy Topic Models and LDA for Interpretability in Text Classification of Clinical Notes"
- Rachel Murphy (Amsterdam University Medical Centre): "Identification of drug-induced acute kidney injury in free text and in coded electronic health record data"
- Myrthe Reuver (VU Amsterdam): "Smoking status classification on sparsely labelled Dutch clinical notes with weak supervision and a pre-trained Transformer model"
16.00 - 17.00 Discussion (issues collected during talks)
Call for Contributions (Closed)
We solicit short presentations (15 to 20 minutes) from researchers covering recent work, including work in progress and work that is recently published at journals and/or conferences in the field or made available via data and software sharing platforms like Zenodo or Github. Please email the title and abstract of your presentation to [CLOSED] before 12 October 2021.
Now that electronic health records are commonly used, the availability of clinical texts is growing. This workshop discusses the automatic analysis of textual clinical health data to advance medical research and improve healthcare related services. We especially encourage presentations discussing possibilities to share clinical texts, models and tools for clinical natural language processing (NLP). In practice, privacy- and legal regulations prevent the free sharing and combination of electronic health records themselves, but de-identified texts, NLP tools and intermediate results may be shared. We hope that sharing will promote cooperation within the Dutch-speaking countries, as well as advance the research in Clinical NLP in those countries. Relevant topics include, but are not limited to:
- Data sets with clinical texts
- Open source tools for Clinical NLP
- Information extraction from clinical text
- Information retrieval for clinical text
- Adapting standard NLP tools for clinical text
- De-identification and ways to preserve privacy in clinical data
- Using medical terminologies and ontologies
- Annotation schemes and annotation methodology for clinical data
- Evaluation methods for the clinical domain
- Text-based clinical prediction models
- Speech recognition for clinical text
We recommend public transport, taking the train either to station Nijmegen Heyendaal, or to Nijmegen Central Station and then Bus 10 to Heyendaal. Get out at bus stop Huygensgebouw. During rush hour, busses go between Nijmegen station and campus Heyendaal every five minutes. Read More
Registration is needed for the catering. Please register before 27 October.
- Djoerd Hiemstra (Radboud University)
- Jan Trienes (University of Duisburg-Essen)
- Dolf Trieschnigg (Nedap Healthcare)
- Suzan Verberne (Leiden University)