DASH

News and Events

AAAI Fall Symposium and EMNLP – November 2021

Health Informatics, Presentation, Publication, Research Paper, SYSLAB, Visit

Professor Hercules Dalianis and I got a paper about the privacy preserving qualities of BERT accepted to the AAAI Fall Symposium on Human Partnership with Medical Artificial Intelligence! The paper is titled Are Clinical BERT Models Privacy Preserving? The Difficulty of Extracting Patient-Condition Associations. Our results strongly suggest that BERT’s poor generative capabilities makes it resistant to training data extraction attacks. Other models, such as GPT-2, have been shown to be susceptible to these attacks. From a privacy perspective, being a poor generator may be a feature!

Later in the same week, I flew from Stockholm to Punta Cana in the Dominican Republic to participate at EMNLP 2021. Almost 500 participants were there, with the total number of participants exceeding 4,000. There were many interesting presentations regarding NLP in general, but also some that were specifically about the privacy aspects of NLP. It was a great experience to learn where the field is headed and also to get to know many talented researchers. I have written a summary of some of the interesting papers – reach out if you are interested in it.

DSV at the First ClinCode Conference in Tromsø, Norway

Health Informatics, Presentation, SYSLAB, Visit

Professor Hercules Dalianis, Sonja Remmer and myself represented DSV at the First ClinCode Conference. The conference gathered experts in medicine and computer science from across the Nordics and took place at the University Hospital of North Norway (UNN) in Tromsø.

The conference was chaired by Hercules, who is also a guest professor at the Norwegian Centre for E-health Research. Sonja shared her work on automatic ICD-10 classification using BERT and I spoke about the difficulty of extracting training data from clinical BERT models.

Several participants had an industry or medical background. This provided valuable insights into how our research at DSV may be used in practice and what challenges are most important. It also highlighted the great potential that can be unlocked by continuing to investigate ICD-10 classification and other medical NLP problems.

Many excellent ideas were hatched in the discussions, and it was lovely to visit the beautiful polar city of Tromsø. Personally, I really look forward to future iterations of the conference!

Press release

Three papers accepted to the International Conference Recent Advances in Natural Language Processing, RANLP 2021, September 1-3, 2021, Bulgaria.

Health Informatics, Publication, Research Paper, SYSLAB

Three papers accepted to the International Conference Recent Advances in Natural Language Processing, RANLP 2021, September 1-3, 2021 in Varna, Bulgaria,
from the Clinical Text Mining group at DSV: 

Sonja Remmer, Anastasios Lamproudis and Hercules Dalianis.
Multi-label Diagnosis Classification of Swedish Discharge Summaries – ICD-10 Code Assignment Using KB-BERT. 

Alberto Blanco, Sonja Remmer, Alicia Pérez, Hercules Dalianis and Arantza Casillas.
On the contribution of per-ICD attention mechanisms to classify health records in languages with fewer resources than English. 

Anastasios Lamproudis, Aron Henriksson and Hercules Dalianis. 
Developing a Clinical Language Model for Swedish: Continued Pretraining of Generic BERT with In-Domain Data. 

The first paper in collaboration with the Norwegian Centre for E-health Research in Tromsø. Norway and the second paper also with the HiTZ Center – Ixa, University of the Basque Country UPV/EHU, Donostia, Spain.

The two first papers study how to automatically assign ICD-10 diagnosis codes to a discharge summary, for Swedish and for Spanish a respectively. Usually this time consuming work is carried out manually by a physician or a coder.We use machine learning and specifically Deep AI Learning to perform this and already manually assign codes to discharges summaries.

In the third paper is constructed a clinical deep learning BERT model for Swedish that performs much better than a regular non-clinical model for clinical down stream tasks as for example automatic ICD-10 diagnosis coding. 

 

Paper published in AMCIS 2021 Proceedings is among the Most Popular Papers

Award, IT Management, Research Paper, SYSLAB

The results of the research work done by Rahmat Mulyana, Lazar Rusu and Erik Perjons (all members of research group in IT Management and Governance at DSV) in IT Governance and Digital Transformation areas has raised the interest of the worldwide IS community, like is the  the Americas Conference on Information Systems (AMCIS) conference, that is a top conference in IS area. Their paper entitled IT Governance Mechanisms Influence on Digital Transformation: A Systematic Literature Review published in AMCIS 2021 Proceedings is mentioned among the Most Popular Papers at AMCIS 2021 (https://aisel.aisnet.org/amcis2021/topdownloads.html).

 

Prof. Anna Dreber talk on (Predicting) replication outcomes, May 12, 2021

Presentation, SYSLAB, Video

Speaker: Anna Dreber, professor, Stockholm School of Economics

Title: (Predicting) replication outcomes

Abstract
Why are there so many false positive results in the published
scientific literature? And what is the actual share of results
that do not replicate in different literatures in the experimental
social sciences? I will discuss several recent large replication
projects, as well as our studies on “wisdom-of-crowds” mechanisms
like prediction markets and forecasting surveys where researchers
attempt to predict replication outcomes as well as new outcomes.

Time: Wednesday May 12, 2021, 13-14.00
Recording

Bio
Anna Dreber is the Johan Björkman Professor of Economics at the
Stockholm School of Economics, as well as a Wallenberg Scholar
and a member of the Royal Swedish Academy of Sciences.
Her research is mainly in meta-science and behavioral economics,
please see https://sites.google.com/site/annadreber/ for more.

Three papers accepted to NoDaLiDa 2021

Health Informatics, Research Paper, SYSLAB

Three papers from the Clinical Text Mining group accepted to the Nordic Conference on Computational Linguistics, NoDaLiDa 2021,

  • Applying and Sharing pre-trained BERT-models for Named Entity Recognition and Classification in Swedish Electronic Patient Records by Mila Grancharova and Hercules Dalianis.
  • Creating and Evaluating a Synthetic Norwegian Clinical Corpus for De-Identification by Synnøve Bråten, Wilhelm Wie and Hercules Dalianis.
  • HB Deid – HB De-identification tool demonstrator by Hanna Berg and Hercules Dalianis.

 

ClinCode project funded by the Research Council of Norway for automatic ICD-10 coding

Health Informatics, New Project, SYSLAB

The project ClinCode – Computer-Assisted Clinical ICD-10 Coding for improving efficiency and quality in healthcare has been funded by Research Council of Norway for 2021-2023 at the Norwegian Centre for E-health Research in Tromsø. ClinCode will be using both Norwegian and Swedish electronic patient records and will therefore partly take part at DSV. Partners are DIPS, that is supplier of electronic health record systems in Norway and UNN, University Hospital of North Norway.