On May 11, 2020 our colleague Gideon Mekonnen Jonathan, PhD student in IT Management and Governance group at DSV/Stockholm University has defended successfully his licentiate thesis entitled: “Information Technology Alignment: The Role of Organizational Structure”. His licentiate thesis is available at the following link in DiVA: http://www.diva-portal.org/smash/get/diva2:1423531/FULLTEXT01.pdf On behalf of research group in IT Management and Governance, I would like to congratulate Gideon Mekonnen Jonathan for this achievement.
The Workshop NLP: mining clinical notes in EHR systems in Tromsø
Hercules and I recently had the opportunity to attend and present at a workshop in clinical text mining on March 10 in Tromsø. The workshop NLP: mining clinical notes was arranged by The Norwegian Center for E-health Research.
During the workshop, Hercules gave a presentation on why NLP is needed. I gave a presentation on De-identification of text in electronic health records, and the Stockholm University master student Synnøve Bråten presented her current master thesis work on creating a synthetic Norwegian reference standard for de-identification. Sumithra Velupillai and Natalia Viani, from King’s College London, presented different NLP problems for clinical research and how to set up a clinical NLP research study.
PhD Student Mahbub Ul Alam Received the Best Paper Award at BIOSTEC HEALTHINF 2020
Hello Everyone,
Greetings. I hope you are well. I would like to share some very good news with you.
I presented a research paper entitled ‘Deep Learning from Heterogeneous Sequences of Sparse Medical Data for Early Prediction of Sepsis‘ at the 13th International Conference on Health Informatics (HEALTHINF), Malta, Valletta, 24-26 February 2020. HEALTHINF is part of BIOSTEC, the 13th International Joint Conference on Biomedical Engineering Systems and Technologies. It was organized by the Institute for Systems and Technologies of Information, Control and Communication (INSTICC).
The paper won the HEALTHINF 2020 Best Paper Award. The decision criterion considered both the paper quality (assessed by the Program Committee), and the oral presentation quality (feedback given by session chairs at the conference venue). Overall it was an enjoyable experience, and I learned a lot from all.
Want to know more about the paper or sepsis in general? Please check out the following presentation video I made!
Abstract:
Sepsis is a life-threatening complication to infections, and early treatment is key for survival. Symptoms of sepsis are difficult to recognize, but prediction models using data from electronic health records (EHRs) can facilitate early detection and intervention. Recently, deep learning architectures have been proposed for the early prediction of sepsis. However, most efforts rely on high-resolution data from intensive care units (ICUs). Prediction of sepsis in the non-ICU setting, where hospitalization periods vary greatly in length and data is more sparse, is not as well studied. It is also not clear how to learn effectively from longitudinal EHR data, which can be represented as a sequence of time windows. In this article, we evaluate the use of an LSTM network for early prediction of sepsis according to Sepsis-3 criteria in a general hospital population. An empirical investigation using six different time window sizes is conducted. The best model uses a two-hour window and assumes data is missing not at random, clearly outperforming scoring systems commonly used in healthcare today. It is concluded that the size of the time window has a considerable impact on predictive performance when learning from heterogeneous sequences of sparse medical data for early prediction of sepsis.
Best Paper Award Certificate
Receiving Award from the Program Chair Dr. Fedrico Cabitza
Rebecka Weegar’s defence of her PhD-thesis “Mining Clinical Text in Cancer Care”
Rebecka Weegar defended today January 27, 2020, successfully her PhD thesis , with the title Mining Clinical Text in Cancer Care. Opponent were Associate professor Lilja Øvrelid at Department of Informatics University of Oslo.
Nailing of Rebecka Weegar’s thesis
Rebecka Weegar nailed today her PhD-thesis with the title Mining clinical text in cancer care.
Jury member of the PhD defence of Tim Huygh at University of Antwerp, Belgium
On December 5, 2019 I have been a jury member in the PhD defence of Tim Huygh at University of Antwerp, Belgium. His PhD thesis is entitled “Understanding IT Governance: Conceptualization and Enabling IT Business Value”. The abstract of this PhD thesis is included below together with a picture after this PhD defence with Tim Huygh, Steven De Haes (as Tim Huygh’s PhD supervisor) and the jury members.
Understanding IT Governance: Conceptualization and Enabling IT Business Value
Date: 5 December 2019
Venue: Master Aula André Leysen 001.B – Antwerp Management School, Boogkeers 5 – 2000 Antwerp
Time: 4:00 PM
PhD candidate: Tim Huygh
Principal investigator: Prof Steven De Haes
Short description: PhD defence Tim Huygh – Faculty of Business and Economics
Abstract
An increasing (operational and strategic) dependence on IT for organizations results in a growing need for effective IT governance. Effective IT governance effectuates appropriate control over an organization’s current and future IT use, as to enable the creation and protection of IT business value. However, the research domain of IT governance is somewhat hampered by a lack of theoretical underpinnings for IT governance, which makes it difficult to explain from a theoretical perspective how effective IT governance should be organized and why.
In response, this PhD thesis investigates the concept of IT governance through Beer’s Viable System Model (VSM). In that context, the research that was conducted serves multiple purposes. First, an organizing logic for IT governance is articulated that is grounded in the VSM and informed by extant IT governance research. Second, extending the discussion beyond the conceptual level, two in-depth case studies are presented that demonstrate how the VSM can be used as a lens for describing and diagnosing IT governance in practice. Third and finally, four empirical IT governance-related research studies are presented that are inspired by the VSM-based organizing logic for IT governance, which demonstrates that this logic can provide structure and theoretical underpinnings to IT governance-related empirical research.
For academics, this thesis contributes to the theoretical discourse on IT governance. It answers the question why IT governance can continue to fulfil its general purpose of creating and protecting IT business value. Furthermore, it provides strong theoretical underpinnings for how to organize effective IT governance. For practitioners, this thesis shows how the VSM can be used as a lens to describe and diagnose IT governance in practice. Furthermore, it provides insights on the IT governance mechanisms and practices that may be used to instantiate the required functions of an IT governance arrangement.
Link: https://www.uantwerpen.be/en/research-groups/management-information-systems/
NoDaLiDa 2019 Conference in Turku, Finland
Hercules Dalianis and I recently attended NoDaLiDa 2019, the Nordic Conference on Computational Linguistics, in Turku (Åbo), Finland between September 30 to October 2 2019.
The first NoDaLiDa conference was in Gothenburg in 1977 and included 13 papers written on typewriters. The papers were in Swedish, Norwegian, Danish and English. This years rendition was considerably larger with over 75 papers presented during workshops or the main conference. None was written on a typewriter to my knowledge and all were in English. The papers did not only include research related to the Nordic languages, but also Spanish, Czech and Tibetan to name a few.
Both Hercules and I presented papers during the workshop on NLP and pseudonymization. I presented the paper Augmenting a De-identification System for Swedish Clinical Text Using Open Resources and Deep Learning, co-written with Hercules, and Hercules presented his paper Pseudonymisation of Swedish Electronic Patient Records Using a Rule-Based Approach.
We have written a report from the conference, which is available in Swedish.
All the best,
Hanna
Erasmus+ at Athens University of Economics and Business
I have been at Athens University of Economics and Business (AUEB) for a month teaching a course called Clinical Text Mining at their Master program in Data Science. This is an exchange through Erasmus+.
I have enjoyed it a lot and also visiting associate professor Ion Androutsopoulos and his post doc Jannis Pavlopoulos at the AUEB Natural Language Processing group and learned a lot of new things among them how to generate text from radiology images.