News and Events
Andrea Andrenucci defended successfully his dissertation with the title Using Language Technology to Mediate Medical Information on Health Portals – User Studies and Experiments on Monday Oct 29 2018. Opponent was Dr. Diego Molla-Aliod, from Macquarie University, Sydney Australia.
Today Andrea Andrenucci nailed his PhD thesis. (Spikning av avhandling)
Andrea nailing his PhD thesis
Co-supervisor Sumithra Velupillai on Skype and supervisor Hercules Dalianis holding the laptop.
Dear all!
Don’t miss to register for The Seventh Swedish Language Technology Conference (SLTC 2018) at Frescati, 7-9 Nov 2018. Interesting talks as well as exciting panels in Clinical text mining and Fake news and troll detection with invited experts.
Best
Hercules
Hello everyone! I hope you all are having a lovely time. 🙂
I am Mahbub Ul Alam. I’ve recently started as a PhD student here at DSV.
My research interest is in ‘Cognitive internet of things (IoT) based smart health-care systems using deep learning and advanced machine learning’.
Potential research problem areas include:
1. Machine learning framework for IoT.
2. Intelligent data, i.e., machine-understandable, resource-recognition, knowledge representation, big data, deep learning, and advanced machine learning.
3. Clinical decision support systems in health-IoT.
4. Patient-centric personalized health-care systems and applications.
5. Distributed intelligent data processing in IoT.
I have a master’s degree at the Institute of Natural Language Processing (IMS), University of Stuttgart, Germany. In my master’s thesis, I worked to understand the hidden layer mechanisms of deep neural networks in natural language processing (automatic speech recognition) domain.
I have a bit of work experience in software engineering at Samsung Research and Development Institute Bangladesh.
I believe in diversity, and love to explore new and fresh technological innovations. I like to think that every aspect of my previous experiences is helping me to move forward for my future career. I always keep in mind that, the central principle of my life is ‘Let all of us prosper together.’
The people are super nice and friendly here, and I am looking forward to working together with all of you at DSV.
Let all of us prosper together. 🙂
Mahbub
Mahbub Ul Alam
Deep learning based on various neural network architectures has seen tremendous success in recent years, substantially outperforming alternative learning approaches in fields such as natural language processing. By learning abstract representations through multiple processing layers, the learning task can be simplified while removing the need for carefully handcrafted features. Deep learning hence provides an effective paradigm for obtaining end-to-end learning models from complex data, such as the vast amounts of longitudinal and heterogeneous data that are stored in electronic health records. Learning general-purpose representations of patients can be useful for modeling patient trajectories and disease progression, supporting early prediction and detection of adverse events, such as healthcare-associated infections or adverse drug effects. There are numerous open research questions w.r.t. deep learning from healthcare data, including (i) effectively learning from small amounts of (labeled) data through, e.g., unsupervised pre-training, (ii) modeling the temporality of clinical events, and (iii) creating interpretable models that can be understood by clinical decision makers.
The PhD project involves designing novel deep learning architectures that address these challenges in order to make better use of heterogeneous healthcare data, in particular free-text clinical notes, for ultimately supporting healthcare by improving patient safety and reducing healthcare costs. In HEALTH BANK, we have access to eight years of specialized healthcare data from Karolinska University Hospital and are currently in the process of also obtaining primary care data, thereby allowing patients to be followed throughout the healthcare system.
Three research applications from the IS unit researchers have been approved. The applications were all sent to the Stockholm County Council (SLL) – Stockholm University Call in October 2017.
KVALPA: What quality indicators in the patient journal’s free text are needed to measure the quality of care? The project aims to create an automatic method for this through machine learning. Project leader: Hercules Dalianis
IMPROVE JANUSMED WITH PROCESS MINING. The project is about developing safer drug prescription by evaluating and improving Janusmed with process mining. Janusmed is a decision support system that controls and warns whether there is a risk of serious drug interactions as well as side effects due to enhanced effects when co-administered with multiple drugs. Stockholm County Council (SLL) provides, develops and manages Janusmed. Janusmed is available today on the web via janusinfo.se and is also integrated with the SLL journal systems. To the best of our knowledge, process mining has not yet been applied in any research project in Sweden. Project leader: Paul Johannesson. Participants: Amin Jalali, Erik Perjons (and Uno Fors in a limited role).
CAPABILITY AND VALUE-BASED CHANGE ANALYSIS OF THE 1177 VÅRDGUIDEN. The aim of the project is to develop a method to support the management organization for the 1177 Vårdguiden at SLL in assessing and analyzing how change proposals of the 1177 service, including affects on the various actors involved in the network around the service – and estimates of costs and benefits for the various actors. The method is based on (1) network-based analysis of the values and abilities of the various stakeholders in the network, and (2) on existing enterprise architecture of the management organization – in form of enterprise models such as value, process and information models over the 1177 service. Project leader: Erik Perjons. Participants: Martin Henkel, Ilia Bider (and Anders Tell in a limited role).
I was invited to the Norwegian Center for E-health Research (Nasjonalt senter for e-helseforskning), in Tromsø, north Norway to be part of the Workshop on health analytics: using language technology and machine learning on clinical text.
There were over 25 participants speaking over 20 languages (incl Sami of course).
I presented part of my co0ming text book Clinical text mining: Secondary use of electronic patient records and specifically the parts that treated applications.
Robert Jenssen from the University of Tromsø had a very pedagogical presentation about deep learning. There were several other speakers as well.
Tromsø is north of the Polar circle and today started the Polar night for another 2 months.
Polar night
Per Atle, Stein Olav Skrovseth, Hercules, Øystein Nytrø, Anne Torill, Karl Øyvind
Øystein Nytrø, Hercules, Anne Torill Nordsletta
Rebecka and I participated at RANLP 2017 in Varna Bulgaria, 2-8 September 2017.
RANLP stands for Recent Advances in Natural Language Processing.
RANLP has been active för 28 years, starting as a summer school.
This time there were around 100 participants mainly from the whole of Europe.
Rebecka presented her article with the title Efficient Encoding of Pathology Reports Using Natural Language Processing, written with her two co-authors Jan Nygård and Hercules Dalianis. The pathology reports were Norwegian Prostate cancer report written in Norwegian from the Cancer Registry of Norway. At RANLP there was also the BioNLP workshop.
Rebecka and I have written a report from the conference that is available by asking me.
Best
Hercules
