LIFE SCIENCE LIVE 2019
Artificial Intelligence & Health –
May 15–16, Turku Fair and Congress Center
Life Science Live consists of three parallel seminars:
Plenary. IBM: Andrew Fried, IBM Global Life Sciences Industry Leader
Part One of Session One. Confirmed Speakers:
Professor Moncef Grabbouj, University of Tampere
Real-Time Patient-Specific ECG Classification by Convolutional Neural Networks
In this talk, we shall discuss how we approach AI from a signal processing, pattern recognition and machine learning point of view to solve pertinent problems in many areas, including biomedical signal processing. We present a hierarchical layered approach that exploits different types of sensor and non-sensor signals and design suitable representation, processing and analysis algorithms in order to apply machine learning, including deep and shallow learning. We shall then exploit the layered approach in a wide array of applications, with specific emphasis on ECG classification, where we shall present a fast and accurate patient-specific electrocardiogram (ECG) classification and monitoring system. The proposed system uses an adaptive implementation of 1D Convolutional Neural Networks (CNNs) which is used to fuse the two major blocks of the ECG classification into a single learning body: feature extraction and classification. For each patient, an individual and simple CNN will be trained using a relatively short segment of patient ECG training data. The proposed solution can be used for real-time ECG monitoring and early alert system on a light-weight wearable device. We will also show that the network can be used to classify possibly long ECG data accurately. The results over the MIT-BIH arrhythmia benchmark database demonstrate that the proposed solution achieves a superior classification compared to the state-of-the-art methods for the detection of ventricular ectopic beats (VEB) and supraventricular ectopic beats (SVEB).
Professor Martin Cowie, Imperial College London
Learning lessons the hard way in remote monitoring of complex cardiac disease
10.30 Opening words by the Chair of the day. Jari Forsström, Abomics Oy and Healthtech Finland, Genomic Industry SIG
10.45 Finnish biotech year 2018. Tero Piispanen, HealthTurku, Turku Science Park Oy
11.15 Are there any more traditional Venture Capitalists? Walter Stockinger, Hadean Ventures
Evidencing value based care through hospital EHRs and ICHOM standards: Thomas Allvin, EFPIA
The hospital perspective: Juuso Blomster, University of Turku
The pharma industry perspective: Bart Vannieuwenhuyse, Janssen
The patient perspective: Peter van Galen, Belgium, Patient representative
Sammeli Liikkanen, Chief digital officer, Orion Corporation, Orion PharmaOrion
Arho Virkki, Lääketieteellisen matematiikan dosentti, Auria tietopalvelun johtaja
Kristoffer Miving, Digital lead, Nordics & Baltics, Janssen
Tommi Lehtonen, CEO, Blueprint Genetics Oy
Karen Madden, VP Technology and Innovation,PerkinElmer Inc.
Ilkka Räsänen, Leading Expert, Sitra
Part Two of Session One. Confirmed Speaker:
Professor Ion Petre, University of Turku
Jason Swedlow,Centre for Gene Regulation & Expression, University of Dundee, UK, Glencoe Software Inc., Seattle, WA
OME’s Bio-Formats, OMERO, & IDR: Open Tools for Accessing, Integrating, Mining and Publishing Image Data @ Scale: Despite significant advances in biological imaging and analysis, major informatics challenges remain unsolved: file formats are proprietary, storage and analysis facilities are lacking, as are standards for sharing image data and results. The Open Microscopy Environment (OME; http://openmicroscopy.org) is an open-source software framework developed to address these challenges. OME releases specifications and software for managing image datasets and integrating them with other scientific data. OME’s Bio-Formats and OMERO are used in 1000’s of labs worldwide to enable discovery with imaging.
We have used Bio-Formats and OMERO to build solutions for sharing and publishing imaging data. The Image Data Resource (IDR; https://idr.openmicroscopy.org) includes image data linked to >40 independent studies from genetic, RNAi, chemical, localisation and geographic high content screens, super-resolution microscopy, and digital pathology. Datasets range from several GBs to tens of TBs. Wherever possible, we have integrated image data with all relevant experimental, imaging and analytic metadata. With this metadata integration, we have run queries across studies to identify gene networks that link to cellular phenotypes. We have also built cloud-based analysis tools portals to catalyse the re-use and re-analysis of published imaging data.
To catalyse commercial access to OME’s tools, we formed Glencoe Software in 2005 as a commercial arm of OME. Glencoe provides commercial licenses of OME software, along with guaranteed support and customisation. Glencoe has built PathViewer (http://www.glencoesoftware.com/products/pathviewer/), a web-based WSI visualisation and annotation tool that is used in several top 10 pharmaceutical companies and for digital pathology data sharing, analysis and also for e-learning in medical education.
In our latest work, OME and Glencoe have collaborated to build Parade, a web-based data mining application that uses data analytics stored in OMERO to query, select and analyse large collection of images in drug discovery and digital pathology.
Measuring and improving data quality in hospitals:
Professor Pascal Coorevits, i~HD and University of Gent
Frank Staelens, OLV Hospital Aalst, Belgium
Complying with the GDPR when reusing real world data for research:
Dr Nathan Lea, i~HD and University College London
Saara Malkamäki, SITRA
Dr Filip De Meyer, i~HD and University of Gent
15.15 The New Modalities Ecosystem project ; what is there for me? Antti Haapalinna, Orion Pharma Ltd
15.40 How to explore the commercial potential of a life science idea? Giles Dudley, Senior Business Developer, BioInnovation Institute (Novo Foundation)
16.05 How Business Finland can help drive innovation and international growth in Life Sciences. Marko Salonen, Senior Director, SME & Midcap, Health & Wellbeing, Business Finland
16.20 Ending discussion. Jari Forsström, Business Finland
Dipak Kalra, President of the European Institute for Innovation through Health Data
Part One of Session Two
Professor Olli Raitakari, University of Turku
Epigenetic inheritance of disease risk – implications for public health
Dr. Laura Elo, University of Turku
Transforming data to knowledge for better healthcare: The rapid developments in modern biotechnology have enabled large-scale measurements of molecular events in health and disease. This has opened up new possibilities to improve clinical decision making and drug development. However, data alone are not enough but effective computational methods and models are needed. The focus of this talk is on computational approaches that enable robust and reproducible interpretation of the large-scale molecular as well as clinical data. The ultimate goal is to improve the diagnosis, prognosis and treatment of complex diseases, such as diabetes and cancer.
Opening remarks, Professor Dipak Kalra, President of i~HD
EHR2EDC, Nadir Ammour, Sanofi
EHDEN, Nigel Hughes, Janssen
Trillium II and the International Patient Summary, Dr Catherine Chronaki, HL7 Europe
Digital Health Europe, Oliver Zobell, Scientific Officer eHealth, Jülich
Register for one-on-one partnering sessions
UK Department for International Trade (British Embassy Helsinki) and The Science & Innovation Network in collaboration with Scottish Development International and Turku University of Applied Sciences welcome you to discover how the UK triple helix of academia, industry and government utilises artificial intelligence as enabler in the health technology space.
The keynote speakers representing the following organisations to be announced and the final programme published closer to the date.
- The Alan Turing Institute – UK national institute for data science and AI
- UK Medicines Discovery Catapult
- iCAIRD (The Industrial Centre for Artificial Intelligence Research in Digital Diagnostics)
Please join the discussion and come to network with like-minded professionals. Registration to the event closes on Monday 6 May. Please, register here
For any queries, please don’t hesitate to contact the organiser.
Part Two of Session Two
Dr. Antti Karlsson, Auria Biobank
Huge amounts of tissue samples and related patient information are gathered in biobanks. This combined with modern research tools and computing power creates vast amounts of possibilities. Using clear examples, I will shortly introduce different research projects we have done ranging from ordinary retrospective register studies all the way to using artificial intelligence in the analysis of patient dictations and histopathological images
Dr. Teemu Suna, Nightingale Health Ltd.
Chair: Dipak Kalra
Petri Virolainen, Turku university hospital
Use of pharmacogenetic data in connection with personalized pharmaceutical treatment: Jari Forström, Turku University Hospital and Abomics Ltd
Register for one-on-one partnering sessions
Sampo Sammalisto, Ph.D. Program manager, Personalised Health, Health & Wellbeing, Business Finland