AI-driven Insights from Real World Data
Defining Behavioral Biomarkers and Phenotypes
The symposium
The predictive capabilities of traditional, vital-based biomarkers on trial outcomes has been under investigation in clinical trials. However, Real World Data is much more than measured vitals: patient-reported outcomes and physical measurements from trial participants’ lifestyles can provide us with extended biomarkers. Can they be useful in predicting future patient reported outcomes or even trial outcomes? Can they be used to model patients or to cluster them into behavioural phenotypes? These are questions addressed under the framework of the workshop, where we will see how AI can support traditional industries, such as Life Sciences, as well as Health, Wellbeing and Ageing. We will also present commercial applications and R&D projects, discussing the challenges and opportunities through the introduction of AI.
the programme
09.00 - 09.30 | Registration & Coffee |
09.30 - 09.45 | Welcome notes by Prof.dr.ir. Hermie Hermens (University of Twente) & Dr. Sofoklis Kyriazakos (Innovation Sprint) |
09.45 - 10.10 | Inspiring keynote, Christina Kyriakopoulou (European Commission, DG-RTD) |
10.10 - 10.35 | Modeling a treatment protocol with little clinical data, Rom Langerak (University of Twente) |
10.35 - 10.50 | Startup talk: Healthentia.com, Sofoklis Kyriazakos (Innovation Sprint) |
10.50 - 11.20 | Startup talk: BowheadHealth.com, Francisco Diaz-Mitoma (Bowhead Health) |
11.20 - 11.50 | Coffee break |
11.50 - 12.15 | Defining Biomarkers & Behavioral Phenotypes, Alfredo Cesario & Aristodemos Pnevmatikakis (Innovation Sprint) |
12.15 - 12.40 | MDR impact on Software as Medical Devices, Kyun Thibaut (COVARTIM) |
12.40 - 13.05 | Generator project, Vincenzo Valentini (Policlinico Gemelli / UCSC) |
13.05 - 13.45 | Lunch |
13.45 - 14.00 | AI-driven clinical study APACHE (cervical cancer), Vincenzo Valentini (Policlinico Gemelli / UCSC) |
14.00 - 14.15 | AI-driven clinical study PADAWAN (Non Alcoholic Fatty Liver Disease), Luca Miele (Policlinico Gemelli / UCSC) |
14.15 - 14.40 | Intelligent triage for low back pain, Wendy Oude Nijeweme – d’Hollosy (University of Twente) |
14.40 - 15.05 | Towards holistic profiling and personalized cancer treatment, Annemieke Witteveen (University of Twente) |
15.05 - 16.05
| Pitches from R&D projects (10 minutes each) - H2020 EU-STANDS4PM, Marc Kirschner (FZ-Juelich)
- H2020 REPO-TRIAL, Harald Schmidt (Maastricht University)
- H2020 INFINITECH, Christiane Grundloh (RRD)
- H2020 COUCH, Harm op den Akker (RRD)
- H2020 PANACEA, Aristodemos Pnevmatikakis (Innovation Sprint)
- H2020 CO-ADAPT, Konstantina Kostopoulou (Innovation Sprint)
|
16.05 - 16.30 | Panel discussion: How AI can be integrated to Life Sciences and Healthcare |
16.30 - 17.00 | Networking drinks |
speakers
Kyun Thibaut
MDR impact on Software as Medical Devices
The MDR 2017/745, which is applicable from May 2020 onwards, has a significant impact on Softwares as Medical Devices. This presentation will introduce the major changes and the best way to prepare for the upcoming changes through the analysis of practical cases.
Dr. Aristodemos Pnevmatikakis
Defining Biomarkers & Behavioral Phenotypes
Since there is a wealth of data available, the extraction can even be automatic, as driven by machine learning algorithms, can then be matched to patient-reported or treatment outcomes to establish those that have some outcome predictive capabilities. Such behavioural biomarkers can be grouped to form behavioural phenotypes. This novel phenotyping is needed in the Clinical Research scenario to trim the trials’ design as close as possible to the real world. In this talk, our approach is presented, together with an example using artificial data.
Dr. Marc Kirschner
A European standardization framework for data integration and data-driven in-silico models
EU-STANDS4PM will assess and evaluate national standardization strategies for health data integration as well as data-driven in silico modelling approaches for personalized medicine with the aim to bundle European standardization efforts. A central goal is to develop harmonized standards as well as recommendations and guidelines for predictive data-driven in silico methodologies applied in personalized medicine.
Dr. Sofoklis Kyriazakos
Healthentia.com
Healthentia solution extends the use of a traditional ePRO application by adding activity data and vital sign monitoring collected from IoT devices to combine them with the patient reported outcomes to derive patient behavioural phenotypes using A.I. and machine learning to link them with drug/intervention efficacy.
Prof. Dr. Dr. Harald H.H.W. Schmidt
The end of medicine as know we it.
Existing drugs often fail to provide relevant benefit for most patients. The efficacy of the discovery of new drugs is low and in a constant decline predicting that pharma’s current approach may by the end of the 20’s no longer be financially sustainable. More inspiring things during this presentation.
dr. Annemieke Witteveen
Towards holistic profiling and personalized cancer treatment
Annemieke Witteveen, PhD works on self-management and decision support for oncology within the Personalized eHealth Technology research program of the University of Twente. Cancer patients are highly heterogeneous and the benefit of personalizing treatment is great. Witteveen will elaborate on the personalization of breast cancer follow-up using individual risk profiles and the PARTNR platform for personalized prediction, monitoring and treatment of cancer-related fatigue.
Konstantina Kostopoulou
Moderator of panel “How AI can be integrated to Life Sciences and Healthcare”
Dr.ir. Rom Langerak
An example of modeling a treatment protocol with little clinical data
Medical protocols for diagnosis and treatment can be complex since they have to deal with effectiveness, timing, costs, and uncertainty. In addition, they are often composed of various processes in parallel. Formal modeling and analysis of such protocols may help to deal with this complexity. In this presentation we show how we have used the tool UPPAAL (originated in Computer Science) in some practical cases. This approach is also interesting when there is little clinical data, and especially in the context of personalized medicine.
dr. ir. Wendy Oude Nijeweme - d'Hollosy
Intelligent triage and referral for neck and low back pain
Of all Dutch adults, 1 in 5 has musculoskeletal pain, mostly neck and low back pain. More than 50% of these people have limited functioning. Experienced disease burden can be reduced by starting an appropriate treatment as early as possible. However, it appears that more than 30% of the patients are referred back to the general practitioner (GP) with a rereferral to somewhere else. This results in an inefficient care path. In my presentation, I will tell about the first steps taken to optimize the triage and referral on NLBP by means of a data-driven approach.
Prof.dr.ir. Hermie Hermens
Welcome & introduction of the symposium
Francisco Diaz-Mitoma Jr.
Owning Your Health Data is a Human Right
We live in an age of zero privacy. We believe health data is the world's most valuable information. We believe that people should own and control their health data. Bowhead Health's technology empowers people to own and control their health data with military grade encryption. If people decide to they can share their health data with researchers.
when & where
- 17 December 2019
- 09.00 - 17.00 (registration between 9.00 - 9.30, drinks at 16.30)
- Language: English
- The TechMed Centre (Technohal building 18), Auditorium (TL 1133)
On the campus of The University of Twente, Drienerlolaan 5, Enschede, The Netherlands; Route
Registration
We welcome a maximum number 80 participants. We will count on your participation for reserving a meal-filling lunch and drinks. If you cannot attend the event for which you have already registered, we kindly ask that you let usknow. Simply e-mail techmed-events@utwente.nl.
ORGANIZATION
This event is an initiative of the company Innovation Sprint which is situated in Brussels and TechMed Centre's strategic programme Personalized eHealth Technology.
Innovation Sprint
We are an e-health startup with focus on digital transfomation of companies and orgnaizations seeking disruption. We combine medical, ICT and data analysis expertise to improve health and pharmaceutical products and services, and to develop personalised healthcare solutions.
PERSONALIZED EHEALTH TECHNOLOGY
It becomes more and more evident that the current approach to healthcare is not sustainable, especially when considering the increasing volume and demands of chronic diseases, requiring a rethinking of strategies towards innovative solutions. The use of Information and Communication Technologies in healthcare – eHealth – is a promising strategy to improve healthcare worldwide. Biological (e.g. genetic pre-disposition), behavioral (e.g. lifestyles) and environmental (e.g. physical and social context) factors influence the surge and progression of chronic diseases. eHealth also allows to target this challenge of diversity, for example, by providing personalized solutions adaptable to each user, and also to changes over time. Every individual, dealing with any specific condition presents a distinctly unique case, highlighting the need for Personalized eHealth Technology.