AI-RONDO: Greater control over Parkinson’s and Alzheimer’s using apps and avatars

Speaking more softly and poor articulation could be an indication of Parkinson’s or Alzheimer’s, or that these conditions are worsening. Radboud University, Radboud university medical center (Radboudumc) and imec, partners in OnePlanet Research Center, are using artificial intelligence (AI) to analyse signs of this kind. The aim is to detect the disease at an early stage. They are also developing digital aids, such as apps and avatars, for patients already suffering from these diseases, so that they receive an indication at home that the disease is changing and care providers can intervene in time. The institutes are now setting up a new ICAI lab to this purpose: AI-RONDO (Risk Profiling and Decision Support). 

“There is already a lot of data on patients suffering from Parkinson’s and Alzheimer’s, which are two common disorders of the brain. By using AI algorithms and models on this information, we can find new links and for example pinpoint groups facing an increased risk of developing complications. Using these enriched data we are able, following diagnosis, to prescribe treatment for a patient specifically designed for their personal risk profile. We can also analyze those signs – such as speaking more softly, articulating less clearly, a change in walking patterns or heart rate – that indicate that something is going wrong,” says Marjan Meinders, one of the lab’s three academic directors. “On the basis of a sign like this, a care provider can prevent further deterioration.”

Digital Tools

AI-RONDO will use digital tools to collect data in the home situation and to provide the patient with customized personal advice. For example an app linked to a bracelet that provides an analysis of how symptoms changed over the course of the day, linked to the taking of medication. Or an avatar, a virtual assistant that engages in conversation with the patient while simultaneously collecting new data on the progression of the disease from their speech. Meinders: “This extra support – in addition to regular care – offers patients more information on and a greater understanding of their own health. This means they have greater control and are able to delay the disease’s progress themselves.”

24th ICAI lab

The research is being conducted in ICAI’s AI-RONDO lab. ICAI (Innovation Center for Artificial Intelligence) is a national network that focusses on technology and talent development between knowledge institutions, industry and government in the field of AI. AI-RONDO is the 24th ICAI lab in the Netherlands and the second in which Radboud University, Radboudumc and imec, partners in OnePlanet Research Center, are collaborating. In February this year, they set up the ICAI lab AI for Precision Health, Nutrition and Behavior along with the 4th partner Wageningen University & Research.

Partners

OnePlanet Research Center wants to stimulate innovations in the Dutch province of Gelderland and works closely with industry and societal organizations from the region. Several regional partners are already involved in AI-RONDO, and the research team cordially calls on other interested parties to come forward as well. The current partners are: ANT Neuro, Artinis Medical Systems, imec-NL, InfoSupport, NIVEL, Noldus Information Technology, Orikami Personalized Healthcare, ParkinsonNet, Stichting Open Spraaktechnologie and Virtask.

More information on AI-RONDO

Second Utrecht University AI lab joins ICAI network

After the success of the National Police Lab AI, now the second Utrecht University AI lab joins ICAI: AI & Mobility Lab. Utrecht computer science researchers launched this second AI Lab in January 2021. The new lab focuses on the themes of mobility, transport and logistics. The researchers work with partner organisations NS, ProRail and Qbuzz, to link, strengthen and further expand research into mobility issues.

Transport organisations, distributors and public organisations encounter major challenges, to which AI research can contribute. Public transportation, shared mobility, road traffic, logistics and human movement behaviour raise issues about safety, robustness, accessibility, travel time, health and such. In the AI & Mobility Lab, Utrecht computer science researchers will collaborate with various organisations to develop innovative AI techniques for challenges in mobility and public transportation.

Important role for AI research

Mobility is in full swing. Cities are especially getting busier, and because of increasing concern for sustainability, alternatives for privately-owned petrol or diesel cars are becoming more and more important. Commuters will increasingly use combinations of different forms of mobility and public transportation. Public transportation is becoming more electrified and is expected to play a crucial role in future transport.

Artificial intelligence will make a strong contribution to these developments. There are important challenges in managing and controlling vehicle and passenger flows, infrastructure planning, and the development of new tools and platforms for matching supply and demand such as MaaS (Mobility as a Service). Researchers in the AI & Mobility Lab will work on data-driven techniques, operations research, algorithms, human-centered AI and agent-based simulation.

Marjan van den Akker, coordinator of the AI & Mobility Lab: “The challenges of our stakeholders are complex and require a state-of-the-art approach. Where needed, we collaborate with researchers from different disciplines. By developing knowledge and techniques together, we strive to make a strong societal impact.”

Education

In addition to research, the AI Labs of Utrecht University also play an important role in education for professionals, and programmes where students work together with professionals.

Read more on Utrecht AI & Mobility Lab

e/MTIC AI-Lab becomes fourth TU/e ICAI Lab

In the field of healthcare, AI still has several issues to address. In hospitals, professionals are still hesitant to employ AI-based techniques because of lack of transparency, interpretability and clinical evidence.

Through the e/MTIC AI-Lab, AI will be made available to work in close collaboration with the clinical staff and MedTech industries to help improve personalized treatment. This lab has now also joined ICAI and is the fourth TU/e ICAI lab. ICAI is a network of Dutch research programs that is designed to bring together researchers in the field of AI. e/MTIC is a unique collaboration between Eindhoven University of Technology, Catharina Hospital, Maxima Medical Center, Kempenhaeghe Epilepsy and Sleep Center and Philips to enable a fast track to high-tech health innovations.

AI techniques mostly act as a black box without knowing precisely what part of the data is being used and how. Furthermore, AI tends to be specialized and lacks robustness when small changes to existing procedures are required. In these cases, human doctors are still much better able to handle the complexity of the situation. However, that does not mean that the work of humans is always correct, but they are able to weigh up when it is necessary to ask for help from someone else, for example, something AI cannot do today.

New Healthcare Systems

In healthcare, systems are continuously evolving and the ability of specialists to fully understand the complex inter-relationships of the various components is becoming more difficult. It will be particularly important for this information to be organized, not just using new forms of presentation such as virtual reality and digital twins but also by linking models of information to predict what the doctor should see next.

These new systems must be designed in a manner to protect people, the environment and the economy. ‘Responsible AI’ is a term that is usually applied to dealing with consumers or private individuals. For healthcare, this encompasses responsible use and storage of sensitive personal data, but also promotion of patient empowerment, avoidance of harm and bias, and protection against misuse.

E/MTIC ICAI Research Focus

Many of the e/MTIC researchers are currently working on and implementing analysis techniques and (prediction) algorithms for improved (patient) monitoring and diagnosis and to help optimize individual treatment strategies in collaboration with many medical specialists. Due to the many complexity and heterogeneities in medical data, these approaches and other innovations will be further developed, implemented and automated through projects in e/MTIC. The research focus is on robustness and improved stability of algorithms and methods.

In the e/MTIC ICAI lab, AI will be mainly used for the following application areas:

  • Imaging: strongly enhanced Ultrasound, MRI and CT imaging by embedding task-adaptive AI across the imaging chain
  • Patient monitoring: strongly enhanced monitoring of vital signs both in clinical and in extramural settings
  • Clinical decision support systems: Use AI to combine various data streams (e.g. EMR, images, spot checks) to produce explainable and patient-specific advice, early warning and alarms.

The academic directors of the lab are professors Frans van de Vosse and Jan BergmansCarmen van Vilsteren is the lab manager.

Fast Track to Clinical Innovation

Given that the main purpose of e/MTIC is to provide a “Fast track to clinical innovation”, Artificial Intelligence is an extremely important instrument to support this goal. Both in clinical decision support in general, and in-patient monitoring and image analysis in particular, novel AI techniques provide powerful approaches to identify patient deterioration at an earlier stage, diagnose conditions more accurately, better guide treatment, and improve secondary prevention.

Eindhoven Medtech Innovation Center

Bringing technical innovations all the way from early research to implementation and commercialization can often take a long time. In healthcare innovation, in particular, this lost time can often equate to lost lives. The goal of the Eindhoven MedTech Innovation Center (e/MTIC) is to create and expand an ecosystem that strongly increases the speed of high-tech health innovation, maximizing value for patients. We consider such an ecosystem to be an unmet need and a unique opportunity for the Brainport region to make significant contributions to visionary new developments in healthcare.

e/MTIC is a large-scale research collaboration between the Catharina Hospital (CH), the Maxima Medical Center (MMC), Kempenhaeghe Epilepsy and Sleep Center (KH), Eindhoven University of Technology (TU/e) and Royal Philips Eindhoven (RPE) in the domains cardiovascular medicine, perinatal medicine and sleep medicine. The partnership has evolved over several decades, has a strong scientific and valorization track record and currently encompasses around 100 PhD students, supervised by a similar number of experts from the various partners.

Find out more about e/MTIC AI-Lab

ICAI Day – The Program

Date: Thursday April 22, 2021
Time: 14:00 – 16:15 CET
Location: The online event will be recorded and streamed, live from Den Bosch.

On April 22 we celebrate our third birthday with the first official ICAI Day! Together with JADS, we hereby present the program. We will take you on a virtual tour to meet the various ICAI locations where you receive an update about their activities and research. Multiple start-ups will present themselves and at the end of the event you can meet and mingle via virtual drinks.                          

14:00Welcome by host Nathan de Groot
Introduction by Maarten de Rijke, scientific director of ICAI
14:20Interview with JADS and KPN on Responsible AI Lab
14:45Break out round 1 – three ICAI locations to choose from: Utrecht, Amsterdam, and Nijmegen
15:20AI Startup Talkshow: Techleap, Bluetick and Seedlink
15:45Break out round 2 – three ICAI locations to choose from: Eindhoven, Wageningen, and Delft
16:15Wrap up and virtual drinks at Gathertown, possibility to talk with start-ups of different locations

This day is for everybody interested in ICAI or parts of the program. So do not hesitate to forward this event to all people who would like to take a look behind the scenes at ICAI.

Find out more about the ICAI Day and program here and subscribe here.

We’ll see you there!

ICAI Day – Save the date

Date: Thursday April 22, 2021
Time: 14:00 – 16:15 CET
Location: The online event will be recorded and streamed, live from JADS.
Subscription link

On April 22 we celebrate our third birthday. With great pleasure we invite you to the first official ICAI Day!

Together with JADS (Jheronimus Acadamy of Data Science) in Den Bosch, we plan to take you on a virtual bus tour along the various ICAI locations, labs and partners.

We offer you a diverse and interactive program with (video) pitches, breakout sessions, table interviews, and a start-up talkshow. Host of the afternoon will be Nathan de Groot, online facilitator, day chair and trainer.

This day is for everybody interested in ICAI. So do not hesitate to forward this event to all people who would like to take a look behind the scenes at ICAI.

Find out more about the ICAI Day and program here.

We look forward to see you there!

Second LTP AI Matchmaking Meetup

NWO has recently published a call for Long Term Programmes (LTPs). The strategic aim of an LTP is to provide a powerful and long-term stimulus for the development of a scientific field in the Netherlands, focusing on a societal theme and/or key technologies.

ICAI is leading an effort to build a consortium for an LTP around AI with the title: ‘Trustworthy Artificial Intelligence-based Systems for Sustainable Growth.’

The program’s ambition is to help drive growth through AI-based solutions that are sustainable environmentally (through reduced computational and data requirements), industrially (through talent and tool development), and societally (through fairness and transparency).

The LTP offers the possibility to focus on specific application areas of AI, such as: Energy Transition & Sustainability; Agriculture, Water & Food; Health & Care; Security; Financial Services; Mobility, Transport & Logistics, etc. It builds on the thriving ICAI network of academic-industrial collaborations.

We are looking for both academic and industry partners to join this initiative. This is why we will organise a second LTP Matchmaking Meetup on 12 March 2021, 14:00 – 14:30h.

This meetup will be a shortened version of the first matchmaking meetup held on 11 February and will be a general introduction to the LTP, aimed at those who are interested in the possibility to be part of the consortium.

Meetup programme:

14:00 Introduction of the LTP program + R&D goals
14:10 Application areas + what are we looking for & what can we offer
14:20 Q&A

Sign up for participation here.

ICAI Interview with Rinke Hoekstra: ‘Academics help seeing the big picture.’

Rinke Hoekstra, Lead Architect at Elsevier, is Industry Director of Discovery Lab. This ICAI-lab, a collaboration of Elsevier, University of Amsterdam and Vrije Universiteit Amsterdam, kicked off in April 2020. Hoekstra: ‘Within Elsevier this is already seen as one of the most successful collaborations with academic partners.’

You’re the Industry Director of Discovery Lab. Can you briefly explain what your role is?

‘My role is to intermediate between the company and the partners. I make sure the lab is not overloaded by requests from the company. The lab members have to do research, but as a company, we have to make sure the research is of use to us. That’s a tension. We have to find a good trade-off there.’

What are the challenges involved with that?

‘I communicate the relevance of the lab for the company. The company as a whole is used to deal with a one-year-horizon, but the outcome of the lab will take years. A lot of people in the company don’t think in these terms of long- term innovation. It’s all very academic to them. Another challenge is bringing interesting problems to the academic partners. It’s quite challenging to make sure that we find the right nuggets of data within the organization that are of use to the researchers to play with.‘

‘Our customers are researchers. We feel that it’s our job to help them do research’

How is the lab working out so far?

‘The PhD researchers and the Elsevier data scientists just hit it off and started working. They created a very convincing story in their presentation during the internal kick-off of the lab. I see that internally this is already seen as one of the most successful collaborations with academic partners. The other Elsevier research collaborations are typically at a higher level. They have a couple of meetings every year and then the researchers go off and do their research. But in this lab the data scientists are really working together with the lab members in a self-organized way. They are also bringing in master students who do their research with us. We are creating our own little community. If you don’t have that shared community, you will never have a good collaboration.’

What was the motivation of Elsevier to enter this lab?

‘Our customers are researchers, either in academia, R&D companies or health. We feel that it’s our job to help them do research. We can sell products so they can do their research better, but we can also directly collaborate with them. It is a good opportunity to do research that we don’t necessarily see within our own organization.’

‘We have a longstanding collaboration with Amsterdam Data Science. And we saw this opportunity to work even more closely with our ADS partners. It is so interesting to work with these people. Frank van Harmelen is clearly one of the world leaders in terms of knowledge representation and reasoning knowledge graphs. Paul Groth’s work on provenance and learning knowledge graphs from structured information is well regarded. Maarten de Rijke is obviously big in information retrieval. And the group of Max Welling in machine learning: all world-class researchers. On other universities they have maybe one or two of these fields covered. It is very rare to see that combination in one place.’

What is the most interesting thing about your job?

‘I stay very close to academia and to that kind of free and open thinking. As a lead architect within Elsevier I work with the same technology and problems, but the context is very different. So it’s good to have this more open context where you can freely discuss ideas without somebody saying: ‘what’s the use case?’.’

At the ICAI Lunch Meetup of February 18, 2021, Rinke Hoekstra will present Discovery Lab. More info and sign up here.

OnePlanet opens ICAI Lab ‘AI for Precision Health, Nutrition and Behaviour’

Together with research partners Radboud University, Radboudumc and Wageningen University & Research, OnePlanet Research Center opens the new ICAI Lab. Using AI, they want to improve personalized lifestyle feedback and stimulate healthy behaviour. For example, by developing smart chatbots that motivate people to eat healthier or quit smoking.

The effect of lifestyle changes varies greatly from person to person. It depends on someone’s genetics, eating pattern, activity and the environment in which they live. By combining data on these factors, a deeper insight into the effects of lifestyle feedback is created.

From sensors to coaching

The research team is focusing on three tracks. They develop new sensors to be able to collect more and better health data. Besides that, they also develop smart AI algorithms and machine learning techniques to be able to extract more knowledge, and therefore value, from these data. With this enriched knowledge, lifestyle feedback can be further personalized. This helps in coaching people towards healthier behaviour.

The team focuses mainly on applications in diet coaching, prevention of cognitive decline, prevention of orthostatic hypotension and health-promoting chatbots for smoking addiction and sexual health.

Multidisciplinary approach

These efforts require a multidisciplinary approach. Lab Manager Ruud van Stiphout: “The academic partners will bring domain knowledge and AI expertise to the table, while the industrial partners provide the use cases and innovations that create societal impact. By combining these different disciplines, we can address lifestyle challenges integrally. This ensures optimal impact.”

The research team

The ICAI Lab consists of 7 PhD students and 2 postdocs working on these challenging AI issues. The lab itself is coordinated by Guido Camps (Wageningen University & Research) and Tibor Bosse (Radboud University), the two scientific directors, Ruud van Stiphout (OnePlanet) operates as lab manager and Elena Marchiori and Ton Coolen (Radboud University) coordinate the work packages.

More info on the lab

The Netherlands AI Coalition and ICAI strengthen cooperation


The Netherlands AI Coalition (NL AIC) and the Innovation Center for Artificial Intelligence (ICAI) are strengthening their ties. The organisations are committed to developing the Netherlands into a leading AI country. ICAI has been involved since the foundation of the NL AIC as one of the leading scientific AI communities with research labs throughout the country. It was decided to further strengthen the cooperation by making use of each other’s strengths and expertise. This will allow us to serve companies, government, educational and research institutions and civil society organisations even better.

The cooperation focuses on strengthening AI knowledge and talent in the Netherlands. The first steps will be taken in the areas of Research & Innovation and Human Capital: two important pillars to get the Netherlands in a vanguard position in terms of knowledge and application of Artificial Intelligence (AI) for prosperity and wellbeing.

Research en Innovation

The collaboration should lead to further growth in the number of ICAI labs in 2021. ICAI focuses on the joint development of AI technology by means of industrial labs. These are collaborations between knowledge institutions, industrial partners and/or public organizations. ICAI now has 20 labs, In Amsterdam, Delft, Den Bosch, Eindhoven, Nijmegen, Utrecht, and Wageningen. Work is in progress on the development of another 10 labs, at current locations and at new locations such as Enschede, Maastricht, Rotterdam and Tilburg. Each of the locations has its own area of expertise that match the forces of the region.

Further building up and rolling out the network of ICAI labs is an essential part of the national AI network, which the NL AIC wants to realise together with partners. The choice has been made to work with hubs and spokes, which together form the structure of the AI network. The labs will play an important role within this network’s hub-and-spoke structure. The Netherlands AI Coalition will work to support ICAI in the development of the lab network. Maarten de Rijke, scientific director ICAI: “We are faced with major societal challenges. AI technology can be an important part of the solutions. Spread throughout the country, the ICAI labs strengthen the national and local research and innovation capacity in AI technology. Let’s get to work!”

Human Capital

AI is changing our work and society. By investing in AI in the right way, we can grow as a country and take an important position. This should lead to retention and even expansion of work and jobs if we develop the right expertise. The opportunity for the Netherlands is to prepare for this. Kees van der Klauw, Coalition Manager NL AIC: “Our joint ambition is to develop and retain talent (students and researchers) for the Netherlands and to attract foreign talent to the Netherlands. We do this, for example, by connecting the PhD students in the ICAI labs to the Dutch lmarket. We let them get acquainted with Dutch organisations that are looking for AI talent. We also want to strengthen each other in developing and making available AI courses and training. For example, ICAI contributed to the National AI Course and worked on the development of two AI MOOCs (Massive Open Online Courses) last year. The Human Capital working group of the NL AIC aims to make courses in AI widely available and, where necessary, to develop them further per sector. These are activities in which we can strengthen and support each other.”

Acceleration

By jointly investing in people and talent development, we can make steps towards making the Netherlands ready for the future. Both organisations are convinced of the importance of investing in AI and of taking action to drive research, innovation and talent development around AI. “Through this collaboration, we achieve acceleration and broaden the impact.”

ICAI Interview with Jesse Scholtes: Making an impact in the real world

Program manager of FAST LAB, Jesse Scholtes, makes sure the collaboration between the researchers of TU Eindhoven and their five industry partners runs smoothly. Scholtes: ‘My main role is to manage the expectations and create a win-win situation.’

FAST LAB (new Frontiers in Autonomous Systems Technology) has joined ICAI this week. The lab is in its fourth year of research and creates smart industrial mobile robots that can deal with sudden obstacles in environments like farms, airports and oil & gas sites. The researchers of Eindhoven University of Technology work together with the industry partners Rademaker, ExRobotics, Vanderlande, Lely and Diversey.

Jesse Scholtes

How is it to work with so many different partners in one lab?

Scholtes: ‘Academia and industry are different worlds. Our industry partners want to implement the technology into their products as soon as possible. They are short-term driven. The academic world wants to come up with the best idea and the best way of solving something. For me it’s important to manage the expectations continuously, be very transparent about what we do and how that will turn into a benefit for our partners.’

How do you make this work?

‘Two things are important. One is the realization of all parties that it’s a shared investment. If the companies would develop this research on their own, it would cost them a lot more. The second thing we did from the start is make sure the involved companies are not each other’s competitors. That’s the biggest prerequisite for success. The companies share the same kind of R&D questions, but are active in a different domain. If you take away the potential commercial risk, then people open up, start to talk, share ideas and learn from each other.’

How do you translate that into concrete results?

‘In the first year the researchers spend a lot of time at the industry partners to understand what their challenges are. One of the core things that we have adopted is the end-of-year-demonstration. Researchers bring their new ideas, implement them into the systems of the industry partner and test them in a real world environment. Here we can see the results of what we’ve made and we can also steer the project to a different direction if needed.’

What are you most proud of regarding FAST LAB?

‘That we created a very open friendship and constructive partnership with our researchers and the partners. They really came together as a team, working on the same topics and helping each other. That cannot be taken for granted.’

Where do you see FAST LAB in the next few years?

‘FAST LAB will continue for one more year. But we are working on a successor with existing partners and probably with some new partners. There is a lot of interest. I hope we can create an ecosystem of companies and university-researchers working together and creating this type of win-win situation. As long as we continue to do that, we can continue this cycle and provide much needed continuity in development of novel ideas.’

On the ICAI Lunch Meetup of January 21, 2021, Jesse Scholtes will present the FAST LAB. More info and sign up here.