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 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.”

DSM and TU Delft establish artificial intelligence laboratory to drive bioscience innovation

Royal DSM, a global science-based company in Nutrition, Health and Sustainable Living, and TU Delft, ranked among the top universities in biotechnology research globally, today announce the establishment of the Artificial Intelligence Lab for Biosciences (the AI4B.io Lab). This laboratory will be the first of its kind in Europe to apply artificial intelligence (AI) to full-scale biomanufacturing, from microbial strain development to process optimization and scheduling.

The AI4B.io Lab will be part of the Dutch National Innovation Center for AI (ICAI), which works to keep the Netherlands at the forefront of knowledge and talent development in AI. It will be led by Professor Marcel Reinders, Director TU Delft Bioengineering Institute. DSM regards biosciences as an important tool for addressing climate change and resource scarcity and optimizing the global food system so will invest EUR 2.5 million into the laboratory over the first five years.

With more than 150 years of experience, DSM has already developed an extensive portfolio of sustainable, bio-based solutions that help address some of the key challenges facing society. Now, developments in the understanding of biology, as well as major advances in digital transformation, are opening up exciting possibilities for new bio-based products, applications, and manufacturing processes. Integrating biosciences and digital technologies can help to reduce the time spent on innovation cycles, from prototyping to scaling and commercialization.

Bringing the desired objective to life, digitally

Traditionally, scientific research is based on trial and error within multiple sub-studies that work together toward a specific objective, such as a new product or production technology. What makes AI unique is that it allows scientists to invert this process. The desired objective is brought to life in a digital environment using ‘digital twins’ (a virtual ‘mirror’ of the desired real-world situation), while machine learning helps determine how to achieve it. Although AI is already widely applied in engineering research – for instance, to replace physical wind turbines or tunnels with digital twins – the AI4B.io Lab will be the first of its kind to explore AI’s potential in biosciences and biomanufacturing.

No innovation without collaboration

Working closely together with partners can drive progress and create access to new technologies. For this reason, DSM decided to partner with TU Delft in setting up and developing the AI4B.io Lab. It will be the third ICAI Lab on the TU Delft Campus, joining the AI for Retail Lab Delft of Ahold Delhaize, and the AI for Fintech Lab of ING. Additionally, TU Delft will invest in 24 interdisciplinary AI laboratories on a broad range of topics to further drive collaboration between scientists working in AI and scientists from other domains. The AI4B.io Lab will also collaborate with Planet B.io, the open-innovation ecosystem at the Biotech Campus Delft – for instance, by providing research insights and consultancy to biotechnology startups on the campus. Both DSM and TU Delft are founding partners of Planet B.io.

Through these extensive and broad collaborations, the partnership will further strengthen the position of Delft as the bio-economy capital of the world.

Professor Marcel Reinders, Director TU Delft Bioengineering Institute: ‘’Biotechnology can contribute significantly to solving major societal challenges, such as climate change, healthy nutrition for the world’s rapidly growing population, and raw material scarcity. AI plays a crucial role in the development of biotechnology applications, but – scientifically speaking – there are still many unanswered questions at the cellular, lab, and process level. By linking our fundamental research to concrete opportunities at DSM, we can maximize our impact.”

Marcel Reinders, Scientific Director of AI4B.io Lab

 

Marcus Remmers, Chief Technology Officer DSM: “TU Delft has a proven track record of groundbreaking research in AI, bioengineering, and bioinformatics. DSM is a global, science-based company that creates sustainable, bio-based products and solutions at commercial scale. This makes our parties the perfect match to tackle important scientific and societal challenges together.”

Cindy Gerhardt, Managing Director Planet B.io: ‘’At Planet B.io, we stimulate open innovation and collaboration between startups, corporations, and knowledge institutes to develop bio-based products and solutions. We look forward to working together with the AI4B.io Lab to maximize the potential of AI and biosciences.’’

DSM – Bright Science. Brighter Living.™

Royal DSM is a global, purpose-led, science-based company active in Nutrition, Health and Sustainable Living. DSM’s purpose is to create brighter lives for all. DSM addresses with its products and solutions some of the world’s biggest challenges while simultaneously creating economic, environmental and societal value for all its stakeholders – customers, employees, shareholders, and society at large. DSM delivers innovative solutions for human nutrition, animal nutrition, personal care and aroma, medical devices, green products and applications, and new mobility and connectivity. DSM and its associated companies deliver annual net sales of about €10 billion with approximately 23,000 employees. The company was founded in 1902 and is listed on Euronext Amsterdam. More information can be found at www.dsm.com.

TU Delft

TU Delft has a strong foundation. As the builder of the world-famous Dutch waterworks and a pioneer in biotechnology, TU Delft is a leading international university that combines science, development, and design. As the oldest and largest technical university in the Netherlands, TU Delft provides world-class education, research, and innovation. Generations of its engineers have proven to be entrepreneurial problem solvers in business and social contexts. TU Delft’s eight faculties offer 16 bachelor’s and more than 32 master’s courses. More than 25,000 of its students and 6,000 of its employees share a fascination with science, design, and technology. Their shared mission: impact for a better society.

Read more on the AI4B.io Lab

3 factors for a successful university-business collaboration

Mark Siebert, Director of Research Collaborations at Elsevier, wrote an interesting piece on Elsevier Connect about the ingredients that make a collaboration between academia and industry work. He used his personal impressions and lessons learned from establishing Elsevier’s Discovery Lab. 3 success factors played a role he says:

  1. Build credibility, reliability and shared excitement as you get to know each other’s unique abilities.
  2. Differentiate business/research priorities and legal requirements to minimize “self-orientation.”
  3. Use facilitated communication to connect the interests and expectations that must converge to build trust.

‘There is nothing better in a partnership than winning together’, Siebert concludes.

Read the whole article here

Prepare to Integrate AI in Your Organization – New Online Program

How can your organization benefit from AI? The new online program AI in Practice, starting on November 3, helps professionals to implement AI in their own organization. This program has been developed in collaboration with the Labs of ICAI and is offered on the edX.org platform.

Just like electricity must have been more than 100 years ago, AI is now a disruptive force with the potential to revolutionize industries and businesses across the board. We may not yet be able to properly imagine how it will affect our work and lives, but organizations need to start thinking about how AI can be applied to improve everyday practice.

The program consists of 2 short online courses aimed at anyone who, regardless of their professional background or job role, is interested in learning how AI can help their organizations solve specific problems, drive efficiency and improve performance and decision-making.

Is this then a program for you or for someone you know? Visit our program page and help us spread the word by sharing this with your networks, colleagues and anyone interested in learning how AI can help their organizations and how to develop a plan for its application.

Start date: November 3, 2020

Snoek op Zolder – New podcast by NL AIC and ICAI

Now listen to the second episode of ‘Snoek op Zolder’, starring professor Frank van Harmelen. Snoek op Zolder is the new weekly science podcast by the Dutch AI Coalition (NL AIC) and ICAI.

In this second episode, Hosts Hennie Huijgens and Sietse van Gorkum speak with Frank van Harmelen (VU), professor knowledge representation and reasoning, on the Discovery Lab. Within this lab, Elsevier, VU and UvA, conduct research into the use of AI to support scientist in their research methods. They discuss the twenty million euros, ten-year collaboration between researchers from six Dutch universities in the Hybrid Intelligence Center and the research lag of Europe compared to America and China.

Special treat: the song ‘Artificial Intelligence’ written exclusively for this podcast by singer-songwriter Yanna Pelser.

About de podcast

In Snoek op Zolder the hosts will be discussing small and large AI innovations, exciting research results and earth-shaking theories every week with passionate curiosity and humor. With this podcast they aim to spread knowledge about AI and inspire people to learn more about it.

There will be a new podcast every week, you can listen to the first episode on any podcast app or platform!