This page gives an overview of research projects I am or have been involved in. For those projects, I was involved in acquiring the funding and had key roles executing the project: either as PI, Co-PI, or technical manager for the project, or leading NTNU’s work in the project.
SmaRTWork: A digital system for personalised return to work recommendations for sick-listed with musculoskeletal disorders
Project summary: Long-term sickness absence has vast consequences, both for the sick-listed worker and society. Musculoskeletal disorders are the most common reason for sickness absence. Despite extensive research on return to work interventions, the results are inconsistent and there is a lack of evidence regarding who needs what measures and at what time. This project aims is to develop and evaluate an intelligent decision support system that 1) enables early identification of individuals at risk of long-term sick leave due to musculoskeletal disorders, and 2) provides personalized recommendations to facilitate sustainable return to work. The foundation for the decision support system will be case-based reasoning (CBR). The main principle of CBR is to reuse knowledge from previous successful cases to suggest solutions for new and similar cases. Workers who have been sick-listed for 8 weeks due to musculoskeletal disorders will be invited to use the SmaRTWork tool. After consent, they will receive credentials to access the web-based tool, which can be accessed by a computer/tablet/phone. SmaRTWork is a user-centered system, where the sick-listed worker chooses to act upon the tailored recommendations they receive about measures to facilitate return to work. To increase acceptability, credibility, and likelihood for uptake, the involvement of users and stakeholders in development and evaluation will be crucial. In addition, user representatives will be invited to take part in an advisory board. The effect of the SmaRTWork tool on return to work will be evaluated in a randomized controlled trial. Furthermore, a process evaluation assesses facilitators and barriers for implementation, and qualitative studies explore how the sick-listed workers and other relevant stakeholders experience using the system.
Role: I lead the technical development of the SmaRTWork decision support system. This includes leading research on the underlying CBR system, overseeing the implementation, and supervising one Ph.D. student.
Funding: 12 M NOK (1,2 M EUR) via HELSEVEL, RCN: 315041
Duration: 1 Aug 2021 – 30 Jul 2027
EXAIGON: Explainable AI systems for gradual industry adoption
Project summary: The recent rapid advances of Artificial Intelligence (AI) hold promise for multiple benefits to society in the near future. AI systems are becoming ubiquitous and disruptive to industries such as healthcare, transportation, manufacturing, robotics, retail, banking, and energy. However, in order to make AI systems deployable in social environments, industry, and business-critical applications, several challenges related to their trustworthiness must be addressed first: Lack of transparency and interpretability, lack of robustness, and inability to generalize to situations beyond their past experiences. Explainable AI (XAI) aims at remedying these problems by developing methods for understanding how black-box models make their predictions and what are their limitations. The call for such solutions comes from the research community, the industry, and high-level policymakers, who are concerned about the impact of deploying AI systems to the real world in terms of efficiency, safety, and respect for human rights. The EXAIGON project (2020-2024) will deliver research and competence building on XAI, including algorithm design and human-machine co-behavior, to meet society’s and industry’s standards for deployment of trustworthy AI systems in social environments and business-critical applications.
Role: I work on methods to enhance the explainability of CBR systems as well as using CBR to explain black-box machine learning models.
Funding: 16 M NOK (1,6 M EUR) via IKTPLUSS, RCN: 304843
Duration: 1 Apr 2020 – 30 Mar 2020
SupportPrim: Optimizing management of musculoskeletal disorders in primary care
Project summary: Optimizing the management of musculoskeletal pain disorders in primary care (SUPPORTPRIM) Musculoskeletal disorders are the number one cause of years lived with disability worldwide. In Norway, every fourth patient in primary care suffers from musculoskeletal disorders. The benefits from treatment are modest, however, and knowledge of best practices is limited. The SUPPORTPRIM project will address these challenges in two main steps: 1) To optimize person-centered care, we will employ innovative methods from artificial intelligence using an approach called Case-Based Reasoning to build a clinical decision support system that uses patient data already collected from patients who have received primary care physiotherapy. Case-Based Reasoning aims to guide new treatment decision-making based on the outcomes in similar patients who received the treatment in the past. Previous cases with musculoskeletal disorders will be used to help similar cases in the future, just as humans learn from their own experience. The study team will then assess the efficacy of the clinical decision support system in physiotherapy practice in a randomized controlled trial in Norway. 2) This effort will be expanded to general practice in Norway by implementing a stratified care approach, involving the matching of patients with musculoskeletal disorders to specific treatments, using the Keele STarT MSK Tool. The efficacy of the stratified care approach will be assessed in a randomized controlled trial in general practice. Finally, the clinical decision support system from physiotherapy practice will be extended and adapted to fit general practice. State-of-the-art personalized treatment plans are envisioned to benefit a much larger proportion of patients with musculoskeletal disorders than a “one-size-fits-all” approach. SupportPRIM facilitates and emphasizes the co-decision process between the patient and physiotherapist.
Role: I lead the technical development of the SupportPrim decision support system. This includes leading research on the underlying CBR system, overseeing the implementation, and supervising two Ph.D. students.
Funding: 12 M NOK (1,2 M EUR) via BEHANDLING, RCN: 303331
Duration: 1 Aug 2020 – 30 Jul 2024
PABS: Physical Activity Behaviour and Sleep and their impact on public health
Project summary: In this project we use unique data from the HUNT Study and innovative methods and technology to advance the current knowledge about the impact of physical activity behavior and sleep on public health.
Role: I lead the technical development of the Machine Learning models to determine physical activity and sleep patterns.
Funding: 12 M NOK (1,2 M EUR) via NTNU Helse
Duration: 1 Apr 2020 – 31 Mar 2024
AI4EU: European Artificial Intelligence On-Demand Platform and Ecosystem
Project summary: Artificial Intelligence is a disruptive technology of our times with expected impacts rivalling those of electricity or printing. Resources for innovation are currently dominated by giant tech companies in North America and China. To ensure European independence and leadership, we must invest wisely by bundling, connecting and opening our AI resources. AI4EU will efficiently build a comprehensive European AI-on-demand platform to lower barriers to innovation, to boost technology transfer and catalyse the growth of start-ups and SMEs in all sectors through Open calls and other actions. The platform will act as a broker, developer and one-stop shop providing and showcasing services, expertise, algorithms, software frameworks, development tools, components, modules, data, computing resources, prototyping functions and access to funding. Training will enable different user communities (engineers, civic leaders, etc.) to obtain skills and certifications. The AI4EU Platform will establish a world reference, built upon and interoperable with existing AI and data components (e.g. the Acumos open-source framework, QWT search engine..) and platforms. It will mobilize the whole European AI ecosystem and already unites 80 partners in 21 countries including researchers, innovators and related talents. Eight industry-driven AI pilots will demonstrate the value of the platform as an innovation tool. In order to enhance the platform, research on five key interconnected AI scientific areas will be carried out using platform technologies and results will be implemented. The pilots and research will showcase how AI4EU can stimulate scientific discovery and technological innovation. The AI4EU Ethical Observatory will be established to ensure the respect of human centred AI values and European regulations. Sustainability will be ensured via the creation of the AI4EU Foundation. The results will feed a new and comprehensive Strategic Research Innovation Agenda for Europe.
Role: Participation in Task 6.8 – AI4IoT pilot. This pilot explores the use of the AI4EU platform on air quality data captured by IoT devices. This includes deploying micro sensors, creating a data management platform for storing and processing data as well as running experiments targeting air quality prediction and decision support through machine learning models, simulations and visualisations. To improve data quality and services the pilot enhances pollution data with other information such as mobility patterns, weather forecasts, and environmental data.
Funding: 20,7 M EUR through EU H2020 RIA. Grant agreement ID: 825619.
Duration: 1 Jan 2019 – 31 Dec 2021
Back-UP: Personalised prognostic models to improve well-being and return to work after back and neck pain
Project summary: Neck and low back pain (NLBP) are leading causes for years lived with disability in Europe and worldwide. About 70% of all adults experience NLBP at some point in their lives, and both conditions are among the top ten in terms of overall disease burden expressed as disability-adjusted life years. Management of NLBP is a difficult challenge for healthcare professionals since their decisions have a decisive impact on the patient’s future health and welfare, as well as on the economic burden on the public and private healthcare systems. However, health professionals often lack appropriate information to tailor the management and follow-up of individual patients and to predict the outcome of a certain treatment. At the European level, diverse research initiatives are undergoing at this moment for tackling NLBP from diverse angles, including biomarkers (PainOmics), pain self-management (selfBACK), lifestyle and workplace conditions (AHA), or patients stratification (STarT Back). The BACK-UP project provides a wider vision of NLBP, bringing together the research groups that are leading these and other innovative approaches to create a prognostic model to underpin more effective and efficient management of NLBP based on the digital representation of multidimensional clinical information and on simulations of the outcomes of possible interventions. Patient-specific models will provide a personalized evaluation of the patient case, using multidimensional health data from the following sources: personal, health, psychological, behavioral, and socioeconomic factors related to NLBP; biological patient characteristics, including musculoskeletal structures and function, and molecular data; and workplace and lifestyle risk factors. Back-UP will provide health, well-being, and economic benefits to different user profiles (clinicians, employers/insurance companies, and patients) and will create a channel for sharing information during the rehabilitation and return to work process.
Role: I led the further development of the selfBACK decision support system expanding to neck and low back pain. I further led the machine learning task developing prognostic models from patient-reported outcome measures.
Funding: 5,13 M EUR through EU H2020 RIA. Grant agreement ID: 777090
Duration: 1 Jan 2018 – 30 Apr 2021
selfBACK: A decision support system for self-management of low back pain
Project summary: The recent global burden of disease study showed that low back pain (LBP) is the most significant contributor to disability in Europe. Most patients seen in primary care with LBP have non-specific LBP (≥85%), i.e., pain that cannot reliably be attributed to a specific disease/pathology. LBP is the fourth most common diagnosis seen in primary care (after an upper respiratory infection, hypertension, and coughing). Self-management in the form of physical activity and strength/stretching exercises constitutes the core component in the management of non-specific LBP; however, adherence to self-management is challenging due to a lack of feedback and reinforcement. This project aims to develop a decision support system – selfBACK – that will be used by the patient him/herself to facilitate, improve and reinforce self-management of LBP. Specifically, selfBACK will be designed to assist the patient in deciding and reinforcing the appropriate actions to manage their own LBP after consulting a health care professional in primary care. The decision support will be conveyed to the patient via a smartphone app in the form of advice for self-management. The advice will be tailored to each patient based on the symptom state, symptom progression, the patient’s goal-setting, and a range of patient characteristics including information from a physical activity-detecting wristband worn by the patient. The second part of the project will evaluate the effectiveness of selfBACK in a randomized controlled trial using pain-related disability as the primary outcome. We envisage that patients who use selfBACK will have 20% reduction in pain-related disability at 9 months follow-up compared to patients receiving treatment as usual. Process evaluation will be carried out as an integrated part of the trial to document the implementation and map the patients’ satisfaction with selfBACK. A business plan with a targeted commercialization strategy will be developed to transfer the selfBACK technology into the market.
Role: I served as project manager for the overall project which is coordinated at NTNU. Further, I have been responsible for the overall technical development in the project.
Funding: 4,92 M EUR through EU H2020 RIA. Grant agreement ID: 689043.
Duration: 1 Jan 2016 – 31 Mar 2021
Exposed SFI: Knowledge and technology for robust, safe and efficient fish farming at exposed locations.