Francisco Pereira

Francisco Pereira says: “As the climate continues to impact our world, policymakers require advanced scientific simulation tools to navigate the intricate challenges and uncertainties that arise. While existing tools offer detail, they often fall short due to their narrow focus and resource-consuming performance. The APEX project addresses this challenge by introducing an integrated platform powered by machine learning, which synergizes various simulation tools to address the entire problem, not just isolated parts, while simultaneously optimising their performance. Utilizing today’s immense computational power, APEX explores and virtually tests a vast array of options, providing policymakers with a comprehensive and transparent analysis of a wide range of alternatives.

APEX will be applied in crucial domains such as transport, energy, and the environment, areas that have significant societal impact. Committed to the principles of human-aligned AI, APEX ensures that its artificial intelligence operates with a focus on transparency, fairness, and accountability, aligning technological advancements with human values and ethical considerations.”

Liselotte Vogdrup Petersen

Liselotte V. Petersen says: “The overarching purpose is to optimize estimation in case-cohort samples and explore genetic pathways using information from Danish registers. The case-cohort sampling design has several advantages compared to other sampling designs as the control group can be reused to study other case groups and absolute measures such as percentages (and the certainty of the percentage) can be estimated. However, this is not covered in standard statistical packages for scenarios such as competing risk. Therefore, we will explore the possibilities and provide recommendations to optimize estimations in case-cohort studies, including time to event data in genome-wide association studies. We also aim to find subgroups of cases that have distinct biological pathways to disease by utilizing register-based information on exposures in various case-only genome-wide association studies.”

Nicolai Birkbak

Nicolai Birkbak says: “The aim of this project is to unravel the mysteries of how our immune system changes as we age and how these changes influence our overall health. Using cutting-edge technology, we will delve into the intricacies of individual cells from thousands of people, with a particular focus on understanding how age and biological sex impact the immune system. Our goal is to develop innovative methods and apply advanced artificial intelligence tools to accurately measure the health and state of the immune system and demonstrate how immune health relates to general health and particularly to cancer development and outcome. This knowledge holds the potential to transform how we view the relevance of immune health. Potentially, it could pave the way for new immune-boosting strategies to prevent and treat various age-related diseases, offering a brighter and healthier future for individuals as they grow older.”

Helene Charlotte Wiese Rytgaard

Helene Charlotte Wiese Rytgaard says: “One of the key challenges in medical research consists in analyzing the effects of treatments administered over time using real-world data. Here traditional statistical methods and standalone machine learning approaches may either be inapplicable or fail to yield clinically meaningful results. The obstacles that a sound statistical approach needs to deal with are continuous-time dynamics, including irregular monitoring, and complex treatment decisions, changes of patient characteristics, and health outcomes. This research project aims to develop, extend and implement advanced statistical methods integrating machine learning techniques for analyzing treatment effects in observational healthcare data, to provide more reliable tools for informed medical decision-making by patients, clinicians, and drug developers. The project will expand and enhance modern statistical causal inference tools combined with machine learning techniques and continuous-time models, to data-adaptively model the dependence between life-course events and treatment decisions, while accurately and efficiently addressing essential medical questions regarding dynamic administering of treatment. The goal is to provide a toolbox containing methods and corresponding software implementations that can be used to gain valuable insights into how the administration of treatments over time impacts patient survival and disease progression, beyond what is possible with existing methods.”

David Duchene Garzon

David Duchene Garzon says: “Identifying infected animals as early as possible allows us to minimize the spread of a pathogen and even prevent a pandemic. At the moment, we can only make sure that an
animal is infected by costly laboratory analysis. This is problematic for livestock and wildlife given the limited funds that can be spent on each animal, yet these settings are the most common source of dangerous pathogens to humans. Surprisingly, video data is not yet being used for identifying infected animals, despite great strides in video analysis in recent years.

This project will cover this gap and improve our ability to halt epidemics in their tracks. A broad range of animals will be filmed, and their behavior will be compared with their blood tests. Whether infected or not, each recording will help train computers, which will inform us about how pathogens can drive behaviour. A free app will then be developed for companies, governments, and lay people to detect infected animals at a minimal cost.”

Mathias Spliid Heltberg

Mathias Spliid Heltberg says: “Modern data analysis has transformed how we study life’s complexities. My proposal merges different ways to study the complex machinery of living cells, and by developing new algorithms and applying advanced methods to analyze the data, I aim to obtain new levels of details of the physical mechanisms in the cell.

When we look into the center of a cell, we see proteins gathered in small droplets and showing waves in their concentration profile. To understand how this can emerge, we are using new tools to analyze data and develop new ways to obtain more information from the experiments. With this, the hope is to reveal how droplets and oscillations interact and understand how this can impact cellular function. Last year, I discovered that DNA repair is guided by formation of droplets and oscillations in the concentration of proteins, and with new data analysis I hope to advance this hypothesis. Put in simple terms, my group will use data analysis to solve a puzzle: how cells orchestrate resources in space and time to complete fundamental tasks.”

Josefine Bohr Brask

Josefine Bohr Brask says: “Social networks describe the pattern of social connections between individuals in a population. For example, the friendships among children in a school class, the grouping patterns within a dolphin population, and the grooming interactions within a group of chimpanzees, can all be described as a social network, where each node is an individual and the links are their social connections.

Social networks play an important role in the lives of both humans and non-human animals. The structure of the networks affect the spread of disease and information, and the social connectedness of individuals affect their health, well-being and survival. Social networks are therefore of great scientific interest.

A key question about social networks is how the complex structures arise from the behavioural strategies that individuals use to select their social partners. Answering this question is essential for understanding social systems, and for predicting their reaction to future societal and environmental challenges.

In this project, we develop and use new computational methods for the study of networks, within two main methodological regimes: statistical analysis of network data, and simulation of networks via computer algorithms (generative network modelling). Our aim with this is to advance the study of networks and our understanding of the emergence of social network structures.”

Kristian Thijssen

Kristian Thijssen says: “Many organisms at high enough density start to display collective motion, including flocks of birds, schools of fish and on the micro-scale microorganisms. These swimming microorganisms are found everywhere: within humans, in soils and in industrial installations, and they display remarkable pattern formations at sufficiently high densities. We describe the collective motion of these swimmers as a “living liquid”. Just like a regular liquid, the container of the living liquid governs the dynamics, i.e. in a box, flowing through a pipe etc. However, many relevant biological systems exist in pliable environments where this living liquid can alter its soft surrounding. Hence, we expect to observe mutual interactions between liquid and surrounding, which this proposal seeks to investigate. This could open pathways for regulating bacteria dynamics to aid biodegradation, hinder contamination, combat medical infections and help with fertility problems to improve non-hormonal birth control.”

Sisse Njor

Sisse Njor says: “The purpose of this project is to improve existing analytical tools used to estimate the major benefits and harms of cancer screening.

Researchers are globally striving to produce reliable estimates on the major benefits and harms of cancer screening and to agree upon which methods that produce reliable estimates. However, the existing analytical tools are increasingly obsolete and require updating. This project will suggest and validate a new method based on existing analytical tools from other research areas. A method that will hopefully enable researchers to produce reliable estimates on the major benefits and harms of cancer screening, both for the entire population and for subgroups.

With the increasing moves to use individualized screening it is extremely important to know if there are subgroups that only have a very small reduction in cancer mortality when participating in screening or subgroups who have a particular high risk of overdiagnosis. The new method may provide these answers”.

Sisse Njor holds a Senior Researcher position at Randers Regional Hospital, Department of Public Health Programmes since 2017, and is furthermore affiliated to Aarhus University, Institute of Clinical Medicine as an Associate Professor and the Danish Clinical Quality Program, National Clinical Registries as an epidemiologist.

Lars Kai Hansen

Can artificial intelligence algorithms learn to communicate in a language we understand?

Lars Kai Hansen says: “Machine learning algorithms are often perceived as complex black boxes and much research has already gone into opening the black box to explain what has been learned from data. The communication aspects of explainable AI have attracted less attention. The cognitive spaces project is aimed at relating AI explanations better to given user groups and effectively let the algorithms speak the user’s language. We will realize the vision by aligning learned representations of data with formal human knowledge graphs. We hope to understand and push the limits to deep learning interactivity by theoretical and experimental analysis, design of new learning schemes to enable knowledge aware models and explanation.

Our primary use case concerns cognitive spaces for deeper understanding of electric brainwaves (EEG). These signals are of increasing diagnostic importance and EEG signals play a fundamental role in neuroscience. In an ambitious attempt to understand EEG models better we will use cognitive space methods for real-time “captioning” of the brainwave signal”.

Since 2000 Lars Kai Hansen has been a Professor at Technical University of Denmark where he heads the Cognitive Systems group.