Projects
From large-scale data to earlier disease prevention.
Our group is interested in finding new ways to early identify common preventable diseases. To do that we develop statistical and AI approaches and apply them to millions of health information from electronic health record/national health registries (e.g. ML4Health). We then integrate registry-based information with genetic and proteomics information from large biobank-based studies (e.g. Finngen) to help identify groups of individuals that can most benefit from existing pharmacological interventions. Finally, we aim to implement these approaches by recontacting individuals and establishing prospective, possibly randomized, clinical studies.
Explore genetics & omics ↓ · Explore AI for health ↓
Interested in a project or collaboration? Contact Andrea Ganna →
Genetics & omics
GENETICS & OMICS
GenCOST: genetics and healthcare costs
We are coordinating the GenCOST consortium, a large multinational consortia comprising over 2 million individuals from cohorts across Europe, America and Australia, also including several cohorts of diverse ancestry. This consortium aims to analyse the effects of genetic variation on healthcare costs in a diverse meta-analysis. The study will include a range of healthcare costs, including hospitalizations, medications, medical procedures and GP visits, estimating the total cost of an individual to a healthcare system. The study aims to find the genetic factors which are responsible for increased healthcare costs for an individual, analysing this from both a biological and public health perspective.
GENETICS & OMICS
PODCAST: how medicines reshape the plasma proteome
Commonly prescribed drugs may leave reproducible signatures in the proteins circulating in our blood, reflecting both their intended mechanisms and off-target effects. PODCAST investigates these changes using biobank samples linked to national prescription records.
We compare drug-response signatures across clinical studies with paired samples collected before and after treatment and biobank datasets, assessing how well each reproduces the gold standard. By linking these proteomic signatures to disease outcomes, we aim to inform drug repurposing and the monitoring of adverse effects. This project is done in collaboration with Jeff Barret.
GENETICS & OMICS
Genetics of longitudinal laboratory measures
Repeated clinical laboratory measurements serve as powerful indicators of an individual's health status and disease progression. These measurements are not only sensitive and objective but also provide valuable insights into underlying biological mechanisms. While it's relatively straightforward to identify genetic variants linked to the average or variability of these measurements through GWAS, the question of whether the trajectory of an individual's lab values is also genetically determined remains largely unexplored. In this project, we aim to uncover the genetic factors that shape the trajectory of lab values, leveraging 221 million measurements from 482,287 Finnish individuals in the FinnGen cohort. By gaining a deeper understanding of these genetic influences, we hope to develop clinically meaningful disease predictors that can better inform healthcare practices.
GENETICS & OMICS
The nature of nurture
The goal of the project is to explore the interaction between genetic endowments and socio-economic conditions in shaping health and socio-economic outcomes in life. We do so by taking advantage of rich Finnish administrative data on socio-economic status, health, and genes. Many common diseases have a strong genetic component, but in order to understand better the development of such health conditions, we need to highlight which environmental factors are responsible for their emergence. Moreover, health conditions can themselves be attenuated or enhanced by socio-economic outcomes. Thus, it becomes important to consider both health and socioeconomic factors into account in the same setting. To explore these questions, we have linked approximately 180,000 individuals with genetic information available with details health and socio-economic information from Statistics Finland, including income, education and labour market. This project is carried out in collaboration with Stefano Lombardi at VATT, THL and Blood Service Biobank. See privacy notice.
GENETICS & OMICS
Beyond Chromosomes: the sex-specific proteome
This project aims to investigate the sex-specific human proteome and the underlying factors of variability both between and within the sexes. By analyzing a large-scale proteomics dataset from multiple studies, this project evaluates sex biases in proteins, analyzes correlation structures that drive sex differences in the proteome, and develops a machine-learning model to quantify proteomic sex and its variability. The goal is to deepen our understanding of how sex-specific proteomic profiles influence biological diversity and disease susceptibility, enhancing knowledge of sex differences beyond genetic factors alone. As part of this project we are recruiting a cohort of individuals undergoing gender affirming hormonal therapy with sample collection pre vs post transition. See Privacy notice
GENETICS & OMICS
BioMOb: biological mechanisms of obesity
BioMOb is an international research project investigating the biological mechanisms underlying obesity through a multi-omics approach. The study integrates genomic, single-cell transcriptomic, and proteomic analyses from blood-derived immune cells and adipose tissue samples. The project combines unique cohorts from Finland and Japan, including individuals with different forms of obesity such as bariatric surgery patients and Japanese sumo wrestlers, who represent a distinct metabolic phenotype despite high body mass. This design enables the identification of both shared and population-specific molecular pathways underlying obesity. By integrating data across multiple biological layers, BioMOb aims to uncover key drivers of obesity and related metabolic complications, ultimately supporting the development of more precise and personalized prevention and treatment strategies. See Privacy Notice
AI for health
AI FOR HEALTH
ML4health: nationwide health foundation models
ML4health combines health data with a wide range of other information from nearly the whole Finnish population. The research data include information about diagnoses, treatment of diseases, medications, laboratory values, medical notes, home care, and institutional care. On top of that, it includes basic personal information, living history, marriage history, pregnancies and births, education, job position, social assistance, and death times and reasons. By leveraging this high-resolution longitudinal data, we aim to develop self-supervised health data foundation models, and other modern AI approaches to improve prediction of phenotypes with scarce training data, such as rare cancers or disease progression and recurrence. These models are known to benefit from heterogeneous, large training data, making the Finnish registries ideal for development of such models. With our European collaborators, we will also study the performance of such models across different European healthcare systems. See privacy policy
AI FOR HEALTH
FINe-Health Foundry
FINe-Health Foundry leverages Finland’s unique national health databases for new types of AI-assisted care and health systems operations and planning solutions. The project will build the world’s first nationwide healthcare foundation model, a ‘Swiss Army knife’ AI model that can support doctors making clinical decisions in real-time and create scenarios at the population-level based on different interventions.
This project is a collaboration with ELLIS Institute Finland.
AI FOR HEALTH
PRIMUS: learning from doctor–patient networks
In the PRIMUS consortium, we're setting out to create new ways to understand large-scale networks and make learning models that are tailored to each user, mainly to assist doctors in making better decisions. A big part of this project looks at how doctors' own backgrounds and behaviors might affect their decisions and the outcomes for their patients. We'll use machine learning to predict how patients might do based on things like what doctors specialize in, what medicines they use, and their own life experiences. We're also interested in seeing how major events in a doctor's life might change the way they care for patients. This project is done in collaboration with Sami Kaski at Aalto University/FCAI and Markus Perola at THL. See privacy notice
AI FOR HEALTH
VALID-AI: Smarter targeting of blood test checkups
VALID-AI aims to improve the efficiency and equity of preventive healthcare by using AI to identify individuals who would benefit most from targeted blood test screening. Using nationwide health records from ML4HEALTH (N=5.2 million) and genetic data from FinnGen (N≈520,000), we develop models to predict abnormal clinical biomarkers, including kidney function, cholesterol, and glucose levels. We then recontact approximately 2,000 Finnish biobank participants to prospectively validate the models' predictive performance through targeted blood testing.
AI FOR HEALTH
f.AI.r.HEALTH: fairness in disease prevention
f.AI.r.HEALTH is a collaboration between teams in Denmark, Estonia, Finland, and Sweden aiming to develop practical guidelines for assessing when AI models are fair enough for real-world healthcare deployment. The project evaluates algorithmic bias in health foundation models, such as Delphi-2M, using nationwide electronic health records across the four countries. We assess differences in model performance across sociodemographic groups in clinical scenarios, including disease screening, cardiovascular risk prediction, and treatment allocation, and investigate the sources of bias across healthcare systems. Through Discrete Choice Experiments, we also examine how clinicians, patients, and policymakers balance predictive accuracy and fairness. Our goal is to develop an empirically validated, stakeholder-informed framework for determining acceptable levels of algorithmic bias in healthcare AI.