Lab profile
About DSGE Lab
The lab develops and applies computational methods, including statistical and deep learning approaches, to decode large-scale biological and electronic health records data. Their work integrates genetic data with information from electronic health records and national health registries to enhance early detection of common diseases and enable more effective public health interventions, with the goal of identifying individuals who can most benefit from existing pharmacological interventions.
Genetic epidemiologyDisease risk predictionElectronic health records analysisProteomics and biomarker discoveryHealthcare costs genomicsAI foundation models for health dataMultimodal AIFairness in health AI
01 · Research focus
Research areas and highlights
Topics and recent work as stated on the lab’s own site.
- Removing genomics from biomarkers to improve disease predictionIntegrates genomic data with blood-based and clinical biomarkers to strengthen biomarker-disease associations and improve downstream prediction by adjusting biomarker measurements for their genetically predicted component.
- GenCOST consortiumA large multinational consortium comprising over 2 million individuals analyzing the effects of genetic variation on healthcare costs across Europe, America and Australia.
- New methods to study the genetic of longitudinal clinical laboratory measuresAims to uncover genetic factors that shape the trajectory of lab values leveraging 221 million measurements from 482,287 Finnish individuals in the FinnGen cohort.
- The nature of nurture: the interplay between genetic and the social environment in impacting healthExplores the interaction between genetic endowments and socio-economic conditions in shaping health and socio-economic outcomes using Finnish administrative data on approximately 180,000 individuals.
- Beyond Chromosomes: Unveiling the Sex-Specific Proteome and Its Impact on Human HealthInvestigates the sex-specific human proteome and underlying factors of variability by analyzing large-scale proteomics datasets and developing machine-learning models to quantify proteomic sex.
- BioMOb – Biological Mechanisms of ObesityAn international research project investigating biological mechanisms underlying obesity through multi-omics approach combining unique cohorts from Finland and Japan including bariatric surgery patients and Japanese sumo wrestlers.
- ML4health - AI foundation models for nationwide health and socio-economic dataDevelops self-supervised health data foundation models using high-resolution longitudinal data from nearly the whole Finnish population to improve prediction of phenotypes with scarce training data.
- Improving the transferability of multimodal AI for disease risk predictionDevelops methods to enhance the portability of AI models across healthcare systems and expand their capacity to incorporate multimodal data while ensuring fairness in prediction.
- PRIMUS consortium: machine learning for doctor-patient networksCreates new ways to understand large-scale networks and make learning models tailored to each user to assist doctors in making better decisions by analyzing how doctors' backgrounds and behaviors affect patient outcomes.
- Can AI identify people with the highest need for a blood test checkup?Develops and prospectively validates a deep-learning approach to identify individuals who would benefit most from targeted screening for clinically actionable biomarkers using nationwide FinRegistry data.
- f.AI.r.HEALTH: Ethical and computational evaluation of fairness in AI for personalized disease preventionA collaboration across Denmark, Estonia, Finland, and Sweden to produce practical guidelines for evaluating fairness in AI models by measuring algorithmic bias across socio-demographic subgroups in clinical use cases.
- INTERVENE-EU project
02 · People
Leadership and researchers
People listed on the lab’s team pages, by role.
Andrea GannaDirector · PI, Associate Professor
Tatiana CajusoSenior Scientist (title of docent)LinkedIn ↗
Tuomo HartonenSenior scientist, Team lead
Anna-Leena VuorinenSenior Scientist
03 · Research intelligence
Research Intelligence evidence
Publications, grants and clinical trials linked to the lab’s researchers in Health AI Central’s research data.
Publications & preprints
- Genetic regulation across germline and somatic variation on the Y chromosome contributes to type 2 diabetes.Nature medicine · 2026
- Correction: GRIN2A null variants confer a high risk for early-onset schizophrenia and other mental disorders and potentially enable precision therapy.Molecular psychiatry · 2026
- GRIN2A null variants confer a high risk for early-onset schizophrenia and other mental disorders and potentially enable precision therapy.Molecular psychiatry · 2026
04 · Updates
Updates and lab news
News and events from the lab’s own site.
No news has been collected from the lab’s site yet.
05 · Official presence
Lab sources and channels
The lab’s own pages and accounts.
06 · Related
Related labs and centers
Labs at the same institution and labs working on similar topics.