THTuomo Hartonen

Tuomo Hartonen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Tuomo Hartonen has a total of 156 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Sex-related signatures in the plasma proteome not attributable to XX and XY chromosomes and their impact on health and disease

    by Essi Viippola, Tuomo Hartonen, Meihui Zhu, Zhijian Yang, Ryuya Edahiro, Tomoko Nakanishi, Ao Lan, Masahiro Kanai, Nhi N. L. Nguyen, Tatiana Cajuso, et al.

    Sex differences in human health are typically modeled as binary comparisons between males (XY) and females (XX). However, sex-linked molecular traits vary continuously and are shaped by environmental factors. Here, we introduce the Proteomic Sex Index (PSI), a continuous, plasma proteomics–based measure that quantifies the degree to which an individual’s proteome aligns with their chromosomal sex, with higher PSI values indicating profiles less typical for their sex. Leveraging data from 51,310 individuals from six demographically heterogeneous cohorts, we show that PSI captures broad, biologically meaningful variation in sex-enriched traits and diseases. Individuals with proteomic profiles shifted away from their chromosomal sex exhibited trait values less characteristic of that sex. For example, males with higher PSI were shorter, had lower grip strength, and showed reduced severity of COVID-19 (OR=0.59, p =3.0×10 −7 ). Analyses of individuals undergoing gender-affirming hormone therapy showed that, although PSI correlated with circulating sex hormones, it also captured additional variation independent of hormone levels. PSI is partially heritable and genetically influenced. Individuals with Klinefelter syndrome (XXY) had markedly elevated PSI (OR=13.7, p =1.1×10 −13 ), and genome-wide association studies of PSI identified sex-biased cis-pQTLs with evidence of causal links to sex-specific disease risk. PSI provides a nuanced, individualized measure of sex-related biology that enables the study of within-sex molecular variation and its links to health and disease.

  • Open Access

    Association and risk prediction of 19 complex diseases with polygenic scores and socioeconomic status

    by Fiona A Hagenbeek, Anne Richmond, Max Tamlander, Kira Detrois, Zhiyu Yang, Tuomo Hartonen, Daniel L McCartney, Finn Gen, Riccardo E Marioni, Pekka Martikainen, et al.

    Background: Differences in disease risk are linked to inherited genetic variation and social circumstances, but how these factors jointly relate to multiple diseases is not fully understood. This study investigates the independent and combined associations of genetic predisposition and socioeconomic status with common diseases. Methods: We analyzed data from 743,194 adults from three biobank studies in Finland and the United Kingdom, including European and non-European ancestry individuals. Genetic predisposition was measured using polygenic scores for 19 common diseases. Socioeconomic status was assessed through education and occupation. We evaluated associations of genetic and socioeconomic factors with disease risk and whether genetic associations differed across education levels. Models including both genetic and educational factors were compared with models including only one factor and models including their interaction. Results: Here, we show that both genetic predisposition and socioeconomic status are associated with disease risk across most conditions. For seven diseases, genetic associations are stronger in highly educated groups, while occupation shows smaller differences. Patterns are generally consistent across ancestry groups, though education associations are less stable in non-European individuals. While both education and polygenic scores independently improved prediction, combining both provided additional modest improvement to prediction for 16 and 12 out of 19 diseases in FinnGen and the UK Biobank, respectively. Conclusions: Genetic variation and social circumstances are linked to differences in disease risk both independently, and in combination with one another. Considering both factors modestly improves identification of higher-risk groups and highlights the value of accounting for social context alongside inherited variation in population-level assessments.

  • Open Access

    The impact of polygenic score and socioeconomic status in predicting risk for 19 complex diseases

    by Fiona A. Hagenbeek, Anne Richmond, Max Tamlander, Kira Detrois, Zhiyu Yang, Tuomo Hartonen, Daniel L. McCartney, Finn Gen, Riccardo E. Marioni, Pekka Martikainen, et al.

    Both socioeconomic circumstances and genetic predisposition shape disease risk, yet their joint contribution across diseases has not been systematically examined. We studied 19 high-burden diseases in 743,194 participants (729,928 European; 13,266 non-European ancestry) from FinnGen, the UK Biobank, and Generation Scotland. Higher educational attainment was associated with lower risk of most conditions, but with higher risk of most common cancers. These associations were largely independent of disease-specific polygenic scores (PGSs). For seven out of 19 diseases, PGSs showed stronger effects among individuals with high education. Joint inclusion of education and PGSs modestly improved prediction for 14 and 10 out of 19 diseases in FinnGen and the UK Biobank, respectively. PGS associations were consistent across ancestries, whereas education effects were less stable; results using an alternative socioeconomic measure were directionally similar but smaller. Our findings highlight the distinct and partly interacting contributions of socioeconomic and genetic factors to disease risk.


  • Open Access

    Cross-biobank generalizability and accuracy of electronic health record-based predictors compared to polygenic scores

    by Kira E. Detrois, Tuomo Hartonen, Maris Teder-Laving, Bradley Jermy, Kristi Läll, Zhiyu Yang, Estonian Biobank research team, Finn Gen, Reedik Mägi, Samuli Ripatti, et al.

    Electronic health record (EHR)-based phenotype risk scores (PheRS) leverage individuals’ health trajectories to estimate disease risk, similar to how polygenic scores (PGS) use genetic information. While PGS generalizability has been studied, less is known about PheRS generalizability across healthcare systems and whether PheRS are complementary to PGS. We trained elastic-net-based PheRS to predict the onset of 13 common diseases for 845,929 individuals (age = 32–70 years) from three biobank-based studies in Finland (FinnGen), the UK (UKB) and Estonia (EstB). All PheRS were statistically significantly associated with the diseases of interest and most generalized well without retraining when applied to other studies. PheRS and PGS were only moderately correlated and models including both predictors improved onset prediction compared to PGS alone for 8 of 13 diseases. Our results indicate that EHR-based risk scores can transfer well between EHRs, capture largely independent information from PGS, and provide additive benefits for disease risk prediction.


  • Open Access

    Transferability and accuracy of electronic health record-based predictors compared to polygenic scores

    by Kira E. Detrois, Tuomo Hartonen, Maris Teder-Laving, Bradley Jermy, Kristi Läll, Zhiyu Yang, FinnGen Estonian Biobank research team, Reedik Mägi, Samuli Ripatti, Andrea Ganna

    Electronic health record (EHR)-based phenotype risk scores (PheRS) leverage individuals’ health trajectories to infer disease risk. Similarly, polygenic scores (PGS) use genetic information to estimate disease risk. While PGS generalizability has been previously studied, less is known about PheRS transferability across healthcare systems and whether PheRS provide complementary risk information to PGS. We trained PheRS to predict the onset of 13 common diseases with high health burden in a total of 845,929 individuals (age 32-70) from 3 biobank-based studies from Finland (FinnGen), the UK (UKB) and Estonia (EstB). The PheRS were based on elastic-net models, incorporating up to 242 diagnoses captured in the EHR up to 10 years before baseline. Individuals were followed up for a maximum of 8 years, during which disease incidence was observed. PGS were calculated for each disease using recent publicly available results from genome-wide association studies. All 13 PheRS were significantly associated with the diseases of interest. The PheRS trained in different biobanks utilized partially distinct diagnoses, reflecting differences in medical code usage across the countries. Even with the large variability in the prevalence of various diagnoses, most PheRS trained in the UKB or EstB transferred well to FinnGen without re-training. PheRS and PGS were only moderately correlated (Pearson’s r ranging from 0.00 to 0.08), and models including both PheRS and PGS improved onset prediction compared to PGS alone for 8/13 diseases. PheRS was able to identify a subset of individuals at high-risk better than PGS for 8/13 disease. Our results indicate that EHR-based risk scores and PGS capture largely independent information and provide additive benefits for disease risk prediction. Furthermore, for many diseases the PheRS models transfer well between different EHRs. Given the large availability of EHR, PheRS can provide a complementary tool to PGS for risk stratification.


  • Open Access

    A unified framework for estimating country-specific cumulative incidence for 18 diseases stratified by polygenic risk

    by Bradley Jermy, Kristi Läll, Brooke N. Wolford, Ying Wang, Kristina Zguro, Yipeng Cheng, Masahiro Kanai, Stavroula Kanoni, Zhiyu Yang, Tuomo Hartonen, et al.

    Polygenic scores (PGSs) offer the ability to predict genetic risk for complex diseases across the life course; a key benefit over short-term prediction models. To produce risk estimates relevant to clinical and public health decision-making, it is important to account for varying effects due to age and sex. Here, we develop a novel framework to estimate country-, age-, and sex-specific estimates of cumulative incidence stratified by PGS for 18 high-burden diseases. We integrate PGS associations from seven studies in four countries (N = 1,197,129) with disease incidences from the Global Burden of Disease. PGS has a significant sex-specific effect for asthma, hip osteoarthritis, gout, coronary heart disease and type 2 diabetes (T2D), with all but T2D exhibiting a larger effect in men. PGS has a larger effect in younger individuals for 13 diseases, with effects decreasing linearly with age. We show for breast cancer that, relative to individuals in the bottom 20% of polygenic risk, the top 5% attain an absolute risk for screening eligibility 16.3 years earlier. Our framework increases the generalizability of results from biobank studies and the accuracy of absolute risk estimates by appropriately accounting for age- and sex-specific PGS effects. Our results highlight the potential of PGS as a screening tool which may assist in the early prevention of common diseases.


  • Open Access

    Evaluation of polygenic scoring methods in five biobanks reveals greater variability between biobanks than between methods and highlights benefits of ensemble learning

    by Remo Monti, Lisa Eick, Georgi Hudjashov, Kristi Läll, Stavroula Kanoni, Brooke N. Wolford, Benjamin Wingfield, Oliver Pain, Sophie Wharrie, Bradley Jermy, et al.

    Methods to estimate polygenic scores (PGS) from genome-wide association studies are increasingly utilized. However, independent method evaluation is lacking, and method comparisons are often limited. Here, we evaluate polygenic scores derived using seven methods in five biobank studies (totaling about 1.2 million participants) across 16 diseases and quantitative traits, building on a reference-standardized framework. We conducted meta-analyses to quantify the effects of method choice, hyperparameter tuning, method ensembling and target biobank on PGS performance. We found that no single method consistently outperformed all others. PGS effect sizes were more variable between biobanks than between methods within biobanks when methods were well-tuned. Differences between methods were largest for the two investigated autoimmune diseases, seropositive rheumatoid arthritis and type 1 diabetes. For most methods, cross-validation was more reliable for tuning hyperparameters than automatic tuning (without the use of target data). For a given target phenotype, elastic net models combining PGS across methods (ensemble PGS) tuned in the UK Biobank provided consistent, high, and cross-biobank transferable performance, increasing PGS effect sizes (β-coefficients) by a median of 5.0% relative to LDpred2 and MegaPRS (the two best performing single methods when tuned with cross-validation). Our interactively browsable online-results ( https://methodscomparison.intervenegeneticscores.org/ ) and open-source workflow prspipe ( https://github.com/intervene-EU-H2020/prspipe ) provide a rich resource and reference for the analysis of polygenic scoring methods across biobanks.


  • Open Access

    Deep learning-based prediction of one-year mortality in the entire Finnish population is an accurate but unfair digital marker of aging

    by Andrius Vabalas, Tuomo Hartonen, Pekka Vartiainen, Sakari Jukarainen, Essi Viippola, Rodosthenis S. Rodosthenous, Aoxing Liu, Sara Hägg, Markus Perola, Andrea Ganna

    Background: Accurately predicting short-term mortality is important for optimizing healthcare resource allocation, developing risk-reducing interventions, and improving end-of-life care. Moreover, short-term mortality risk reflects individual frailty and can serve as digital aging marker. Previous studies have focused on specific, high-risk populations. Predicting all-cause mortality in an unselected population incorporating both health and socioeconomic factors has direct public health relevance but requires careful fairness considerations. Methods: We developed a deep learning model to predict 1-year mortality using nationwide longitudinal data from the Finnish population ( N = 5.4 million), including >8,000 features and spanning back up to 50 years. We used the area under the receiver operating characteristic curve (AUC) as a primary metric to assess model performance and fairness. Findings: The model achieved an AUC of 0.944 with strong calibration, outperforming a baseline model that only included age and sex (AUC = 0.897). The model generalized well to different causes of death (AUC > 0.800 for 45 out of 50 causes), including COVID-19 which was not present in the training data. The model performed best among young females and worst in older males (AUC = 0.910 vs. AUC = 0.718). Extensive fairness analyses revealed that individuals belonging to multiple disadvantaged groups had the worst model performance, not explained by age and sex differences, reduced healthcare contact, or smaller training set sizes within these groups. Conclusion: A deep learning model based on nationwide longitudinal multi-modal data accurately identified short-term mortality risk holding the potential for developing a population-wide in-silico aging marker. Unfairness in model predictions represents a major challenge to the equitable integration of these approaches in public health interventions.


  • Open Access

    Data Resource Profile: Nationwide registry data for high-throughput epidemiology and machine learning (FinRegistry)

    by Essi Viippola, Sara Kuitunen, Rodosthenis S Rodosthenous, Andrius Vabalas, Tuomo Hartonen, Pekka Vartiainen, Joanne Demmler, Anna-Leena Vuorinen, Aoxing Liu, Aki S Havulinna, et al.

    Nationwide health-related registry data provide comprehensive insights into population health and, combined with other data such as demographics, familial relations and socioeconomic data, enable the exploration of various dimensions of human behaviour and health. With the increasing size and variety of available data, advanced statistical and machine learning methods present novel possibilities for prediction and causal inference. 1–3 At the same time, efforts to extract high-quality ‘phenotypes’ from registries, for example clinical endpoints, are needed to provide interpretable results. In this spirit, projects such as the CALIBER initiative have provided curated phenotype definitions based on UK’s primary and secondary health care data. 4 Traditionally, the identification of risk factors and the creation of prediction models for diseases have been conducted using a targeted approach where a specific condition, risk factor or medication is studied for its association with a single disease. Several studies 4–10 have shown the potential of data-driven approaches in examining the associations of a large number of risk factors and thousands of disease trajectories. These studies have been accompanied by an increasing trend towards making the results publicly available through web portals, to enable the re-use of the results by other researchers.


  • Open Access

    Nationwide health, socio-economic and genetic predictors of COVID-19 vaccination status in Finland

    by Tuomo Hartonen, Bradley Jermy, Hanna Sõnajalg, Pekka Vartiainen, Kristi Krebs, Andrius Vabalas, Finn Gen, Estonian Biobank Research Team, Andres Metspalu, Tõnu Esko, et al.

    Understanding factors associated with COVID-19 vaccination can highlight issues in public health systems. Using machine learning, we considered the effects of 2,890 health, socio-economic and demographic factors in the entire Finnish population aged 30–80 and genome-wide information from 273,765 individuals. The strongest predictors of vaccination status were labour income and medication purchase history. Mental health conditions and having unvaccinated first-degree relatives were associated with reduced vaccination. A prediction model combining all predictors achieved good discrimination (area under the receiver operating characteristic curve, 0.801; 95% confidence interval, 0.799–0.803). The 1% of individuals with the highest predicted risk of not vaccinating had an observed vaccination rate of 18.8%, compared with 90.3% in the study population. We identified eight genetic loci associated with vaccination uptake and derived a polygenic score, which was a weak predictor in an independent subset. Our results suggest that individuals at higher risk of suffering the worst consequences of COVID-19 are also less likely to vaccinate.