arXiv subjects

Andrea Ganna

Publications and source records attributed to Andrea Ganna.

4 recordsLinked to original sources

arXiv2026

Effects of Genetic Propensity for Education on Labor Market and Health Trajectories across the Working Life

Education is a major source of inequality in income and health. Polygenic indices for educational attainment (EA-PGI) capture both direct and indirect genetic influences on education, but their effects on income and health remain unclear. Using Finnish registry data on 51,056 graduates followed annually since graduation for up to 25 years, we report three findings. First, higher EA-PGI strongly predicts income growth, but only among higher educated people: tertiary-educated graduates at the 90th percentile earn EUR 45,392 (13.1 percent) higher discounted lifetime income than those at the 10th percentile. This effect is not mediated by overall health and is entirely absent for the secondary (high school)-educated workers, who do not benefit from higher EA-PGI levels. Second, EA-PGI does not predict income differences at labor market entry or the quality of the first employer, but rather higher job-to-job mobility toward higher-quality firms that drives the long-run income divergence. Third, controlling for parental EA-PGI in 12,871 parent-offspring trios reduces the discounted lifetime income gap by 71 percent, and the effect of paternal (but not maternal) EA-PGI on offspring income exceeds that of the offspring's own EA-PGI. These findings suggest that genetic factors associated with educational attainment predict income trajectories primarily through faster and more frequent changes to higher-paying employers. However, much of this association reflects indirect paternal genetic effects, consistent with enduring paternal patterns of intergenerational job and income transmission.

econ.GN↗

arXiv2024

Bayesian Meta-Learning for Improving Generalizability of Health Prediction Models With Similar Causal Mechanisms

Machine learning strategies like multi-task learning, meta-learning, and transfer learning enable efficient adaptation of machine learning models to specific applications in healthcare, such as prediction of various diseases, by leveraging generalizable knowledge across large datasets and multiple domains. In particular, Bayesian meta-learning methods pool data across related prediction tasks to learn prior distributions for model parameters, which are then used to derive models for specific tasks. However, inter- and intra-task variability due to disease heterogeneity and other patient-level differences pose challenges of negative transfer during shared learning and poor generalizability to new patients. We introduce a novel Bayesian meta-learning approach that aims to address this in two key settings: (1) predictions for new patients (same population as the training set) and (2) adapting to new patient populations. Our main contribution is in modeling similarity between causal mechanisms of the tasks, for (1) mitigating negative transfer during training and (2) fine-tuning that pools information from tasks that are expected to aid generalizability. We propose an algorithm for implementing this approach for Bayesian deep learning, and apply it to a case study for stroke prediction tasks using electronic health record data. Experiments for the UK Biobank dataset as the training population demonstrated significant generalizability improvements compared to standard meta-learning, non-causal task similarity measures, and local baselines (separate models for each task). This was assessed for a variety of tasks that considered both new patients from the training population (UK Biobank) and a new population (FinnGen).

cs.LG↗

arXiv2024

Towards modeling evolving longitudinal health trajectories with a transformer-based deep learning model

Health registers contain rich information about individuals' health histories. Here our interest lies in understanding how individuals' health trajectories evolve in a nationwide longitudinal dataset with coded features, such as clinical codes, procedures, and drug purchases. We introduce a straightforward approach for training a Transformer-based deep learning model in a way that lets us analyze how individuals' trajectories change over time. This is achieved by modifying the training objective and by applying a causal attention mask. We focus here on a general task of predicting the onset of a range of common diseases in a given future forecast interval. However, instead of providing a single prediction about diagnoses that could occur in this forecast interval, our approach enable the model to provide continuous predictions at every time point up until, and conditioned on, the time of the forecast period. We find that this model performs comparably to other models, including a bi-directional transformer model, in terms of basic prediction performance while at the same time offering promising trajectory modeling properties. We explore a couple of ways to use this model for analyzing health trajectories and aiding in early detection of events that forecast possible later disease onsets. We hypothesize that this method may be helpful in continuous monitoring of peoples' health trajectories and enabling interventions in ongoing health trajectories, as well as being useful in retrospective analyses.

cs.LG↗

arXiv2023

Characterizing personalized effects of family information on disease risk using graph representation learning

Family history is considered a risk factor for many diseases because it implicitly captures shared genetic, environmental and lifestyle factors. Finland's nationwide electronic health record (EHR) system spanning multiple generations presents new opportunities for studying a connected network of medical histories for entire families. In this work we present a graph-based deep learning approach for learning explainable, supervised representations of how each family member's longitudinal medical history influences a patient's disease risk. We demonstrate that this approach is beneficial for predicting 10-year disease onset for 5 complex disease phenotypes, compared to clinically-inspired and deep learning baselines for Finland's nationwide EHR system comprising 7 million individuals with up to third-degree relatives. Through the use of graph explainability techniques, we illustrate that a graph-based approach enables more personalized modeling of family information and disease risk by identifying important relatives and features for prediction.

stat.AP↗