Comprehensive interaction modeling with machine learning improves prediction of disease risk in the UK Biobank

Abstract Understanding how risk factors interact to jointly influence disease risk can provide insights into disease development and improve risk prediction. Here we introduce survivalFM, a machine learning extension to the widely used Cox proportional hazards model that enables scalable estimation...

Full description

Saved in:
Bibliographic Details
Main Authors: Heli Julkunen, Juho Rousu
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-61891-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849332249643712512
author Heli Julkunen
Juho Rousu
author_facet Heli Julkunen
Juho Rousu
author_sort Heli Julkunen
collection DOAJ
description Abstract Understanding how risk factors interact to jointly influence disease risk can provide insights into disease development and improve risk prediction. Here we introduce survivalFM, a machine learning extension to the widely used Cox proportional hazards model that enables scalable estimation of all potential pairwise interaction effects on time-to-event outcomes. The method approximates interaction effects using a low-rank factorization, allowing it to overcome the computational and statistical limitations typically associated with high-dimensional interaction modeling. Applied to the UK Biobank dataset across nine disease examples and diverse clinical and omics risk factors, survivalFM improves prediction performance in terms of discrimination, explained variation, and reclassification in 30.6%, 41.7%, and 94.4% of the scenarios tested, respectively. In a clinical cardiovascular risk prediction scenario using the established QRISK3 model, the method adds predictive value by identifying interactions beyond the age interaction effects currently included. These results demonstrate that comprehensive modeling of interactions can facilitate advanced insights into disease development and improve risk predictions.
format Article
id doaj-art-7d3af86617f54fce9d8a9a95d1eea647
institution Kabale University
issn 2041-1723
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-7d3af86617f54fce9d8a9a95d1eea6472025-08-20T03:46:15ZengNature PortfolioNature Communications2041-17232025-07-0116111510.1038/s41467-025-61891-yComprehensive interaction modeling with machine learning improves prediction of disease risk in the UK BiobankHeli Julkunen0Juho Rousu1Department of Computer Science, Aalto UniversityDepartment of Computer Science, Aalto UniversityAbstract Understanding how risk factors interact to jointly influence disease risk can provide insights into disease development and improve risk prediction. Here we introduce survivalFM, a machine learning extension to the widely used Cox proportional hazards model that enables scalable estimation of all potential pairwise interaction effects on time-to-event outcomes. The method approximates interaction effects using a low-rank factorization, allowing it to overcome the computational and statistical limitations typically associated with high-dimensional interaction modeling. Applied to the UK Biobank dataset across nine disease examples and diverse clinical and omics risk factors, survivalFM improves prediction performance in terms of discrimination, explained variation, and reclassification in 30.6%, 41.7%, and 94.4% of the scenarios tested, respectively. In a clinical cardiovascular risk prediction scenario using the established QRISK3 model, the method adds predictive value by identifying interactions beyond the age interaction effects currently included. These results demonstrate that comprehensive modeling of interactions can facilitate advanced insights into disease development and improve risk predictions.https://doi.org/10.1038/s41467-025-61891-y
spellingShingle Heli Julkunen
Juho Rousu
Comprehensive interaction modeling with machine learning improves prediction of disease risk in the UK Biobank
Nature Communications
title Comprehensive interaction modeling with machine learning improves prediction of disease risk in the UK Biobank
title_full Comprehensive interaction modeling with machine learning improves prediction of disease risk in the UK Biobank
title_fullStr Comprehensive interaction modeling with machine learning improves prediction of disease risk in the UK Biobank
title_full_unstemmed Comprehensive interaction modeling with machine learning improves prediction of disease risk in the UK Biobank
title_short Comprehensive interaction modeling with machine learning improves prediction of disease risk in the UK Biobank
title_sort comprehensive interaction modeling with machine learning improves prediction of disease risk in the uk biobank
url https://doi.org/10.1038/s41467-025-61891-y
work_keys_str_mv AT helijulkunen comprehensiveinteractionmodelingwithmachinelearningimprovespredictionofdiseaseriskintheukbiobank
AT juhorousu comprehensiveinteractionmodelingwithmachinelearningimprovespredictionofdiseaseriskintheukbiobank