Data-driven identification of predictive risk biomarkers for subgroups of osteoarthritis using interpretable machine learning
Abstract Osteoarthritis (OA) is increasing in prevalence and has a severe impact on patients’ lives. However, our understanding of biomarkers driving OA risk remains limited. We developed a model predicting the five-year risk of OA diagnosis, integrating retrospective clinical, lifestyle and biomark...
Main Authors: | , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-04-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-024-46663-4 |
_version_ | 1797219722106765312 |
---|---|
author | Rikke Linnemann Nielsen Thomas Monfeuga Robert R. Kitchen Line Egerod Luis G. Leal August Thomas Hjortshøj Schreyer Frederik Steensgaard Gade Carol Sun Marianne Helenius Lotte Simonsen Marianne Willert Abd A. Tahrani Zahra McVey Ramneek Gupta |
author_facet | Rikke Linnemann Nielsen Thomas Monfeuga Robert R. Kitchen Line Egerod Luis G. Leal August Thomas Hjortshøj Schreyer Frederik Steensgaard Gade Carol Sun Marianne Helenius Lotte Simonsen Marianne Willert Abd A. Tahrani Zahra McVey Ramneek Gupta |
author_sort | Rikke Linnemann Nielsen |
collection | DOAJ |
description | Abstract Osteoarthritis (OA) is increasing in prevalence and has a severe impact on patients’ lives. However, our understanding of biomarkers driving OA risk remains limited. We developed a model predicting the five-year risk of OA diagnosis, integrating retrospective clinical, lifestyle and biomarker data from the UK Biobank (19,120 patients with OA, ROC-AUC: 0.72, 95%CI (0.71–0.73)). Higher age, BMI and prescription of non-steroidal anti-inflammatory drugs contributed most to increased OA risk prediction ahead of diagnosis. We identified 14 subgroups of OA risk profiles. These subgroups were validated in an independent set of patients evaluating the 11-year OA risk, with 88% of patients being uniquely assigned to one of the 14 subgroups. Individual OA risk profiles were characterised by personalised biomarkers. Omics integration demonstrated the predictive importance of key OA genes and pathways (e.g., GDF5 and TGF-β signalling) and OA-specific biomarkers (e.g., CRTAC1 and COL9A1). In summary, this work identifies opportunities for personalised OA prevention and insights into its underlying pathogenesis. |
first_indexed | 2024-04-24T12:38:09Z |
format | Article |
id | doaj.art-35ed3f0bace2485dadb823e4a9c370cd |
institution | Directory Open Access Journal |
issn | 2041-1723 |
language | English |
last_indexed | 2024-04-24T12:38:09Z |
publishDate | 2024-04-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Nature Communications |
spelling | doaj.art-35ed3f0bace2485dadb823e4a9c370cd2024-04-07T11:24:17ZengNature PortfolioNature Communications2041-17232024-04-0115111710.1038/s41467-024-46663-4Data-driven identification of predictive risk biomarkers for subgroups of osteoarthritis using interpretable machine learningRikke Linnemann Nielsen0Thomas Monfeuga1Robert R. Kitchen2Line Egerod3Luis G. Leal4August Thomas Hjortshøj Schreyer5Frederik Steensgaard Gade6Carol Sun7Marianne Helenius8Lotte Simonsen9Marianne Willert10Abd A. Tahrani11Zahra McVey12Ramneek Gupta13Novo Nordisk Research Centre OxfordNovo Nordisk Research Centre OxfordNovo Nordisk Research Centre OxfordNovo Nordisk Research Centre OxfordNovo Nordisk Research Centre OxfordNovo Nordisk Research Centre OxfordNovo Nordisk A/SNovo Nordisk Research Centre OxfordTechnical University of DenmarkNovo Nordisk A/SNovo Nordisk A/SNovo Nordisk A/SNovo Nordisk Research Centre OxfordNovo Nordisk Research Centre OxfordAbstract Osteoarthritis (OA) is increasing in prevalence and has a severe impact on patients’ lives. However, our understanding of biomarkers driving OA risk remains limited. We developed a model predicting the five-year risk of OA diagnosis, integrating retrospective clinical, lifestyle and biomarker data from the UK Biobank (19,120 patients with OA, ROC-AUC: 0.72, 95%CI (0.71–0.73)). Higher age, BMI and prescription of non-steroidal anti-inflammatory drugs contributed most to increased OA risk prediction ahead of diagnosis. We identified 14 subgroups of OA risk profiles. These subgroups were validated in an independent set of patients evaluating the 11-year OA risk, with 88% of patients being uniquely assigned to one of the 14 subgroups. Individual OA risk profiles were characterised by personalised biomarkers. Omics integration demonstrated the predictive importance of key OA genes and pathways (e.g., GDF5 and TGF-β signalling) and OA-specific biomarkers (e.g., CRTAC1 and COL9A1). In summary, this work identifies opportunities for personalised OA prevention and insights into its underlying pathogenesis.https://doi.org/10.1038/s41467-024-46663-4 |
spellingShingle | Rikke Linnemann Nielsen Thomas Monfeuga Robert R. Kitchen Line Egerod Luis G. Leal August Thomas Hjortshøj Schreyer Frederik Steensgaard Gade Carol Sun Marianne Helenius Lotte Simonsen Marianne Willert Abd A. Tahrani Zahra McVey Ramneek Gupta Data-driven identification of predictive risk biomarkers for subgroups of osteoarthritis using interpretable machine learning Nature Communications |
title | Data-driven identification of predictive risk biomarkers for subgroups of osteoarthritis using interpretable machine learning |
title_full | Data-driven identification of predictive risk biomarkers for subgroups of osteoarthritis using interpretable machine learning |
title_fullStr | Data-driven identification of predictive risk biomarkers for subgroups of osteoarthritis using interpretable machine learning |
title_full_unstemmed | Data-driven identification of predictive risk biomarkers for subgroups of osteoarthritis using interpretable machine learning |
title_short | Data-driven identification of predictive risk biomarkers for subgroups of osteoarthritis using interpretable machine learning |
title_sort | data driven identification of predictive risk biomarkers for subgroups of osteoarthritis using interpretable machine learning |
url | https://doi.org/10.1038/s41467-024-46663-4 |
work_keys_str_mv | AT rikkelinnemannnielsen datadrivenidentificationofpredictiveriskbiomarkersforsubgroupsofosteoarthritisusinginterpretablemachinelearning AT thomasmonfeuga datadrivenidentificationofpredictiveriskbiomarkersforsubgroupsofosteoarthritisusinginterpretablemachinelearning AT robertrkitchen datadrivenidentificationofpredictiveriskbiomarkersforsubgroupsofosteoarthritisusinginterpretablemachinelearning AT lineegerod datadrivenidentificationofpredictiveriskbiomarkersforsubgroupsofosteoarthritisusinginterpretablemachinelearning AT luisgleal datadrivenidentificationofpredictiveriskbiomarkersforsubgroupsofosteoarthritisusinginterpretablemachinelearning AT augustthomashjortshøjschreyer datadrivenidentificationofpredictiveriskbiomarkersforsubgroupsofosteoarthritisusinginterpretablemachinelearning AT frederiksteensgaardgade datadrivenidentificationofpredictiveriskbiomarkersforsubgroupsofosteoarthritisusinginterpretablemachinelearning AT carolsun datadrivenidentificationofpredictiveriskbiomarkersforsubgroupsofosteoarthritisusinginterpretablemachinelearning AT mariannehelenius datadrivenidentificationofpredictiveriskbiomarkersforsubgroupsofosteoarthritisusinginterpretablemachinelearning AT lottesimonsen datadrivenidentificationofpredictiveriskbiomarkersforsubgroupsofosteoarthritisusinginterpretablemachinelearning AT mariannewillert datadrivenidentificationofpredictiveriskbiomarkersforsubgroupsofosteoarthritisusinginterpretablemachinelearning AT abdatahrani datadrivenidentificationofpredictiveriskbiomarkersforsubgroupsofosteoarthritisusinginterpretablemachinelearning AT zahramcvey datadrivenidentificationofpredictiveriskbiomarkersforsubgroupsofosteoarthritisusinginterpretablemachinelearning AT ramneekgupta datadrivenidentificationofpredictiveriskbiomarkersforsubgroupsofosteoarthritisusinginterpretablemachinelearning |