Deep learning can predict cardiovascular events from liver imaging
Background & Aims - Cardiovascular mortality remains the leading cause of death and a significant source of morbidity, with metabolic alterations being key etiological factors. As the main metabolic organ, the liver could predict prodromal changes associated with increased cardiovascular risk. H...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
August 2025
|
| In: |
JHEP reports
Year: 2025, Volume: 7, Issue: 8, Pages: 1-13 |
| ISSN: | 2589-5559 |
| DOI: | 10.1016/j.jhepr.2025.101427 |
| Online Access: | Verlag, kostenfrei, Volltext: https://doi.org/10.1016/j.jhepr.2025.101427 Verlag, kostenfrei, Volltext: https://www.sciencedirect.com/science/article/pii/S2589555925001041 
|
| Author Notes: | Gregory Patrick Veldhuizen, Tim Lenz, Didem Cifci, Marko van Treeck, Jan Clusmann, Yazhou Chen, Carolin V. Schneider, Tom Luedde, Peter W. de Leeuw, Ali El-Armouche, Daniel Truhn, Jakob Nikolas Kather |
MARC
| LEADER | 00000naa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1942083394 | ||
| 003 | DE-627 | ||
| 005 | 20251124100709.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 251124s2025 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.jhepr.2025.101427 |2 doi | |
| 035 | |a (DE-627)1942083394 | ||
| 035 | |a (DE-599)KXP1942083394 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Veldhuizen, Gregory Patrick |e VerfasserIn |0 (DE-588)1321720475 |0 (DE-627)1881603628 |4 aut | |
| 245 | 1 | 0 | |a Deep learning can predict cardiovascular events from liver imaging |c Gregory Patrick Veldhuizen, Tim Lenz, Didem Cifci, Marko van Treeck, Jan Clusmann, Yazhou Chen, Carolin V. Schneider, Tom Luedde, Peter W. de Leeuw, Ali El-Armouche, Daniel Truhn, Jakob Nikolas Kather |
| 264 | 1 | |c August 2025 | |
| 300 | |b Illustrationen, Diagramme | ||
| 300 | |a 13 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Online verfügbar 22 April 2025, Version des Artikels 7 July 2025 | ||
| 500 | |a Gesehen am 24.11.2025 | ||
| 520 | |a Background & Aims - Cardiovascular mortality remains the leading cause of death and a significant source of morbidity, with metabolic alterations being key etiological factors. As the main metabolic organ, the liver could predict prodromal changes associated with increased cardiovascular risk. However, quantifying this risk remains challenging. This study explores the use of transformer neural networks on liver magnetic resonance imaging (MRI) data to enhance cardiovascular risk prediction. - Methods - Using the extensive collection of liver MRIs in the UK Biobank, we developed a feature extractor with a vision transformer backbone trained in a self-supervised manner. This encoder was then used to predict cardiovascular outcomes from liver MRI scans. Unlike traditional methods, no manual feature selection was required, minimizing bias. Performance was assessed via fivefold cross validation, where predicted risk scores were compared against actual cardiovascular outcomes. - Results - The model was trained on 44,672 liver MRIs. In the fivefold cross-validation predicting major adverse cardiac events, the mean AUC was 0.70 with a 95% CI of 0.69-0.72 and p <0.001. The F-statistic from the one-way ANOVA comparing the Systematic Coronary Risk Evaluation 2 (SCORE2) values of the three prediction model score groups was 68.49 with p <0.001. The log-rank test comparing the survival of those with prediction model scores above and below 0.5 had a test statistic of 43 and p <0.001. The multivariate log-rank test comparing the survival of those in the four quartiles of prediction model scores had a test statistic of 61 and p <0.001. - Conclusions - Vision transformer-based models demonstrate promise as quantifiable biomarkers for cardiovascular risk assessment by capturing subtle metabolic and vascular information from liver MRI scans. These findings highlight their strong predictive performance and potential value in risk stratification. Further prospective studies and external validation will be required to establish their clinical utility. - Impact and implications - Our study demonstrates that deep learning applied to liver MRI can predict cardiovascular risk, highlighting the role of the liver as a metabolic indicator of early cardiovascular disease. These findings are significant for clinicians and researchers seeking non-invasive, imaging-based biomarkers for cardiovascular risk stratification, particularly in patients who might not yet exhibit overt symptoms. If validated in prospective studies, this approach could enhance current risk assessment models, allowing for earlier and more personalized interventions in high-risk individuals. However, further validation is necessary before clinical implementation, ensuring broad applicability and integration into existing prevention frameworks. | ||
| 650 | 4 | |a Biomarker development | |
| 650 | 4 | |a Cardiovascular risk | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Liver MRI | |
| 650 | 4 | |a Major adverse cardiac events (MACE) | |
| 650 | 4 | |a Risk stratification | |
| 650 | 4 | |a Self-supervised learning (SSL) | |
| 650 | 4 | |a Survival analysis | |
| 650 | 4 | |a UK Biobank | |
| 650 | 4 | |a Vision transformer (ViT) | |
| 700 | 1 | |a Lenz, Tim |e VerfasserIn |4 aut | |
| 700 | 1 | |a Cifci, Didem |e VerfasserIn |4 aut | |
| 700 | 1 | |a van Treeck, Marko |e VerfasserIn |4 aut | |
| 700 | 1 | |a Clusmann, Jan |e VerfasserIn |4 aut | |
| 700 | 1 | |a Chen, Yazhou |e VerfasserIn |4 aut | |
| 700 | 1 | |a Schneider, Carolin V. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Luedde, Tom |e VerfasserIn |4 aut | |
| 700 | 1 | |a de Leeuw, Peter W. |e VerfasserIn |4 aut | |
| 700 | 1 | |a El-Armouche, Ali |e VerfasserIn |4 aut | |
| 700 | 1 | |a Truhn, Daniel |e VerfasserIn |4 aut | |
| 700 | 1 | |a Kather, Jakob Nikolas |d 1989- |e VerfasserIn |0 (DE-588)1064064914 |0 (DE-627)812897587 |0 (DE-576)423589091 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t JHEP reports |d Amsterdam : Elsevier, 2019 |g 7(2025), 8 vom: Aug., Artikel-ID 101427, Seite 1-13 |h Online-Ressource |w (DE-627)166592800X |w (DE-600)2972660-8 |x 2589-5559 |7 nnas |a Deep learning can predict cardiovascular events from liver imaging |
| 773 | 1 | 8 | |g volume:7 |g year:2025 |g number:8 |g month:08 |g elocationid:101427 |g pages:1-13 |g extent:13 |a Deep learning can predict cardiovascular events from liver imaging |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.jhepr.2025.101427 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 856 | 4 | 0 | |u https://www.sciencedirect.com/science/article/pii/S2589555925001041 |x Verlag |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20251124 | ||
| 993 | |a Article | ||
| 994 | |a 2025 | ||
| 998 | |g 1064064914 |a Kather, Jakob Nikolas |m 1064064914:Kather, Jakob Nikolas |d 910000 |d 910100 |e 910000PK1064064914 |e 910100PK1064064914 |k 0/910000/ |k 1/910000/910100/ |p 12 |y j | ||
| 999 | |a KXP-PPN1942083394 |e 4811859626 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"recId":"1942083394","physDesc":[{"extent":"13 S.","noteIll":"Illustrationen, Diagramme"}],"title":[{"title_sort":"Deep learning can predict cardiovascular events from liver imaging","title":"Deep learning can predict cardiovascular events from liver imaging"}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"language":["eng"],"note":["Online verfügbar 22 April 2025, Version des Artikels 7 July 2025","Gesehen am 24.11.2025"],"origin":[{"dateIssuedDisp":"August 2025","dateIssuedKey":"2025"}],"relHost":[{"name":{"displayForm":["EASL, European Association for the Study of the Liver"]},"origin":[{"dateIssuedDisp":"[2019]-","publisherPlace":"Amsterdam","publisher":"Elsevier"}],"pubHistory":["Volume 1, issue (JMay 2019)-"],"id":{"eki":["166592800X"],"issn":["2589-5559"],"zdb":["2972660-8"]},"part":{"volume":"7","year":"2025","text":"7(2025), 8 vom: Aug., Artikel-ID 101427, Seite 1-13","extent":"13","issue":"8","pages":"1-13"},"title":[{"title_sort":"JHEP reports","title":"JHEP reports"}],"language":["eng"],"type":{"bibl":"periodical","media":"Online-Ressource"},"recId":"166592800X","physDesc":[{"extent":"Online-Ressource"}],"disp":"Deep learning can predict cardiovascular events from liver imagingJHEP reports"}],"person":[{"family":"Veldhuizen","given":"Gregory Patrick","role":"aut","display":"Veldhuizen, Gregory Patrick"},{"display":"Lenz, Tim","family":"Lenz","given":"Tim","role":"aut"},{"display":"Cifci, Didem","family":"Cifci","given":"Didem","role":"aut"},{"role":"aut","given":"Marko","family":"van Treeck","display":"van Treeck, Marko"},{"display":"Clusmann, Jan","given":"Jan","role":"aut","family":"Clusmann"},{"family":"Chen","role":"aut","given":"Yazhou","display":"Chen, Yazhou"},{"family":"Schneider","given":"Carolin V.","role":"aut","display":"Schneider, Carolin V."},{"display":"Luedde, Tom","family":"Luedde","role":"aut","given":"Tom"},{"role":"aut","given":"Peter W.","family":"de Leeuw","display":"de Leeuw, Peter W."},{"display":"El-Armouche, Ali","given":"Ali","role":"aut","family":"El-Armouche"},{"display":"Truhn, Daniel","family":"Truhn","given":"Daniel","role":"aut"},{"given":"Jakob Nikolas","role":"aut","family":"Kather","display":"Kather, Jakob Nikolas"}],"id":{"doi":["10.1016/j.jhepr.2025.101427"],"eki":["1942083394"]},"name":{"displayForm":["Gregory Patrick Veldhuizen, Tim Lenz, Didem Cifci, Marko van Treeck, Jan Clusmann, Yazhou Chen, Carolin V. Schneider, Tom Luedde, Peter W. de Leeuw, Ali El-Armouche, Daniel Truhn, Jakob Nikolas Kather"]}} | ||
| SRT | |a VELDHUIZENDEEPLEARNI2025 | ||