Cover Image

Medical history predicts phenome-wide disease onset and enables the rapid response to emerging health threats

The COVID-19 pandemic exposed a global deficiency of systematic, data-driven guidance to identify high-risk individuals. Here, we illustrate the utility of routinely recorded medical history to predict the risk for 1741 diseases across clinical specialties and support the rapid response to emerging...

Full description

Saved in:
Bibliographic Details
Previous Title:Steinfeldt, Jakob Retracted article: Medical history predicts phenome-wide disease onset and enables the rapid response to emerging health threats
Main Authors: Steinfeldt, Jakob (Author) , Wild, Benjamin (Author) , Buergel, Thore (Author) , Pietzner, Maik (Author) , Upmeier zu Belzen, Julius (Author) , Vauvelle, Andre (Author) , Hegselmann, Stefan (Author) , Denaxas, Spiros (Author) , Hemingway, Harry (Author) , Langenberg, Claudia (Author) , Landmesser, Ulf (Author) , Deanfield, John (Author) , Eils, Roland (Author)
Format: Article (Journal)
Language:English
Published: 2025
In: Nature Communications
Year: 2025, Volume: 16, Pages: 1-15
ISSN:2041-1723
DOI:10.1038/s41467-025-55879-x
Online Access:Verlag, kostenfrei, Volltext: https://doi.org/10.1038/s41467-025-55879-x
Verlag, kostenfrei, Volltext: https://www.nature.com/articles/s41467-025-55879-x
Get full text
Author Notes:Jakob Steinfeldt, Benjamin Wild, Thore Buergel, Maik Pietzner, Julius Upmeier zu Belzen, Andre Vauvelle, Stefan Hegselmann, Spiros Denaxas, Harry Hemingway, Claudia Langenberg, Ulf Landmesser, John Deanfield & Roland Eils
Description
Summary:The COVID-19 pandemic exposed a global deficiency of systematic, data-driven guidance to identify high-risk individuals. Here, we illustrate the utility of routinely recorded medical history to predict the risk for 1741 diseases across clinical specialties and support the rapid response to emerging health threats such as COVID-19. We developed a neural network to learn from health records of 502,489 UK Biobank participants. Importantly, we observed discriminative improvements over basic demographic predictors for 1546 (88.8%) endpoints. After transferring the unmodified risk models to the All of US cohort, we replicated these improvements for 1115 (78.9%) of 1414 investigated endpoints, demonstrating generalizability across healthcare systems and historically underrepresented groups. Ultimately, we showed how this approach could have been used to identify individuals vulnerable to severe COVID-19. Our study demonstrates the potential of medical history to support guidance for emerging pandemics by systematically estimating risk for thousands of diseases at once at minimal cost.
Item Description:Online veröffentlicht: 10. Januar 2025
Gesehen am 11.02.2025
Physical Description:Online Resource
ISSN:2041-1723
DOI:10.1038/s41467-025-55879-x

Similar Items