98%
921
2 minutes
20
Accurate and convenient assessment of individual aging is crucial for identifying health risks and preventing aging-related diseases. Nonetheless, current aging proxies often face challenges such as methodological limitations, weak associations with adverse outcomes and limited generalizability. Here we propose a framework that leverages large language models (LLMs) to estimate individual overall and organ-specific aging using only health examination reports. We validated this approach across six population-based cohorts, encompassing over 10 million participants and demonstrated effectiveness and reliability. Our results showed that the LLM-predicted overall age achieved a concordance index (C-index) of 0.757 (95% CI 0.752-0.761) for all-cause mortality, significantly outperforming other aging proxies such as telomere length, frailty index, eight epigenetic ages and four machine-learning models predictions. The overall age gap was strongly associated with multiple aging-related phenotypes and health outcomes, showing a hazard ratio of 1.055 (95% CI 1.050-1.060) for all-cause mortality. For organ-specific aging, LLM-predicted ages and age gaps also demonstrated superior performance in predicting corresponding organ-specific diseases compared to machine-learning models. Additionally, we examined the dynamic aging assessment capability of LLMs and applied age gaps to identify proteomic biomarkers associated with accelerated aging and to develop risk prediction models of 270 diseases. Interpretability analyses were also conducted to explore the decision-making process of LLMs. In conclusion, our LLM-based aging assessment framework offers a precise, reliable and cost-effective approach for estimating overall and organ-specific aging. It has potential for personalized aging assessment and health management in large-scale general populations.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1038/s41591-025-03856-8 | DOI Listing |
Korean J Clin Oncol
August 2025
Department of Surgery, Soonchunhyang University Bucheon Hospital, Soonchunhyang University College of Medicine, Bucheon, Korea.
Purpose: Multiple primary tumors arising in the same individual pose challenges for precision oncology, particularly in the context of hereditary cancer syndromes such as Lynch syndrome. While these tumors may originate from a shared germline predisposition, it remains unclear whether they also share somatic alterations that could be therapeutically exploited. This study aimed to characterize the extent of somatic genomic overlap between synchronous or metachronous gastric and colorectal cancers within young Korean patients.
View Article and Find Full Text PDFmedRxiv
August 2025
Institute of Epidemiology and Social Medicine, University of Münster, Münster, Germany.
Background: Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disorder with a largely unknown duration and pathophysiology of the pre-diagnostic phase, especially for the common non-monogenic form.
Methods: We leveraged the European Prospective Investigation into Cancer and Nutrition (EPIC) cohort with up to 30 years of follow-up to identify incident ALS cases across five European countries. Pre-diagnostic plasma samples from initially healthy participants underwent high-throughput proteomic profiling (7,285 protein markers, SomaScan).
Biogerontology
August 2025
Department of Structural and Functional Biology, Institute of Biosciences of Botucatu, Sao Paulo State University (UNESP), Botucatu, SP, 18618-689, Brazil.
Maternal malnutrition affects millions of people worldwide in two main ways: through food insecurity and hunger, as well as through diets high in ultra-processed, low-nutrient foods. These effects are often linked to deficiencies in specific macronutrients and micronutrients, which can lead to organ-specific consequences in the biological development of the child-a context explored within the framework of the Developmental Origins of Health and Disease (DOHaD). Given the extensive effects of maternal protein restriction (MPR) on offspring development, this review focuses specifically on low-protein diets and their impact on various organs and systems.
View Article and Find Full Text PDFSci Rep
August 2025
Institute of Human Nutrition, Columbia University Irving Medical Center, New York, USA.
Caloric restriction (CR) can enhance human health, though underlying mechanisms, particularly related to energy expenditure, remain unclear. This ancillary investigation of the only randomized controlled trial of long-term CR in normal-weight adults, aimed to quantify metabolic adaptation following weight loss by assessing changes in energy-expending tissues and organs using magnetic resonance imaging (MRI). Participants in the CR group were prescribed 24-month 25% CR causing a ~ 13% weight loss at 12 months followed by 12 month weight maintenance, whereas the control group maintained ad libitum food intake throughout.
View Article and Find Full Text PDFPhysiol Rep
August 2025
Department of Biochemistry, Microbiology and Immunology, Faculty of Medicine, The University of Ottawa, Ottawa, Ontario, Canada.
The association between metabolic dysfunction-associated steatotic liver disease (MASLD) and cardiovascular disease is well characterized; however, the underlying mechanism is incompletely understood. Interestingly, hepatocyte-specific silencing of dipeptidyl peptidase 4 (DPP4) prevents liver fibrosis and adipose tissue inflammation; however, how this affects the heart remains to be investigated. This study evaluates how diastolic function and molecular signatures of heart failure, like inflammation and fibrosis, are affected in male Dpp4+/+, Dpp4-/-, and Dpp4flox/flox mice injected with a TBG-CRE to selectively eliminate DPP4 from hepatocytes (Dpp4hep-/-) and respective controls (Dpp4GFP), aged and fed an HFHC diet for 24 weeks.
View Article and Find Full Text PDF