Transforming Mortality Prediction: A Transformer-Based Mortality Prediction Model
The Journals of Gerontology, Series B: Psychological Sciences and Social Sciences · 2025
DOI: 10.1093/geronb/gbaf089 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journals of Gerontology, Series B: Psychological Sciences and Social Sciences, 2025. Verfasst von Jordan Weiss und 3 weiteren Autor:innen. Beteiligte Einrichtung: Stanford Center on Longevity, Stanford University, Stanford, California, USA. Hauptthemen laut MEDLINE: Mortality, Models, Statistical. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 32 Literaturangaben.
Abstract (Originalsprache)
Objectives
Mortality prediction and the identification of mortality risks are central to social and biological sciences. Traditional models often assess linear associations between single risk factors and mortality. Transformer models, capable of capturing long-term dependencies across multiple variables, offer a novel approach to mortality prediction. This study introduces a transformer-based model applied to data from the Health and Retirement Study (HRS).
Methods
We analyzed data provided by 38,193 adults aged ≥ 50 years participating in the HRS, a longitudinal U.S. study surveyed biennially since 1992. Linked mortality data were obtained from the National Death Index and postmortem interviews. Using the transformer architecture, we modeled changes in 126 risk factors spanning financial, physical, and mental health domains manifesting over 29 years. Prediction performance was assessed across multiple settings, with traditional statistical and machine learning (ML) models serving as benchmarks.
Results
Over a median follow-up of 9 years, 17,448 deaths occurred (crude rate: 39.6 per 1,000 person-years). The transformer model consistently outperformed traditional and ML methods, achieving a 2-fold improvement in average precision scores for next-wave mortality prediction relative to the best benchmark model.
Discussion
Transformer-based models, such as BEHRT, significantly enhance mortality prediction compared with traditional approaches. These findings highlight the potential of transformer neural network models in social science-focused population health research on aging.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Stanford Center on Longevity, Stanford University, Stanford, California, USA.
- Optimal Aging Institute & Division of Precision Medicine, NYU Grossman School of Medicine, New York City, New York, USA.
- Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA.
- Department of Communication, Stanford University, Palo Alto, California, USA.
- Department of Psychology, Stanford University, Palo Alto, California, USA.
- Department of Epidemiology and Population Health, Stanford University, Palo Alto, California, USA.
ORCID-Profile: David H Rehkopf
Zitieren
APA
Weiss, J., Azhir, A., Ram, N., & Rehkopf, D. H. (2025). Transforming Mortality Prediction: A Transformer-Based Mortality Prediction Model. The Journals of Gerontology, Series B: Psychological Sciences and Social Sciences. https://doi.org/10.1093/geronb/gbaf089
Vancouver
Weiss J, Azhir A, Ram N, Rehkopf DH. Transforming Mortality Prediction: A Transformer-Based Mortality Prediction Model. The Journals of Gerontology, Series B: Psychological Sciences and Social Sciences. 2025. doi:10.1093/geronb/gbaf089
BibTeX
@article{Weiss2025,
author = {Weiss, Jordan and Azhir, Alaleh and Ram, Nilam and Rehkopf, David H},
title = {Transforming Mortality Prediction: A Transformer-Based Mortality Prediction Model},
journal = {The Journals of Gerontology, Series B: Psychological Sciences and Social Sciences},
year = {2025},
doi = {10.1093/geronb/gbaf089}
}
EUVIMED