Arbeitsbereich

Bevölkerungsdynamik und Nachhaltiges Wohlbefinden

Auf einen Blick Projekte Publikationen Team

Projekt

Forecasting Individual-Level Mortality

Ugofilippo Basellini, Emilio Zagheni, Maria Laura Miranda (MPIDR / Federal University of Minas Gerais, Belo Horizonte, Brasilien), Monica Alexander (University of Toronto, Kanada), Luca Badolato (The Ohio State University, Columbus, Vereinigte Staaten), Ari Gabriel Decter-Frain (Cornell University, Ithaca, Vereinigte Staaten), Nicolas Irons (University of Washington, Seattle, Vereinigte Staaten), Erin Walk (University of Pennsylvania, Philadelphia, Vereinigte Staaten), Elnura Zhalieva (Mohamed bin Zayed University of Artificial Intelligence, Masdar City, Abu Dhabi, Vereinigte Arabische Emirate)

Ausführliche Beschreibung

The prediction of individual-level mortality is a fundamental challenge, with implications for people and societies. Accurate longevity predictions improve life planning, the targeting of high-risk individuals, and the organization of social interventions, policies, and public spending. Demographers and actuaries have been primarily concerned with mortality modeling and prediction at the macro level, leveraging strong regularities in mortality rates over age, sex, space, and time. Apart from clinical settings, predictions of mortality at the individual level have been largely overlooked, and formulating such predictions has remained a challenging task.

In this project, we look at the individual level, tackling the overarching challenge of predicting and understanding mortality risk by addressing four interrelated questions. First, we systematically assess limits to the micro-level predictability of longevity, considering both traditional and innovative machine learning methods. Second, we measure how prediction accuracy varies across socioeconomic groups, reflecting the underlying lifespan inequality. Third, we identify the key variables needed to accurately predict mortality and analyze whether they differ across socioeconomic groups. Finally, we compare the self-reported survival predictions of individuals with the outputs of statistical models.

In the first stage of the project, we investigate these four issues by using the Health and Retirement Study (HRS), one of the most authoritative longitudinal surveys of aging in the United States. So far, we have found that machine learning and traditional models report comparable predictive accuracy and relatively high discriminative performance, although all models have failed to capture the considerable heterogeneity of lifespans at the individual level. For men, non-Hispanic Blacks, and low-educated individuals, predictive accuracy is typically lower than for other socioeconomic groups, as their subjective predictions of their own lifespans tend to be less accurate those of other groups. We further observed small variations in the most important features across groups, with variables related to habits, health history, and finances being relevant predictors (Badolato et al. 2026). Future work will be directed to the analysis of different contexts and potentially to cross-country comparisons, particularly across countries where HRS sister studies are available.

Prediction accuracy of individual-level lifespan for different models by gender, race and ethnicity, and education

Integrated Brier Score and Mean Area Under the Curve by gender (panel a.), race and ethnicity (panel b.), and education (panel c.). Prediction accuracy across models is worse for Men, non-Hispanic Blacks and low-educated individuals as compared to other socioeconomic groups. © © Badolato et al. (2023)

Publikationen

Badolato, L.; Decter-Frain, A. G.; Irons, N. J.; Miranda, M. L.; Walk, E.; Zhalieva, E.; Alexander, M. J.; Basellini, U.; Zagheni, E.:

The limits of predicting individual-level longevity: insights from the U.S. Health and Retirement Study

Demography 63:1, 351–374. (2026)    

Li, Z. R.; Wu, Z.; Chen, I.; Clark, S. J.:

Bayesian nested latent class models for cause-of-death assignment using verbal autopsies across multiple domains

Annals of Applied Statistics 18:2, 1137–1159. (2024)    

Badolato, L.; Decter-Frain, A. G.; Irons, N. J.; Miranda, M. L.; Walk, E.; Zhalieva, E.; Alexander, M. J.; Basellini, U.; Zagheni, E.:

The limits of predicting individual-level longevity

MPIDR Working Paper WP-2023-008. (2023)