Uncertainty-Aware Remaining Lifespan Prediction from Images

TL;DR

This paper introduces a novel method using pretrained vision transformers to predict remaining lifespan from images, providing accurate estimates with calibrated uncertainty, advancing noninvasive health screening techniques.

Contribution

The work demonstrates state-of-the-art lifespan prediction accuracy and effective uncertainty modeling from facial and body images using vision transformers.

Findings

Achieved MAE of 7.41 years on an established dataset.

Achieved MAE of around 5 years on new datasets.

Provided calibrated uncertainty estimates with low expected calibration error.

Abstract

Predicting mortality-related outcomes from images offers the prospect of accessible, noninvasive, and scalable health screening. We present a method that leverages pretrained vision transformer foundation models to estimate remaining lifespan from facial and whole-body images, alongside robust uncertainty quantification. We show that predictive uncertainty varies systematically with the true remaining lifespan, and that this uncertainty can be effectively modeled by learning a Gaussian distribution for each sample. Our approach achieves state-of-the-art mean absolute error (MAE) of 7.41 years on an established dataset, and further achieves 4.91 and 4.99 years MAE on two new, higher-quality datasets curated and published in this work. Importantly, our models provide calibrated uncertainty estimates, as demonstrated by a bucketed expected calibration error of 0.82 years on the Faces Dataset. While not intended for clinical deployment, these results highlight the potential of extracting medically relevant signals from images. We make all code and datasets available to facilitate further research.