From Group-Differences to Single-Subject Probability: Conformal Prediction-based Uncertainty Estimation for Brain-Age Modeling
This enables clinical use of brain-age as a biomarker for neurological disorders by providing statistically guaranteed uncertainty estimates at the single-subject level.
The paper tackled the lack of single-subject risk assessment in brain-age modeling by combining uncertainty-aware deep neural networks with conformal prediction theory, achieving comparable error to state-of-the-art models and showing that higher individual probabilities of accelerated brain-aging are associated with Alzheimer's Disease, Bipolar Disorder, and Major Depressive Disorder in a sample of 16,794 participants.
The brain-age gap is one of the most investigated risk markers for brain changes across disorders. While the field is progressing towards large-scale models, recently incorporating uncertainty estimates, no model to date provides the single-subject risk assessment capability essential for clinical application. In order to enable the clinical use of brain-age as a biomarker, we here combine uncertainty-aware deep Neural Networks with conformal prediction theory. This approach provides statistical guarantees with respect to single-subject uncertainty estimates and allows for the calculation of an individual's probability for accelerated brain-aging. Building on this, we show empirically in a sample of N=16,794 participants that 1. a lower or comparable error as state-of-the-art, large-scale brain-age models, 2. the statistical guarantees regarding single-subject uncertainty estimation indeed hold for every participant, and 3. that the higher individual probabilities of accelerated brain-aging derived from our model are associated with Alzheimer's Disease, Bipolar Disorder and Major Depressive Disorder.