Researchers have developed a new AI framework called Disease Continuum Positioning (DCP) that continuously estimates disease severity from longitudinal imaging data. DCP models disease severity as a low-dimensional probabilistic latent variable by jointly integrating longitudinal observations with weak clinical supervision. The proposed Disease Continuum Score (DCS) accurately characterizes disease severity and exhibits strong clinical relevance, preserving longitudinal disease evolution and predicting future disease conversion. This work was tested on the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. --- Why it matters: This matters to researchers in AI because it provides a new approach for continuous assessment of Alzheimer's disease progression beyond conventional diagnostic labels and clinical scores. The framework's ability to model disease severity as a probabilistic latent variable can be applied to other longitudinal studies, enabling more accurate predictions and better understanding of complex diseases. Source: https://arxiv.org/abs/2608.19436