Robust parametric modeling of Alzheimer’s disease progression

•A parametric disease progression modeling method is proposed based on alternating Mestimation which is robust to outliers.•A novel generalized logistic function, called modified Stannard, is proposed which better fits the AD biomarker trajectories.•An end-to-end approach is introduced that performs biomarker trajectory modeling and clinical status classification.•The proposed method is applied to model the progression of Alzheimer’s disease using volumetric MRI and PET biomarkers, CSF measures, as well as cognitive tests.•The generalizability of the proposed method is evaluated based on the prediction performance within and across cohorts.