This toolbox compares two longitudinal approaches for predicting MCI-to-Alzheimer conversion using ADNI data: a) two-group comparison (LDA trained on LME trajectory residues) and b) survival analysis (extended Cox model with LME random effects). Input: longitudinal MRI markers (cortical thickness, subcortical volumes via FreeSurfer) and neuropsychological measurements with demographic covariates. Output: cross-validated AUC, accuracy, sensitivity and specificity at baseline, 12, 24 and 36 months. Language: MATLAB R2018b. Related papers: DOI 10.1016/j.jneumeth.2020.108698 (JNM 2020), DOI 10.1016/j.jneumeth.2022.109581 (JNM 2022), DOI 10.1177/25424823241306097 (JAD Reports 2025). Permanent archive: https://doi.org/10.5281/zenodo.19755827