Converse or reverse? Machine-learning modeling for disease progression: A study based on Alzheimer’s disease continuum cohort

• Comparison of representative machine learning models in risk prediction across multimodal clinical data. • Amyloid uptake, APOE4 status, and clinical dysfunction (visuospatial attention and memory) is closed related to the normal-to-dementia continuum. • Random Forest outperforms other models and achieves an average sensitivity of 70.8% and specificity of 96.8% across stable, convertible, and reversible participant groups. . Longitudinal trajectories from healthy aging to Mild Cognitive Impairment and Alzheimer’s Disease involve complex mechanisms. We evaluated five machine learning approaches (Random Forest, Support Vector Machines, Radial Basis Function Networks, Backpropagation Networks, Convolutional Neural Network) to assess the importance of potential predictive markers across the health-to-dementia continuum. Using the ADNI cohort across four phases (ADNI1, ADNIGO, ADNI2, ADNI3), we analyzed participants with distinct trajectories: stable, convertible, and reverse progression. Random Forest outperformed other models across key effectiveness metrics and achieved a macro-averaged sensitivity of 70.8% and specificity of 96.8% across all participant groups. Random Forest identified visuospatial and memory-related cognitive dysfunction as key predictive clinical features and several amyloid-related neuroimaging biomarkers — including temporal variations of amyloid uptake within inferior lateral ventricles, para-hippocampus—for classifying participant groups. Additionally, plasma APOE4 and long neurofilament light chain levels emerged as promising predictors for tracking progression. These findings highlight the potential of machine learning in classifying disease trajectories.