Background: Synthetic patient data may facilitate biomedical research, trial planning, and the construction of synthetic control arms, but there is a lack of methods that enable the realistic generation of mixed-type longitudinal clinical trial data, specifically in the presence of treatment effects. Methods: We developed MultiNSDE, a neural stochastic differential equation framework for modeling high-dimensional static and longitudinal clinical study data, including continuous, categorical, and time-to-event outcomes. The model separates treatment- and placebo-associated dynamics, enabling individual trajectory simulation and counterfactual treatment assignment. Results: MultiNSDE was evaluated on three neurodegenerative disease trial datasets: A4 in Alzheimer’s disease, PRO-ACT in amyotrophic lateral sclerosis, and DATATOP in Parkinson’s disease. The model reproduced static and longitudinal data distributions, extrapolated clinically plausible trajectories, and generated coherent counterfactual outcomes under treatment-to-placebo and placebo-to-treatment shifts. Synthetic data generated by MultiNSDE preserved average treatment effect estimates observed in the real datasets. Conclusions: MultiNSDE enables generation of realistic mixed-type longitudinal clinical trial data while preserving clinically meaningful treatment-effect structure. It may support disease modeling, counterfactual simulation, and synthetic control generation in neurodegenerative disease research.