Background/Objectives: Patient reported outcome measures (PROMs) capture the patient’s own perspective on their health, illness, and therapeutic effects on the illness. However, their analysis and interpretation is challenging due to their multidimensional nature, poor correlation with clinical and physiological outcomes, lack of standardized interpretation, and discrete nature of the data. We describe a generative stochastic modeling approach and show that it improves the pharmacometric characterization of multi-item PROMS. Methods: The Restricted Boltzmann Machine (RBM) modeling approach was described and used to model the relationship between efavirenz mid-dose concentrations, clinical variables (CD4 count and viral load) and time varying patient reported neuropsychological impairment symptoms. The model was used to derive a variable importance ranking for all the PROM items, clinical variables, and drug concentrations. Results: The model adequately characterizes the PROMs. Variable importance ranking reveals that mid-dose concentrations are not more predictive of post-baseline PROMs than clinical variables and baseline PROMs. Conclusions: Generative stochastic modeling with RBMs adequately characterizes PROMS and their relationship to other variables and drug concentrations, is readily adaptable to the pharmacometric workflow, and is able to generate individual-level disease progression trajectories using baseline variables.