Abstract: Prediction of the longer term trajectory of a disease is a crucial challenge for personalized medicine and population health management. However, many complex chronic diseases exhibit large degrees of heterogeneity, and furthermore there's not always one readily available biomarker to quantify disease severity. Even when such a clinical variable exists, there are often additional related biomarkers routinely measured for patients that will better inform the predictions of their future disease state. to the present end, we propose a unique probabilistic generative model for multivariate longitudinal data that captures dependencies between multivariate trajectories. Our local accountable care organization then uses the model predictions during chart reviews of high risk patients with chronic nephrosis. Keywords— kidney cancer, machine learning , Kidney Cancer Predication , chronic kidney disease