In end-stage renal disease population, patient reported outcomes are important health indicators that can help clinicians anticipate patients' health care needs and provide timely interventions. By focusing on the joint distribution of these outcomes, we hope to better describe their association and evolution over time as well as identify groups of patients with similar characteristics. The motivating data consist of patients' reported measures of multidimensional quality of life (QoL; overall symptoms, physical-, cognitive functioning, and emotional-, spiritual well-being) in 227 chronic dialysis patients over a one year period. Additionally, incidence of clinical events such as hospitalizations, emergency visits and deaths during this period were also recorded. Because the QoL measures can be continuous and discrete, we implemented a multivariate generalized linear mixed effects model with a mixture of normally distributed random effects to model the joint outcome trajectories and classified patients in clusters. Preliminary results show that two clusters of subjects-one which correspond to patients with a better prognosis compared to the other can be identified from the data.