Introduction: Deep vein thrombosis is the development of single or multiple blood clots within the deep veins of the extremities or pelvis, usually accompanied by inflammation of the vessel wall. The major complication thrombosis is excess bleeding and abnormal blood clotting or pulmonary embolism. Identifying the problem of blood clotting and excess bleeding may help regularly monitor Prothrombin Time and Partial Thromboplastin Time to maintain its therapeutic range. The main objective of this study was to identify the risk factors of Prothrombin Time and Partial Thromboplastin Time deep vein thrombosis outpatients under follow up. Methodology: A retrospective longitudinal study was conducted on deep vein thrombosis patients who were on treatment follow up at Felege Hiwot Referral Hospital from January 1, 2016 to December 30, 2020. A total of 248 patients were selected by using simple random sampling from the medical records of patients taking warfarin and heparin treatment. Joint linear mixed effect model were used to infer the evolution of bivariate longitudinal outcomes of Prothrombin Time and Partial Thromboplastin Time for deep vein thrombosis patients. Data management was done by SPSS 23 and SAS 9.4. Result: The joint mixed effect model with unstructured covariance was significantly best fit to the data. The correlation between the evolutions of prothrombin time and partial thromboplastin time was 0.7984 and also assessed the evolution of the association between responses over-time. Among all covariates included in joint-mixed-effect-models age(p<0.0001), fibrogen status(p<0.0001), heart disease status(p=0.0004), international normal ratio(p<0.0001), alcohol status (0.03975), visit weeks(p<0.0001) and the interaction of age with visit week(p=0.00232), fibrogen status with visit week(p<0.0001), INR with visit week(p<0.0001) were statistically significant to log of prothrombin time and age(p<0.0001), sex(p=0.0039), fibrogen status(p<0.0001), international normal ratio(p<0.0001), alcohol status (0.0489), visit weeks(p<0.0001) and the interaction of age with visit week(0.00045), fibrogen status with visit week(p<0.0001), international normalized ratio with visit week(p<0.0001) were statistically significant to log partial thromboplastin time.. Conclusion: sex, visit week, marital status married and interaction of sex with visit week and marital status divorce with visit week were negatively Associated with prothrombin time while age, international normalized ratio status, fibrogen status, heart disease, alcohol status, interaction of age with week, international normalized ratio with week, alcohol status with weeks were positively associated with prothrombin time. visit week, sex, marital status windowed and interaction of sex with visit week and marital status divorce with visit week were negatively Associated with partial thromboplastin time. while age, international normalized ratio, fibrogen status, heart disease, alcohol status, interaction of age with week, international normalized ratio with week, alcohol status with weeks were positively associated with partial thromboplastin time. The joint modeling of longitudinal bivariate responses is necessary to explore the association between paired response variables like prothrombin time and partial thromboplastin time. Fitting joint model with modern computing method is recommended to address questions for association of the evolutions with better accuracy