Background: To characterize whether medical comorbidities, depression and anxiety predict patient-reported functional improvement after total knee arthroplasty (TKA). Methods. We analyzed the prospectively collected data from the Mayo Clinic Total Joint Registry for patients who underwent primary or revision TKA between 1993-2005. Using multivariable-adjusted logistic regression analyses, we examined whether medical comorbidities, depression and anxiety were associated with patient-reported subjective improvement in knee function 2- or 5-years after primary or revision TKA. Odds ratios (OR), along with 95% confidence intervals (CI) and p-value are presented. Results: We studied 7,139 primary TKAs at 2- and 4,234 at 5-years; and, 1,533 revision TKAs at 2-years and 881 at 5-years. In multivariable-adjusted analyses, we found that depression was associated with significantly lower odds of 0.5 (95% confidence interval [CI]: 0.3 to 0.9; p = 0.02) of 'much better' knee functional status (relative to same or worse status) 2 years after primary TKA. Higher Deyo-Charlson index was significantly associated with lower odds of 0.5 (95% CI: 0.2 to 1.0; p = 0.05) of 'much better' knee functional status after revision TKA for every 5-point increase in score. Conclusions: Depression in primary TKA and higher medical comorbidity in revision TKA cohorts were associated with suboptimal improvement in index knee function. It remains to be seen whether strategies focused at optimization of medical comorbidities and depression pre- and peri-operatively may help to improve TKA outcomes. Study limitations include non-response bias and the use of diagnostic codes, which may be associated with under-diagnosis of conditions. © 2014 Singh and Lewallen; licensee BioMed Central Ltd.