The Value of Claims-Based Nontraditional Risk Factors in Predicting Long-term Mortality After MitraClip Procedure

Background: We sought to identify nontraditional risk factors coded in administrative claims data and evaluate their ability to improve prediction of long-term mortality in patients undergoing percutaneous mitrel valve repair. Methods: Patients undergoing transcatheter mitrel valve repair using MitraClip implantation between September 28, 2010, and September 30, 2015 were identified among Medicare fee-for-service beneficiaries. We used nested Cox regression models to identify claims codes predictive of long-term mortality. Four groups of variables were introduced sequentially: cardiac and noncardiac risk factors, presentation characteristics, and nontraditional risk factors. Results: A total of 3782 patients from 280 clinical sites received treatment with MitraClip over the study period. During the follow-up period, 1114 (29.5%) patients died with a median follow-up time period of 13.6 (9.6 to 17.3) months. The discrimination of a model to predict long-term mortality including only cardiac risk factors was 0.58 (0.55 to 0.60). Model discrimination improved with the addition of noncardiac risk factors (c = 0.63, 0.61 to 0.65; integrated discrimination improvement [IDI] = 0.038, P < 0.001), and with the subsequent addition of presentation characteristics (c = 0.67, 0.65 to 0.69; IDI = 0.033, P < 0.001 compared with the second model). Finally, the addition of nontraditional risk factors significantly improved model discrimination (c = 0.70, 0.68 to 0.72; IDI = 0.019, P < 0.001, compared with the third model). Conclusions: Risk-prediction models, which include nontraditional risk factors as identified in claims data, can be used to predict long-term mortality risk more accurately in patients who have undergone MitraClip procedures.