| Popis: |
Slide presentation to accompany manuscript. Background: The inability to identify dates of death in insurance claims data is a major limitation to retrospective claims-based research. Deaths likely result in disenrollment; however, disenrollment may also reflect a change in insurance provider. We aim to develop a user-friendly public algorithm to predict death within the year of disenrollment using an administrative claims database. Methods: We identified adults (18+ years) with at least 1 year of continuous enrollment prior to disenrollment in 2007-2018. Using Social Security Death Index, inpatient discharge status, and death indicators in the administrative data as the gold standard, we used claims in the prior year to predict death. Models including candidate predictors for age, sex, Census region, month of disenrollment, chronic condition indicators (components of the Elixhauser score), and prior healthcare utilization were estimated using used elastic net regression tuned by 5-fold cross-validation and final models evaluated in an independent testing set. Weighted analysis adjusts for rare outcome (i.e., class imbalance). Sensitivity and specificity associated with various thresholds of predicted probability to classify death at disenrollment were calculated. Results: We identified 13,360,460 beneficiaries who disenrolled during the study period, with 5% of patients who died within the 61 days of disenrollment. The strongest predictors of death were age at disenrollment, diagnosis of metastatic cancer in the year prior to death, and type of care received (e.g., inpatient stay, hospice care). Using a prediction threshold of 30%, the algorithm classified death at disenrollment with a sensitivity of 0.684 and specificity of 0.985 (ROC=0.97). Conclusions: Our algorithm uses publicly defined chronic conditions and utilization patterns that are easy to implement in claims data and predicts death at disenrollment. Users can easily implement the algorithm and can choose the prediction threshold (balancing sensitivity and specificity) to |
