Development of Prognostic Prediction Model to Estimate Mortality for Frail Oldest Old: Prospective Cohort Study.

Abstract

This study was performed to derive and validate a prognostic prediction model for individualized estimation of mortality risk among the frail oldest old (aged 80 years or older). This analysis was based on the prospective open cohort study from the Chinese Longevity and Health Longitudinal Survey. A total of 14 118 frail oldest old were included from the 2002 wave to 2014 waves; the study outcome was all-cause mortality. Available predictors included frailty, demographics, and social factors. Cox models were used to estimate the coefficients of the predictors and least absolute shrinkage and selection operator was used for selecting predictors. Model performance was measured by discrimination and calibration with internal validation by bootstrapping. We also developed a nomogram to visualize and predict the 3-year mortality risk based on the obtained prognostic prediction model. During the 16-years follow-up, 10 410 (76.42%) deaths were identified. The final model comprises the following factors: frailty, age, sex, race, birthplace, education, occupation, marital status, residence, economic condition, number of children, and the question "who do you ask for help first when in trouble." The model has valid predictive ability as measured and validated by Harrell's C statistic (0.602) and calibration plots. This study provides a basic prognostic prediction model to quantify absolute mortality risk for the frail oldest old. Future studies are needed, firstly, to update, adjust, and perform external validation of the present model by using phenotypic frailty, and secondly, to add biomarkers, environmental, and psychological factors to the prediction model.