Discrimination, calibration, and point estimate accuracy of GRU-D-Weibull architecture for real-time individualized endpoint prediction

Real-time individual endpoint prediction has always been a challenging task but of great clinic utility for both patients and healthcare providers. GRU-D-Weibull has a maximum C-index of 0.77 at 4.3 years of follow-up, compared to 0.68 achieved by competing models. The average absolute L1-loss of GRU-D-Weibull is around one year, with a minimum of 40% Parkes' serious error after index date. GRU-D-Weibull is not calibrated and significantly underestimates true survival probability. Feature importance tests indicate blood pressure becomes increasingly important during follow-up, while eGFR and blood albumin are less important. Most continuous features have non-linear/parabola impact on predicted survival time, and the results are generally consistent with existing knowledge. GRU-D-Weibull as a semi-parametric temporal model shows advantages in built-in parameterization of missingness, native support for asynchronously arrived measurement, capability of output both probability and point estimates at arbitrary time point for arbitrary prediction horizon, improved discrimination and point estimate accuracy after incorporating newly arrived data. Further research on its performance with more comprehensive input features, in-process or post-process calibration are warranted to benefit CKD4 or alike terminally-ill patients. Author Contribution: XR performed data analysis and manuscript writing. LW performed data extraction, curation, and proof-reading. CT and WC provided expert opinion on selection of study population, explanation of observations, and proof-reading.