Assessing predictive discrimination performance of biomarkers in the presence of treatment-induced dependent censoring

Improved mortality prediction for pediatric acute liver failure using dynamic prediction strategy

OBJECTIVES

To develop and validate a prediction tool for pediatric acute liver failure (PALF) mortality risks that captures the rapid and heterogeneous clinical course for accurate and updated prediction.

METHODS

Data included 1144 participants with PALF enrolled during three phases of the PALF registry study over 15 years. Using joint modeling, we built a dynamic prediction tool for mortality by combining longitudinal trajectories of multiple laboratory and clinical variables. The predictive performance for 7-day and 21-day mortality was assessed using the area under curve (AUC) through cross-validation and split-by-time validation.

RESULTS

We constructed a prognostic joint model that combines the temporal trajectories of international normalized ratio, total bilirubin, hepatic encephalopathy, platelet count, and serum creatinine. Dynamic prediction using updated information improved predictive performance over static prediction using the information at enrollment (Day 0) only. In cross-validation, AUC increased from 0.784 to 0.887 when measurements obtained between Days 1 and 2 were incorporated. AUC remained similar when we used the earlier subset of the sample for training and the later subset for testing.

CONCLUSIONS

Serial measurements of five variables in the first few days of PALF capture the dynamic clinical course of the disease and improve risk prediction for mortality. Continuous disease monitoring and updating risk prognosis are beneficial for timely and judicious medical decisions.

Dynamic risk score modeling for multiple longitudinal risk factors and survival

Modeling disease risk and survival using longitudinal risk factor trajectories is of interest in various clinical scenarios. The capacity to build a prognostic model using the trajectories of multiple longitudinal risk factors, in the presence of potential dependent censoring, would enable more informed, personalized decision making. A dynamic risk score modeling framework is proposed for multiple longitudinal risk factors and survival in the presence of dependent censoring, where both events depend on participants' post-baseline clinical progression and form a competing risks structure. The model requires relatively few random effects regardless of the number of longitudinal risk factors and can therefore accommodate multiple longitudinal risk factors in a parsimonious manner. The proposed method performed satisfactorily in extensive simulation studies. It is further applied to the motivating registry study on pediatric acute liver failure to model death using the trajectories of multiple clinical and biochemical markers. Once established, the model yields an easily calculable longitudinal risk score that can be used for disease monitoring among future patients.