Multivariate longitudinal data for survival analysis of cardiovascular event prediction in young adults: insights from a comparative explainable study

Abstract

Background Multivariate longitudinal data are under-utilized for survival analysis compared to cross-sectional data (CS - data collected once across cohort). Particularly in cardiovascular risk prediction, despite available methods of longitudinal data analysis, the value of longitudinal information has not been established in terms of improved predictive accuracy and clinical applicability. Methods We investigated the value of longitudinal data over and above the use of cross-sectional data via 6 distinct modeling strategies from statistics, machine learning, and deep learning that incorporate repeated measures for survival analysis of the time-to-cardiovascular event in the Coronary Artery Risk Development in Young Adults (CARDIA) cohort. We then examined and compared the use of model-specific interpretability methods (Random Survival Forest Variable Importance) and model-agnostic methods (SHapley Additive exPlanation (SHAP) and Temporal Importance Model Explanation (TIME)) in cardiovascular risk prediction using the top-performing models. Results In a cohort of 3539 participants, longitudinal information from 35 variables that were repeatedly collected in 6 exam visits over 15 years improved subsequent long-term (17 years after) risk prediction by up to 8.3% in C-index compared to using baseline data (0.78 vs. 0.72), and up to approximately 4% compared to using the last observed CS data (0.75). Time-varying AUC was also higher in models using longitudinal data (0.86–0.87 at 5 years, 0.79–0.81 at 10 years) than using baseline or last observed CS data (0.80–0.86 at 5 years, 0.73–0.77 at 10 years). Comparative model interpretability analysis revealed the impact of longitudinal variables on model prediction on both the individual and global scales among different modeling strategies, as well as identifying the best time windows and best timing within that window for event prediction. The best strategy to incorporate longitudinal data for accuracy was time series massive feature extraction, and the easiest interpretable strategy was trajectory clustering. Conclusion Our analysis demonstrates the added value of longitudinal data in predictive accuracy and epidemiological utility in cardiovascular risk survival analysis in young adults via a unified, scalable framework that compares model performance and explainability. The framework can be extended to a larger number of variables and other longitudinal modeling methods. Trial registration ClinicalTrials.gov Identifier: NCT00005130, Registration Date: 26/05/2000.

Utility of multimodal longitudinal imaging data for dynamic prediction of cardiovascular and renal disease: the CARDIA study

“…As a benchmark, we also fit static survival models at three time points (5 years, 15 years, and 25 years after baseline) to compare with the dynamic survival models. ( 18 ) The idea is similar to landmarking approaches, in which a survival model is fit to the subjects who are still at risk at the landmarking time. For consistency in comparison, we used Dynamic-DeepHit and made an artificial cut-off at the landmarking time (meaning, covariate measurements after Y5, Y15, and Y25 were excluded from the static model at landmarking time 5 years, 15 years, and 25 years after baseline, respectively).…”

Utility of Multimodal Longitudinal Imaging Data for Dynamic Prediction of Cardiovascular and Renal Disease: The CARDIA Study

“…16,17 As a benchmark, we also fit static survival models at three time points (5 years, 15 years, and 25 years after baseline) to compare with the dynamic survival models. 18 The idea is similar to landmarking approaches, in which a survival model is fit to the subjects who are still at risk at the landmarking time. For consistency in comparison, we used Dynamic-DeepHit and made an artificial cut-off at the landmarking time (meaning, covariate measurements after Y5, Y15, and Y25 were excluded from the static model at landmarking time 5 years, 15 years, and 25 years after baseline, respectively).…”

Machine learning‐based prediction of clinical outcomes after traumatic brain injury: Hidden information of early physiological time series

“…A study of publications from 2009 to 2016 revealed that less than 8% of predictive models included longitudinal data as time‐varying covariates. 6 Neglecting the potential of these high‐dimensional, longitudinal, time‐varying covariates to improve prediction, as demonstrated in cardiovascular disease risk prediction, 7 , 8 is a prevailing issue.…”