Prospective prediction of childhood body mass index trajectories using multi-task Gaussian processes

Abstract

Background Body mass index (BMI) trajectories of children have been used to assess their growth with respect to their peers, as well as to anticipate future obesity and disease risk. While retrospective modelling of childhood BMI trajectories has been an active area of research, prospective prediction of continuous BMI trajectories from historical growth data has not been well investigated.Materials and Methods Using longitudinal BMI measurements between birth and age 10y from a longitudinal mother-offspring cohort, we leveraged a multi-task Gaussian processes-based method called MagmaClust to develop and evaluate a unified framework for modeling, clustering and prospective prediction of BMI trajectories. We compared the sensitivity to missing values and trajectory prediction performance of the proposed method with cubic B-spline and multilevel Jenss-Bayley models. Predicted trajectories were also utilized to prospectively estimate overweight/obesity risk at age 10y.Results MagmaClust identified 5 distinct patterns of BMI trajectories between 0 to 10y. The method outperformed both cubic B-spline and multilevel Jenss-Bayley models in the accuracy of retrospective BMI trajectories while being more robust to missing data (up to 90%). It was also better at prospectively forecasting BMI trajectories of children for periods ranging from 2 to 8 years into the future, using historic BMI data. Given BMI data between birth and age 2 years, prediction of overweight/obesity status at age 10 years, as computed from MagmaClust’s predictions exhibited high specificity (0.94) and accuracy (0.86). The accuracy and sensitivity of predictions increased as BMI data from additional timepoints were utilized for prediction.Conclusion MagmaClust provides a unified, probabilistic, non-parametric framework to model, cluster and prospectively predict childhood BMI trajectories and overweight/obesity risk. The proposed method offers a convenient tool for clinicians to monitor BMI growth in children, allowing them to prospectively identify children with high predicted overweight/obesity risk and implement timely interventions.