Glucose values prediction five years ahead with a new framework of missing responses in reproducing kernel Hilbert spaces, and the use of continuous glucose monitoring technology
This research provides a new framework for handling missing longitudinal data in medical studies, which is significant for clinicians and researchers analyzing long-term health trends and developing personalized interventions.
This study addresses the challenge of missing data in longitudinal medical studies, specifically 40% of glycosylated hemoglobin (A1C) biomarker data five years ahead in the AEGIS study. It proposes a new data analysis framework based on learning in reproducing kernel Hilbert spaces (RKHS) to predict glucose values five years in advance, identifying new factors associated with long-term glucose evolution and demonstrating the clinical sensibility of CGM data.
AEGIS study possesses unique information on longitudinal changes in circulating glucose through continuous glucose monitoring technology (CGM). However, as usual in longitudinal medical studies, there is a significant amount of missing data in the outcome variables. For example, 40 percent of glycosylated hemoglobin (A1C) biomarker data are missing five years ahead. With the purpose to reduce the impact of this issue, this article proposes a new data analysis framework based on learning in reproducing kernel Hilbert spaces (RKHS) with missing responses that allows to capture non-linear relations between variable studies in different supervised modeling tasks. First, we extend the Hilbert-Schmidt dependence measure to test statistical independence in this context introducing a new bootstrap procedure, for which we prove consistency. Next, we adapt or use existing models of variable selection, regression, and conformal inference to obtain new clinical findings about glucose changes five years ahead with the AEGIS data. The most relevant findings are summarized below: i) We identify new factors associated with long-term glucose evolution; ii) We show the clinical sensibility of CGM data to detect changes in glucose metabolism; iii) We can improve clinical interventions based on our algorithms' expected glucose changes according to patients' baseline characteristics.