RT Journal Article
T1 Kernel machine learning methods to handle missing responses with complex predictors: application in modelling five-year glucose changes using distributional representations
A1 Matabuena Rodríguez, Marcos
A1 Félix Lamas, Paulo
A1 García Meixide, Carlos
A1 Gude Sampedro, Francisco
K1 Missing data
K1 Kernel methods
K1 Statistical independence
K1 Variable selection
K1 Regression modelling
K1 Diabetes mellitus
K1 Continuous glucose monitoring
AB Background and objectives: Missing data is a ubiquitous problem in longitudinal studies due to the number of patients lost to follow-up. Kernel methods have enriched the machine learning field by successfully managing non-vectorial predictors, such as graphs, strings, and probability distributions, and have emerged as a promising tool for the analysis of complex data stemming from modern healthcare. This paper proposes a new set of kernel methods to handle missing data in the response variables. These methods will be applied to predict long-term changes in glycated haemoglobin (A1c), the primary biomarker used to diagnose and monitor the progression of diabetes mellitus, making emphasis on exploring the predictive potential of continuous glucose monitoring (CGM). Methods: We propose a new framework of non-linear kernel methods for testing statistical independence, selecting relevant predictors, and quantifying the uncertainty of the resultant predictive models. As a novelty in the clinical analysis, we used a distributional representation of CGM as a predictor and compared its performance with that of traditional diabetes biomarkers. Results: The results show that, after the incorporation of CGM information, predictive ability increases from  to . In addition, uncertainty analysis is useful for characterising some subpopulations where predictivity is worsened, and a more personalised clinical follow-up is advisable according to expected patient uncertainty in glucose values. Conclusions: The proposed methods have proven to deal effectively with missing data. They also have the potential to improve the results of predictive tasks by including new complex objects as explanatory variables and modelling arbitrary dependence relations. The application of these methods to a longitudinal study of diabetes showed that the inclusion of a distributional representation of CGM data provides greater sensitivity in predicting five-year A1c changes than classical diabetes biomarkers and traditional CGM metrics
PB Elsevier
YR 2022
FD 2022
LK http://hdl.handle.net/10347/29089
UL http://hdl.handle.net/10347/29089
LA eng
NO Computer Methods and Programs in Biomedicine 221(2022) 106905
NO This study was supported by ISCIII (PI20/01069, RD21/0016/0022; Cofinanciado por la Unión Europea/FEDER, ”A way to make Europe”); and the Ministry of Science, Innovation and Universities of Spain (RTI2018-099646-B-I00)
DS Minerva
RD 22 abr 2026