imputeCGM

MaRDI QIDQ7374877CRANFDO

Authors Shubh Saraswat, Hasin Shahed Shad, Xiaohua Douglas Zhang

Last update 16 July 2026

Copyright license GNU General Public License, version 2.0, GNU General Public License, version 3.0

Software version identifier 0.0.3

Description

Imputes missing glucose values in repeated-measures continuous glucose monitoring (CGM) data. Workflows create time-series features from raw timestamps, support model selection, and return the user's original columns plus an imputed glucose column. Methods include multiple imputation by chained equations using 'mice' (Azur et al. (2011) <doi:10.1002/mpr.329>), Random Forest regression using 'ranger' (Breiman (2001) <doi:10.1023/A:1010933404324>), k-nearest-neighbor regression using 'FNN' (Zhang (2016) <doi:10.21037/atm.2016.03.37>), 'XGBoost' using 'xgboost' (Chen and Guestrin (2016) <doi:10.1145/2939672.2939785>), 'LightGBM' using 'lightgbm' (Ke et al. (2017) <https://papers.nips.cc/paper/6907-lightgbm-a-highly-efficient-gradient-boosting-decision>), and ARIMA forecasting using 'forecast' (Hyndman and Khandakar (2008) <doi:10.18637/jss.v027.i03>). A 'Python'-compatible backend uses 'reticulate' to call 'pandas', 'scikit-learn', 'statsmodels', 'xgboost', and optional 'lightgbm'.

Cites work

• Automatic Time Series Forecasting: TheforecastPackage forR
• Unnamed Publication
• Introduction to machine learning: k-nearest neighbors
• Multiple imputation by chained equations: what is it and how does it work?
• XGBoost

This page was built for software: imputeCGM