Accepted for/Published in: JMIR Medical Informatics
Date Submitted: Jan 31, 2022
Date Accepted: May 31, 2022
Predicting Risk of Hypoglycemia Patients with Type 2 Diabetes with Electronic Health Record Machine Learning Model
ABSTRACT
Background:
Hypoglycemia is a common adverse event in the treatment of diabetes. To effectively cope with hypoglycemia, effective hypoglycemia prediction models need to be developed.
Objective:
The aim of this study was to develop and validate machine learning models to predict the risk of hypoglycemia in adult patients with type 2 diabetes.
Methods:
We used the electronic health records of all adult type 2 diabetes patients admitted to West China Hospital between November 2019 and December 2021. The prediction model was developed based on XGBoost and natural language processing. F1 score, area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA) were used as the main criteria to evaluate the performance.
Results:
We included 29,843 patients with type 2 diabetes, of whom 2,804 patients (9.4%) developed hypoglycemia. In this study, the embedding machine learning model (XGBoost3) showed the best performance in all the models. The AUC, accuracy, and the F1-score of XGBoost are 0.78, 0.93, and 0.91, respectively. The XGboost3 was also superior to other models in decision curve analysis (DCA).
Conclusions:
The ensemble machine learning model can be used to effectively predict the prediction of hypoglycemic in type 2 diabetes patients.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.