Alhassan, Zakhriya and Watson, Matthew and Budgen, David and Alshammari, Riyad and Alessa, Ali and Al Moubayed, Noura (2021) 'Improving Current Glycated Hemoglobin Prediction in Adults: Use of Machine Learning Algorithms with Electronic Health Records.', JMIR medical informatics., 9 (5). e25237.
Background: Predicting the risk of glycated hemoglobin (HbA1c) elevation can help identify patients with the potential for developing serious chronic health problems such as diabetes. Early preventive interventions based upon advanced predictive models using electronic health records (EHR) data for identifying such patients can ultimately help provide better health outcomes. Objective: Our study investigates the performance of predictive models to forecast HbA1c elevation levels by employing several machine learning models. We also investigate utilizing the patient's EHR longitudinal data in the performance of the predictive models. Explainable methods have been employed to interpret the decisions made by the blackbox models. Methods: This study employed Multiple Logistic Regression, Random Forest, Support Vector Machine and Logistic Regression models, as well as a deep learning model (Multi-layer perceptron) to classify patients with normal (<5.7%) and elevated (≥5.7%) levels of HbA1c. We also integrated current visit data with historical (longitudinal) data from previous visits. Explainable machine learning methods were used to interrogate the models and provide an understanding of the reasons behind the decisions made by the models. All models were trained and tested using a large dataset from Saudi Arabia with 18,844 unique patient records. Results: The machine learning models achieved promising results for predicting current HbA1c elevation risk. When employed with longitudinal data, the machine learning models outperformed the Multiple Logistic Regression model employed in the comparative study. The multi-layer perceptron model achieved an accuracy of 83.22% for the AUC-ROC when used with historical data. All models showed close level of agreement on the contribution of random blood sugar and age variables with and without longitudinal data. Conclusions: This study shows that machine learning models can provide promising results for the task of predicting current HbA1c levels (≥5.7% or less). Utilizing the patient's longitudinal data improved the performance and affected the relative importance for the predictors used. The models showed results that are consistent with comparable studies.
|Full text:||(AM) Accepted Manuscript|
Available under License - Creative Commons Attribution 4.0.
Download PDF (726Kb)
|Publisher Web site:||https://doi.org/10.2196/25237|
|Publisher statement:||© The authors. All rights reserved. This is a privileged document currently under peer-review/community review. Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review 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.|
|Date accepted:||22 April 2021|
|Date deposited:||28 April 2021|
|Date of first online publication:||22 April 2021|
|Date first made open access:||28 April 2021|
Save or Share this output
|Look up in GoogleScholar|