Prediction of Type 2 Diabetes Based on Machine Learning Algorithm
Prediction of type 2 diabetes (T2D) occurrence allows a person at risk to take actions that can prevent onset or delay the progression of the disease. In this study, we developed a machine learning (ML) model to predict T2D occurrence in the following year (Y + 1) using variables in the current year...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-03-01
|
Series: | International Journal of Environmental Research and Public Health |
Subjects: | |
Online Access: | https://www.mdpi.com/1660-4601/18/6/3317 |
id |
doaj-5d32856e915a4bd39cb4da8af74279ea |
---|---|
record_format |
Article |
spelling |
doaj-5d32856e915a4bd39cb4da8af74279ea2021-03-24T00:04:58ZengMDPI AGInternational Journal of Environmental Research and Public Health1661-78271660-46012021-03-01183317331710.3390/ijerph18063317Prediction of Type 2 Diabetes Based on Machine Learning AlgorithmHenock M. Deberneh0Intaek Kim1Department of Information and Communications Engineering, Myongji University, 116 Myongji-ro, Yongin, Gyeonggi 17058, KoreaDepartment of Information and Communications Engineering, Myongji University, 116 Myongji-ro, Yongin, Gyeonggi 17058, KoreaPrediction of type 2 diabetes (T2D) occurrence allows a person at risk to take actions that can prevent onset or delay the progression of the disease. In this study, we developed a machine learning (ML) model to predict T2D occurrence in the following year (Y + 1) using variables in the current year (Y). The dataset for this study was collected at a private medical institute as electronic health records from 2013 to 2018. To construct the prediction model, key features were first selected using ANOVA tests, chi-squared tests, and recursive feature elimination methods. The resultant features were fasting plasma glucose (FPG), HbA1c, triglycerides, BMI, gamma-GTP, age, uric acid, sex, smoking, drinking, physical activity, and family history. We then employed logistic regression, random forest, support vector machine, XGBoost, and ensemble machine learning algorithms based on these variables to predict the outcome as normal (non-diabetic), prediabetes, or diabetes. Based on the experimental results, the performance of the prediction model proved to be reasonably good at forecasting the occurrence of T2D in the Korean population. The model can provide clinicians and patients with valuable predictive information on the likelihood of developing T2D. The cross-validation (CV) results showed that the ensemble models had a superior performance to that of the single models. The CV performance of the prediction models was improved by incorporating more medical history from the dataset.https://www.mdpi.com/1660-4601/18/6/3317type 2 diabetesmachine learningprediction |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Henock M. Deberneh Intaek Kim |
spellingShingle |
Henock M. Deberneh Intaek Kim Prediction of Type 2 Diabetes Based on Machine Learning Algorithm International Journal of Environmental Research and Public Health type 2 diabetes machine learning prediction |
author_facet |
Henock M. Deberneh Intaek Kim |
author_sort |
Henock M. Deberneh |
title |
Prediction of Type 2 Diabetes Based on Machine Learning Algorithm |
title_short |
Prediction of Type 2 Diabetes Based on Machine Learning Algorithm |
title_full |
Prediction of Type 2 Diabetes Based on Machine Learning Algorithm |
title_fullStr |
Prediction of Type 2 Diabetes Based on Machine Learning Algorithm |
title_full_unstemmed |
Prediction of Type 2 Diabetes Based on Machine Learning Algorithm |
title_sort |
prediction of type 2 diabetes based on machine learning algorithm |
publisher |
MDPI AG |
series |
International Journal of Environmental Research and Public Health |
issn |
1661-7827 1660-4601 |
publishDate |
2021-03-01 |
description |
Prediction of type 2 diabetes (T2D) occurrence allows a person at risk to take actions that can prevent onset or delay the progression of the disease. In this study, we developed a machine learning (ML) model to predict T2D occurrence in the following year (Y + 1) using variables in the current year (Y). The dataset for this study was collected at a private medical institute as electronic health records from 2013 to 2018. To construct the prediction model, key features were first selected using ANOVA tests, chi-squared tests, and recursive feature elimination methods. The resultant features were fasting plasma glucose (FPG), HbA1c, triglycerides, BMI, gamma-GTP, age, uric acid, sex, smoking, drinking, physical activity, and family history. We then employed logistic regression, random forest, support vector machine, XGBoost, and ensemble machine learning algorithms based on these variables to predict the outcome as normal (non-diabetic), prediabetes, or diabetes. Based on the experimental results, the performance of the prediction model proved to be reasonably good at forecasting the occurrence of T2D in the Korean population. The model can provide clinicians and patients with valuable predictive information on the likelihood of developing T2D. The cross-validation (CV) results showed that the ensemble models had a superior performance to that of the single models. The CV performance of the prediction models was improved by incorporating more medical history from the dataset. |
topic |
type 2 diabetes machine learning prediction |
url |
https://www.mdpi.com/1660-4601/18/6/3317 |
work_keys_str_mv |
AT henockmdeberneh predictionoftype2diabetesbasedonmachinelearningalgorithm AT intaekkim predictionoftype2diabetesbasedonmachinelearningalgorithm |
_version_ |
1724205372249473024 |