Yujia Liu1, Shangyuan Ye2, Xianchao Xiao1, Chenglin Sun1, Gang Wang1, Guixia Wang1, Bo Zhang3. 1. Department of Endocrinology and Metabolism, The First Hospital of Jilin University, Changchun, Jilin 130021, People's Republic of China. 2. Department of Population Medicine, Harvard Pilgrim Health Care and Harvard Medical School, Boston, MA, USA. 3. Department of Neurology and ICCTR Biostatistics and Research Design Center, Boston Children's Hospital and Harvard Medical School, Boston, MA, USA.
Abstract
BACKGROUND: This study proposes the use of machine learning algorithms to improve the accuracy of type 2 diabetes predictions using non-invasive risk score systems. METHODS: We evaluated and compared the prediction accuracies of existing non-invasive risk score systems using the data from the REACTION study (Risk Evaluation of Cancers in Chinese Diabetic Individuals: A Longitudinal Study). Two simple risk scores were established on the bases of logistic regression. Machine learning techniques (ensemble methods) were used to improve prediction accuracies by combining the individual score systems. RESULTS: Existing score systems from Western populations performed worse than the scores from Eastern populations in general. The two newly established score systems performed better than most existing scores systems but a little worse than the Chinese score system. Using ensemble methods with model selection algorithms yielded better prediction accuracy than all the simple score systems. CONCLUSION: Our proposed machine learning methods can be used to improve the accuracy of screening the undiagnosed type 2 diabetes and identifying the high-risk patients.
BACKGROUND: This study proposes the use of machine learning algorithms to improve the accuracy of type 2 diabetes predictions using non-invasive risk score systems. METHODS: We evaluated and compared the prediction accuracies of existing non-invasive risk score systems using the data from the REACTION study (Risk Evaluation of Cancers in Chinese Diabetic Individuals: A Longitudinal Study). Two simple risk scores were established on the bases of logistic regression. Machine learning techniques (ensemble methods) were used to improve prediction accuracies by combining the individual score systems. RESULTS: Existing score systems from Western populations performed worse than the scores from Eastern populations in general. The two newly established score systems performed better than most existing scores systems but a little worse than the Chinese score system. Using ensemble methods with model selection algorithms yielded better prediction accuracy than all the simple score systems. CONCLUSION: Our proposed machine learning methods can be used to improve the accuracy of screening the undiagnosed type 2 diabetes and identifying the high-risk patients.
Authors: Lei Chen; Dianna J Magliano; Beverley Balkau; Stephen Colagiuri; Paul Z Zimmet; Andrew M Tonkin; Paul Mitchell; Patrick J Phillips; Jonathan E Shaw Journal: Med J Aust Date: 2010-02-15 Impact factor: 7.738
Authors: Thomas P A Debray; Hendrik Koffijberg; Daan Nieboer; Yvonne Vergouwe; Ewout W Steyerberg; Karel G M Moons Journal: Stat Med Date: 2014-01-14 Impact factor: 2.373
Authors: William C Knowler; Elizabeth Barrett-Connor; Sarah E Fowler; Richard F Hamman; John M Lachin; Elizabeth A Walker; David M Nathan Journal: N Engl J Med Date: 2002-02-07 Impact factor: 91.245
Authors: Luis Fregoso-Aparicio; Julieta Noguez; Luis Montesinos; José A García-García Journal: Diabetol Metab Syndr Date: 2021-12-20 Impact factor: 3.320
Authors: Jorge A Morgan-Benita; Carlos E Galván-Tejada; Miguel Cruz; Jorge I Galván-Tejada; Hamurabi Gamboa-Rosales; Jose G Arceo-Olague; Huizilopoztli Luna-García; José M Celaya-Padilla Journal: Healthcare (Basel) Date: 2022-07-22
Authors: Martina Vettoretti; Enrico Longato; Alessandro Zandonà; Yan Li; José Antonio Pagán; David Siscovick; Mercedes R Carnethon; Alain G Bertoni; Andrea Facchinetti; Barbara Di Camillo Journal: BMJ Open Diabetes Res Care Date: 2020-07