Literature DB >> 31889178

A combined strategy of feature selection and machine learning to identify predictors of prediabetes.

Kushan De Silva1,2, Daniel Jönsson3, Ryan T Demmer4.   

Abstract

OBJECTIVE: To identify predictors of prediabetes using feature selection and machine learning on a nationally representative sample of the US population.
MATERIALS AND METHODS: We analyzed n = 6346 men and women enrolled in the National Health and Nutrition Examination Survey 2013-2014. Prediabetes was defined using American Diabetes Association guidelines. The sample was randomly partitioned to training (n = 3174) and internal validation (n = 3172) sets. Feature selection algorithms were run on training data containing 156 preselected exposure variables. Four machine learning algorithms were applied on 46 exposure variables in original and resampled training datasets built using 4 resampling methods. Predictive models were tested on internal validation data (n = 3172) and external validation data (n = 3000) prepared from National Health and Nutrition Examination Survey 2011-2012. Model performance was evaluated using area under the receiver operating characteristic curve (AUROC). Predictors were assessed by odds ratios in logistic models and variable importance in others. The Centers for Disease Control (CDC) prediabetes screening tool was the benchmark to compare model performance.
RESULTS: Prediabetes prevalence was 23.43%. The CDC prediabetes screening tool produced 64.40% AUROC. Seven optimal (≥ 70% AUROC) models identified 25 predictors including 4 potentially novel associations; 20 by both logistic and other nonlinear/ensemble models and 5 solely by the latter. All optimal models outperformed the CDC prediabetes screening tool (P < 0.05). DISCUSSION: Combined use of feature selection and machine learning increased predictive performance outperforming the recommended screening tool. A range of predictors of prediabetes was identified.
CONCLUSION: This work demonstrated the value of combining feature selection with machine learning to identify a wide range of predictors that could enhance prediabetes prediction and clinical decision-making.
© The Author(s) 2019. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  NHANES; feature selection; machine learning; prediabetes; predictors

Year:  2020        PMID: 31889178      PMCID: PMC7647289          DOI: 10.1093/jamia/ocz204

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   4.497


  35 in total

1.  Training neural network classifiers for medical decision making: the effects of imbalanced datasets on classification performance.

Authors:  Maciej A Mazurowski; Piotr A Habas; Jacek M Zurada; Joseph Y Lo; Jay A Baker; Georgia D Tourassi
Journal:  Neural Netw       Date:  2007-12-27

2.  A simple tool detected diabetes and prediabetes in rural Chinese.

Authors:  Zhong Xin; Jing Yuan; Lin Hua; Ya-Hong Ma; Lei Zhao; Yi Lu; Jin-Kui Yang
Journal:  J Clin Epidemiol       Date:  2010-03-01       Impact factor: 6.437

3.  Comparing glycemic indicators of prediabetes: a prospective study of obese Latino Youth.

Authors:  Joon Young Kim; Michael I Goran; Claudia M Toledo-Corral; Marc J Weigensberg; Gabriel Q Shaibi
Journal:  Pediatr Diabetes       Date:  2014-11-11       Impact factor: 4.866

4.  The inevitable application of big data to health care.

Authors:  Travis B Murdoch; Allan S Detsky
Journal:  JAMA       Date:  2013-04-03       Impact factor: 56.272

5.  Rule extraction from support vector machines using ensemble learning approach: an application for diagnosis of diabetes.

Authors:  Longfei Han; Senlin Luo; Jianmin Yu; Limin Pan; Songjing Chen
Journal:  IEEE J Biomed Health Inform       Date:  2014-05-19       Impact factor: 5.772

6.  Reverse Engineering and Evaluation of Prediction Models for Progression to Type 2 Diabetes: An Application of Machine Learning Using Electronic Health Records.

Authors:  Jeffrey P Anderson; Jignesh R Parikh; Daniel K Shenfeld; Vladimir Ivanov; Casey Marks; Bruce W Church; Jason M Laramie; Jack Mardekian; Beth Anne Piper; Richard J Willke; Dale A Rublee
Journal:  J Diabetes Sci Technol       Date:  2015-12-20

7.  "Prediabetes": Are There Problems With This Label? Yes, the Label Creates Further Problems!

Authors:  John S Yudkin
Journal:  Diabetes Care       Date:  2016-08       Impact factor: 19.112

8.  Prediabetes and the risk of cancer: a meta-analysis.

Authors:  Yi Huang; Xiaoyan Cai; Miaozhen Qiu; Peisong Chen; Hongfeng Tang; Yunzhao Hu; Yuli Huang
Journal:  Diabetologia       Date:  2014-09-11       Impact factor: 10.122

Review 9.  Association between prediabetes and risk of cardiovascular disease and all cause mortality: systematic review and meta-analysis.

Authors:  Yuli Huang; Xiaoyan Cai; Weiyi Mai; Meijun Li; Yunzhao Hu
Journal:  BMJ       Date:  2016-11-23

10.  Predicting diabetes mellitus using SMOTE and ensemble machine learning approach: The Henry Ford ExercIse Testing (FIT) project.

Authors:  Manal Alghamdi; Mouaz Al-Mallah; Steven Keteyian; Clinton Brawner; Jonathan Ehrman; Sherif Sakr
Journal:  PLoS One       Date:  2017-07-24       Impact factor: 3.240

View more
  6 in total

1.  A Cardiovascular Disease Prediction Model Based on Routine Physical Examination Indicators Using Machine Learning Methods: A Cohort Study.

Authors:  Xin Qian; Yu Li; Xianghui Zhang; Heng Guo; Jia He; Xinping Wang; Yizhong Yan; Jiaolong Ma; Rulin Ma; Shuxia Guo
Journal:  Front Cardiovasc Med       Date:  2022-06-17

2.  Nutritional markers of undiagnosed type 2 diabetes in adults: Findings of a machine learning analysis with external validation and benchmarking.

Authors:  Kushan De Silva; Siew Lim; Aya Mousa; Helena Teede; Andrew Forbes; Ryan T Demmer; Daniel Jönsson; Joanne Enticott
Journal:  PLoS One       Date:  2021-05-05       Impact factor: 3.240

3.  Identification of Prediabetes Discussions in Unstructured Clinical Documentation: Validation of a Natural Language Processing Algorithm.

Authors:  Jessica L Schwartz; Eva Tseng; Nisa M Maruthur; Masoud Rouhizadeh
Journal:  JMIR Med Inform       Date:  2022-02-24

Review 4.  Machine learning for diabetes clinical decision support: a review.

Authors:  Ashwini Tuppad; Shantala Devi Patil
Journal:  Adv Comput Intell       Date:  2022-04-13

5.  Identifying Glucose Metabolism Status in Nondiabetic Japanese Adults Using Machine Learning Model with Simple Questionnaire.

Authors:  Tomoki Uchida; Takeshi Kanamori; Takanori Teramoto; Yuji Nonaka; Hiroki Tanaka; Satoshi Nakamura; Norihito Murayama
Journal:  Comput Math Methods Med       Date:  2022-09-09       Impact factor: 2.809

Review 6.  Machine Learning Applications in Endocrinology and Metabolism Research: An Overview.

Authors:  Namki Hong; Heajeong Park; Yumie Rhee
Journal:  Endocrinol Metab (Seoul)       Date:  2020-03
  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.