Cargando…

Metabolic Syndrome Prediction Using Machine Learning Models with Genetic and Clinical Information from a Nonobese Healthy Population

The prevalence of metabolic syndrome (MS) in the nonobese population is not low. However, the identification and risk mitigation of MS are not easy in this population. We aimed to develop an MS prediction model using genetic and clinical factors of nonobese Koreans through machine learning methods....

Descripción completa

Detalles Bibliográficos
Autores principales: Choe, Eun Kyung, Rhee, Hwanseok, Lee, Seungjae, Shin, Eunsoon, Oh, Seung-Won, Lee, Jong-Eun, Choi, Seung Ho
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Korea Genome Organization 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6440667/
https://www.ncbi.nlm.nih.gov/pubmed/30602092
http://dx.doi.org/10.5808/GI.2018.16.4.e31
_version_ 1783407431931396096
author Choe, Eun Kyung
Rhee, Hwanseok
Lee, Seungjae
Shin, Eunsoon
Oh, Seung-Won
Lee, Jong-Eun
Choi, Seung Ho
author_facet Choe, Eun Kyung
Rhee, Hwanseok
Lee, Seungjae
Shin, Eunsoon
Oh, Seung-Won
Lee, Jong-Eun
Choi, Seung Ho
author_sort Choe, Eun Kyung
collection PubMed
description The prevalence of metabolic syndrome (MS) in the nonobese population is not low. However, the identification and risk mitigation of MS are not easy in this population. We aimed to develop an MS prediction model using genetic and clinical factors of nonobese Koreans through machine learning methods. A prediction model for MS was designed for a nonobese population using clinical and genetic polymorphism information with five machine learning algorithms, including naïve Bayes classification (NB). The analysis was performed in two stages (training and test sets). Model A was designed with only clinical information (age, sex, body mass index, smoking status, alcohol consumption status, and exercise status), and for model B, genetic information (for 10 polymorphisms) was added to model A. Of the 7,502 nonobese participants, 647 (8.6%) had MS. In the test set analysis, for the maximum sensitivity criterion, NB showed the highest sensitivity: 0.38 for model A and 0.42 for model B. The specificity of NB was 0.79 for model A and 0.80 for model B. In a comparison of the performances of models A and B by NB, model B (area under the receiver operating characteristic curve [AUC] = 0.69, clinical and genetic information input) showed better performance than model A (AUC = 0.65, clinical information only input). We designed a prediction model for MS in a nonobese population using clinical and genetic information. With this model, we might convince nonobese MS individuals to undergo health checks and adopt behaviors associated with a preventive lifestyle.
format Online
Article
Text
id pubmed-6440667
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher Korea Genome Organization
record_format MEDLINE/PubMed
spelling pubmed-64406672019-04-03 Metabolic Syndrome Prediction Using Machine Learning Models with Genetic and Clinical Information from a Nonobese Healthy Population Choe, Eun Kyung Rhee, Hwanseok Lee, Seungjae Shin, Eunsoon Oh, Seung-Won Lee, Jong-Eun Choi, Seung Ho Genomics Inform Original Article The prevalence of metabolic syndrome (MS) in the nonobese population is not low. However, the identification and risk mitigation of MS are not easy in this population. We aimed to develop an MS prediction model using genetic and clinical factors of nonobese Koreans through machine learning methods. A prediction model for MS was designed for a nonobese population using clinical and genetic polymorphism information with five machine learning algorithms, including naïve Bayes classification (NB). The analysis was performed in two stages (training and test sets). Model A was designed with only clinical information (age, sex, body mass index, smoking status, alcohol consumption status, and exercise status), and for model B, genetic information (for 10 polymorphisms) was added to model A. Of the 7,502 nonobese participants, 647 (8.6%) had MS. In the test set analysis, for the maximum sensitivity criterion, NB showed the highest sensitivity: 0.38 for model A and 0.42 for model B. The specificity of NB was 0.79 for model A and 0.80 for model B. In a comparison of the performances of models A and B by NB, model B (area under the receiver operating characteristic curve [AUC] = 0.69, clinical and genetic information input) showed better performance than model A (AUC = 0.65, clinical information only input). We designed a prediction model for MS in a nonobese population using clinical and genetic information. With this model, we might convince nonobese MS individuals to undergo health checks and adopt behaviors associated with a preventive lifestyle. Korea Genome Organization 2018-12 2018-12-28 /pmc/articles/PMC6440667/ /pubmed/30602092 http://dx.doi.org/10.5808/GI.2018.16.4.e31 Text en Copyright © 2018 by Korea Genome Organization It is identical to the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/).
spellingShingle Original Article
Choe, Eun Kyung
Rhee, Hwanseok
Lee, Seungjae
Shin, Eunsoon
Oh, Seung-Won
Lee, Jong-Eun
Choi, Seung Ho
Metabolic Syndrome Prediction Using Machine Learning Models with Genetic and Clinical Information from a Nonobese Healthy Population
title Metabolic Syndrome Prediction Using Machine Learning Models with Genetic and Clinical Information from a Nonobese Healthy Population
title_full Metabolic Syndrome Prediction Using Machine Learning Models with Genetic and Clinical Information from a Nonobese Healthy Population
title_fullStr Metabolic Syndrome Prediction Using Machine Learning Models with Genetic and Clinical Information from a Nonobese Healthy Population
title_full_unstemmed Metabolic Syndrome Prediction Using Machine Learning Models with Genetic and Clinical Information from a Nonobese Healthy Population
title_short Metabolic Syndrome Prediction Using Machine Learning Models with Genetic and Clinical Information from a Nonobese Healthy Population
title_sort metabolic syndrome prediction using machine learning models with genetic and clinical information from a nonobese healthy population
topic Original Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6440667/
https://www.ncbi.nlm.nih.gov/pubmed/30602092
http://dx.doi.org/10.5808/GI.2018.16.4.e31
work_keys_str_mv AT choeeunkyung metabolicsyndromepredictionusingmachinelearningmodelswithgeneticandclinicalinformationfromanonobesehealthypopulation
AT rheehwanseok metabolicsyndromepredictionusingmachinelearningmodelswithgeneticandclinicalinformationfromanonobesehealthypopulation
AT leeseungjae metabolicsyndromepredictionusingmachinelearningmodelswithgeneticandclinicalinformationfromanonobesehealthypopulation
AT shineunsoon metabolicsyndromepredictionusingmachinelearningmodelswithgeneticandclinicalinformationfromanonobesehealthypopulation
AT ohseungwon metabolicsyndromepredictionusingmachinelearningmodelswithgeneticandclinicalinformationfromanonobesehealthypopulation
AT leejongeun metabolicsyndromepredictionusingmachinelearningmodelswithgeneticandclinicalinformationfromanonobesehealthypopulation
AT choiseungho metabolicsyndromepredictionusingmachinelearningmodelswithgeneticandclinicalinformationfromanonobesehealthypopulation