Evolutionary methods for variable selection in the epidemiological modeling of cardiovascular diseases
Abstract Background The redundancy of information is becoming a critical issue for epidemiologists. High-dimensional datasets require new effective variable selection methods to be developed. This study implements an advanced evolutionary variable selection method which is applied for cardiovascular...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2018-08-01
|
| Series: | BioData Mining |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13040-018-0180-x |
| _version_ | 1811242819252125696 |
|---|---|
| author | Christina Brester Jussi Kauhanen Tomi-Pekka Tuomainen Sari Voutilainen Mauno Rönkkö Kimmo Ronkainen Eugene Semenkin Mikko Kolehmainen |
| author_facet | Christina Brester Jussi Kauhanen Tomi-Pekka Tuomainen Sari Voutilainen Mauno Rönkkö Kimmo Ronkainen Eugene Semenkin Mikko Kolehmainen |
| author_sort | Christina Brester |
| collection | DOAJ |
| description | Abstract Background The redundancy of information is becoming a critical issue for epidemiologists. High-dimensional datasets require new effective variable selection methods to be developed. This study implements an advanced evolutionary variable selection method which is applied for cardiovascular predictive modeling. The epidemiological follow-up study KIHD (Kuopio Ischemic Heart Disease Risk Factor Study) was used to compare the designed variable selection method based on an evolutionary search with conventional stepwise selection. The sample contains in total 433 predictor variables and a response variable indicating incidents of cardiovascular diseases for 1465 study subjects. Results The effectiveness of variable selection methods was investigated in combination with two models: Generalized Linear Logistic Regression and Support Vector Machine. We managed to decrease the number of variables from 433 to 38 and save the predictive ability of the models used. Their performance was evaluated with an F-score metric. At most, we gained 65.6% and 67.4% of the F-score before and after variable selection respectively. All the results were averaged over 5-folds of a cross-validation procedure. Conclusions The presented evolutionary variable selection method allows a reduced set of variables to be chosen which are relevant to predicting cardiovascular diseases. A reference list of the most meaningful variables is introduced to be used as a basis for new epidemiological studies. In general, the multicollinearity of variables enables different combinations of predictors to be used and the same performance of models to be attained. |
| first_indexed | 2024-04-12T13:56:43Z |
| format | Article |
| id | doaj.art-3972bf4e75d44e209f039a165bfff975 |
| institution | Directory Open Access Journal |
| issn | 1756-0381 |
| language | English |
| last_indexed | 2024-04-12T13:56:43Z |
| publishDate | 2018-08-01 |
| publisher | BMC |
| record_format | Article |
| series | BioData Mining |
| spelling | doaj.art-3972bf4e75d44e209f039a165bfff9752022-12-22T03:30:20ZengBMCBioData Mining1756-03812018-08-0111111410.1186/s13040-018-0180-xEvolutionary methods for variable selection in the epidemiological modeling of cardiovascular diseasesChristina Brester0Jussi Kauhanen1Tomi-Pekka Tuomainen2Sari Voutilainen3Mauno Rönkkö4Kimmo Ronkainen5Eugene Semenkin6Mikko Kolehmainen7Department of Environmental and Biological Sciences, University of Eastern FinlandInstitute of Public Health and Clinical Nutrition, University of Eastern FinlandInstitute of Public Health and Clinical Nutrition, University of Eastern FinlandInstitute of Public Health and Clinical Nutrition, University of Eastern FinlandDepartment of Environmental and Biological Sciences, University of Eastern FinlandInstitute of Public Health and Clinical Nutrition, University of Eastern FinlandInstitute of Computer Science and Telecommunications, Reshetnev Siberian State University of Science and TechnologyDepartment of Environmental and Biological Sciences, University of Eastern FinlandAbstract Background The redundancy of information is becoming a critical issue for epidemiologists. High-dimensional datasets require new effective variable selection methods to be developed. This study implements an advanced evolutionary variable selection method which is applied for cardiovascular predictive modeling. The epidemiological follow-up study KIHD (Kuopio Ischemic Heart Disease Risk Factor Study) was used to compare the designed variable selection method based on an evolutionary search with conventional stepwise selection. The sample contains in total 433 predictor variables and a response variable indicating incidents of cardiovascular diseases for 1465 study subjects. Results The effectiveness of variable selection methods was investigated in combination with two models: Generalized Linear Logistic Regression and Support Vector Machine. We managed to decrease the number of variables from 433 to 38 and save the predictive ability of the models used. Their performance was evaluated with an F-score metric. At most, we gained 65.6% and 67.4% of the F-score before and after variable selection respectively. All the results were averaged over 5-folds of a cross-validation procedure. Conclusions The presented evolutionary variable selection method allows a reduced set of variables to be chosen which are relevant to predicting cardiovascular diseases. A reference list of the most meaningful variables is introduced to be used as a basis for new epidemiological studies. In general, the multicollinearity of variables enables different combinations of predictors to be used and the same performance of models to be attained.http://link.springer.com/article/10.1186/s13040-018-0180-xVariable selectionCardiovascular diseasePredictive modelingKuopio ischemic heart disease risk factor study |
| spellingShingle | Christina Brester Jussi Kauhanen Tomi-Pekka Tuomainen Sari Voutilainen Mauno Rönkkö Kimmo Ronkainen Eugene Semenkin Mikko Kolehmainen Evolutionary methods for variable selection in the epidemiological modeling of cardiovascular diseases BioData Mining Variable selection Cardiovascular disease Predictive modeling Kuopio ischemic heart disease risk factor study |
| title | Evolutionary methods for variable selection in the epidemiological modeling of cardiovascular diseases |
| title_full | Evolutionary methods for variable selection in the epidemiological modeling of cardiovascular diseases |
| title_fullStr | Evolutionary methods for variable selection in the epidemiological modeling of cardiovascular diseases |
| title_full_unstemmed | Evolutionary methods for variable selection in the epidemiological modeling of cardiovascular diseases |
| title_short | Evolutionary methods for variable selection in the epidemiological modeling of cardiovascular diseases |
| title_sort | evolutionary methods for variable selection in the epidemiological modeling of cardiovascular diseases |
| topic | Variable selection Cardiovascular disease Predictive modeling Kuopio ischemic heart disease risk factor study |
| url | http://link.springer.com/article/10.1186/s13040-018-0180-x |
| work_keys_str_mv | AT christinabrester evolutionarymethodsforvariableselectionintheepidemiologicalmodelingofcardiovasculardiseases AT jussikauhanen evolutionarymethodsforvariableselectionintheepidemiologicalmodelingofcardiovasculardiseases AT tomipekkatuomainen evolutionarymethodsforvariableselectionintheepidemiologicalmodelingofcardiovasculardiseases AT sarivoutilainen evolutionarymethodsforvariableselectionintheepidemiologicalmodelingofcardiovasculardiseases AT maunoronkko evolutionarymethodsforvariableselectionintheepidemiologicalmodelingofcardiovasculardiseases AT kimmoronkainen evolutionarymethodsforvariableselectionintheepidemiologicalmodelingofcardiovasculardiseases AT eugenesemenkin evolutionarymethodsforvariableselectionintheepidemiologicalmodelingofcardiovasculardiseases AT mikkokolehmainen evolutionarymethodsforvariableselectionintheepidemiologicalmodelingofcardiovasculardiseases |