Prediction of Breast Cancer Survival by Machine Learning Methods: An Application of Multiple Imputation
Background: The low breast cancer survival rates in less developed countries are critical. The machine learning techniques predict cancers survival with high accuracy. Missing data are the most important limitation for using the highest potential of these techniques to predict cancers survival. Mult...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tehran University of Medical Sciences
2021-02-01
|
| Series: | Iranian Journal of Public Health |
| Subjects: | |
| Online Access: | https://ijph.tums.ac.ir/index.php/ijph/article/view/16101 |
| _version_ | 1818777913705627648 |
|---|---|
| author | Hadi Lotfnezhad Afshar Nasrollah JABBARI Hamid Reza KHALKHALI Omid ESNAASHARI |
| author_facet | Hadi Lotfnezhad Afshar Nasrollah JABBARI Hamid Reza KHALKHALI Omid ESNAASHARI |
| author_sort | Hadi Lotfnezhad Afshar |
| collection | DOAJ |
| description | Background: The low breast cancer survival rates in less developed countries are critical. The machine learning techniques predict cancers survival with high accuracy. Missing data are the most important limitation for using the highest potential of these techniques to predict cancers survival. Multiple imputation (MI) was implemented and analyzed in detail to impute the missing data of a breast cancer dataset.
Methods: The dataset was from The Omid Treatment and Research Center Urmia, Iran between Jan 2006 and Dec 2012 and had information from 856 women. The algorithms such as C5 and repeated incremental pruning to produce error reduction were applied on the imputed versions of the original dataset and the non-imputed dataset to predict and extract clinical rules, respectively.
Results: The findings showed the performance of C5 in all the evaluation criteria including accuracy (84.42%), sensitivity (92.21%), specificity (64%), Kappa statistic (59.06%), and the area under the receiver operator characteristic (ROC) curve (0.84), was improved after imputation.
Conclusion: The dataset of the present study met the requirements for using the multiple imputation method. The extracted rules after the application of MI were more comprehensive and contained knowledge that is more clinical. However, the clinical value of the extracted rules after filling in the missing data did not noticeably increase. |
| first_indexed | 2024-12-18T11:36:23Z |
| format | Article |
| id | doaj.art-7aea0784e0734eca8109974c23778cea |
| institution | Directory Open Access Journal |
| issn | 2251-6085 2251-6093 |
| language | English |
| last_indexed | 2024-12-18T11:36:23Z |
| publishDate | 2021-02-01 |
| publisher | Tehran University of Medical Sciences |
| record_format | Article |
| series | Iranian Journal of Public Health |
| spelling | doaj.art-7aea0784e0734eca8109974c23778cea2022-12-21T21:09:30ZengTehran University of Medical SciencesIranian Journal of Public Health2251-60852251-60932021-02-0150310.18502/ijph.v50i3.5606Prediction of Breast Cancer Survival by Machine Learning Methods: An Application of Multiple ImputationHadi Lotfnezhad Afshar0Nasrollah JABBARI1Hamid Reza KHALKHALI2Omid ESNAASHARI3Department of Health Information Technology, School of Paramedical, Urmia University of Medical Sciences, Urmia, IranDepartment of Medical Physics, Solid Tumor Research Center, School of Paramedical, Urmia University of Medical Sciences, Ur-mia, IranDepartment of Biostatistics and Epidemiology, Patient Safety Research Center, School of Medicine, Urmia University of Medical Sciences, Urmia, IranOmid Treatment and Research Center, Urmia, IranBackground: The low breast cancer survival rates in less developed countries are critical. The machine learning techniques predict cancers survival with high accuracy. Missing data are the most important limitation for using the highest potential of these techniques to predict cancers survival. Multiple imputation (MI) was implemented and analyzed in detail to impute the missing data of a breast cancer dataset. Methods: The dataset was from The Omid Treatment and Research Center Urmia, Iran between Jan 2006 and Dec 2012 and had information from 856 women. The algorithms such as C5 and repeated incremental pruning to produce error reduction were applied on the imputed versions of the original dataset and the non-imputed dataset to predict and extract clinical rules, respectively. Results: The findings showed the performance of C5 in all the evaluation criteria including accuracy (84.42%), sensitivity (92.21%), specificity (64%), Kappa statistic (59.06%), and the area under the receiver operator characteristic (ROC) curve (0.84), was improved after imputation. Conclusion: The dataset of the present study met the requirements for using the multiple imputation method. The extracted rules after the application of MI were more comprehensive and contained knowledge that is more clinical. However, the clinical value of the extracted rules after filling in the missing data did not noticeably increase.https://ijph.tums.ac.ir/index.php/ijph/article/view/16101Breast neoplasmsSurvivalObserver variationImputationMachine learning |
| spellingShingle | Hadi Lotfnezhad Afshar Nasrollah JABBARI Hamid Reza KHALKHALI Omid ESNAASHARI Prediction of Breast Cancer Survival by Machine Learning Methods: An Application of Multiple Imputation Iranian Journal of Public Health Breast neoplasms Survival Observer variation Imputation Machine learning |
| title | Prediction of Breast Cancer Survival by Machine Learning Methods: An Application of Multiple Imputation |
| title_full | Prediction of Breast Cancer Survival by Machine Learning Methods: An Application of Multiple Imputation |
| title_fullStr | Prediction of Breast Cancer Survival by Machine Learning Methods: An Application of Multiple Imputation |
| title_full_unstemmed | Prediction of Breast Cancer Survival by Machine Learning Methods: An Application of Multiple Imputation |
| title_short | Prediction of Breast Cancer Survival by Machine Learning Methods: An Application of Multiple Imputation |
| title_sort | prediction of breast cancer survival by machine learning methods an application of multiple imputation |
| topic | Breast neoplasms Survival Observer variation Imputation Machine learning |
| url | https://ijph.tums.ac.ir/index.php/ijph/article/view/16101 |
| work_keys_str_mv | AT hadilotfnezhadafshar predictionofbreastcancersurvivalbymachinelearningmethodsanapplicationofmultipleimputation AT nasrollahjabbari predictionofbreastcancersurvivalbymachinelearningmethodsanapplicationofmultipleimputation AT hamidrezakhalkhali predictionofbreastcancersurvivalbymachinelearningmethodsanapplicationofmultipleimputation AT omidesnaashari predictionofbreastcancersurvivalbymachinelearningmethodsanapplicationofmultipleimputation |