Determinants of Cesarean Section among Primiparas: A Comparison of Classification Methods
Background: Over the last few decades, Cesarean section (CS) rates have increased significantly worldwide particularly in Iran. Classification methods including logistic regression (LR), random forest (RF) and artificial neural network (ANN) were used to identify factors related to CS among primipar...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tehran University of Medical Sciences
2018-12-01
|
| Series: | Iranian Journal of Public Health |
| Subjects: | |
| Online Access: | https://ijph.tums.ac.ir/index.php/ijph/article/view/15520 |
| _version_ | 1818878516062584832 |
|---|---|
| author | Saman MAROUFIZADEH Payam AMINI Mostafa HOSSEINI Amir ALMASI-HASHIANI Maryam MOHAMMADI Behnaz NAVID Reza OMANI-SAMANI |
| author_facet | Saman MAROUFIZADEH Payam AMINI Mostafa HOSSEINI Amir ALMASI-HASHIANI Maryam MOHAMMADI Behnaz NAVID Reza OMANI-SAMANI |
| author_sort | Saman MAROUFIZADEH |
| collection | DOAJ |
| description | Background: Over the last few decades, Cesarean section (CS) rates have increased significantly worldwide particularly in Iran. Classification methods including logistic regression (LR), random forest (RF) and artificial neural network (ANN) were used to identify factors related to CS among primipars.
Methods: This cross-sectional study included 2120 primipars who gave singleton birth in Tehran, Iran between 6 and 21 July 2015. To identify factor associated with CS, the classification methods were compared in terms of sensitivity, specificity, and accuracy.
Results: The CS rate was 72.1%. Mother’s age, SES, BMI, baby’s head circumference and infant weight were the most important determinant variables for CS as identified by the ANN method which had the highest accuracy (0.70). The association of RF predictions and observed values was 0.36 (kappa).
Conclusion: The ANN method had the best performance that classified CS delivery compared to the RF and LR methods. The ANN method might be used as an appropriate method for such data. |
| first_indexed | 2024-12-19T14:15:25Z |
| format | Article |
| id | doaj.art-f12ba3e855794bbf9ee2d766bca924ea |
| institution | Directory Open Access Journal |
| issn | 2251-6085 2251-6093 |
| language | English |
| last_indexed | 2024-12-19T14:15:25Z |
| publishDate | 2018-12-01 |
| publisher | Tehran University of Medical Sciences |
| record_format | Article |
| series | Iranian Journal of Public Health |
| spelling | doaj.art-f12ba3e855794bbf9ee2d766bca924ea2022-12-21T20:18:00ZengTehran University of Medical SciencesIranian Journal of Public Health2251-60852251-60932018-12-014712Determinants of Cesarean Section among Primiparas: A Comparison of Classification MethodsSaman MAROUFIZADEH0Payam AMINI1Mostafa HOSSEINI2Amir ALMASI-HASHIANI3Maryam MOHAMMADI4Behnaz NAVID5Reza OMANI-SAMANI6Department of Epidemiology and Reproductive Health, Reproductive Epidemiology Research Center, Royan Institute for Reproductive Biomedicine, ACECR, Tehran, IranDepartment of Epidemiology and Reproductive Health, Reproductive Epidemiology Research Center, Royan Institute for Reproductive Biomedicine, ACECR, Tehran, IranDepartment of Epidemiology and Biostatistics, School of Public Health, Tehran University of Medical Sciences, Tehran, IranDepartment of Epidemiology and Reproductive Health, Reproductive Epidemiology Research Center, Royan Institute for Reproductive Biomedicine, ACECR, Tehran, IranDepartment of Epidemiology and Reproductive Health, Reproductive Epidemiology Research Center, Royan Institute for Reproductive Biomedicine, ACECR, Tehran, IranDepartment of Epidemiology and Reproductive Health, Reproductive Epidemiology Research Center, Royan Institute for Reproductive Biomedicine, ACECR, Tehran, IranDepartment of Epidemiology and Reproductive Health, Reproductive Epidemiology Research Center, Royan Institute for Reproductive Biomedicine, ACECR, Tehran, IranBackground: Over the last few decades, Cesarean section (CS) rates have increased significantly worldwide particularly in Iran. Classification methods including logistic regression (LR), random forest (RF) and artificial neural network (ANN) were used to identify factors related to CS among primipars. Methods: This cross-sectional study included 2120 primipars who gave singleton birth in Tehran, Iran between 6 and 21 July 2015. To identify factor associated with CS, the classification methods were compared in terms of sensitivity, specificity, and accuracy. Results: The CS rate was 72.1%. Mother’s age, SES, BMI, baby’s head circumference and infant weight were the most important determinant variables for CS as identified by the ANN method which had the highest accuracy (0.70). The association of RF predictions and observed values was 0.36 (kappa). Conclusion: The ANN method had the best performance that classified CS delivery compared to the RF and LR methods. The ANN method might be used as an appropriate method for such data.https://ijph.tums.ac.ir/index.php/ijph/article/view/15520Cesarean sectionPrimiparasArtificial neural networkRandom forestLogistic regressionClassification |
| spellingShingle | Saman MAROUFIZADEH Payam AMINI Mostafa HOSSEINI Amir ALMASI-HASHIANI Maryam MOHAMMADI Behnaz NAVID Reza OMANI-SAMANI Determinants of Cesarean Section among Primiparas: A Comparison of Classification Methods Iranian Journal of Public Health Cesarean section Primiparas Artificial neural network Random forest Logistic regression Classification |
| title | Determinants of Cesarean Section among Primiparas: A Comparison of Classification Methods |
| title_full | Determinants of Cesarean Section among Primiparas: A Comparison of Classification Methods |
| title_fullStr | Determinants of Cesarean Section among Primiparas: A Comparison of Classification Methods |
| title_full_unstemmed | Determinants of Cesarean Section among Primiparas: A Comparison of Classification Methods |
| title_short | Determinants of Cesarean Section among Primiparas: A Comparison of Classification Methods |
| title_sort | determinants of cesarean section among primiparas a comparison of classification methods |
| topic | Cesarean section Primiparas Artificial neural network Random forest Logistic regression Classification |
| url | https://ijph.tums.ac.ir/index.php/ijph/article/view/15520 |
| work_keys_str_mv | AT samanmaroufizadeh determinantsofcesareansectionamongprimiparasacomparisonofclassificationmethods AT payamamini determinantsofcesareansectionamongprimiparasacomparisonofclassificationmethods AT mostafahosseini determinantsofcesareansectionamongprimiparasacomparisonofclassificationmethods AT amiralmasihashiani determinantsofcesareansectionamongprimiparasacomparisonofclassificationmethods AT maryammohammadi determinantsofcesareansectionamongprimiparasacomparisonofclassificationmethods AT behnaznavid determinantsofcesareansectionamongprimiparasacomparisonofclassificationmethods AT rezaomanisamani determinantsofcesareansectionamongprimiparasacomparisonofclassificationmethods |