This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
Research Article
Mohammad Mehdi hosseini
Islamic Azad University, Shahrood
Corresponding Author
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Purpose This study aimed to determine the relationship between maternal risk factors and stillbirth in some provinces. In the field of health, databases contain a wide range of public health variables. The purpose of this article is to explore the concepts related to data mining and its application in the field of health.
Methods This study is a case-control. The study population consisted of 3340 mothers who referred to health centers of some provinces of the country in 2016. The 1459 mothers had a history of stillbirth and 1881 of them had a live birth at the last pregnancy. Then, data mining algorithms were used to investigate the desired data.
Results Number Abortion, Mo Blood Group, Number Live Birth, Parity pregnancy, tanesh life, Mo Age ,Neonate weight, Smoking during pregnancy, Mo Educate, Number Death Neonate, Job Number, City Number, and Type Delivery Maternal risk factors are stillbirths. The accuracy of Naïve Bayes 82.71%, Logistic Regression 87.42%, Deep Learning 86.06%, Decision Tree 87%, Gradient Boosted 84.49%, Svm 86.79%.
Conclusion This study supports the hypothesis that Factors affecting stillbirth in some algorithms are somewhat identical and in others different and that different preventive and treatment strategies might be required. The overall conclusion of this study shows that Logistic Regression models and Decision Tree are the most suitable models for prediction (classification) Stillbirth mothers (among the models investigated in this study). On the most important predictors, variables NumberAboration, Paritypregnancy, taneshlife, NumberDeathNeonate, City Number are presented as the most critical predictors in this study.
Keywords
relationship, risk, health, mothers
Figure 1
Figure 2
Figure 3
Figure 4
The full text of this article is available to read as a PDF.
Loading...
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
History
CURRENT STATUS: Posted
Version 1
Posted 06 Jan, 2021
No community comments so far
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Subject Areas
Maternal & Fetal Medicine
Learn more about our company.
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Research Article
Mohammad Mehdi hosseini
Islamic Azad University, Shahrood
Corresponding Author
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
History
CURRENT STATUS: Posted
Version 1
Posted 06 Jan, 2021
No community comments so far
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Subject Areas
Maternal & Fetal Medicine
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Purpose This study aimed to determine the relationship between maternal risk factors and stillbirth in some provinces. In the field of health, databases contain a wide range of public health variables. The purpose of this article is to explore the concepts related to data mining and its application in the field of health.
Methods This study is a case-control. The study population consisted of 3340 mothers who referred to health centers of some provinces of the country in 2016. The 1459 mothers had a history of stillbirth and 1881 of them had a live birth at the last pregnancy. Then, data mining algorithms were used to investigate the desired data.
Results Number Abortion, Mo Blood Group, Number Live Birth, Parity pregnancy, tanesh life, Mo Age ,Neonate weight, Smoking during pregnancy, Mo Educate, Number Death Neonate, Job Number, City Number, and Type Delivery Maternal risk factors are stillbirths. The accuracy of Naïve Bayes 82.71%, Logistic Regression 87.42%, Deep Learning 86.06%, Decision Tree 87%, Gradient Boosted 84.49%, Svm 86.79%.
Conclusion This study supports the hypothesis that Factors affecting stillbirth in some algorithms are somewhat identical and in others different and that different preventive and treatment strategies might be required. The overall conclusion of this study shows that Logistic Regression models and Decision Tree are the most suitable models for prediction (classification) Stillbirth mothers (among the models investigated in this study). On the most important predictors, variables NumberAboration, Paritypregnancy, taneshlife, NumberDeathNeonate, City Number are presented as the most critical predictors in this study.
Figure 1
Figure 2
Figure 3
Figure 4
The full text of this article is available to read as a PDF.
Loading...