The use of Machine Learning to predict adverse birth outcomes: Empirical real world evidence from a human cohort study in Adama, Ethiopia
(2023) BMEM01 20222Department of Biomedical Engineering
- Abstract
- Since Ethiopia has a high number of recorded adverse birth outcomes, the city of Adama was subjected to a study (Flanagan et al., 2022) that gathered data from 2085 pregnancies. This thesis utilizes that data to investigate the usage of machine learning in environmental epidemiology. Using the classification methods logistic regression, random forest, support vector classifier, and k-nearest neighbors, two different sampling methods were implemented to handle the imbalanced dataset. The original imbalanced dataset performed worst though similar to the undersampled dataset. Oversampling the dataset with SMOTE yielded the best result with the random forest classifier and had an AUC score of 0.72 and an f1-score of 0.85. With further work,... (More)
- Since Ethiopia has a high number of recorded adverse birth outcomes, the city of Adama was subjected to a study (Flanagan et al., 2022) that gathered data from 2085 pregnancies. This thesis utilizes that data to investigate the usage of machine learning in environmental epidemiology. Using the classification methods logistic regression, random forest, support vector classifier, and k-nearest neighbors, two different sampling methods were implemented to handle the imbalanced dataset. The original imbalanced dataset performed worst though similar to the undersampled dataset. Oversampling the dataset with SMOTE yielded the best result with the random forest classifier and had an AUC score of 0.72 and an f1-score of 0.85. With further work, more data, and higher evaluation scores, machine learning may be a way to implement preventable medicine in Adama, Ethiopia. However, more research is needed, especially with larger study populations, to improve the accuracy of these models and find the most important features to analyze for this region. (Less)
- Popular Abstract
- Predicting adverse birth outcomes with machine learning in Ethiopia.
The number of adverse birth outcomes has long been a problem in Sub-Saharan Africa. Most of these cases are mainly preventable, however, 84% of all stillbirths around the world still occur in this region. The technology of machine learning has now emerged as an alternative to understanding the connections between environmental factors and adverse birth outcomes. Hopefully, this can help us find the key factors of the region and prevent future cases of stillbirth and neonatal death.
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9107476
- author
- Bol, Stephanie LU
- supervisor
-
- Anna Oudin LU
- Andreas Jakobsson LU
- organization
- alternative title
- Användningen av maskininlärning för att förutsäga dödfödsel och neonatal död i Adama, Etiopien
- course
- BMEM01 20222
- year
- 2023
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- Machine Learning, Adverse birth outcomes, Stillbirth, Neonatal death, Adama, Ethiopia, Oversampling, Undersampling, Random Forest
- language
- English
- additional info
- 2023-03
- id
- 9107476
- date added to LUP
- 2023-02-17 15:44:36
- date last changed
- 2023-02-20 09:02:28
@misc{9107476, abstract = {{Since Ethiopia has a high number of recorded adverse birth outcomes, the city of Adama was subjected to a study (Flanagan et al., 2022) that gathered data from 2085 pregnancies. This thesis utilizes that data to investigate the usage of machine learning in environmental epidemiology. Using the classification methods logistic regression, random forest, support vector classifier, and k-nearest neighbors, two different sampling methods were implemented to handle the imbalanced dataset. The original imbalanced dataset performed worst though similar to the undersampled dataset. Oversampling the dataset with SMOTE yielded the best result with the random forest classifier and had an AUC score of 0.72 and an f1-score of 0.85. With further work, more data, and higher evaluation scores, machine learning may be a way to implement preventable medicine in Adama, Ethiopia. However, more research is needed, especially with larger study populations, to improve the accuracy of these models and find the most important features to analyze for this region.}}, author = {{Bol, Stephanie}}, language = {{eng}}, note = {{Student Paper}}, title = {{The use of Machine Learning to predict adverse birth outcomes: Empirical real world evidence from a human cohort study in Adama, Ethiopia}}, year = {{2023}}, }