Machine learning approach for pre-eclampsia risk factors association

Date
2018Author
Martínez Velasco, Antonieta Teodora
Martinez-Villaseñor, Lourdes
Miralles, Luis
Metadata
Show full item recordAbstract
The preeclampsia/eclampsia syndrome is a multisystem disorder that usually includes cardiovascular changes, hematologic abnormalities, hepatic and renal impairment, and neurologic or cerebral manifestations. Preeclampsia (PE) is a clinical syndrome that afflicts 3–5% of pregnancies and it is a leading cause of maternal mortality, especially in developing countries. To understand in greater depth the preeclampsia/eclampsia syndrome, we applied some well-known Machine Learning (ML) techniques. ML has been successfully applied to medical research to improve the diagnosis and the prevention of complex diseases and syndromes. In our contribution, we have created a supervised model to predict if a patient suffers the disease. This model has been optimized by selecting the best features and by optimizing the threshold when predicting a class. We used these techniques to point out the most related features of the patients to the disease. Finally, we used interpretability techniques to extract and visualize through a decision tree the most relevant associations of the disease with the patients' features. © 2018 Association for Computing Machinery.
Collections
Related items
Showing items related by title, author, creator and subject.
-
Stochastic parallel extreme artificial hydrocarbon networks : an implementation for fast and robust supervised machine learning in high-dimensional data
Ponce, Hiram; González Mora, José Guillermo (Elsevier Ltd., 2020-03)Artificial hydrocarbon networks (AHN) – a supervised learning method inspired on organic chemical structures and mechanisms – have shown improvements in predictive power and interpretability in comparison with other ... -
A method to improve speed of training algorithm in artificial hydrocarbon networks
Martinez-Villaseñor, Lourdes; Ponce, Hiram (Institute of Electrical and Electronics Engineers Inc., 2020)Artificial hydrocarbon networks (AHN) is a supervised machine learning method inspired on chemical carbon networks that simulate heuristic chemical rules involved within organic molecules to represent the structure and ... -
A methodology based on deep learning for advert value calculation in CPM, CPC and CPA networks
Miralles, Luis (Springer Verlag, 2017)In this research, we propose a methodology for advert value calculation in CPM, CPC and CPA networks. Accurately estimating this value increases the three previous networks’ incomes by selecting the most profitable advert. ...