Predicting the Risk of Preeclampsia using Soft Voting-based Ensemble and Its Recommendation

Preeclampsia is one of the leading causes of maternal deaths and pregnancy-related complications in many low-income countries. Factors related to preeclampsia include lack of prenatal care and access to medical services, lack of facilities, and inadequate diagnosis and treatment of preeclampsia patients. Early detection and prompt treatment of preeclampsia are essential for the prevention of eclampsia and other life-threatening complications. Several studies have developed the risk prediction models for preeclampsia using mobile applications and machine learning techniques. The use of a soft voting-based ensemble method and recommendation system for women at high risk of preeclampsia remains unexplored. We developed a mobile application with two functionalities of preeclampsia prediction and recommendation system for women at high risk of preeclampsia. We employed the soft voting ensemble learning for the preeclampsia prediction. We obtained a high accuracy value of 98.51% ± 0.0186% compared to the six individual classifiers (k-Nearest Neighbors, Linear SVM, RBF SVM, Gaussian Process, Multi-Layer Perceptron, and Ada Boost). Our proposed recommender system also yielded in a high accuracy value of 96.66% ± 0.0229%. Both our proposed ensemble based on soft-voting and recommendation system had small variance values, which indicated high stability.

[1]  Iwan Syarif,et al.  Predicting The Risk of Preeclampsia with History of Hypertension Using Logistic Regression and Naive Bayes , 2018, 2018 International Conference on Applied Science and Technology (iCAST).

[2]  R Ganapathy,et al.  Remote monitoring of blood pressure to reduce the risk of preeclampsia related complications with an innovative use of mobile technology. , 2016, Pregnancy hypertension.

[3]  Christos Schizas,et al.  Neural networks to estimate the risk for preeclampsia occurrence , 2009, 2009 International Joint Conference on Neural Networks.

[4]  Octavio Rivera-Romero,et al.  Mobile Health Solutions for Hypertensive Disorders in Pregnancy: Scoping Literature Review , 2018, JMIR mHealth and uHealth.

[5]  David J. Fleet,et al.  Gaussian Process Dynamical Models , 2005, NIPS.

[6]  Iwan Syarif,et al.  Neural Networks Algorithm to Inquire Previous Preeclampsia Factors in Women with Chronic Hypertension During Pregnancy in Childbirth Process , 2018, 2018 International Electronics Symposium on Knowledge Creation and Intelligent Computing (IES-KCIC).

[7]  Iuliana Marin,et al.  Security of an Electronic Heal Thcare System which Facilitates the Detection of Preeclampsia Through a Smart Bracelet , 2018, 2018 10th International Conference on Electronics, Computers and Artificial Intelligence (ECAI).

[8]  Janet Moore,et al.  A prospective study of maternal, fetal and neonatal deaths in low- and middle-income countries. , 2014, Bulletin of the World Health Organization.

[9]  Patricio Encalada,et al.  Electronic System for Detection and Control of Preeclampsia in Pregnant Women , 2019, 2019 Sixth International Conference on eDemocracy & eGovernment (ICEDEG).

[10]  Thanh Cong Bui,et al.  Predictive value of the sFlt-1 and PlGF in women at risk for preeclampsia in the south of Vietnam. , 2018, Pregnancy hypertension.

[11]  A. Baschat,et al.  First‐trimester screening for pre‐eclampsia: moving from personalized risk prediction to prevention , 2015, Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology.

[12]  Geoffrey Muchiri Muketha,et al.  A 24-hour ambulatory blood pressure monitoring system for preeclampsia management in antenatal care , 2019, Informatics in Medicine Unlocked.

[13]  P. Konar,et al.  Bearing fault detection of induction motor using wavelet and Support Vector Machines (SVMs) , 2011, Appl. Soft Comput..

[14]  Iuliana Marin,et al.  Early Detection of Preeclampsia based on a Machine Learning Approach , 2019, 2019 E-Health and Bioengineering Conference (EHB).

[15]  Hemant D. Tagare,et al.  An algorithm to screen for preeclampsia using a smart phone , 2014, 2014 IEEE Healthcare Innovation Conference (HIC).

[16]  Andrea Montanari,et al.  Early prediction of preeclampsia via machine learning. , 2020, American journal of obstetrics & gynecology MFM.

[17]  Pasquale Lops,et al.  Introducing Serendipity in a Content-Based Recommender System , 2008, 2008 Eighth International Conference on Hybrid Intelligent Systems.

[18]  Yuliya A. Zhivolupova.  Remote Monitoring System for Preeclampsia Detection and Control , 2019, 2019 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus).

[19]  Elena Carreras,et al.  A new model for screening for early-onset preeclampsia. , 2020, American journal of obstetrics and gynecology.

[20]  Ying Cao,et al.  Advance and Prospects of AdaBoost Algorithm , 2013, ACTA AUTOMATICA SINICA.

[21]  Guy Albert Dumont,et al.  Development of mHealth Applications for Pre-Eclampsia Triage , 2014, IEEE Journal of Biomedical and Health Informatics.

[22]  D. Wright,et al.  Predictive performance of the competing risk model in screening for preeclampsia , 2019, American journal of obstetrics and gynecology.

[23]  Noam Shomron,et al.  Early Detection of Preeclampsia Using Circulating Small non-coding RNA , 2018, Scientific Reports.

[24]  D. Wright,et al.  Two‐stage screening for preterm preeclampsia at 11–13 weeks’ gestation , 2019, American journal of obstetrics and gynecology.

[25]  Kypros H. Nicolaides,et al.  Chronic hypertension: first‐trimester blood pressure control and likelihood of severe hypertension, preeclampsia, and small for gestational age , 2018, American journal of obstetrics and gynecology.

[26]  J. Repke,et al.  Preeclampsia: Short-term and Long-term Implications. , 2015, Obstetrics and gynecology clinics of North America.

[27]  A. Papageorghiou,et al.  Early-Pregnancy Multiple Serum Markers and Second-Trimester Uterine Artery Doppler in Predicting Preeclampsia , 2010, Obstetrics and gynecology.

[28]  Kleanthis Neokleous,et al.  Neural networks to investigate the effects of smoking and alcohol abuse on the risk for preeclampsia , 2009, 2009 9th International Conference on Information Technology and Applications in Biomedicine.

[29]  Joel J. P. C. Rodrigues,et al.  A preeclampsia diagnosis approach using Bayesian networks , 2016, 2016 IEEE International Conference on Communications (ICC).

[30]  Belinda Jim,et al.  Preeclampsia: Updates in Pathogenesis, Definitions, and Guidelines. , 2016, Clinical journal of the American Society of Nephrology : CJASN.

[31]  Andrew H. Shennan,et al.  Recent advances in the diagnosis and management of pre-eclampsia , 2015, F1000prime reports.

[32]  Surya Cheemalapati,et al.  mHealth dipstick analyzer for monitoring of pregnancy complications , 2016, 2016 IEEE SENSORS.

[33]  C. Dolea,et al.  World Health Organization , 1949, International Organization.

[34]  T. Murlidharan Nair,et al.  Statistical and artificial neural network-based analysis to understand complexity and heterogeneity in preeclampsia , 2018, Comput. Biol. Chem..

[35]  D. Wlody,et al.  Hypertension in pregnancy. , 1992, The New England journal of medicine.