Early Risk Detection of Pre-eclampsia  for Pregnant Women Using Artificial Neural Network

Purwanti, Endah; Preswari, Ichroom Septa; Ernawati, Ernawati

doi:10.3991/ijoe.v15i02.9680

Cited by 4 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent times, electronic components are being integrated in a lot of systems to aid smart operation [1]- [4]. Several researchers have explored the potentials of electronic components to aid medical practitioners' works in terms of saving lives and preventing emergencies such as early detection of cancerous cells [5], [6], early risk detection of pre-eclampsia for pregnant women [7]- [9], type 2 diabetes [10]- [13], and cardiovascular disease [14]- [16].…”

Section: Introductionmentioning

confidence: 99%

Application of a wireless apnea monitoring device for crisis alertness and sleep diagnosis

et al. 2022

View full text Add to dashboard Cite

Over the past five decades, obstructive sleep apnea has been noted as a prevalent symptom in adults with escalated health conditions like stroke, obesity, high blood pressure, cardiovascular complications and chronic kidney diseases; to mention but a few. Apnea hypopnea index (AHI) is the average number of apnea or hypopnea events which occur during a complete sleep cycle per hour. It is a measure of determining the severity of sleep apnea, where an index range of 5 to 15 indicates mild, 15 to 30, moderate and above 30 denotes severe sleep apnea. In a bid to perform this diagnosis, several approaches have been considered. In this study vibrating sensor module and an Arduino Uno Rev3 microcontroller which retrieve breathing status data during sleep and identifies apnea events is proposed. The developed monitoring device displays the apnea count, effectively, which can be used to determine AHI. It also incorporates a Bluetooth module for wireless, real-time data monitoring which allows for more comfortable usability. The result is the successful implementation of an efficient, cost-effective system which can be used for sleep apnea diagnosis and provides preventive health care measures.

show abstract

Section: Introductionmentioning

confidence: 99%

Application of a wireless apnea monitoring device for crisis alertness and sleep diagnosis

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In research by Chu et al [11], predictions of adverse events in pregnant women were performed by using several classical ML algorithms, including Support Vector Machine (SVM), Random Forest (RF), AdaBoost, Decision Tree (DT), k-Nearest Neighbor (kNN), Multilayer Perceptron (MLP), and Naïve Bayes (NB). Following this, Purwanti, Preswari, and Ernawati [12] proposed to apply Artificial Neural Network to detect preeclampsia in pregnant women using 11 risk factors as classification features. Besides, the application of such classical ML technique was performed in [13] to predict the presence of preeclampsia by employing the Logistic Regression (LR), DT, Artificial Neural Network (ANN), RF, SVM, and Ensemble Algorithm which applied on the National Health Insurance Dataset in Indonesia.…”

Section: Introductionmentioning

confidence: 99%

Impact of Feature Selection and Data Augmentation for Pregnancy Risk Detection in Indonesia

Basuki¹,

Irfan²,

Azhar³

2022

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

This paper aims to develop an automatic system for pregnancy risk detection in Indonesia. The system requires a sophisticated approach to achieve the required performance as a sensitive field. Existing works are developed using small-sized datasets and limited classification features. Moreover, all features treated equally make the detection results hard to interpret which features contribute more. To address these issues, we propose to combine more complex features, data augmentation methods, and feature selection techniques. We prefer to use all 118 pregnancy indicators and 400 instances from Puskesmas as an original dataset. Next, the new datasets are used to build two data augmentation methods, i.e., GMM and CTGAN. Each data augmentation method generates 2,000 new synthetic instances. Following this, five machine learning methods combined with three feature selection approaches, i.e., RFE, Random Forest, and Chi-Square, are implemented in all datasets. Through experiments, we observed that feature selection techniques play an essential role in improving classification accuracies. While the GMM-based augmentation demonstrated performance improvement, the CTGAN-based synthetic dataset depicted low performances. The best accuracy on all experiment settings reached 95%. By using Random Forest combined with RFE on a GMM-based dataset, the highest accuracy was achieved using only five features. Another notable result is that both XGBoost and Decision Tree reached the same 95% accuracy on the GMM-based dataset on only nine features. The overall results show that appropriate data augmentation and feature selection are a matter for achieving better performance in this research.

show abstract

“…Blood disorders cause numerous Non-Communicable Diseases (NCDs), among which are, cardio-vascular sicknesses, malignancies, diabetes and respiratory infections [1] [3]. NCDs are responsible for 36 million deaths in the world every year, as revealed by the World Economic Forum and the Harvard School [2] [4]. The dielectric parameters of blood are of incredible significance for different restorative applications.…”

Section: Introductionmentioning

confidence: 99%

Photonic Crystal and its Application as a Biosensor for the Early Detection of Cancerous Cells

2020

View full text Add to dashboard Cite

<p>The motivation for this paper is the strikingly sad statistics, obtained from various research bodies globally, regarding the effect of cancers on the global populace and the impact of current methods put in place for the early diagnosis of cancer. This paper is novel for many reasons. Primarily, it presents the use of an optical biosensor based on photonic crystal for cancer cell detection. This biosensor was recently developed as an ultra-compact biochemical sensor based on a 2D photonic crystal cavity known for altering its spectrum in proportion to minute changes in refractive index. Secondarily, The Finite Difference Time Domain (FDTD) and Plane Wave Expansion (PWE) techniques were applied to analyze the possibility of using photonic crystals as biosensors for the detection of cancer cells. The obtained resonant wavelength from the analysis of simulated results was 1.54964 µm and transmitted power obtained from the analysis was 51.9%. For the cancerous cell sample, The PC 12 Cell, the obtained resonant wavelength from analysis of the simulated results was 1.54964 µm and the transmitted power obtained from the analysis was 55.6%.</p>

show abstract

Early Risk Detection of Pre-eclampsia for Pregnant Women Using Artificial Neural Network

Cited by 4 publications

References 3 publications

Application of a wireless apnea monitoring device for crisis alertness and sleep diagnosis

Application of a wireless apnea monitoring device for crisis alertness and sleep diagnosis

Impact of Feature Selection and Data Augmentation for Pregnancy Risk Detection in Indonesia

Photonic Crystal and its Application as a Biosensor for the Early Detection of Cancerous Cells

Contact Info

Product

Resources

About