English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Although the neonatal mortality rate has been diminished over time in Bangladesh, the rate is still very high. The day of birth is the most vulnerable period for newborns. This study assessed to predict and detect associated risk predictors of the first-day neonatal mortality through Machine Learning (ML) algorithm. We investigated the potential risk factors on the information collected from 43,772 evermarried women of different backgrounds extracted from the 2014 Bangladesh Demographic and Health Survey (BDHS). Based on this demographic and socio-economic risk factors, our goal is to predict the prevalence of first-day neonatal mortality in Bangladesh. Analysis was done using different ML algorithms. Boruta algorithm and Support Vector Machine (SVM) were used to extract the relevant risk factors of the first-day neonatal mortality. Prediction of the prevalence of the first-day neonatal mortality was executed using Decision Tree (DT), Random Forest (RF), SVM, and Logistic Regression (LR), and their performances were appraised using different parameters of confusion matrix, Receiver Operating Characteristics (ROC) curves, and k-fold cross-validation techniques. About two-thirds of the firstday neonatal mortality occurred in the rural area. Male children had high neonatal mortality, with a rate of 51.2%. Mother Age at 1st birth, Husband/partner’s education level, Type of cooking fuel, Total children ever born, Wealth index, Mother’s education level, Access to media, and Type of place of residence were selected as significant risk predictors for predicting the first-day neonatal mortality. Results found that the SVM with Gaussian kernel (Accuracy = 0.8358, Sensitivity = 0. 8637, Specificity = 0.3333, Precision = 0.9588, area under the ROC curve (AUC) = 0.6596, k-fold accuracy=0.8530) performed better among the four machine learning models to predict the firstday neonatal mortality in Bangladesh. Machine learning framework can detect significant predictors of the first-day neonatal mortality, therefore may help the health-policymakers, stakeholders, and family members to understand and prevent this public health problem.  Keywords: infant health; decision tree; random forest; support vector machine; feature selection; logistic regression; boruta algorithm; confusion matrix; ROC; k-fold cross-validation.

Risk predictors selection and predict for the first-day neonatal mortality in Bangladesh using machine learning techniques