Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Predicting low birth weight in Bangladesh using interpretable machine learning models.

Samrat Kumar Dev Sharma¹, Md Yusuf Hossain Ador², Md Rukonuzzaman²

¹Department of Statistics, Jagannath University, Dhaka, 1100, Bangladesh. samrat.sdev@gmail.com.

BMC Pregnancy and Childbirth

|May 27, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Regression Toward the Mean

Regression Toward the Mean

Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when researchers try to extrapolate results...

Steps in Outbreak Investigation

Steps in Outbreak Investigation

In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Outcome of Correction of Adolescent Idiopathic Scoliosis by the Axial Translational Technique With a Pedicle-Screw-and-Rod Construct.

Cureus·2026

Same author

Role of oligopeptides as co-formers in stabilizing amorphous dipyridamole: mechanistic insights using molecular docking simulations.

International journal of pharmaceutics·2026

Same author

Distribution, source, and risk analysis of PAHs and trace elements in roadside soils of Dhaka-Bhanga expressway: a case study.

Environmental monitoring and assessment·2026

Same author

Microbial Safety and Antimicrobial Resistance Patterns of Popular Street Foods in Gopalganj, Bangladesh.

Journal of food protection·2026

Same author

Evaluation of a disability-inclusive ultra-poor graduation programme in Bangladesh: study protocol for a cluster-randomised controlled trial.

Trials·2026

Same author

Parametric hypothesis testing for pathway based hierarchical structural component models.

Genes & genomics·2026

Same journal

Uterine cystic adenomyoma arising from cesarean scar diverticulum: a case report and literature review.

BMC pregnancy and childbirth·2026

Same journal

A core outcome measurement set for hyperemesis gravidarum research: a consensus study.

BMC pregnancy and childbirth·2026

Same journal

Development and validation of machine learning models for obstructive sleep apnea risk stratification in high-risk pregnant women.

BMC pregnancy and childbirth·2026

Same journal

The acceptability and feasibility of a randomised controlled trial of serial prophylactic exchange blood transfusion versus usual care in pregnant women with sickle cell disease: a qualitative study.

BMC pregnancy and childbirth·2026

Same journal

Mesh closure of a protruding caesarean scar pregnancy in the 11th week of pregnancy.

BMC pregnancy and childbirth·2026

Same journal

Effects of perinatal depression on early breastfeeding: the role of childbirth experience.

BMC pregnancy and childbirth·2026

See all related articles

This study developed machine learning models to predict low birth weight (LBW) in Bangladesh. XGBoost showed strong performance, identifying key risk factors like geography and paternal education for targeted interventions.

Area of Science:

Public Health
Machine Learning
Biostatistics

Background:

Low birth weight (LBW) is a major cause of neonatal mortality in low- and middle-income countries.
Predictive modeling using machine learning can aid in identifying at-risk infants.

Purpose of the Study:

To develop and evaluate machine learning classifiers for predicting LBW using Bangladesh Demographic and Health Survey data.
To distinguish predictive modeling from causal inference in LBW risk assessment.

Main Methods:

Analysis of 3,400 mother-child pairs from the 2022 Bangladesh Demographic and Health Survey.
Utilized survey weights, stratification, and clustering with class-weight optimization for imbalanced data.
Evaluated seven machine learning classifiers using cluster-aware splits and assessed performance with discrimination and calibration metrics.

Keywords:

Bangladesh Demographic and Health Survey Machine learning Predictive modeling SHAP XGBoost

Related Experiment Videos

Main Results:

XGBoost achieved the best performance (AUROC=0.828) for LBW prediction.
Key predictors identified by SHAP analysis include geographical division, birth order, paternal education, and household wealth.
Interpretable ML models highlight potential interactions influencing LBW risk.

Conclusions:

Survey-aware machine learning, specifically XGBoost, offers a robust framework for LBW risk stratification in Bangladesh.
Interpretable ML models can inform targeted maternal health interventions, though external validation is needed.
Future research should focus on prospective validation and integrating clinical biomarkers for enhanced prediction.