Predicting child mortality determinants in Uttar Pradesh using Machine Learning: Insights from the National Family and Health Survey (2019–21)
Aim: This study aimed to delineate spatial variations in under-five mortality across Uttar Pradesh and evaluate the efficacy of various machine learning algorithms in identifying critical determinants influencing these mortality rates. Methods: The study utilized data from the National Family and He...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Clinical Epidemiology and Global Health |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2213398425000387 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861210799407104 |
|---|---|
| author | Pinky Pandey Sacheendra Shukla Niraj Kumar Singh Mukesh Kumar |
| author_facet | Pinky Pandey Sacheendra Shukla Niraj Kumar Singh Mukesh Kumar |
| author_sort | Pinky Pandey |
| collection | DOAJ |
| description | Aim: This study aimed to delineate spatial variations in under-five mortality across Uttar Pradesh and evaluate the efficacy of various machine learning algorithms in identifying critical determinants influencing these mortality rates. Methods: The study utilized data from the National Family and Health Survey (NFHS) - V. Four machine learning algorithms—Random Forests, Logistic Regression, K-Nearest Neighbors (KNN), and Naive Bayes—were applied alongside a traditional logistic regression model. Predictive performance was evaluated using metrics such as model accuracy and receiver operating characteristic (ROC) curves. Descriptive analysis highlighted regional variations in under-five mortality rates. Results: Notable regional disparities in under-five mortality were observed across Uttar Pradesh. Predictive accuracies ranged from 76 % to 79.4 %, with the logistic regression model achieving the highest accuracy (79.4 %). All ML models demonstrated comparable predictive capabilities. The most effective model identified key determinants of under-five mortality, including breastfeeding status, number of births in the preceding five years, child's gender, birth intervals, antenatal care, birth order, type of water source, and maternal body mass index. Conclusion: Machine learning models provide valuable insights into the determinants of under-five mortality, with the logistic regression model demonstrating superior predictive performance. Policy measures targeting critical factors, such as promoting breastfeeding, optimizing birth intervals, and improving maternal health and antenatal care, can significantly enhance childhood survival rates in Uttar Pradesh. |
| format | Article |
| id | doaj-art-c4a67da46b8c456eb125d27cecd4ea01 |
| institution | Kabale University |
| issn | 2213-3984 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Clinical Epidemiology and Global Health |
| spelling | doaj-art-c4a67da46b8c456eb125d27cecd4ea012025-02-10T04:34:22ZengElsevierClinical Epidemiology and Global Health2213-39842025-03-0132101949Predicting child mortality determinants in Uttar Pradesh using Machine Learning: Insights from the National Family and Health Survey (2019–21)Pinky Pandey0Sacheendra Shukla1Niraj Kumar Singh2Mukesh Kumar3Department of Statistics, Amity Institute of Applied Sciences, AUUP, India; Corresponding author.Department of Statistics, Amity Institute of Applied Sciences, AUUP, IndiaDepartment of Statistics, Amity Institute of Applied Sciences, AUUP, IndiaDepartment of Statistics, Lucknow University, IndiaAim: This study aimed to delineate spatial variations in under-five mortality across Uttar Pradesh and evaluate the efficacy of various machine learning algorithms in identifying critical determinants influencing these mortality rates. Methods: The study utilized data from the National Family and Health Survey (NFHS) - V. Four machine learning algorithms—Random Forests, Logistic Regression, K-Nearest Neighbors (KNN), and Naive Bayes—were applied alongside a traditional logistic regression model. Predictive performance was evaluated using metrics such as model accuracy and receiver operating characteristic (ROC) curves. Descriptive analysis highlighted regional variations in under-five mortality rates. Results: Notable regional disparities in under-five mortality were observed across Uttar Pradesh. Predictive accuracies ranged from 76 % to 79.4 %, with the logistic regression model achieving the highest accuracy (79.4 %). All ML models demonstrated comparable predictive capabilities. The most effective model identified key determinants of under-five mortality, including breastfeeding status, number of births in the preceding five years, child's gender, birth intervals, antenatal care, birth order, type of water source, and maternal body mass index. Conclusion: Machine learning models provide valuable insights into the determinants of under-five mortality, with the logistic regression model demonstrating superior predictive performance. Policy measures targeting critical factors, such as promoting breastfeeding, optimizing birth intervals, and improving maternal health and antenatal care, can significantly enhance childhood survival rates in Uttar Pradesh.http://www.sciencedirect.com/science/article/pii/S2213398425000387Under-five mortalityMachine LearningKNNRandom ForestROC curve |
| spellingShingle | Pinky Pandey Sacheendra Shukla Niraj Kumar Singh Mukesh Kumar Predicting child mortality determinants in Uttar Pradesh using Machine Learning: Insights from the National Family and Health Survey (2019–21) Clinical Epidemiology and Global Health Under-five mortality Machine Learning KNN Random Forest ROC curve |
| title | Predicting child mortality determinants in Uttar Pradesh using Machine Learning: Insights from the National Family and Health Survey (2019–21) |
| title_full | Predicting child mortality determinants in Uttar Pradesh using Machine Learning: Insights from the National Family and Health Survey (2019–21) |
| title_fullStr | Predicting child mortality determinants in Uttar Pradesh using Machine Learning: Insights from the National Family and Health Survey (2019–21) |
| title_full_unstemmed | Predicting child mortality determinants in Uttar Pradesh using Machine Learning: Insights from the National Family and Health Survey (2019–21) |
| title_short | Predicting child mortality determinants in Uttar Pradesh using Machine Learning: Insights from the National Family and Health Survey (2019–21) |
| title_sort | predicting child mortality determinants in uttar pradesh using machine learning insights from the national family and health survey 2019 21 |
| topic | Under-five mortality Machine Learning KNN Random Forest ROC curve |
| url | http://www.sciencedirect.com/science/article/pii/S2213398425000387 |
| work_keys_str_mv | AT pinkypandey predictingchildmortalitydeterminantsinuttarpradeshusingmachinelearninginsightsfromthenationalfamilyandhealthsurvey201921 AT sacheendrashukla predictingchildmortalitydeterminantsinuttarpradeshusingmachinelearninginsightsfromthenationalfamilyandhealthsurvey201921 AT nirajkumarsingh predictingchildmortalitydeterminantsinuttarpradeshusingmachinelearninginsightsfromthenationalfamilyandhealthsurvey201921 AT mukeshkumar predictingchildmortalitydeterminantsinuttarpradeshusingmachinelearninginsightsfromthenationalfamilyandhealthsurvey201921 |