Model Performance Results for Skilled Birth Attendant Prediction in Bangladesh

An Artificial Neural Network model achieved the highest AUC score of 0.81 in predicting the use of Skilled Birth Attendants in Bangladesh. This 5.5 KB dataset, authored by Rafayet Rahman Ridoy and last updated in May 2026, contains results from a study that applied multilevel logistic regression and machine learning to analyze socioeconomic determinants of maternal healthcare. The study identified wealth, education, and antenatal care as key predictors and revealed regional disparities favoring urban areas like Dhaka and Khulna.

Use Cases

• Benchmarking machine learning model performance based on reported metrics like AUC, accuracy, and F1 score.
• Analyzing socioeconomic determinants of healthcare access based on features like wealth index and education level mentioned in the description.
• Studying regional disparities in maternal health service utilization across divisions like Dhaka, Khulna, Mymensingh, and Sylhet.
• Applying SHAP analysis for model interpretability on healthcare prediction tasks.

Strengths

• Includes performance metrics for multiple machine learning models, with a top AUC score of 0.81.
• Applies advanced analytical methods including multilevel regression, inequality decomposition, and interpretable ML (SHAP).
• Released under a permissive CC-BY-4.0 license.
• Dataset has a specific last update timestamp: 2026-05-07 17:27:14.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 5.5 KB, indicating limited scope, likely containing only summary results.

Provenance

Source

figshare

Collection Method

Results from a study applying statistical and machine learning methods to survey or health records data.

Time Range

null

Freshness

Last updated 2026-05-07 17:27:14; freshness should be verified.

Geography

Bangladesh, with mentions of specific divisions (Khulna, Dhaka, Mymensingh, Sylhet) and urban/rural areas.