Monthly trends, determinants, and forecasting of perinatal mortality in Ghana: a comparison of ARIMA, BPNN, DLNN, and GRNN models - Report - MDSpire

Monthly trends, determinants, and forecasting of perinatal mortality in Ghana: a comparison of ARIMA, BPNN, DLNN, and GRNN models

  • By

  • Agyei Helena Lartey

  • Denis Dekugmen Yar

  • Ama Asamaniwa Attua

  • Godfred Nyanney

  • Akuffo Samuel Tete Manukure

  • Isaac Takyi Boahen

  • Theophilus Oduro Kankam

  • Collins Mawuli Bakudie

  • July 10, 2026

  • 0 min

Share

Clinical Report: Analysis of Monthly Patterns of Perinatal Mortality in Ghana

Overview

This study analyzes perinatal mortality rates in Ghana, revealing a PMR of 24.98 per 1,000 births.

Background

Perinatal mortality is a significant public health concern, reflecting the quality of maternal and newborn care. In Ghana, the perinatal mortality rate remains high, contributing to under-5 mortality.

Data Highlights

MetricValue
Overall PMR24.98 per 1,000 births
Live births46,108
Perinatal deaths1,152
Best ARIMA model RMSE11.74
BPNN RMSE14.98
DLNN RMSE12.87
GRNN RMSE13.33

Key Findings

  • The overall perinatal mortality rate in the study was 24.98 per 1,000 births.
  • The best-performing forecasting model was ARIMA (3, 0, 0).
  • The first-differenced PMR series was stationary.

Clinical Implications

Improving antenatal care coverage may help reduce perinatal mortality rates. Healthcare providers should focus on managing hypertensive disorders during pregnancy to enhance maternal and neonatal outcomes.

Conclusion

ARIMA models provide valuable forecasting capabilities for healthcare planning.

Related Resources & Content

  1. Frontiers in Reproductive Health, 2026 -- Trends and inequalities in health facility deliveries among women of reproductive age in Ghana, 1993–2022
  2. BMJ Paediatrics Open, 2026 -- Development of a prediction model for infant hospitalisation and death using clinical features assessed by community health workers during routine postnatal home visits in Dhaka, Bangladesh
  3. BMC Pregnancy and Childbirth, 2026 -- Prediction of low 5-minute Apgar scores: development and internal validation of parity-stratified clinical prediction models for sub-Saharan Africa
  4. Frontiers in Psychiatry — A novel interpretable machine learning framework for predicting postpartum depression: a SHAP-based analysis of maternal and infant health indicators
  5. WHO - Stillbirth
  6. Outcomes of a Program to Reduce Birth-Related Mortality in Tanzania | New England Journal of Medicine

Original Source(s)

Monthly trends, determinants, and forecasting of perinatal mortality in Ghana: a comparison of ARIMA, BPNN, DLNN, and GRNN models

  • by Agyei Helena Lartey, Denis Dekugmen Yar, Ama Asamaniwa Attua, Godfred Nyanney, Akuffo Samuel Tete Manukure, Isaac Takyi Boahen, Theophilus Oduro Kankam, Collins Mawuli Bakudie

  • July 10, 2026

Related Content

Evaluation of efficacy and optimal therapeutic parameters of ALA-PDT in the management of HPV-associated cervical intraepithelial neoplasia grade I

A Web-Based Intervention for Reducing Sexually Transmitted Infections and Substance Use During Pregnancy: Randomized Controlled Trial

Efficacy and safety of PARP inhibitors in older patients with advanced ovarian cancer: a systematic review and network meta-analysis