Skip to main content

01.12.2019 | Research article | Ausgabe 1/2019 Open Access

BMC Medical Informatics and Decision Making 1/2019

Development and evaluation of a mobile application for case management of small and sick newborns in Bangladesh

BMC Medical Informatics and Decision Making > Ausgabe 1/2019
Lauren E. Schaeffer, Salahuddin Ahmed, Mahmoodur Rahman, Rachel Whelan, Sayedur Rahman, Arunangshu Dutta Roy, Tanzia Ahmed Nijhum, Nazmun Nahar Bably, Helen D’Couto, Carly Hudelson, Iffat Ara Jaben, Sayed Rubayet, Abdullah Baqui, Anne CC Lee
Wichtige Hinweise

Electronic supplementary material

The online version of this article (https://​doi.​org/​10.​1186/​s12911-019-0835-7) contains supplementary material, which is available to authorized users.

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.



In low-income settings, community health workers (CHWs) are frequently the first point of contact for newborns. Mobile technology may aid health workers in classifying illness and providing referral and management guidance for newborn care. This study evaluates the potential for mobile health technology to improve diagnosis and case management of newborns in Bangladesh.


A mobile application based on Bangladesh’s Comprehensive Newborn Care Package national guidelines (mCNCP) was developed to aid CHWs in identifying and managing small and sick infants. After a 2-day training, CHWs assessed newborns at Sylhet Osmani Medical College Hospital and in the Projahnmo research site (Sylhet, Bangladesh) using either mCNCP or a comparable paper form (pCNCP), similar to standard IMCI-formatted paper forms. CHWs were randomized to conduct a block of ~ 6 newborn assessments starting with either mCNCP or pCNCP, then switched to the alternate method. Physicians using mCNCP served as gold standard assessors. CHW performance with mCNCP and pCNCP were compared using chi-squared tests of independence for equality of proportions, and logistic regressions clustered by CHW.


Two hundred seven total CHW assessments were completed on 101 enrolled infants. mCNCP assessments were more often fully completed and completed faster than pCNCP assessments (100% vs 23.8%, p < 0.001; 17.5 vs 23.6 min; p < 0.001). mCNCP facilitated calculations of respiratory rate, temperature, and gestational age. CHWs using mCNCP were more likely to identify small newborns (Odds Ratio (OR): 20.8, Confidence Interval (CI): (7.1, 60.8), p < 0.001), and to correctly classify 7 out of 16 newborn conditions evaluated, including severe weight loss (OR: 13.1, CI: (4.6, 37.5), p < 0.001), poor movement (OR: 6.6, CI: (2.3, 19.3), p = 0.001), hypothermia (OR: 14.9, CI: (2.7, 82.2), p = 0.002), and feeding intolerance (OR: 2.1, CI: (1.3, 3.3), p = 0.003). CHWs with mCNCP were more likely to provide counseling as needed on 4 out of 7 case management recommendations evaluated, including kangaroo mother care.


CHWs in rural Bangladesh with limited experience using tablets successfully used a mobile application for neonatal assessment after a two-day training. mCNCP may aid frontline health workers in Bangladesh to improve completion of neonatal assessment, classification of illnesses, and adherence to neonatal management guidelines.
Über diesen Artikel

Weitere Artikel der Ausgabe 1/2019

BMC Medical Informatics and Decision Making 1/2019 Zur Ausgabe