An integrated knowledge ecosystem for infant mortality in Kilifi health and demographic surveillance system (KHDSS)
Date
2019
Authors
Amadi, David Kivuli
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Infant mortality is a key population indicator and remains a problem that requires global
attention. Kenya, like many countries in Sub Saharan Africa, did not achieve the Millennium
Development Goal number 4 (Reducing childhood mortality by 2015). Factors that
contribute to infant mortality require scientific evidence thus focus has been put on visualization
applications for the generation of new hypotheses and to inform decision. The
need for rapid access to information in an explosive data generation in the public health
sector needs a more effective data automation procedure.
The aim of this project is to develop a digital ecosystem platform that brings together
data from selected observational studies, randomized controlled clinical trials, and national
surveys into large composite datasets that give analytical power to answer important
questions on child health and surface the insights that create impact.
Using 2015 data from Kilifi HDSS for children aged less than one year. Shiny datadriven
web application framework for R statistical computing explores and analyses data
on a dashboard to run algorithms. The platform provides utilities for data analytics and
modeling techniques to answer questions on child health such as the relative effects of
pre and postnatal impacts on physical growth.
Exploratory data analysis, descriptive statistics as well as multivariable analysis are presented
by the use of graphs, tables, maps and rate(s) ratios. The visualization platform allows
researchers and policymakers to generate actionable recommendations, predictions,
and new hypotheses that will inform decision
Description
A Research Report submitted to the Faculty of Health Science in partial
fulfillment of the requirements for the degree of Master of Science (MSc) in
Epidemiology - Public Health Informatics
October, 2019