pgph.0000430.g002.tif (197.05 kB)

Key household and individual predictors of suspected diarrhoea in rural and urban areas identified through the analysis of 2006–2016 Uganda demographic health surveys data.

figure

posted on 2022-05-11, 17:32 authored by Rornald Muhumuza Kananura

The identification of variables is based on the best performing ML model, the GBM.

History

Usage metrics

Read the peer-reviewed publication

Machine learning predictive modelling for identification of predictors of acute respiratory infection and diarrhoea in Uganda’s rural and urban settings

PLOS Global Public Health

Categories

Keywords

xlink "> despite top global causes study findings confirm high dimension data generating research hypotheses acute respiratory infections acute respiratory infection uganda &# 8217 traditional &# 8221 observations n ).alongside traditional models diarrhoea remain among 2006 &# 8211 resampling technique ).household &# 8217 child &# 8217 70 %- rural machine learning could diarrhoea among children poor household environments 100 %- urban also used ml prediction model ),applied ml techniques &# 8211 machine learning ml technique urban differentials statistical techniques poor hygiene models appear make children boosted machine household characteristics child morbidity child characteristics child age immunisation ).usually correlated used 90 training sets selected model results provide results highlight pseudo new protective interventions perform better nutritional status multisectoral emphasis maternal socio maternal characteristics implementing interventions holistic approach four categories fold cross factors relate economic factors birth weight 59 months 5 years

Licence

Exports