Using machine learning to understand determinants of IUD use in India: Analyses of the National Family Health Surveys (NFHS-4)

Can we design the next generation of digital health communication programs by leveraging the power of artificial intelligence to segment target audiences, bolster impact and deliver differentiated services? A machine learning analysis of survey data from rural India

“…Our work is relatively new in global health literature related to digital health programmes that are positioned as D2B programmes. While similar ML models are being tested in various domains related to public health, they consist exclusively of unsupervised learning27 28 or supervised learning,1 6 29 30 this analysis is the first of its kind focusing on the use of a combination of supervised and unsupervised learning to identify homogenous clusters for targeting of digital health programmes. Data collected from special surveys like the couple’s dataset used here are comparatively smaller in terms of sample size but large with regard to the number of data elements available.…”

“…Digital health solutions have the potential to address critical gaps in information access and service delivery, which underpin high mortality. 1–9 Mobile health communication programmes, which provide information directly to beneficiaries, are among the few examples of digital health solutions to have scaled widely in a range of settings. 10 11 Historically, these solutions have been designed as ‘blunt instruments’—providing the same content, with the same frequency, using the same digital channel to large target populations.…”

“…Digital health solutions have the potential to address critical gaps in information access and service delivery, which underpin high mortality 1–9. Mobile health communication programmes, which provide information directly to beneficiaries, are among the few examples of digital health solutions to have scaled widely in a range of settings 10 11.…”