{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T12:05:27Z","timestamp":1791374727546,"version":"4.3.1"},"reference-count":39,"publisher":"BMJ","issue":"3","license":[{"start":{"date-parts":[[2023,3,17]],"date-time":"2023-03-17T00:00:00Z","timestamp":1679011200000},"content-version":"unspecified","delay-in-days":16,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000865","name":"Bill and Melinda Gates Foundation","doi-asserted-by":"publisher","award":["OPP1179252"],"award-info":[{"award-number":["OPP1179252"]}],"id":[{"id":"10.13039\/100000865","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2023,2,26]]},"published-print":{"date-parts":[[2023,3]]},"abstract":"\n Objectives<\/jats:title>\n Direct to beneficiary (D2B) mobile health communication programmes have been used to provide reproductive, maternal, neonatal and child health information to women and their families in a number of countries globally. Programmes to date have provided the same content, at the same frequency, using the same channel to large beneficiary populations. This manuscript presents a proof of concept approach that uses machine learning to segment populations of women with access to phones and their husbands into distinct clusters to support differential digital programme design and delivery.<\/jats:p>\n <\/jats:sec>\n \n Setting<\/jats:title>\n Data used in this study were drawn from cross-sectional survey conducted in four districts of Madhya Pradesh, India.<\/jats:p>\n <\/jats:sec>\n \n Participants<\/jats:title>\n Study participant included pregnant women with access to a phone (n=5095) and their husbands (n=3842)<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n We used an iterative process involving K-Means clustering and Lasso regression to segment couples into three distinct clusters. Cluster 1 (n=1408) tended to be poorer, less educated men and women, with low levels of digital access and skills. Cluster 2 (n=666) had a mid-level of digital access and skills among men but not women. Cluster 3 (n=1410) had high digital access and skill among men and moderate access and skills among women. Exposure to the D2B programme \u2018Kilkari\u2019 showed the greatest difference in Cluster 2, including an 8% difference in use of reversible modern contraceptives, 7% in child immunisation at 10 weeks, 3% in child immunisation at 9 months and 4% in the timeliness of immunisation at 10 weeks and 9 months.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Findings suggest that segmenting populations into distinct clusters for differentiated programme design and delivery may serve to improve reach and impact.<\/jats:p>\n <\/jats:sec>\n \n Trial registration number<\/jats:title>\n \n NCT03576157<\/jats:ext-link>\n .\n <\/jats:p>\n <\/jats:sec>","DOI":"10.1136\/bmjopen-2022-063354","type":"journal-article","created":{"date-parts":[[2023,5,3]],"date-time":"2023-05-03T06:52:55Z","timestamp":1683096775000},"page":"e063354","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":12,"title":["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"],"prefix":"10.1136","volume":"13","clinical-trial-number":[{"clinical-trial-number":"nct03576157","registry":"10.18810\/clinical-trials-gov"}],"author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1433-4397","authenticated-orcid":false,"given":"Jean Juste Harrisson","family":"Bashingwa","sequence":"first","affiliation":[{"name":"School of Public Health, University of the Witwatersrand, Johannesburg, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7532-366X","authenticated-orcid":false,"given":"Diwakar","family":"Mohan","sequence":"additional","affiliation":[{"name":"Department of International Health, Johns Hopkins University Bloomberg School of Public Health, Baltimore, Maryland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4785-6482","authenticated-orcid":false,"given":"Sara","family":"Chamberlain","sequence":"additional","affiliation":[{"name":"Independent Consultant, Digital Health & Gender, Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3597-9637","authenticated-orcid":false,"given":"Kerry","family":"Scott","sequence":"additional","affiliation":[{"name":"Department of International Health, Johns Hopkins University Bloomberg School of Public Health, Baltimore, Maryland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4189-5328","authenticated-orcid":false,"given":"Osama","family":"Ummer","sequence":"additional","affiliation":[{"name":"Oxford Policy Management, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Godfrey","sequence":"additional","affiliation":[{"name":"BBC Media Action, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicola","family":"Mulder","sequence":"additional","affiliation":[{"name":"Computational Biology Division, Department of Integrative Biomedical Sciences, IDM, University of Cape Town Faculty of Heath Sciences, Cape Town, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deshendran","family":"Moodley","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Cape Town, Cape Town, South Africa"},{"name":"Centre for Artificial Intelligence Research, University of Cape Town, Cape Town, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8437-7240","authenticated-orcid":false,"given":"Amnesty Elizabeth","family":"LeFevre","sequence":"additional","affiliation":[{"name":"Division of Public Health Medicine, University of Cape Town, School of Public Health, Cape Town, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2023,3,17]]},"reference":[{"key":"2025120519134243000_13.3.e063354.1","first-page":"101234","volume-title":"Analyses of the National Family Health Surveys (NFHS-4)","volume":"19","author":"Dey","year":"2022"},{"key":"2025120519134243000_13.3.e063354.2","doi-asserted-by":"crossref","DOI":"10.1186\/s12913-018-3351-z","article-title":"How can mobile phones be used to improve nutrition service delivery in rural bangladesh?","volume":"18","author":"Khan","year":"2018","journal-title":"BMC Health Serv Res"},{"key":"2025120519134243000_13.3.e063354.3","doi-asserted-by":"crossref","DOI":"10.1136\/bmjgh-2022-008838","article-title":"The impact of a direct to beneficiary mobile communication program on reproductive and child health outcomes: a randomised controlled trial in india","volume":"6","author":"LeFevre","year":"2022","journal-title":"BMJ Glob Health"},{"key":"2025120519134243000_13.3.e063354.4","doi-asserted-by":"crossref","DOI":"10.1136\/bmjgh-2022-009395","article-title":"Optimising the reach of mobile health messaging programmes: an analysis of system generated data for the kilkari programme across 13 states in india","volume":"6","author":"Mohan","year":"2022","journal-title":"BMJ Glob Health"},{"key":"2025120519134243000_13.3.e063354.5","doi-asserted-by":"crossref","DOI":"10.1186\/s13104-017-2416-0","article-title":"Assessing the feasibility of ehealth and mhealth: a systematic review and analysis of initiatives implemented in kenya","volume":"10","author":"Njoroge","year":"2017","journal-title":"BMC Res Notes"},{"key":"2025120519134243000_13.3.e063354.6","doi-asserted-by":"crossref","DOI":"10.1016\/j.ssmph.2020.100687","article-title":"Application of machine learning to understand child marriage in india","volume":"12","author":"Raj","year":"2020","journal-title":"SSM Popul Health"},{"key":"2025120519134243000_13.3.e063354.7","doi-asserted-by":"crossref","first-page":"220","DOI":"10.3390\/encyclopedia1010021","article-title":"Machine learning in healthcare communication","volume":"1","author":"Siddique","year":"2021","journal-title":"Encyclopedia"},{"key":"2025120519134243000_13.3.e063354.8","unstructured":"Deshmukh M , Mechael PJW . DC: mhealth alliance, addressing gender and women\u2019s empowerment in mhealth for MNCH: an analytical framework. 2013."},{"key":"2025120519134243000_13.3.e063354.9","doi-asserted-by":"publisher","DOI":"10.1111\/j.1471-0528.2012.03413.x"},{"key":"2025120519134243000_13.3.e063354.10","doi-asserted-by":"crossref","DOI":"10.1136\/bmjgh-2021-005213","article-title":"Assessing exposure to kilkari: a big data analysis of a large maternal mobile messaging service across 13 states in india","volume":"6","author":"Bashingwa","year":"2021","journal-title":"BMJ Glob Health"},{"key":"2025120519134243000_13.3.e063354.11","doi-asserted-by":"crossref","DOI":"10.1136\/bmjgh-2021-005299","article-title":"Examining the reach and exposure of a mobile phone-based training programme for frontline health workers (ashas) in 13 states across india","volume":"6","author":"Bashingwa","year":"2021","journal-title":"BMJ Glob Health"},{"key":"2025120519134243000_13.3.e063354.12","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1111\/1758-5899.12909","article-title":"Avoiding the road to nowhere: policy insights on scaling up and sustaining digital health","volume":"12","author":"LeFevre","year":"2021","journal-title":"Glob Policy"},{"key":"2025120519134243000_13.3.e063354.13","doi-asserted-by":"crossref","DOI":"10.1186\/s12992-021-00716-1","article-title":"Multiple pathways to scaling up and sustainability: an exploration of digital health solutions in south africa","volume":"17","author":"Swartz","year":"2021","journal-title":"Global Health"},{"key":"2025120519134243000_13.3.e063354.14","unstructured":"GSMA . Connected women: the mobile gender gap report 2020. GSM Association, 2020."},{"key":"2025120519134243000_13.3.e063354.15","doi-asserted-by":"crossref","DOI":"10.1136\/bmjgh-2020-002524","article-title":"Does women\u2019s mobile phone ownership matter for health? Evidence from 15 countries","volume":"5","author":"LeFevre","year":"2020","journal-title":"BMJ Glob Health"},{"key":"2025120519134243000_13.3.e063354.16","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0236078","article-title":"Does having a mobile phone matter? linking phone access among women to health in India: an exploratory analysis of the National family health survey","volume":"15","author":"Mohan","year":"2020","journal-title":"PLoS One"},{"key":"2025120519134243000_13.3.e063354.17","doi-asserted-by":"crossref","DOI":"10.1136\/bmjgh-2021-005868","article-title":"Another voice in the crowd: the challenge of changing family planning and child feeding practices through mhealth messaging in rural central india","volume":"6","author":"Scott","year":"2021","journal-title":"BMJ Glob Health"},{"key":"2025120519134243000_13.3.e063354.18","doi-asserted-by":"crossref","DOI":"10.2196\/11456","article-title":"Use of big data and machine learning methods in the monitoring and evaluation of digital health programs in India: an exploratory protocol","volume":"8","author":"Mohan","year":"2019","journal-title":"JMIR Res Protoc"},{"key":"2025120519134243000_13.3.e063354.19","unstructured":"LeFevre A , Shah N , Scott K , et al . Are stage-based, direct to beneficiary mobile communication programs effective in improving maternal newborn and child health outcomes in india? results from an individually randomised controlled trial of a national programme. BMJ Global Health 2021."},{"key":"2025120519134243000_13.3.e063354.20","doi-asserted-by":"crossref","DOI":"10.1186\/s13063-019-3369-5","article-title":"Are stage-based health information messages effective and good value for money in improving maternal newborn and child health outcomes in India? protocol for an individually randomized controlled trial","volume":"20","author":"LeFevre","year":"2019","journal-title":"Trials"},{"key":"2025120519134243000_13.3.e063354.21","unstructured":"I.I.f.P . Sciences, national family health survey 2015-2016 state fact sheet madhya pradesh. Mumbai: International Institute for Population Sciences, Government of India, Ministry of Health and Family Welfare, 2016."},{"key":"2025120519134243000_13.3.e063354.22","unstructured":"LeFevre A , Shah N , Scott K , et al . Are stage-based mobile health information messages effective in improving maternal newborn and child health outcomes in india? results from an individually randomized controlled trial. Lancet GH 2021."},{"key":"2025120519134243000_13.3.e063354.23","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1016\/j.procs.2015.06.090","article-title":"Image segmentation using K -means clustering algorithm and subtractive clustering algorithm","volume":"54","author":"Dhanachandra","year":"2015","journal-title":"Procedia Computer Science"},{"key":"2025120519134243000_13.3.e063354.24","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(02)00060-2"},{"key":"2025120519134243000_13.3.e063354.25","unstructured":"Kodinariya TM , Makwana P . Review on determining number of cluster in K-means clustering. 2013;1:90\u20135."},{"key":"2025120519134243000_13.3.e063354.26","unstructured":"Arnaud, kml and kml3d: R packages to cluster longitudinal data. 2015;65:1\u201334."},{"key":"2025120519134243000_13.3.e063354.27","doi-asserted-by":"publisher","DOI":"10.1186\/s12882-016-0238-2"},{"key":"2025120519134243000_13.3.e063354.28","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1186\/s12875-018-0790-x","article-title":"Multimorbidity patterns with K-means nonhierarchical cluster analysis","volume":"19","author":"Viol\u00e1n","year":"2018","journal-title":"BMC Fam Pract"},{"key":"2025120519134243000_13.3.e063354.29","doi-asserted-by":"crossref","first-page":"104866","DOI":"10.1016\/j.ijmedinf.2022.104866","article-title":"Performance analysis of machine learning algorithms and screening formulae for \u03b2-thalassemia trait screening of indian antenatal women","volume":"167","author":"Das","year":"2022","journal-title":"Int J Med Inform"},{"key":"2025120519134243000_13.3.e063354.30","doi-asserted-by":"crossref","DOI":"10.3390\/vaccines9060646","article-title":"Finding children with high risk of non-vaccination in 92 low- and middle-income countries: a decision tree approach","volume":"9","author":"Santos","year":"2021","journal-title":"Vaccines (Basel)"},{"key":"2025120519134243000_13.3.e063354.31","doi-asserted-by":"crossref","first-page":"59","DOI":"10.4314\/ijest.v2i2.59139","article-title":"A hybridized K-means clustering approach for high dimensional dataset","volume":"2","author":"Dash","year":"2010","journal-title":"Int J Eng Sci Tech"},{"key":"2025120519134243000_13.3.e063354.32","doi-asserted-by":"crossref","unstructured":"Ding C , He X , Zha H , et al . Adaptive dimension reduction for clustering high dimensional data. 2002 IEEE International Conference on Data Mining, 2002. Proceedings; IEEE, 2002:147\u201354","DOI":"10.1109\/ICDM.2002.1183897"},{"key":"2025120519134243000_13.3.e063354.33","unstructured":"S.J.a.p.a . Dasgupta, experiments with random projection. 2013."},{"key":"2025120519134243000_13.3.e063354.34","doi-asserted-by":"publisher","DOI":"10.1145\/1007730.1007731"},{"key":"2025120519134243000_13.3.e063354.35","doi-asserted-by":"crossref","unstructured":"Ding C , Li T . Adaptive dimension reduction using discriminant analysis and k -means clustering. ICML \u201907 & ILP \u201907; Corvalis Oregon USA.New York, NY, USA, June 20, 2007:521\u20138 doi:10.1145\/1273496.1273562","DOI":"10.1145\/1273496.1273562"},{"key":"2025120519134243000_13.3.e063354.36","doi-asserted-by":"crossref","unstructured":"Muthukrishnan R , Rohini R . LASSO: a feature selection technique in predictive modeling for machine learning. 2016 IEEE International Conference on Advances in Computer Applications (ICACA); Coimbatore, India. IEEE, 2016:18\u201320 doi:10.1109\/ICACA.2016.7887916","DOI":"10.1109\/ICACA.2016.7887916"},{"key":"2025120519134243000_13.3.e063354.37","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00537"},{"key":"2025120519134243000_13.3.e063354.38","doi-asserted-by":"crossref","unstructured":"Chambers JM . Software for data analysis. In: Software for data analysis: programming with R. New York, NY: Springer, 2008. doi:10.1007\/978-0-387-75936-4","DOI":"10.1007\/978-0-387-75936-4"},{"key":"2025120519134243000_13.3.e063354.39","doi-asserted-by":"crossref","unstructured":"Milano F . A python-based software tool for power system analysis. 2013 IEEE Power & Energy Society General Meeting; Vancouver, BC. IEEE, 2013:1\u20135 doi:10.1109\/PESMG.2013.6672387","DOI":"10.1109\/PESMG.2013.6672387"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2022-063354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T03:13:52Z","timestamp":1764990832000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2022-063354"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":39,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,3,17]]},"published-print":{"date-parts":[[2023,3]]}},"alternative-id":["10.1136\/bmjopen-2022-063354"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2022-063354","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}